Stowage/go
2
0
Fork 0
mirror of https://github.com/golang/go.git synced 2025-12-08 06:10:04 +00:00
Code Issues Projects Releases Packages Wiki Activity
go/src/cmd/compile/internal/ssa/_gen/386Ops.go

589 lines
45 KiB
Go
Raw Normal View History

[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// Copyright 2016 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package main
import "strings"
// Notes:
// - Integer types live in the low portion of registers. Upper portions are junk.
// - Boolean types use the low-order byte of a register. 0=false, 1=true.
// Upper bytes are junk.
// - Floating-point types live in the low natural slot of an sse2 register.
// Unused portions are junk.
// - We do not use AH,BH,CH,DH registers.
// - When doing sub-register operations, we try to write the whole
// destination register to avoid a partial-register write.
// - Unused portions of AuxInt (or the Val portion of ValAndOff) are
// filled by sign-extending the used portion. Users of AuxInt which interpret
// AuxInt as unsigned (e.g. shifts) must be careful.
// Suffixes encode the bit width of various instructions.
// L (long word) = 32 bit
// W (word) = 16 bit
// B (byte) = 8 bit
// copied from ../../x86/reg.go
var regNames386 = []string{
"AX",
"CX",
"DX",
"BX",
"SP",
"BP",
"SI",
"DI",
"X0",
"X1",
"X2",
"X3",
"X4",
"X5",
"X6",
"X7",
runtime: asynchronous preemption function for x86 This adds asynchronous preemption function for amd64 and 386. These functions spill and restore all register state that can be used by user Go code. For the moment we stub out the other arches. For #10958, #24543. Change-Id: I6f93fabe9875f4834922a5712362e79045c00aca Reviewed-on: https://go-review.googlesource.com/c/go/+/201759 Run-TryBot: Austin Clements <austin@google.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2019-10-16 19:10:06 -04:00
// If you add registers, update asyncPreempt in runtime
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// pseudo-registers
"SB",
}
func init() {
// Make map from reg names to reg integers.
if len(regNames386) > 64 {
panic("too many registers")
}
num := map[string]int{}
for i, name := range regNames386 {
num[name] = i
}
buildReg := func(s string) regMask {
m := regMask(0)
for _, r := range strings.Split(s, " ") {
if n, ok := num[r]; ok {
m |= regMask(1) << uint(n)
continue
}
panic("register " + r + " not found")
}
return m
}
// Common individual register masks
var (
ax = buildReg("AX")
cx = buildReg("CX")
dx = buildReg("DX")
cmd/compile,runtime: provide index information on bounds check failure A few examples (for accessing a slice of length 3): s[-1] runtime error: index out of range [-1] s[3] runtime error: index out of range [3] with length 3 s[-1:0] runtime error: slice bounds out of range [-1:] s[3:0] runtime error: slice bounds out of range [3:0] s[3:-1] runtime error: slice bounds out of range [:-1] s[3:4] runtime error: slice bounds out of range [:4] with capacity 3 s[0:3:4] runtime error: slice bounds out of range [::4] with capacity 3 Note that in cases where there are multiple things wrong with the indexes (e.g. s[3:-1]), we report one of those errors kind of arbitrarily, currently the rightmost one. An exhaustive set of examples is in issue30116[u].out in the CL. The message text has the same prefix as the old message text. That leads to slightly awkward phrasing but hopefully minimizes the chance that code depending on the error text will break. Increases the size of the go binary by 0.5% (amd64). The panic functions take arguments in registers in order to keep the size of the compiled code as small as possible. Fixes #30116 Change-Id: Idb99a827b7888822ca34c240eca87b7e44a04fdd Reviewed-on: https://go-review.googlesource.com/c/go/+/161477 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2019-02-06 14:12:36 -08:00
bx = buildReg("BX")
si = buildReg("SI")
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
gp = buildReg("AX CX DX BX BP SI DI")
fp = buildReg("X0 X1 X2 X3 X4 X5 X6 X7")
gpsp = gp | buildReg("SP")
gpspsb = gpsp | buildReg("SB")
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
callerSave = gp | fp
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
)
// Common slices of register masks
var (
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
gponly = []regMask{gp}
fponly = []regMask{fp}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
)
// Common regInfo
var (
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
gp01 = regInfo{inputs: nil, outputs: gponly}
gp11 = regInfo{inputs: []regMask{gp}, outputs: gponly}
gp11sp = regInfo{inputs: []regMask{gpsp}, outputs: gponly}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
gp11sb = regInfo{inputs: []regMask{gpspsb}, outputs: gponly}
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
gp21 = regInfo{inputs: []regMask{gp, gp}, outputs: gponly}
cmd/compile: inline atomics from runtime/internal/atomic on amd64 Inline atomic reads and writes on amd64. There's no reason to pay the overhead of a call for these. To keep atomic loads from being reordered, we make them return a <value,memory> tuple. Change the meaning of resultInArg0 for tuple-generating ops to mean the first part of the result tuple, not the second. This means we can always put the store part of the tuple last, matching how arguments are laid out. This requires reordering the outputs of add32carry and sub32carry and their descendents in various architectures. benchmark old ns/op new ns/op delta BenchmarkAtomicLoad64-8 2.09 0.26 -87.56% BenchmarkAtomicStore64-8 7.54 5.72 -24.14% TBD (in a different CL): Cas, Or8, ... Change-Id: I713ea88e7da3026c44ea5bdb56ed094b20bc5207 Reviewed-on: https://go-review.googlesource.com/27641 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-08-23 16:49:28 -07:00
gp11carry = regInfo{inputs: []regMask{gp}, outputs: []regMask{gp, 0}}
gp21carry = regInfo{inputs: []regMask{gp, gp}, outputs: []regMask{gp, 0}}
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
gp1carry1 = regInfo{inputs: []regMask{gp}, outputs: gponly}
gp2carry1 = regInfo{inputs: []regMask{gp, gp}, outputs: gponly}
gp21sp = regInfo{inputs: []regMask{gpsp, gp}, outputs: gponly}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
gp21sb = regInfo{inputs: []regMask{gpspsb, gpsp}, outputs: gponly}
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
gp21shift = regInfo{inputs: []regMask{gp, cx}, outputs: []regMask{gp}}
gp11div = regInfo{inputs: []regMask{ax, gpsp &^ dx}, outputs: []regMask{ax}, clobbers: dx}
gp21hmul = regInfo{inputs: []regMask{ax, gpsp}, outputs: []regMask{dx}, clobbers: ax}
gp11mod = regInfo{inputs: []regMask{ax, gpsp &^ dx}, outputs: []regMask{dx}, clobbers: ax}
gp21mul = regInfo{inputs: []regMask{ax, gpsp}, outputs: []regMask{dx, ax}}
cmd/compile: optimize 386's comparison CMPL/CMPW/CMPB can take a memory operand on 386, and this CL implements that optimization. 1. The total size of pkg/linux_386 decreases about 45KB, excluding cmd/compile. 2. The go1 benchmark shows a little improvement. name old time/op new time/op delta BinaryTree17-4 3.36s ± 2% 3.37s ± 3% ~ (p=0.537 n=40+40) Fannkuch11-4 3.59s ± 1% 3.53s ± 2% -1.58% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.0ns ± 3% 45.8ns ± 3% ~ (p=0.249 n=40+40) FmtFprintfString-4 80.0ns ± 4% 78.8ns ± 3% -1.49% (p=0.001 n=40+40) FmtFprintfInt-4 89.7ns ± 2% 90.3ns ± 2% +0.74% (p=0.003 n=40+40) FmtFprintfIntInt-4 144ns ± 3% 143ns ± 3% -0.95% (p=0.003 n=40+40) FmtFprintfPrefixedInt-4 181ns ± 4% 180ns ± 2% ~ (p=0.103 n=40+40) FmtFprintfFloat-4 412ns ± 3% 408ns ± 4% -0.97% (p=0.018 n=40+40) FmtManyArgs-4 607ns ± 4% 605ns ± 4% ~ (p=0.148 n=40+40) GobDecode-4 7.19ms ± 4% 7.24ms ± 5% ~ (p=0.340 n=40+40) GobEncode-4 7.04ms ± 9% 6.99ms ± 9% ~ (p=0.289 n=40+40) Gzip-4 400ms ± 6% 398ms ± 5% ~ (p=0.168 n=40+40) Gunzip-4 41.2ms ± 3% 41.7ms ± 3% +1.40% (p=0.001 n=40+40) HTTPClientServer-4 62.5µs ± 1% 62.1µs ± 2% -0.61% (p=0.000 n=37+37) JSONEncode-4 20.7ms ± 4% 20.4ms ± 3% -1.60% (p=0.000 n=40+40) JSONDecode-4 69.4ms ± 4% 69.2ms ± 6% ~ (p=0.177 n=40+40) Mandelbrot200-4 5.22ms ± 6% 5.21ms ± 3% ~ (p=0.531 n=40+40) GoParse-4 3.29ms ± 3% 3.28ms ± 3% ~ (p=0.321 n=40+39) RegexpMatchEasy0_32-4 104ns ± 4% 103ns ± 7% -0.89% (p=0.040 n=40+40) RegexpMatchEasy0_1K-4 852ns ± 3% 853ns ± 2% ~ (p=0.357 n=40+40) RegexpMatchEasy1_32-4 113ns ± 8% 113ns ± 3% ~ (p=0.906 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 5% ~ (p=0.326 n=40+40) RegexpMatchMedium_32-4 136ns ± 3% 133ns ± 3% -2.31% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 44.0µs ± 3% 43.7µs ± 3% ~ (p=0.053 n=40+40) RegexpMatchHard_32-4 2.27µs ± 3% 2.26µs ± 4% ~ (p=0.391 n=40+40) RegexpMatchHard_1K-4 68.0µs ± 3% 68.9µs ± 3% +1.28% (p=0.000 n=40+40) Revcomp-4 1.86s ± 5% 1.86s ± 2% ~ (p=0.950 n=40+40) Template-4 73.4ms ± 4% 69.9ms ± 7% -4.78% (p=0.000 n=40+40) TimeParse-4 449ns ± 4% 441ns ± 5% -1.76% (p=0.000 n=40+40) TimeFormat-4 416ns ± 3% 417ns ± 4% ~ (p=0.304 n=40+40) [Geo mean] 67.7µs 67.3µs -0.55% name old speed new speed delta GobDecode-4 107MB/s ± 4% 106MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 109MB/s ± 5% 110MB/s ± 9% ~ (p=0.142 n=38+40) Gzip-4 48.5MB/s ± 5% 48.8MB/s ± 5% ~ (p=0.172 n=40+40) Gunzip-4 472MB/s ± 3% 465MB/s ± 3% -1.39% (p=0.001 n=40+40) JSONEncode-4 93.6MB/s ± 4% 95.1MB/s ± 3% +1.61% (p=0.000 n=40+40) JSONDecode-4 28.0MB/s ± 3% 28.1MB/s ± 6% ~ (p=0.181 n=40+40) GoParse-4 17.6MB/s ± 3% 17.7MB/s ± 3% ~ (p=0.350 n=40+39) RegexpMatchEasy0_32-4 308MB/s ± 4% 311MB/s ± 6% +0.96% (p=0.025 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 3% 1.20GB/s ± 2% ~ (p=0.317 n=40+40) RegexpMatchEasy1_32-4 282MB/s ± 7% 282MB/s ± 3% ~ (p=0.516 n=40+40) RegexpMatchEasy1_1K-4 994MB/s ± 4% 991MB/s ± 5% ~ (p=0.319 n=40+40) RegexpMatchMedium_32-4 7.31MB/s ± 3% 7.49MB/s ± 3% +2.46% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 23.3MB/s ± 3% 23.4MB/s ± 3% ~ (p=0.052 n=40+40) RegexpMatchHard_32-4 14.1MB/s ± 3% 14.1MB/s ± 4% ~ (p=0.391 n=40+40) RegexpMatchHard_1K-4 15.1MB/s ± 3% 14.9MB/s ± 3% -1.27% (p=0.000 n=40+40) Revcomp-4 137MB/s ± 5% 137MB/s ± 2% ~ (p=0.942 n=40+40) Template-4 26.5MB/s ± 4% 27.8MB/s ± 7% +5.03% (p=0.000 n=40+40) [Geo mean] 78.6MB/s 79.0MB/s +0.57% Change-Id: Idcacc6881ef57cd7dc33aa87b711282842b72a53 Reviewed-on: https://go-review.googlesource.com/126618 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-07-29 12:50:50 +00:00
gp2flags = regInfo{inputs: []regMask{gpsp, gpsp}}
gp1flags = regInfo{inputs: []regMask{gpsp}}
gp0flagsLoad = regInfo{inputs: []regMask{gpspsb, 0}}
gp1flagsLoad = regInfo{inputs: []regMask{gpspsb, gpsp, 0}}
flagsgp = regInfo{inputs: nil, outputs: gponly}
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
readflags = regInfo{inputs: nil, outputs: gponly}
flagsgpax = regInfo{inputs: nil, clobbers: ax, outputs: []regMask{gp &^ ax}}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
gpload = regInfo{inputs: []regMask{gpspsb, 0}, outputs: gponly}
gp21load = regInfo{inputs: []regMask{gp, gpspsb, 0}, outputs: gponly}
gploadidx = regInfo{inputs: []regMask{gpspsb, gpsp, 0}, outputs: gponly}
gp21loadidx = regInfo{inputs: []regMask{gp, gpspsb, gpsp, 0}, outputs: gponly}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
gpstore = regInfo{inputs: []regMask{gpspsb, gpsp, 0}}
gpstoreconst = regInfo{inputs: []regMask{gpspsb, 0}}
gpstoreidx = regInfo{inputs: []regMask{gpspsb, gpsp, gpsp, 0}}
gpstoreconstidx = regInfo{inputs: []regMask{gpspsb, gpsp, 0}}
cmd/compile: don't reserve X15 for float sub/div any more We used to reserve X15 to implement the 3-operand floating-point sub/div ops with the 2-operand sub/div that 386/amd64 gives us. Now that resultInArg0 is implemented, we no longer need to reserve X15 (X7 on 386). Fixes #15584 Change-Id: I978e6c0a35236e89641bfc027538cede66004e82 Reviewed-on: https://go-review.googlesource.com/28272 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-31 12:35:32 -07:00
fp01 = regInfo{inputs: nil, outputs: fponly}
fp21 = regInfo{inputs: []regMask{fp, fp}, outputs: fponly}
go/printer, gofmt: handle raw string literals containing newlines better A raw string containing newlines breaks whatever columns structure has been established so far. Recognize the situation and force a new section of alignment with the first line break seen after the the raw string. Applied gofmt to src and misc. Fixes #9064. Change-Id: I961e94b529b1fd421908311f366b113e2ec9b7f0 Reviewed-on: https://go-review.googlesource.com/105040 Reviewed-by: Matthew Dempsky <mdempsky@google.com>
2018-04-05 16:04:56 -07:00
fp21load = regInfo{inputs: []regMask{fp, gpspsb, 0}, outputs: fponly}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
fpgp = regInfo{inputs: fponly, outputs: gponly}
gpfp = regInfo{inputs: gponly, outputs: fponly}
fp11 = regInfo{inputs: fponly, outputs: fponly}
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
fp2flags = regInfo{inputs: []regMask{fp, fp}}
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
fpload = regInfo{inputs: []regMask{gpspsb, 0}, outputs: fponly}
fploadidx = regInfo{inputs: []regMask{gpspsb, gpsp, 0}, outputs: fponly}
fpstore = regInfo{inputs: []regMask{gpspsb, fp, 0}}
fpstoreidx = regInfo{inputs: []regMask{gpspsb, gpsp, fp, 0}}
)
var _386ops = []opData{
// fp ops
cmd/compile: remove backend's "scratch mem" support This CL rebases CL 273987 on top of master with @mdempsky's permission. The last (only?) use for this feature was 387 support, which was removed in golang.org/cl/258957. Change-Id: I4f79fee8d0c336c9b6082bcd5eb6ece52c032dc0 Reviewed-on: https://go-review.googlesource.com/c/go/+/292893 Trust: Cuong Manh Le <cuong.manhle.vn@gmail.com> Run-TryBot: Cuong Manh Le <cuong.manhle.vn@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Matthew Dempsky <mdempsky@google.com>
2021-02-17 15:27:42 +07:00
{name: "ADDSS", argLength: 2, reg: fp21, asm: "ADDSS", commutative: true, resultInArg0: true}, // fp32 add
{name: "ADDSD", argLength: 2, reg: fp21, asm: "ADDSD", commutative: true, resultInArg0: true}, // fp64 add
{name: "SUBSS", argLength: 2, reg: fp21, asm: "SUBSS", resultInArg0: true}, // fp32 sub
{name: "SUBSD", argLength: 2, reg: fp21, asm: "SUBSD", resultInArg0: true}, // fp64 sub
{name: "MULSS", argLength: 2, reg: fp21, asm: "MULSS", commutative: true, resultInArg0: true}, // fp32 mul
{name: "MULSD", argLength: 2, reg: fp21, asm: "MULSD", commutative: true, resultInArg0: true}, // fp64 mul
{name: "DIVSS", argLength: 2, reg: fp21, asm: "DIVSS", resultInArg0: true}, // fp32 div
{name: "DIVSD", argLength: 2, reg: fp21, asm: "DIVSD", resultInArg0: true}, // fp64 div
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile/internal/ssa: populate SymEffects for SSA Ops Changes to ${GOARCH}Ops.go files were mechanically produced using github.com/mdempsky/ssa-symops, a one-off tool that inserts "SymEffect: X" elements by pattern matching against the Op names. Change-Id: Ibf3e481ffd588647f2a31662d72114b740ccbfcf Reviewed-on: https://go-review.googlesource.com/38084 Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-03-09 14:46:43 -08:00
{name: "MOVSSload", argLength: 2, reg: fpload, asm: "MOVSS", aux: "SymOff", faultOnNilArg0: true, symEffect: "Read"}, // fp32 load
{name: "MOVSDload", argLength: 2, reg: fpload, asm: "MOVSD", aux: "SymOff", faultOnNilArg0: true, symEffect: "Read"}, // fp64 load
{name: "MOVSSconst", reg: fp01, asm: "MOVSS", aux: "Float32", rematerializeable: true}, // fp32 constant
{name: "MOVSDconst", reg: fp01, asm: "MOVSD", aux: "Float64", rematerializeable: true}, // fp64 constant
{name: "MOVSSloadidx1", argLength: 3, reg: fploadidx, asm: "MOVSS", aux: "SymOff", symEffect: "Read"}, // fp32 load indexed by i
{name: "MOVSSloadidx4", argLength: 3, reg: fploadidx, asm: "MOVSS", aux: "SymOff", symEffect: "Read"}, // fp32 load indexed by 4*i
{name: "MOVSDloadidx1", argLength: 3, reg: fploadidx, asm: "MOVSD", aux: "SymOff", symEffect: "Read"}, // fp64 load indexed by i
{name: "MOVSDloadidx8", argLength: 3, reg: fploadidx, asm: "MOVSD", aux: "SymOff", symEffect: "Read"}, // fp64 load indexed by 8*i
{name: "MOVSSstore", argLength: 3, reg: fpstore, asm: "MOVSS", aux: "SymOff", faultOnNilArg0: true, symEffect: "Write"}, // fp32 store
{name: "MOVSDstore", argLength: 3, reg: fpstore, asm: "MOVSD", aux: "SymOff", faultOnNilArg0: true, symEffect: "Write"}, // fp64 store
{name: "MOVSSstoreidx1", argLength: 4, reg: fpstoreidx, asm: "MOVSS", aux: "SymOff", symEffect: "Write"}, // fp32 indexed by i store
{name: "MOVSSstoreidx4", argLength: 4, reg: fpstoreidx, asm: "MOVSS", aux: "SymOff", symEffect: "Write"}, // fp32 indexed by 4i store
{name: "MOVSDstoreidx1", argLength: 4, reg: fpstoreidx, asm: "MOVSD", aux: "SymOff", symEffect: "Write"}, // fp64 indexed by i store
{name: "MOVSDstoreidx8", argLength: 4, reg: fpstoreidx, asm: "MOVSD", aux: "SymOff", symEffect: "Write"}, // fp64 indexed by 8i store
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: rename memory-using operations Some *mem ops are loads, some are stores, some are modifications. Replace mem->load for the loads. Replace mem->store for the stores. Replace mem->modify for the load-modify-stores. The only semantic change in this CL is to mark ADD(Q|L)constmodify (which used to be ADD(Q|L)constmem) as both a read and a write, instead of just a write. This is arguably a bug fix, but the bug isn't triggerable at the moment, see CL 112157. Change-Id: Iccb45aea817b606adb2d712ff99b10ee28e4616a Reviewed-on: https://go-review.googlesource.com/112159 Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org>
2018-05-08 09:11:00 -07:00
{name: "ADDSSload", argLength: 3, reg: fp21load, asm: "ADDSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 + tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "ADDSDload", argLength: 3, reg: fp21load, asm: "ADDSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 + tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "SUBSSload", argLength: 3, reg: fp21load, asm: "SUBSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 - tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "SUBSDload", argLength: 3, reg: fp21load, asm: "SUBSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 - tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "MULSSload", argLength: 3, reg: fp21load, asm: "MULSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 * tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "MULSDload", argLength: 3, reg: fp21load, asm: "MULSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 * tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
cmd/compile: optimize 386 code with MULLload/DIVSSload/DIVSDload IMULL/DIVSS/DIVSD all can take the source operand from memory directly. And this CL implement that optimization. 1. The total size of pkg/linux_386 decreases about 84KB (excluding cmd/compile). 2. The go1 benchmark shows little regression in total (excluding noise). name old time/op new time/op delta BinaryTree17-4 3.29s ± 2% 3.27s ± 4% ~ (p=0.192 n=30+30) Fannkuch11-4 3.49s ± 2% 3.54s ± 1% +1.48% (p=0.000 n=30+30) FmtFprintfEmpty-4 45.9ns ± 3% 46.3ns ± 4% +0.89% (p=0.037 n=30+30) FmtFprintfString-4 78.8ns ± 3% 78.7ns ± 4% ~ (p=0.209 n=30+27) FmtFprintfInt-4 91.0ns ± 2% 90.3ns ± 2% -0.82% (p=0.031 n=30+27) FmtFprintfIntInt-4 142ns ± 4% 143ns ± 4% ~ (p=0.136 n=30+30) FmtFprintfPrefixedInt-4 181ns ± 3% 183ns ± 4% +1.40% (p=0.005 n=30+30) FmtFprintfFloat-4 404ns ± 4% 408ns ± 3% ~ (p=0.397 n=30+30) FmtManyArgs-4 601ns ± 3% 609ns ± 5% ~ (p=0.059 n=30+30) GobDecode-4 7.21ms ± 5% 7.24ms ± 5% ~ (p=0.612 n=30+30) GobEncode-4 6.91ms ± 6% 6.91ms ± 6% ~ (p=0.797 n=30+30) Gzip-4 398ms ± 6% 399ms ± 4% ~ (p=0.173 n=30+30) Gunzip-4 41.7ms ± 3% 41.8ms ± 3% ~ (p=0.423 n=30+30) HTTPClientServer-4 62.3µs ± 2% 62.7µs ± 3% ~ (p=0.085 n=29+30) JSONEncode-4 21.0ms ± 4% 20.7ms ± 5% -1.39% (p=0.014 n=30+30) JSONDecode-4 66.3ms ± 3% 67.4ms ± 1% +1.71% (p=0.003 n=30+24) Mandelbrot200-4 5.15ms ± 3% 5.16ms ± 3% ~ (p=0.697 n=30+30) GoParse-4 3.24ms ± 3% 3.27ms ± 4% +0.91% (p=0.032 n=30+30) RegexpMatchEasy0_32-4 101ns ± 5% 99ns ± 4% -1.82% (p=0.008 n=29+30) RegexpMatchEasy0_1K-4 848ns ± 4% 841ns ± 2% -0.77% (p=0.043 n=30+30) RegexpMatchEasy1_32-4 106ns ± 6% 106ns ± 3% ~ (p=0.939 n=29+30) RegexpMatchEasy1_1K-4 1.02µs ± 3% 1.03µs ± 4% ~ (p=0.297 n=28+30) RegexpMatchMedium_32-4 129ns ± 4% 127ns ± 4% ~ (p=0.073 n=30+30) RegexpMatchMedium_1K-4 43.9µs ± 3% 43.8µs ± 3% ~ (p=0.186 n=30+30) RegexpMatchHard_32-4 2.24µs ± 4% 2.22µs ± 4% ~ (p=0.332 n=30+29) RegexpMatchHard_1K-4 68.0µs ± 4% 67.5µs ± 3% ~ (p=0.290 n=30+30) Revcomp-4 1.85s ± 3% 1.85s ± 3% ~ (p=0.358 n=30+30) Template-4 69.6ms ± 3% 70.0ms ± 4% ~ (p=0.273 n=30+30) TimeParse-4 445ns ± 3% 441ns ± 3% ~ (p=0.494 n=30+30) TimeFormat-4 412ns ± 3% 412ns ± 6% ~ (p=0.841 n=30+30) [Geo mean] 66.7µs 66.8µs +0.13% name old speed new speed delta GobDecode-4 107MB/s ± 5% 106MB/s ± 5% ~ (p=0.615 n=30+30) GobEncode-4 111MB/s ± 6% 111MB/s ± 6% ~ (p=0.790 n=30+30) Gzip-4 48.8MB/s ± 6% 48.7MB/s ± 4% ~ (p=0.167 n=30+30) Gunzip-4 465MB/s ± 3% 465MB/s ± 3% ~ (p=0.420 n=30+30) JSONEncode-4 92.4MB/s ± 4% 93.7MB/s ± 5% +1.42% (p=0.015 n=30+30) JSONDecode-4 29.3MB/s ± 3% 28.8MB/s ± 1% -1.72% (p=0.003 n=30+24) GoParse-4 17.9MB/s ± 3% 17.7MB/s ± 4% -0.89% (p=0.037 n=30+30) RegexpMatchEasy0_32-4 317MB/s ± 8% 324MB/s ± 4% +2.14% (p=0.006 n=30+30) RegexpMatchEasy0_1K-4 1.21GB/s ± 4% 1.22GB/s ± 2% +0.77% (p=0.036 n=30+30) RegexpMatchEasy1_32-4 298MB/s ± 7% 299MB/s ± 4% ~ (p=0.511 n=30+30) RegexpMatchEasy1_1K-4 1.00GB/s ± 3% 1.00GB/s ± 4% ~ (p=0.304 n=28+30) RegexpMatchMedium_32-4 7.75MB/s ± 4% 7.82MB/s ± 4% ~ (p=0.089 n=30+30) RegexpMatchMedium_1K-4 23.3MB/s ± 3% 23.4MB/s ± 3% ~ (p=0.181 n=30+30) RegexpMatchHard_32-4 14.3MB/s ± 4% 14.4MB/s ± 4% ~ (p=0.320 n=30+29) RegexpMatchHard_1K-4 15.1MB/s ± 4% 15.2MB/s ± 3% ~ (p=0.273 n=30+30) Revcomp-4 137MB/s ± 3% 137MB/s ± 3% ~ (p=0.352 n=30+30) Template-4 27.9MB/s ± 3% 27.7MB/s ± 4% ~ (p=0.277 n=30+30) [Geo mean] 79.9MB/s 80.1MB/s +0.15% Change-Id: I97333cd8ddabb3c7c88ca5aa9e14a005b74d306d Reviewed-on: https://go-review.googlesource.com/120695 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-06-24 07:04:21 +00:00
{name: "DIVSSload", argLength: 3, reg: fp21load, asm: "DIVSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 / tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "DIVSDload", argLength: 3, reg: fp21load, asm: "DIVSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 / tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
cmd/compile: optimize 386 binary operations with a memory operand Some integer/float binary operations of 386 can take a direct memory operand, which is more efficient than loading to a register. These CL does this optimization by copying the similar solution of amd64. And the go1 benchmark shows some inprovements, especially the test case Template. (excluding noise) name old time/op new time/op delta BinaryTree17-4 3.42s ± 2% 3.40s ± 2% ~ (p=0.069 n=38+39) Fannkuch11-4 3.48s ± 1% 3.53s ± 1% +1.59% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.7ns ± 4% 46.3ns ± 3% -1.03% (p=0.001 n=40+40) FmtFprintfString-4 80.1ns ± 3% 80.6ns ± 3% +0.56% (p=0.029 n=40+40) FmtFprintfInt-4 92.4ns ± 2% 92.3ns ± 3% ~ (p=0.847 n=40+40) FmtFprintfIntInt-4 147ns ± 3% 144ns ± 3% -1.87% (p=0.000 n=40+40) FmtFprintfPrefixedInt-4 182ns ± 2% 184ns ± 3% +0.99% (p=0.002 n=40+40) FmtFprintfFloat-4 387ns ± 3% 384ns ± 3% ~ (p=0.069 n=40+40) FmtManyArgs-4 619ns ± 3% 616ns ± 3% ~ (p=0.320 n=40+40) GobDecode-4 7.28ms ± 6% 7.27ms ± 5% ~ (p=0.897 n=40+40) GobEncode-4 7.33ms ± 6% 7.21ms ± 6% -1.56% (p=0.022 n=38+40) Gzip-4 357ms ± 4% 357ms ± 4% ~ (p=0.071 n=40+40) Gunzip-4 45.3ms ± 3% 45.4ms ± 3% ~ (p=0.452 n=40+40) HTTPClientServer-4 63.0µs ± 2% 62.9µs ± 3% ~ (p=0.760 n=38+39) JSONEncode-4 22.0ms ± 4% 21.7ms ± 4% -1.49% (p=0.000 n=40+40) JSONDecode-4 67.7ms ± 4% 68.3ms ± 3% +0.86% (p=0.039 n=40+40) Mandelbrot200-4 5.16ms ± 3% 5.17ms ± 3% ~ (p=0.418 n=40+40) GoParse-4 3.30ms ± 2% 3.32ms ± 3% +0.55% (p=0.017 n=40+40) RegexpMatchEasy0_32-4 104ns ± 3% 104ns ± 4% ~ (p=0.992 n=40+40) RegexpMatchEasy0_1K-4 852ns ± 3% 851ns ± 2% ~ (p=0.344 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 5% ~ (p=0.937 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 5% 1.04µs ± 4% ~ (p=0.430 n=40+40) RegexpMatchMedium_32-4 132ns ± 4% 131ns ± 3% -1.06% (p=0.027 n=40+40) RegexpMatchMedium_1K-4 43.0µs ± 3% 43.2µs ± 3% ~ (p=0.122 n=40+40) RegexpMatchHard_32-4 2.21µs ± 4% 2.20µs ± 4% ~ (p=0.146 n=40+40) RegexpMatchHard_1K-4 67.1µs ± 4% 67.2µs ± 3% ~ (p=0.859 n=40+40) Revcomp-4 1.85s ± 2% 1.85s ± 3% ~ (p=0.184 n=40+40) Template-4 70.1ms ± 4% 67.5ms ± 3% -3.65% (p=0.000 n=40+40) TimeParse-4 457ns ±16% 439ns ± 4% ~ (p=0.683 n=40+34) TimeFormat-4 413ns ± 3% 414ns ± 3% ~ (p=0.850 n=40+40) [Geo mean] 67.5µs 67.3µs -0.38% name old speed new speed delta GobDecode-4 105MB/s ± 6% 106MB/s ± 5% ~ (p=0.893 n=40+40) GobEncode-4 105MB/s ± 6% 107MB/s ± 7% +1.60% (p=0.023 n=38+40) Gzip-4 54.4MB/s ± 4% 54.5MB/s ± 4% ~ (p=0.073 n=40+40) Gunzip-4 429MB/s ± 3% 428MB/s ± 3% ~ (p=0.453 n=40+40) JSONEncode-4 88.3MB/s ± 5% 89.6MB/s ± 4% +1.51% (p=0.000 n=40+40) JSONDecode-4 28.7MB/s ± 4% 28.4MB/s ± 3% -0.87% (p=0.039 n=40+40) GoParse-4 17.6MB/s ± 3% 17.5MB/s ± 3% -0.55% (p=0.020 n=40+40) RegexpMatchEasy0_32-4 308MB/s ± 4% 308MB/s ± 5% ~ (p=0.988 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 3% 1.20GB/s ± 2% ~ (p=0.329 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 4% 283MB/s ± 4% ~ (p=0.507 n=40+40) RegexpMatchEasy1_1K-4 991MB/s ± 5% 987MB/s ± 4% ~ (p=0.446 n=40+40) RegexpMatchMedium_32-4 7.54MB/s ± 4% 7.63MB/s ± 3% +1.26% (p=0.004 n=40+40) RegexpMatchMedium_1K-4 23.8MB/s ± 3% 23.7MB/s ± 4% ~ (p=0.121 n=40+40) RegexpMatchHard_32-4 14.5MB/s ± 4% 14.6MB/s ± 4% ~ (p=0.145 n=40+40) RegexpMatchHard_1K-4 15.3MB/s ± 4% 15.2MB/s ± 3% ~ (p=0.874 n=40+40) Revcomp-4 137MB/s ± 2% 137MB/s ± 3% ~ (p=0.179 n=40+40) Template-4 27.7MB/s ± 4% 28.7MB/s ± 3% +3.78% (p=0.000 n=40+40) [Geo mean] 78.9MB/s 79.2MB/s +0.38% Change-Id: I3ba688c253b665485c1ebdf5a75f4ce82cc3def3 Reviewed-on: https://go-review.googlesource.com/102036 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com> Reviewed-by: Keith Randall <khr@golang.org>
2018-03-22 02:18:50 +00:00
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// binary ops
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "ADDL", argLength: 2, reg: gp21sp, asm: "ADDL", commutative: true, clobberFlags: true}, // arg0 + arg1
{name: "ADDLconst", argLength: 1, reg: gp11sp, asm: "ADDL", aux: "Int32", typ: "UInt32", clobberFlags: true}, // arg0 + auxint
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "ADDLcarry", argLength: 2, reg: gp21carry, asm: "ADDL", commutative: true, resultInArg0: true}, // arg0 + arg1, generates <carry,result> pair
{name: "ADDLconstcarry", argLength: 1, reg: gp11carry, asm: "ADDL", aux: "Int32", resultInArg0: true}, // arg0 + auxint, generates <carry,result> pair
{name: "ADCL", argLength: 3, reg: gp2carry1, asm: "ADCL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0+arg1+carry(arg2), where arg2 is flags
{name: "ADCLconst", argLength: 2, reg: gp1carry1, asm: "ADCL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0+auxint+carry(arg1), where arg1 is flags
[dev.ssa] cmd/compile: clean up tuple types and selects Make tuple types and their SelectX ops fully generic. These ops no longer need to be lowered. Regalloc understands them and their tuple-generating arguments. We can now have opcodes returning arbitrary pairs of results. (And it would be easy to move to >2 results if needed.) Update arm implementation to the new standard. Implement just enough in 386 port to do 64-bit add. Change-Id: I370ed5aacce219c82e1954c61d1f63af76c16f79 Reviewed-on: https://go-review.googlesource.com/24976 Reviewed-by: Cherry Zhang <cherryyz@google.com> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org>
2016-07-13 16:15:54 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "SUBL", argLength: 2, reg: gp21, asm: "SUBL", resultInArg0: true, clobberFlags: true}, // arg0 - arg1
{name: "SUBLconst", argLength: 1, reg: gp11, asm: "SUBL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 - auxint
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "SUBLcarry", argLength: 2, reg: gp21carry, asm: "SUBL", resultInArg0: true}, // arg0-arg1, generates <borrow,result> pair
{name: "SUBLconstcarry", argLength: 1, reg: gp11carry, asm: "SUBL", aux: "Int32", resultInArg0: true}, // arg0-auxint, generates <borrow,result> pair
{name: "SBBL", argLength: 3, reg: gp2carry1, asm: "SBBL", resultInArg0: true, clobberFlags: true}, // arg0-arg1-borrow(arg2), where arg2 is flags
{name: "SBBLconst", argLength: 2, reg: gp1carry1, asm: "SBBL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0-auxint-borrow(arg1), where arg1 is flags
[dev.ssa] cmd/compile: implement more 64-bit ops on 386 add/sub/mul, plus constant input variants. Change-Id: I1c8006727c4fdf73558da0e646e7d1fa130ed773 Reviewed-on: https://go-review.googlesource.com/25006 Reviewed-by: David Chase <drchase@google.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-18 11:51:48 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "MULL", argLength: 2, reg: gp21, asm: "IMULL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 * arg1
cmd/compile/internal/ssa: emit IMUL3{L/Q} for MUL{L/Q}const on x86 cmd/asm now supports three-operand form of IMUL, so instead of using IMUL with resultInArg0, emit IMUL3 instruction. This results in less redundant MOVs where SSA assigns different registers to input[0] and dst arguments. Note: these have exactly the same encoding when reg0=reg1: IMUL3x $const, reg0, reg1 IMULx $const, reg Two-operand IMULx is like a crippled IMUL3x, with dst fixed to input[0]. This is why we don't bother to generate IMULx for the case where dst is the same as input[0]. Change-Id: I4becda475b3dffdd07b6fdf1c75bacc82af654e4 Reviewed-on: https://go-review.googlesource.com/99656 Run-TryBot: Iskander Sharipov <iskander.sharipov@intel.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Giovanni Bajo <rasky@develer.com> Reviewed-by: Keith Randall <khr@golang.org>
2018-03-09 23:09:46 +03:00
{name: "MULLconst", argLength: 1, reg: gp11, asm: "IMUL3L", aux: "Int32", clobberFlags: true}, // arg0 * auxint
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: add intrinsics for runtime/internal/math on 386 and amd64 Add generic, 386 and amd64 specific ops and SSA rules for multiplication with overflow and branching based on overflow flags. Use these to intrinsify runtime/internal/math.MulUinptr. On amd64 mul, overflow := math.MulUintptr(a, b) if overflow { is lowered to two instructions: MULQ SI JO 0x10ee35c No codegen tests as codegen can not currently test unexported internal runtime functions. amd64: name old time/op new time/op delta MulUintptr/small 1.16ns ± 5% 0.88ns ± 6% -24.36% (p=0.000 n=19+20) MulUintptr/large 10.7ns ± 1% 1.1ns ± 1% -89.28% (p=0.000 n=17+19) Change-Id: If60739a86f820e5044d677276c21df90d3c7a86a Reviewed-on: https://go-review.googlesource.com/c/141820 Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-01-27 11:55:34 +01:00
{name: "MULLU", argLength: 2, reg: regInfo{inputs: []regMask{ax, gpsp}, outputs: []regMask{ax, 0}, clobbers: dx}, typ: "(UInt32,Flags)", asm: "MULL", commutative: true, clobberFlags: true}, // Let x = arg0*arg1 (full 32x32->64 unsigned multiply). Returns uint32(x), and flags set to overflow if uint32(x) != x.
cmd/compile: automatically handle commuting ops in rewrite rules Note that this is a redo of an undo of the original buggy CL 38666. We have lots of rewrite rules that vary only in the fact that we have 2 versions for the 2 different orderings of various commuting ops. For example: (ADDL x (MOVLconst [c])) -> (ADDLconst [c] x) (ADDL (MOVLconst [c]) x) -> (ADDLconst [c] x) It can get unwieldly quickly, especially when there is more than one commuting op in a rule. Our existing "fix" for this problem is to have rules that canonicalize the operations first. For example: (Eq64 x (Const64 <t> [c])) && x.Op != OpConst64 -> (Eq64 (Const64 <t> [c]) x) Subsequent rules can then assume if there is a constant arg to Eq64, it will be the first one. This fix kinda works, but it is fragile and only works when we remember to include the required extra rules. The fundamental problem is that the rule matcher doesn't know anything about commuting ops. This CL fixes that fact. We already have information about which ops commute. (The register allocator takes advantage of commutivity.) The rule generator now automatically generates multiple rules for a single source rule when there are commutative ops in the rule. We can now drop all of our almost-duplicate source-level rules and the canonicalization rules. I have some CLs in progress that will be a lot less verbose when the rule generator handles commutivity for me. I had to reorganize the load-combining rules a bit. The 8-way OR rules generated 128 different reorderings, which was causing the generator to put too much code in the rewrite*.go files (the big ones were going from 25K lines to 132K lines). Instead I reorganized the rules to combine pairs of loads at a time. The generated rule files are now actually a bit (5%) smaller. Make.bash times are ~unchanged. Compiler benchmarks are not observably different. Probably because we don't spend much compiler time in rule matching anyway. I've also done a pass over all of our ops adding commutative markings for ops which hadn't had them previously. Fixes #18292 Change-Id: Ic1c0e43fbf579539f459971625f69690c9ab8805 Reviewed-on: https://go-review.googlesource.com/38801 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-03-30 03:30:22 +00:00
{name: "HMULL", argLength: 2, reg: gp21hmul, commutative: true, asm: "IMULL", clobberFlags: true}, // (arg0 * arg1) >> width
{name: "HMULLU", argLength: 2, reg: gp21hmul, commutative: true, asm: "MULL", clobberFlags: true}, // (arg0 * arg1) >> width
[dev.ssa] cmd/compile: implement more 64-bit ops on 386 add/sub/mul, plus constant input variants. Change-Id: I1c8006727c4fdf73558da0e646e7d1fa130ed773 Reviewed-on: https://go-review.googlesource.com/25006 Reviewed-by: David Chase <drchase@google.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-18 11:51:48 -07:00
cmd/compile: automatically handle commuting ops in rewrite rules Note that this is a redo of an undo of the original buggy CL 38666. We have lots of rewrite rules that vary only in the fact that we have 2 versions for the 2 different orderings of various commuting ops. For example: (ADDL x (MOVLconst [c])) -> (ADDLconst [c] x) (ADDL (MOVLconst [c]) x) -> (ADDLconst [c] x) It can get unwieldly quickly, especially when there is more than one commuting op in a rule. Our existing "fix" for this problem is to have rules that canonicalize the operations first. For example: (Eq64 x (Const64 <t> [c])) && x.Op != OpConst64 -> (Eq64 (Const64 <t> [c]) x) Subsequent rules can then assume if there is a constant arg to Eq64, it will be the first one. This fix kinda works, but it is fragile and only works when we remember to include the required extra rules. The fundamental problem is that the rule matcher doesn't know anything about commuting ops. This CL fixes that fact. We already have information about which ops commute. (The register allocator takes advantage of commutivity.) The rule generator now automatically generates multiple rules for a single source rule when there are commutative ops in the rule. We can now drop all of our almost-duplicate source-level rules and the canonicalization rules. I have some CLs in progress that will be a lot less verbose when the rule generator handles commutivity for me. I had to reorganize the load-combining rules a bit. The 8-way OR rules generated 128 different reorderings, which was causing the generator to put too much code in the rewrite*.go files (the big ones were going from 25K lines to 132K lines). Instead I reorganized the rules to combine pairs of loads at a time. The generated rule files are now actually a bit (5%) smaller. Make.bash times are ~unchanged. Compiler benchmarks are not observably different. Probably because we don't spend much compiler time in rule matching anyway. I've also done a pass over all of our ops adding commutative markings for ops which hadn't had them previously. Fixes #18292 Change-Id: Ic1c0e43fbf579539f459971625f69690c9ab8805 Reviewed-on: https://go-review.googlesource.com/38801 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-03-30 03:30:22 +00:00
{name: "MULLQU", argLength: 2, reg: gp21mul, commutative: true, asm: "MULL", clobberFlags: true}, // arg0 * arg1, high 32 in result[0], low 32 in result[1]
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: move constant divide strength reduction to SSA rules Currently the conversion from constant divides to multiplies is mostly done during the walk pass. This is suboptimal because SSA can determine that the value being divided by is constant more often (e.g. after inlining). Change-Id: If1a9b993edd71be37396b9167f77da271966f85f Reviewed-on: https://go-review.googlesource.com/37015 Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
2017-02-13 16:00:09 -08:00
{name: "AVGLU", argLength: 2, reg: gp21, commutative: true, resultInArg0: true, clobberFlags: true}, // (arg0 + arg1) / 2 as unsigned, all 32 result bits
cmd/compile: use proved bounds to remove signed division fix-ups prove is able to find 94 occurrences in std cmd where a divisor can't have the value -1. The change removes the extraneous fix-up code for these cases. Fixes #25239 Change-Id: Ic184de971f47cc57c702eb72805b8e291c14035d Reviewed-on: https://go-review.googlesource.com/c/130215 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-08-06 19:50:38 +10:00
// For DIVL, DIVW, MODL and MODW, AuxInt non-zero means that the divisor has been proved to be not -1.
{name: "DIVL", argLength: 2, reg: gp11div, asm: "IDIVL", aux: "Bool", clobberFlags: true}, // arg0 / arg1
{name: "DIVW", argLength: 2, reg: gp11div, asm: "IDIVW", aux: "Bool", clobberFlags: true}, // arg0 / arg1
{name: "DIVLU", argLength: 2, reg: gp11div, asm: "DIVL", clobberFlags: true}, // arg0 / arg1
{name: "DIVWU", argLength: 2, reg: gp11div, asm: "DIVW", clobberFlags: true}, // arg0 / arg1
{name: "MODL", argLength: 2, reg: gp11mod, asm: "IDIVL", aux: "Bool", clobberFlags: true}, // arg0 % arg1
{name: "MODW", argLength: 2, reg: gp11mod, asm: "IDIVW", aux: "Bool", clobberFlags: true}, // arg0 % arg1
{name: "MODLU", argLength: 2, reg: gp11mod, asm: "DIVL", clobberFlags: true}, // arg0 % arg1
{name: "MODWU", argLength: 2, reg: gp11mod, asm: "DIVW", clobberFlags: true}, // arg0 % arg1
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "ANDL", argLength: 2, reg: gp21, asm: "ANDL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 & arg1
{name: "ANDLconst", argLength: 1, reg: gp11, asm: "ANDL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 & auxint
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "ORL", argLength: 2, reg: gp21, asm: "ORL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 | arg1
{name: "ORLconst", argLength: 1, reg: gp11, asm: "ORL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 | auxint
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "XORL", argLength: 2, reg: gp21, asm: "XORL", commutative: true, resultInArg0: true, clobberFlags: true}, // arg0 ^ arg1
{name: "XORLconst", argLength: 1, reg: gp11, asm: "XORL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 ^ auxint
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "CMPL", argLength: 2, reg: gp2flags, asm: "CMPL", typ: "Flags"}, // arg0 compare to arg1
{name: "CMPW", argLength: 2, reg: gp2flags, asm: "CMPW", typ: "Flags"}, // arg0 compare to arg1
{name: "CMPB", argLength: 2, reg: gp2flags, asm: "CMPB", typ: "Flags"}, // arg0 compare to arg1
{name: "CMPLconst", argLength: 1, reg: gp1flags, asm: "CMPL", typ: "Flags", aux: "Int32"}, // arg0 compare to auxint
{name: "CMPWconst", argLength: 1, reg: gp1flags, asm: "CMPW", typ: "Flags", aux: "Int16"}, // arg0 compare to auxint
{name: "CMPBconst", argLength: 1, reg: gp1flags, asm: "CMPB", typ: "Flags", aux: "Int8"}, // arg0 compare to auxint
cmd/compile: optimize 386's comparison CMPL/CMPW/CMPB can take a memory operand on 386, and this CL implements that optimization. 1. The total size of pkg/linux_386 decreases about 45KB, excluding cmd/compile. 2. The go1 benchmark shows a little improvement. name old time/op new time/op delta BinaryTree17-4 3.36s ± 2% 3.37s ± 3% ~ (p=0.537 n=40+40) Fannkuch11-4 3.59s ± 1% 3.53s ± 2% -1.58% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.0ns ± 3% 45.8ns ± 3% ~ (p=0.249 n=40+40) FmtFprintfString-4 80.0ns ± 4% 78.8ns ± 3% -1.49% (p=0.001 n=40+40) FmtFprintfInt-4 89.7ns ± 2% 90.3ns ± 2% +0.74% (p=0.003 n=40+40) FmtFprintfIntInt-4 144ns ± 3% 143ns ± 3% -0.95% (p=0.003 n=40+40) FmtFprintfPrefixedInt-4 181ns ± 4% 180ns ± 2% ~ (p=0.103 n=40+40) FmtFprintfFloat-4 412ns ± 3% 408ns ± 4% -0.97% (p=0.018 n=40+40) FmtManyArgs-4 607ns ± 4% 605ns ± 4% ~ (p=0.148 n=40+40) GobDecode-4 7.19ms ± 4% 7.24ms ± 5% ~ (p=0.340 n=40+40) GobEncode-4 7.04ms ± 9% 6.99ms ± 9% ~ (p=0.289 n=40+40) Gzip-4 400ms ± 6% 398ms ± 5% ~ (p=0.168 n=40+40) Gunzip-4 41.2ms ± 3% 41.7ms ± 3% +1.40% (p=0.001 n=40+40) HTTPClientServer-4 62.5µs ± 1% 62.1µs ± 2% -0.61% (p=0.000 n=37+37) JSONEncode-4 20.7ms ± 4% 20.4ms ± 3% -1.60% (p=0.000 n=40+40) JSONDecode-4 69.4ms ± 4% 69.2ms ± 6% ~ (p=0.177 n=40+40) Mandelbrot200-4 5.22ms ± 6% 5.21ms ± 3% ~ (p=0.531 n=40+40) GoParse-4 3.29ms ± 3% 3.28ms ± 3% ~ (p=0.321 n=40+39) RegexpMatchEasy0_32-4 104ns ± 4% 103ns ± 7% -0.89% (p=0.040 n=40+40) RegexpMatchEasy0_1K-4 852ns ± 3% 853ns ± 2% ~ (p=0.357 n=40+40) RegexpMatchEasy1_32-4 113ns ± 8% 113ns ± 3% ~ (p=0.906 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 5% ~ (p=0.326 n=40+40) RegexpMatchMedium_32-4 136ns ± 3% 133ns ± 3% -2.31% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 44.0µs ± 3% 43.7µs ± 3% ~ (p=0.053 n=40+40) RegexpMatchHard_32-4 2.27µs ± 3% 2.26µs ± 4% ~ (p=0.391 n=40+40) RegexpMatchHard_1K-4 68.0µs ± 3% 68.9µs ± 3% +1.28% (p=0.000 n=40+40) Revcomp-4 1.86s ± 5% 1.86s ± 2% ~ (p=0.950 n=40+40) Template-4 73.4ms ± 4% 69.9ms ± 7% -4.78% (p=0.000 n=40+40) TimeParse-4 449ns ± 4% 441ns ± 5% -1.76% (p=0.000 n=40+40) TimeFormat-4 416ns ± 3% 417ns ± 4% ~ (p=0.304 n=40+40) [Geo mean] 67.7µs 67.3µs -0.55% name old speed new speed delta GobDecode-4 107MB/s ± 4% 106MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 109MB/s ± 5% 110MB/s ± 9% ~ (p=0.142 n=38+40) Gzip-4 48.5MB/s ± 5% 48.8MB/s ± 5% ~ (p=0.172 n=40+40) Gunzip-4 472MB/s ± 3% 465MB/s ± 3% -1.39% (p=0.001 n=40+40) JSONEncode-4 93.6MB/s ± 4% 95.1MB/s ± 3% +1.61% (p=0.000 n=40+40) JSONDecode-4 28.0MB/s ± 3% 28.1MB/s ± 6% ~ (p=0.181 n=40+40) GoParse-4 17.6MB/s ± 3% 17.7MB/s ± 3% ~ (p=0.350 n=40+39) RegexpMatchEasy0_32-4 308MB/s ± 4% 311MB/s ± 6% +0.96% (p=0.025 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 3% 1.20GB/s ± 2% ~ (p=0.317 n=40+40) RegexpMatchEasy1_32-4 282MB/s ± 7% 282MB/s ± 3% ~ (p=0.516 n=40+40) RegexpMatchEasy1_1K-4 994MB/s ± 4% 991MB/s ± 5% ~ (p=0.319 n=40+40) RegexpMatchMedium_32-4 7.31MB/s ± 3% 7.49MB/s ± 3% +2.46% (p=0.000 n=40+40) RegexpMatchMedium_1K-4 23.3MB/s ± 3% 23.4MB/s ± 3% ~ (p=0.052 n=40+40) RegexpMatchHard_32-4 14.1MB/s ± 3% 14.1MB/s ± 4% ~ (p=0.391 n=40+40) RegexpMatchHard_1K-4 15.1MB/s ± 3% 14.9MB/s ± 3% -1.27% (p=0.000 n=40+40) Revcomp-4 137MB/s ± 5% 137MB/s ± 2% ~ (p=0.942 n=40+40) Template-4 26.5MB/s ± 4% 27.8MB/s ± 7% +5.03% (p=0.000 n=40+40) [Geo mean] 78.6MB/s 79.0MB/s +0.57% Change-Id: Idcacc6881ef57cd7dc33aa87b711282842b72a53 Reviewed-on: https://go-review.googlesource.com/126618 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-07-29 12:50:50 +00:00
// compare *(arg0+auxint+aux) to arg1 (in that order). arg2=mem.
{name: "CMPLload", argLength: 3, reg: gp1flagsLoad, asm: "CMPL", aux: "SymOff", typ: "Flags", symEffect: "Read", faultOnNilArg0: true},
{name: "CMPWload", argLength: 3, reg: gp1flagsLoad, asm: "CMPW", aux: "SymOff", typ: "Flags", symEffect: "Read", faultOnNilArg0: true},
{name: "CMPBload", argLength: 3, reg: gp1flagsLoad, asm: "CMPB", aux: "SymOff", typ: "Flags", symEffect: "Read", faultOnNilArg0: true},
// compare *(arg0+ValAndOff(AuxInt).Off()+aux) to ValAndOff(AuxInt).Val() (in that order). arg1=mem.
{name: "CMPLconstload", argLength: 2, reg: gp0flagsLoad, asm: "CMPL", aux: "SymValAndOff", typ: "Flags", symEffect: "Read", faultOnNilArg0: true},
{name: "CMPWconstload", argLength: 2, reg: gp0flagsLoad, asm: "CMPW", aux: "SymValAndOff", typ: "Flags", symEffect: "Read", faultOnNilArg0: true},
{name: "CMPBconstload", argLength: 2, reg: gp0flagsLoad, asm: "CMPB", aux: "SymValAndOff", typ: "Flags", symEffect: "Read", faultOnNilArg0: true},
cmd/compile: remove backend's "scratch mem" support This CL rebases CL 273987 on top of master with @mdempsky's permission. The last (only?) use for this feature was 387 support, which was removed in golang.org/cl/258957. Change-Id: I4f79fee8d0c336c9b6082bcd5eb6ece52c032dc0 Reviewed-on: https://go-review.googlesource.com/c/go/+/292893 Trust: Cuong Manh Le <cuong.manhle.vn@gmail.com> Run-TryBot: Cuong Manh Le <cuong.manhle.vn@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Matthew Dempsky <mdempsky@google.com>
2021-02-17 15:27:42 +07:00
{name: "UCOMISS", argLength: 2, reg: fp2flags, asm: "UCOMISS", typ: "Flags"}, // arg0 compare to arg1, f32
{name: "UCOMISD", argLength: 2, reg: fp2flags, asm: "UCOMISD", typ: "Flags"}, // arg0 compare to arg1, f64
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: automatically handle commuting ops in rewrite rules Note that this is a redo of an undo of the original buggy CL 38666. We have lots of rewrite rules that vary only in the fact that we have 2 versions for the 2 different orderings of various commuting ops. For example: (ADDL x (MOVLconst [c])) -> (ADDLconst [c] x) (ADDL (MOVLconst [c]) x) -> (ADDLconst [c] x) It can get unwieldly quickly, especially when there is more than one commuting op in a rule. Our existing "fix" for this problem is to have rules that canonicalize the operations first. For example: (Eq64 x (Const64 <t> [c])) && x.Op != OpConst64 -> (Eq64 (Const64 <t> [c]) x) Subsequent rules can then assume if there is a constant arg to Eq64, it will be the first one. This fix kinda works, but it is fragile and only works when we remember to include the required extra rules. The fundamental problem is that the rule matcher doesn't know anything about commuting ops. This CL fixes that fact. We already have information about which ops commute. (The register allocator takes advantage of commutivity.) The rule generator now automatically generates multiple rules for a single source rule when there are commutative ops in the rule. We can now drop all of our almost-duplicate source-level rules and the canonicalization rules. I have some CLs in progress that will be a lot less verbose when the rule generator handles commutivity for me. I had to reorganize the load-combining rules a bit. The 8-way OR rules generated 128 different reorderings, which was causing the generator to put too much code in the rewrite*.go files (the big ones were going from 25K lines to 132K lines). Instead I reorganized the rules to combine pairs of loads at a time. The generated rule files are now actually a bit (5%) smaller. Make.bash times are ~unchanged. Compiler benchmarks are not observably different. Probably because we don't spend much compiler time in rule matching anyway. I've also done a pass over all of our ops adding commutative markings for ops which hadn't had them previously. Fixes #18292 Change-Id: Ic1c0e43fbf579539f459971625f69690c9ab8805 Reviewed-on: https://go-review.googlesource.com/38801 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-03-30 03:30:22 +00:00
{name: "TESTL", argLength: 2, reg: gp2flags, commutative: true, asm: "TESTL", typ: "Flags"}, // (arg0 & arg1) compare to 0
{name: "TESTW", argLength: 2, reg: gp2flags, commutative: true, asm: "TESTW", typ: "Flags"}, // (arg0 & arg1) compare to 0
{name: "TESTB", argLength: 2, reg: gp2flags, commutative: true, asm: "TESTB", typ: "Flags"}, // (arg0 & arg1) compare to 0
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "TESTLconst", argLength: 1, reg: gp1flags, asm: "TESTL", typ: "Flags", aux: "Int32"}, // (arg0 & auxint) compare to 0
{name: "TESTWconst", argLength: 1, reg: gp1flags, asm: "TESTW", typ: "Flags", aux: "Int16"}, // (arg0 & auxint) compare to 0
{name: "TESTBconst", argLength: 1, reg: gp1flags, asm: "TESTB", typ: "Flags", aux: "Int8"}, // (arg0 & auxint) compare to 0
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "SHLL", argLength: 2, reg: gp21shift, asm: "SHLL", resultInArg0: true, clobberFlags: true}, // arg0 << arg1, shift amount is mod 32
{name: "SHLLconst", argLength: 1, reg: gp11, asm: "SHLL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 << auxint, shift amount 0-31
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// Note: x86 is weird, the 16 and 8 byte shifts still use all 5 bits of shift amount!
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "SHRL", argLength: 2, reg: gp21shift, asm: "SHRL", resultInArg0: true, clobberFlags: true}, // unsigned arg0 >> arg1, shift amount is mod 32
{name: "SHRW", argLength: 2, reg: gp21shift, asm: "SHRW", resultInArg0: true, clobberFlags: true}, // unsigned arg0 >> arg1, shift amount is mod 32
{name: "SHRB", argLength: 2, reg: gp21shift, asm: "SHRB", resultInArg0: true, clobberFlags: true}, // unsigned arg0 >> arg1, shift amount is mod 32
{name: "SHRLconst", argLength: 1, reg: gp11, asm: "SHRL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // unsigned arg0 >> auxint, shift amount 0-31
cmd/compile: move rotate instruction generation to SSA Remove rotate generation from walk. Remove OLROT and ssa.Lrot* opcodes. Generate rotates during SSA lowering for architectures that have them. This CL will allow rotates to be generated in more situations, like when the shift values are determined to be constant only after some analysis. Fixes #18254 Change-Id: I8d6d684ff5ce2511aceaddfda98b908007851079 Reviewed-on: https://go-review.googlesource.com/34232 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-12-08 16:17:20 -08:00
{name: "SHRWconst", argLength: 1, reg: gp11, asm: "SHRW", aux: "Int16", resultInArg0: true, clobberFlags: true}, // unsigned arg0 >> auxint, shift amount 0-15
{name: "SHRBconst", argLength: 1, reg: gp11, asm: "SHRB", aux: "Int8", resultInArg0: true, clobberFlags: true}, // unsigned arg0 >> auxint, shift amount 0-7
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "SARL", argLength: 2, reg: gp21shift, asm: "SARL", resultInArg0: true, clobberFlags: true}, // signed arg0 >> arg1, shift amount is mod 32
{name: "SARW", argLength: 2, reg: gp21shift, asm: "SARW", resultInArg0: true, clobberFlags: true}, // signed arg0 >> arg1, shift amount is mod 32
{name: "SARB", argLength: 2, reg: gp21shift, asm: "SARB", resultInArg0: true, clobberFlags: true}, // signed arg0 >> arg1, shift amount is mod 32
{name: "SARLconst", argLength: 1, reg: gp11, asm: "SARL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // signed arg0 >> auxint, shift amount 0-31
cmd/compile: move rotate instruction generation to SSA Remove rotate generation from walk. Remove OLROT and ssa.Lrot* opcodes. Generate rotates during SSA lowering for architectures that have them. This CL will allow rotates to be generated in more situations, like when the shift values are determined to be constant only after some analysis. Fixes #18254 Change-Id: I8d6d684ff5ce2511aceaddfda98b908007851079 Reviewed-on: https://go-review.googlesource.com/34232 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-12-08 16:17:20 -08:00
{name: "SARWconst", argLength: 1, reg: gp11, asm: "SARW", aux: "Int16", resultInArg0: true, clobberFlags: true}, // signed arg0 >> auxint, shift amount 0-15
{name: "SARBconst", argLength: 1, reg: gp11, asm: "SARB", aux: "Int8", resultInArg0: true, clobberFlags: true}, // signed arg0 >> auxint, shift amount 0-7
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: move SSA rotate instruction detection to arch-independent rules Detect rotate instructions while still in architecture-independent form. It's easier to do here, and we don't need to repeat it in each architecture file. Change-Id: I9396954b3f3b3bfb96c160d064a02002309935bb Reviewed-on: https://go-review.googlesource.com/c/go/+/421195 TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Eric Fang <eric.fang@arm.com> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com> Reviewed-by: David Chase <drchase@google.com> Reviewed-by: Joedian Reid <joedian@golang.org> Reviewed-by: Ruinan Sun <Ruinan.Sun@arm.com> Run-TryBot: Keith Randall <khr@golang.org>
2022-08-03 22:58:30 -07:00
{name: "ROLL", argLength: 2, reg: gp21shift, asm: "ROLL", resultInArg0: true, clobberFlags: true}, // 32 bits of arg0 rotate left by arg1
{name: "ROLW", argLength: 2, reg: gp21shift, asm: "ROLW", resultInArg0: true, clobberFlags: true}, // low 16 bits of arg0 rotate left by arg1
{name: "ROLB", argLength: 2, reg: gp21shift, asm: "ROLB", resultInArg0: true, clobberFlags: true}, // low 8 bits of arg0 rotate left by arg1
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "ROLLconst", argLength: 1, reg: gp11, asm: "ROLL", aux: "Int32", resultInArg0: true, clobberFlags: true}, // arg0 rotate left auxint, rotate amount 0-31
{name: "ROLWconst", argLength: 1, reg: gp11, asm: "ROLW", aux: "Int16", resultInArg0: true, clobberFlags: true}, // arg0 rotate left auxint, rotate amount 0-15
{name: "ROLBconst", argLength: 1, reg: gp11, asm: "ROLB", aux: "Int8", resultInArg0: true, clobberFlags: true}, // arg0 rotate left auxint, rotate amount 0-7
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
// binary-op with a memory source operand
cmd/compile: optimize 386 code with MULLload/DIVSSload/DIVSDload IMULL/DIVSS/DIVSD all can take the source operand from memory directly. And this CL implement that optimization. 1. The total size of pkg/linux_386 decreases about 84KB (excluding cmd/compile). 2. The go1 benchmark shows little regression in total (excluding noise). name old time/op new time/op delta BinaryTree17-4 3.29s ± 2% 3.27s ± 4% ~ (p=0.192 n=30+30) Fannkuch11-4 3.49s ± 2% 3.54s ± 1% +1.48% (p=0.000 n=30+30) FmtFprintfEmpty-4 45.9ns ± 3% 46.3ns ± 4% +0.89% (p=0.037 n=30+30) FmtFprintfString-4 78.8ns ± 3% 78.7ns ± 4% ~ (p=0.209 n=30+27) FmtFprintfInt-4 91.0ns ± 2% 90.3ns ± 2% -0.82% (p=0.031 n=30+27) FmtFprintfIntInt-4 142ns ± 4% 143ns ± 4% ~ (p=0.136 n=30+30) FmtFprintfPrefixedInt-4 181ns ± 3% 183ns ± 4% +1.40% (p=0.005 n=30+30) FmtFprintfFloat-4 404ns ± 4% 408ns ± 3% ~ (p=0.397 n=30+30) FmtManyArgs-4 601ns ± 3% 609ns ± 5% ~ (p=0.059 n=30+30) GobDecode-4 7.21ms ± 5% 7.24ms ± 5% ~ (p=0.612 n=30+30) GobEncode-4 6.91ms ± 6% 6.91ms ± 6% ~ (p=0.797 n=30+30) Gzip-4 398ms ± 6% 399ms ± 4% ~ (p=0.173 n=30+30) Gunzip-4 41.7ms ± 3% 41.8ms ± 3% ~ (p=0.423 n=30+30) HTTPClientServer-4 62.3µs ± 2% 62.7µs ± 3% ~ (p=0.085 n=29+30) JSONEncode-4 21.0ms ± 4% 20.7ms ± 5% -1.39% (p=0.014 n=30+30) JSONDecode-4 66.3ms ± 3% 67.4ms ± 1% +1.71% (p=0.003 n=30+24) Mandelbrot200-4 5.15ms ± 3% 5.16ms ± 3% ~ (p=0.697 n=30+30) GoParse-4 3.24ms ± 3% 3.27ms ± 4% +0.91% (p=0.032 n=30+30) RegexpMatchEasy0_32-4 101ns ± 5% 99ns ± 4% -1.82% (p=0.008 n=29+30) RegexpMatchEasy0_1K-4 848ns ± 4% 841ns ± 2% -0.77% (p=0.043 n=30+30) RegexpMatchEasy1_32-4 106ns ± 6% 106ns ± 3% ~ (p=0.939 n=29+30) RegexpMatchEasy1_1K-4 1.02µs ± 3% 1.03µs ± 4% ~ (p=0.297 n=28+30) RegexpMatchMedium_32-4 129ns ± 4% 127ns ± 4% ~ (p=0.073 n=30+30) RegexpMatchMedium_1K-4 43.9µs ± 3% 43.8µs ± 3% ~ (p=0.186 n=30+30) RegexpMatchHard_32-4 2.24µs ± 4% 2.22µs ± 4% ~ (p=0.332 n=30+29) RegexpMatchHard_1K-4 68.0µs ± 4% 67.5µs ± 3% ~ (p=0.290 n=30+30) Revcomp-4 1.85s ± 3% 1.85s ± 3% ~ (p=0.358 n=30+30) Template-4 69.6ms ± 3% 70.0ms ± 4% ~ (p=0.273 n=30+30) TimeParse-4 445ns ± 3% 441ns ± 3% ~ (p=0.494 n=30+30) TimeFormat-4 412ns ± 3% 412ns ± 6% ~ (p=0.841 n=30+30) [Geo mean] 66.7µs 66.8µs +0.13% name old speed new speed delta GobDecode-4 107MB/s ± 5% 106MB/s ± 5% ~ (p=0.615 n=30+30) GobEncode-4 111MB/s ± 6% 111MB/s ± 6% ~ (p=0.790 n=30+30) Gzip-4 48.8MB/s ± 6% 48.7MB/s ± 4% ~ (p=0.167 n=30+30) Gunzip-4 465MB/s ± 3% 465MB/s ± 3% ~ (p=0.420 n=30+30) JSONEncode-4 92.4MB/s ± 4% 93.7MB/s ± 5% +1.42% (p=0.015 n=30+30) JSONDecode-4 29.3MB/s ± 3% 28.8MB/s ± 1% -1.72% (p=0.003 n=30+24) GoParse-4 17.9MB/s ± 3% 17.7MB/s ± 4% -0.89% (p=0.037 n=30+30) RegexpMatchEasy0_32-4 317MB/s ± 8% 324MB/s ± 4% +2.14% (p=0.006 n=30+30) RegexpMatchEasy0_1K-4 1.21GB/s ± 4% 1.22GB/s ± 2% +0.77% (p=0.036 n=30+30) RegexpMatchEasy1_32-4 298MB/s ± 7% 299MB/s ± 4% ~ (p=0.511 n=30+30) RegexpMatchEasy1_1K-4 1.00GB/s ± 3% 1.00GB/s ± 4% ~ (p=0.304 n=28+30) RegexpMatchMedium_32-4 7.75MB/s ± 4% 7.82MB/s ± 4% ~ (p=0.089 n=30+30) RegexpMatchMedium_1K-4 23.3MB/s ± 3% 23.4MB/s ± 3% ~ (p=0.181 n=30+30) RegexpMatchHard_32-4 14.3MB/s ± 4% 14.4MB/s ± 4% ~ (p=0.320 n=30+29) RegexpMatchHard_1K-4 15.1MB/s ± 4% 15.2MB/s ± 3% ~ (p=0.273 n=30+30) Revcomp-4 137MB/s ± 3% 137MB/s ± 3% ~ (p=0.352 n=30+30) Template-4 27.9MB/s ± 3% 27.7MB/s ± 4% ~ (p=0.277 n=30+30) [Geo mean] 79.9MB/s 80.1MB/s +0.15% Change-Id: I97333cd8ddabb3c7c88ca5aa9e14a005b74d306d Reviewed-on: https://go-review.googlesource.com/120695 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-06-24 07:04:21 +00:00
{name: "ADDLload", argLength: 3, reg: gp21load, asm: "ADDL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 + tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "SUBLload", argLength: 3, reg: gp21load, asm: "SUBL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 - tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "MULLload", argLength: 3, reg: gp21load, asm: "IMULL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 * tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "ANDLload", argLength: 3, reg: gp21load, asm: "ANDL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 & tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "ORLload", argLength: 3, reg: gp21load, asm: "ORL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 | tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "XORLload", argLength: 3, reg: gp21load, asm: "XORL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 ^ tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
cmd/compile: optimize 386 binary operations with a memory operand Some integer/float binary operations of 386 can take a direct memory operand, which is more efficient than loading to a register. These CL does this optimization by copying the similar solution of amd64. And the go1 benchmark shows some inprovements, especially the test case Template. (excluding noise) name old time/op new time/op delta BinaryTree17-4 3.42s ± 2% 3.40s ± 2% ~ (p=0.069 n=38+39) Fannkuch11-4 3.48s ± 1% 3.53s ± 1% +1.59% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.7ns ± 4% 46.3ns ± 3% -1.03% (p=0.001 n=40+40) FmtFprintfString-4 80.1ns ± 3% 80.6ns ± 3% +0.56% (p=0.029 n=40+40) FmtFprintfInt-4 92.4ns ± 2% 92.3ns ± 3% ~ (p=0.847 n=40+40) FmtFprintfIntInt-4 147ns ± 3% 144ns ± 3% -1.87% (p=0.000 n=40+40) FmtFprintfPrefixedInt-4 182ns ± 2% 184ns ± 3% +0.99% (p=0.002 n=40+40) FmtFprintfFloat-4 387ns ± 3% 384ns ± 3% ~ (p=0.069 n=40+40) FmtManyArgs-4 619ns ± 3% 616ns ± 3% ~ (p=0.320 n=40+40) GobDecode-4 7.28ms ± 6% 7.27ms ± 5% ~ (p=0.897 n=40+40) GobEncode-4 7.33ms ± 6% 7.21ms ± 6% -1.56% (p=0.022 n=38+40) Gzip-4 357ms ± 4% 357ms ± 4% ~ (p=0.071 n=40+40) Gunzip-4 45.3ms ± 3% 45.4ms ± 3% ~ (p=0.452 n=40+40) HTTPClientServer-4 63.0µs ± 2% 62.9µs ± 3% ~ (p=0.760 n=38+39) JSONEncode-4 22.0ms ± 4% 21.7ms ± 4% -1.49% (p=0.000 n=40+40) JSONDecode-4 67.7ms ± 4% 68.3ms ± 3% +0.86% (p=0.039 n=40+40) Mandelbrot200-4 5.16ms ± 3% 5.17ms ± 3% ~ (p=0.418 n=40+40) GoParse-4 3.30ms ± 2% 3.32ms ± 3% +0.55% (p=0.017 n=40+40) RegexpMatchEasy0_32-4 104ns ± 3% 104ns ± 4% ~ (p=0.992 n=40+40) RegexpMatchEasy0_1K-4 852ns ± 3% 851ns ± 2% ~ (p=0.344 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 5% ~ (p=0.937 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 5% 1.04µs ± 4% ~ (p=0.430 n=40+40) RegexpMatchMedium_32-4 132ns ± 4% 131ns ± 3% -1.06% (p=0.027 n=40+40) RegexpMatchMedium_1K-4 43.0µs ± 3% 43.2µs ± 3% ~ (p=0.122 n=40+40) RegexpMatchHard_32-4 2.21µs ± 4% 2.20µs ± 4% ~ (p=0.146 n=40+40) RegexpMatchHard_1K-4 67.1µs ± 4% 67.2µs ± 3% ~ (p=0.859 n=40+40) Revcomp-4 1.85s ± 2% 1.85s ± 3% ~ (p=0.184 n=40+40) Template-4 70.1ms ± 4% 67.5ms ± 3% -3.65% (p=0.000 n=40+40) TimeParse-4 457ns ±16% 439ns ± 4% ~ (p=0.683 n=40+34) TimeFormat-4 413ns ± 3% 414ns ± 3% ~ (p=0.850 n=40+40) [Geo mean] 67.5µs 67.3µs -0.38% name old speed new speed delta GobDecode-4 105MB/s ± 6% 106MB/s ± 5% ~ (p=0.893 n=40+40) GobEncode-4 105MB/s ± 6% 107MB/s ± 7% +1.60% (p=0.023 n=38+40) Gzip-4 54.4MB/s ± 4% 54.5MB/s ± 4% ~ (p=0.073 n=40+40) Gunzip-4 429MB/s ± 3% 428MB/s ± 3% ~ (p=0.453 n=40+40) JSONEncode-4 88.3MB/s ± 5% 89.6MB/s ± 4% +1.51% (p=0.000 n=40+40) JSONDecode-4 28.7MB/s ± 4% 28.4MB/s ± 3% -0.87% (p=0.039 n=40+40) GoParse-4 17.6MB/s ± 3% 17.5MB/s ± 3% -0.55% (p=0.020 n=40+40) RegexpMatchEasy0_32-4 308MB/s ± 4% 308MB/s ± 5% ~ (p=0.988 n=40+40) RegexpMatchEasy0_1K-4 1.20GB/s ± 3% 1.20GB/s ± 2% ~ (p=0.329 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 4% 283MB/s ± 4% ~ (p=0.507 n=40+40) RegexpMatchEasy1_1K-4 991MB/s ± 5% 987MB/s ± 4% ~ (p=0.446 n=40+40) RegexpMatchMedium_32-4 7.54MB/s ± 4% 7.63MB/s ± 3% +1.26% (p=0.004 n=40+40) RegexpMatchMedium_1K-4 23.8MB/s ± 3% 23.7MB/s ± 4% ~ (p=0.121 n=40+40) RegexpMatchHard_32-4 14.5MB/s ± 4% 14.6MB/s ± 4% ~ (p=0.145 n=40+40) RegexpMatchHard_1K-4 15.3MB/s ± 4% 15.2MB/s ± 3% ~ (p=0.874 n=40+40) Revcomp-4 137MB/s ± 2% 137MB/s ± 3% ~ (p=0.179 n=40+40) Template-4 27.7MB/s ± 4% 28.7MB/s ± 3% +3.78% (p=0.000 n=40+40) [Geo mean] 78.9MB/s 79.2MB/s +0.38% Change-Id: I3ba688c253b665485c1ebdf5a75f4ce82cc3def3 Reviewed-on: https://go-review.googlesource.com/102036 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com> Reviewed-by: Keith Randall <khr@golang.org>
2018-03-22 02:18:50 +00:00
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
// binary-op with an indexed memory source operand
cmd/compile: indexed loads/stores can't be faultOnNilArg0 Because of the index, these ops can't guarantee faulting if arg0 is nil. Clean up the PPC64 index ops - they can't take a sym or an offset. Noticed while debugging #37881. I don't think it is the cause, but I guess there is a chance. Update #37881 Change-Id: Ic22925250bf7b1ba64e3cea1a65638bc4bab390c Reviewed-on: https://go-review.googlesource.com/c/go/+/224457 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-20 09:59:53 -07:00
{name: "ADDLloadidx4", argLength: 4, reg: gp21loadidx, asm: "ADDL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"}, // arg0 + tmp, tmp loaded from arg1+arg2*4+auxint+aux, arg3 = mem
{name: "SUBLloadidx4", argLength: 4, reg: gp21loadidx, asm: "SUBL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"}, // arg0 - tmp, tmp loaded from arg1+arg2*4+auxint+aux, arg3 = mem
{name: "MULLloadidx4", argLength: 4, reg: gp21loadidx, asm: "IMULL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"}, // arg0 * tmp, tmp loaded from arg1+arg2*4+auxint+aux, arg3 = mem
{name: "ANDLloadidx4", argLength: 4, reg: gp21loadidx, asm: "ANDL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"}, // arg0 & tmp, tmp loaded from arg1+arg2*4+auxint+aux, arg3 = mem
{name: "ORLloadidx4", argLength: 4, reg: gp21loadidx, asm: "ORL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"}, // arg0 | tmp, tmp loaded from arg1+arg2*4+auxint+aux, arg3 = mem
{name: "XORLloadidx4", argLength: 4, reg: gp21loadidx, asm: "XORL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"}, // arg0 ^ tmp, tmp loaded from arg1+arg2*4+auxint+aux, arg3 = mem
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// unary ops
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "NEGL", argLength: 1, reg: gp11, asm: "NEGL", resultInArg0: true, clobberFlags: true}, // -arg0
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: mark NOT as an op that doesn't clobber flags on i386/AMD64 NOT does not affect any FLAGS register values on i386/AMD64 so we do not need to mark it as an Op that clobbers them. Change-Id: I6d99cad49cfa2568b01e58190256582b18fb3b7b Reviewed-on: https://go-review.googlesource.com/c/go/+/354831 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Trust: Josh Bleecher Snyder <josharian@gmail.com>
2021-10-09 17:57:06 +02:00
{name: "NOTL", argLength: 1, reg: gp11, asm: "NOTL", resultInArg0: true}, // ^arg0
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "BSFL", argLength: 1, reg: gp11, asm: "BSFL", clobberFlags: true}, // arg0 # of low-order zeroes ; undef if zero
{name: "BSFW", argLength: 1, reg: gp11, asm: "BSFW", clobberFlags: true}, // arg0 # of low-order zeroes ; undef if zero
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "BSRL", argLength: 1, reg: gp11, asm: "BSRL", clobberFlags: true}, // arg0 # of high-order zeroes ; undef if zero
{name: "BSRW", argLength: 1, reg: gp11, asm: "BSRW", clobberFlags: true}, // arg0 # of high-order zeroes ; undef if zero
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: fix clobberFlags for BSWAP BSWAP does not affect EFLAGS on neither 386 nor x64. Set the clobberFlags value accordingly. Change-Id: Ib9e88400607fea44bb51fe95dc4d77e7cb54bfec Reviewed-on: https://go-review.googlesource.com/c/go/+/391494 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Trust: Ian Lance Taylor <iant@golang.org>
2022-03-10 15:35:17 +01:00
{name: "BSWAPL", argLength: 1, reg: gp11, asm: "BSWAPL", resultInArg0: true}, // arg0 swap bytes
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "SQRTSD", argLength: 1, reg: fp11, asm: "SQRTSD"}, // sqrt(arg0)
cmd/compile: optimize single-precision floating point square root Add generic rule to rewrite the single-precision square root expression with one single-precision instruction. The optimization will reduce two times of precision converting between double-precision and single-precision. On arm64 flatform. previous: FCVTSD F0, F0 FSQRTD F0, F0 FCVTDS F0, F0 optimized: FSQRTS S0, S0 And this patch adds the test case to check the correctness. This patch refers to CL 241877, contributed by Alice Xu (dianhong.xu@arm.com) Change-Id: I6de5d02281c693017ac4bd4c10963dd55989bd7e Reviewed-on: https://go-review.googlesource.com/c/go/+/276873 Trust: fannie zhang <Fannie.Zhang@arm.com> Run-TryBot: fannie zhang <Fannie.Zhang@arm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-12-07 19:15:15 +08:00
{name: "SQRTSS", argLength: 1, reg: fp11, asm: "SQRTSS"}, // sqrt(arg0), float32
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "SBBLcarrymask", argLength: 1, reg: flagsgp, asm: "SBBL"}, // (int32)(-1) if carry is set, 0 if carry is clear.
// Note: SBBW and SBBB are subsumed by SBBL
{name: "SETEQ", argLength: 1, reg: readflags, asm: "SETEQ"}, // extract == condition from arg0
{name: "SETNE", argLength: 1, reg: readflags, asm: "SETNE"}, // extract != condition from arg0
{name: "SETL", argLength: 1, reg: readflags, asm: "SETLT"}, // extract signed < condition from arg0
{name: "SETLE", argLength: 1, reg: readflags, asm: "SETLE"}, // extract signed <= condition from arg0
{name: "SETG", argLength: 1, reg: readflags, asm: "SETGT"}, // extract signed > condition from arg0
{name: "SETGE", argLength: 1, reg: readflags, asm: "SETGE"}, // extract signed >= condition from arg0
{name: "SETB", argLength: 1, reg: readflags, asm: "SETCS"}, // extract unsigned < condition from arg0
{name: "SETBE", argLength: 1, reg: readflags, asm: "SETLS"}, // extract unsigned <= condition from arg0
{name: "SETA", argLength: 1, reg: readflags, asm: "SETHI"}, // extract unsigned > condition from arg0
{name: "SETAE", argLength: 1, reg: readflags, asm: "SETCC"}, // extract unsigned >= condition from arg0
cmd/compile: add intrinsics for runtime/internal/math on 386 and amd64 Add generic, 386 and amd64 specific ops and SSA rules for multiplication with overflow and branching based on overflow flags. Use these to intrinsify runtime/internal/math.MulUinptr. On amd64 mul, overflow := math.MulUintptr(a, b) if overflow { is lowered to two instructions: MULQ SI JO 0x10ee35c No codegen tests as codegen can not currently test unexported internal runtime functions. amd64: name old time/op new time/op delta MulUintptr/small 1.16ns ± 5% 0.88ns ± 6% -24.36% (p=0.000 n=19+20) MulUintptr/large 10.7ns ± 1% 1.1ns ± 1% -89.28% (p=0.000 n=17+19) Change-Id: If60739a86f820e5044d677276c21df90d3c7a86a Reviewed-on: https://go-review.googlesource.com/c/141820 Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-01-27 11:55:34 +01:00
{name: "SETO", argLength: 1, reg: readflags, asm: "SETOS"}, // extract if overflow flag is set from arg0
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// Need different opcodes for floating point conditions because
// any comparison involving a NaN is always FALSE and thus
// the patterns for inverting conditions cannot be used.
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "SETEQF", argLength: 1, reg: flagsgpax, asm: "SETEQ", clobberFlags: true}, // extract == condition from arg0
{name: "SETNEF", argLength: 1, reg: flagsgpax, asm: "SETNE", clobberFlags: true}, // extract != condition from arg0
{name: "SETORD", argLength: 1, reg: flagsgp, asm: "SETPC"}, // extract "ordered" (No Nan present) condition from arg0
{name: "SETNAN", argLength: 1, reg: flagsgp, asm: "SETPS"}, // extract "unordered" (Nan present) condition from arg0
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "SETGF", argLength: 1, reg: flagsgp, asm: "SETHI"}, // extract floating > condition from arg0
{name: "SETGEF", argLength: 1, reg: flagsgp, asm: "SETCC"}, // extract floating >= condition from arg0
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
{name: "MOVBLSX", argLength: 1, reg: gp11, asm: "MOVBLSX"}, // sign extend arg0 from int8 to int32
{name: "MOVBLZX", argLength: 1, reg: gp11, asm: "MOVBLZX"}, // zero extend arg0 from int8 to int32
{name: "MOVWLSX", argLength: 1, reg: gp11, asm: "MOVWLSX"}, // sign extend arg0 from int16 to int32
{name: "MOVWLZX", argLength: 1, reg: gp11, asm: "MOVWLZX"}, // zero extend arg0 from int16 to int32
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "MOVLconst", reg: gp01, asm: "MOVL", typ: "UInt32", aux: "Int32", rematerializeable: true}, // 32 low bits of auxint
cmd/compile: remove backend's "scratch mem" support This CL rebases CL 273987 on top of master with @mdempsky's permission. The last (only?) use for this feature was 387 support, which was removed in golang.org/cl/258957. Change-Id: I4f79fee8d0c336c9b6082bcd5eb6ece52c032dc0 Reviewed-on: https://go-review.googlesource.com/c/go/+/292893 Trust: Cuong Manh Le <cuong.manhle.vn@gmail.com> Run-TryBot: Cuong Manh Le <cuong.manhle.vn@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Matthew Dempsky <mdempsky@google.com>
2021-02-17 15:27:42 +07:00
{name: "CVTTSD2SL", argLength: 1, reg: fpgp, asm: "CVTTSD2SL"}, // convert float64 to int32
{name: "CVTTSS2SL", argLength: 1, reg: fpgp, asm: "CVTTSS2SL"}, // convert float32 to int32
{name: "CVTSL2SS", argLength: 1, reg: gpfp, asm: "CVTSL2SS"}, // convert int32 to float32
{name: "CVTSL2SD", argLength: 1, reg: gpfp, asm: "CVTSL2SD"}, // convert int32 to float64
{name: "CVTSD2SS", argLength: 1, reg: fp11, asm: "CVTSD2SS"}, // convert float64 to float32
{name: "CVTSS2SD", argLength: 1, reg: fp11, asm: "CVTSS2SD"}, // convert float32 to float64
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
{name: "PXOR", argLength: 2, reg: fp21, asm: "PXOR", commutative: true, resultInArg0: true}, // exclusive or, applied to X regs for float negation.
cmd/compile/internal/ssa: populate SymEffects for SSA Ops Changes to ${GOARCH}Ops.go files were mechanically produced using github.com/mdempsky/ssa-symops, a one-off tool that inserts "SymEffect: X" elements by pattern matching against the Op names. Change-Id: Ibf3e481ffd588647f2a31662d72114b740ccbfcf Reviewed-on: https://go-review.googlesource.com/38084 Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-03-09 14:46:43 -08:00
{name: "LEAL", argLength: 1, reg: gp11sb, aux: "SymOff", rematerializeable: true, symEffect: "Addr"}, // arg0 + auxint + offset encoded in aux
cmd/compile: automatically handle commuting ops in rewrite rules Note that this is a redo of an undo of the original buggy CL 38666. We have lots of rewrite rules that vary only in the fact that we have 2 versions for the 2 different orderings of various commuting ops. For example: (ADDL x (MOVLconst [c])) -> (ADDLconst [c] x) (ADDL (MOVLconst [c]) x) -> (ADDLconst [c] x) It can get unwieldly quickly, especially when there is more than one commuting op in a rule. Our existing "fix" for this problem is to have rules that canonicalize the operations first. For example: (Eq64 x (Const64 <t> [c])) && x.Op != OpConst64 -> (Eq64 (Const64 <t> [c]) x) Subsequent rules can then assume if there is a constant arg to Eq64, it will be the first one. This fix kinda works, but it is fragile and only works when we remember to include the required extra rules. The fundamental problem is that the rule matcher doesn't know anything about commuting ops. This CL fixes that fact. We already have information about which ops commute. (The register allocator takes advantage of commutivity.) The rule generator now automatically generates multiple rules for a single source rule when there are commutative ops in the rule. We can now drop all of our almost-duplicate source-level rules and the canonicalization rules. I have some CLs in progress that will be a lot less verbose when the rule generator handles commutivity for me. I had to reorganize the load-combining rules a bit. The 8-way OR rules generated 128 different reorderings, which was causing the generator to put too much code in the rewrite*.go files (the big ones were going from 25K lines to 132K lines). Instead I reorganized the rules to combine pairs of loads at a time. The generated rule files are now actually a bit (5%) smaller. Make.bash times are ~unchanged. Compiler benchmarks are not observably different. Probably because we don't spend much compiler time in rule matching anyway. I've also done a pass over all of our ops adding commutative markings for ops which hadn't had them previously. Fixes #18292 Change-Id: Ic1c0e43fbf579539f459971625f69690c9ab8805 Reviewed-on: https://go-review.googlesource.com/38801 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-03-30 03:30:22 +00:00
{name: "LEAL1", argLength: 2, reg: gp21sb, commutative: true, aux: "SymOff", symEffect: "Addr"}, // arg0 + arg1 + auxint + aux
cmd/compile/internal/ssa: populate SymEffects for SSA Ops Changes to ${GOARCH}Ops.go files were mechanically produced using github.com/mdempsky/ssa-symops, a one-off tool that inserts "SymEffect: X" elements by pattern matching against the Op names. Change-Id: Ibf3e481ffd588647f2a31662d72114b740ccbfcf Reviewed-on: https://go-review.googlesource.com/38084 Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-03-09 14:46:43 -08:00
{name: "LEAL2", argLength: 2, reg: gp21sb, aux: "SymOff", symEffect: "Addr"}, // arg0 + 2*arg1 + auxint + aux
{name: "LEAL4", argLength: 2, reg: gp21sb, aux: "SymOff", symEffect: "Addr"}, // arg0 + 4*arg1 + auxint + aux
{name: "LEAL8", argLength: 2, reg: gp21sb, aux: "SymOff", symEffect: "Addr"}, // arg0 + 8*arg1 + auxint + aux
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// Note: LEAL{1,2,4,8} must not have OpSB as either argument.
// auxint+aux == add auxint and the offset of the symbol in aux (if any) to the effective address
cmd/compile/internal/ssa: populate SymEffects for SSA Ops Changes to ${GOARCH}Ops.go files were mechanically produced using github.com/mdempsky/ssa-symops, a one-off tool that inserts "SymEffect: X" elements by pattern matching against the Op names. Change-Id: Ibf3e481ffd588647f2a31662d72114b740ccbfcf Reviewed-on: https://go-review.googlesource.com/38084 Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-03-09 14:46:43 -08:00
{name: "MOVBload", argLength: 2, reg: gpload, asm: "MOVBLZX", aux: "SymOff", typ: "UInt8", faultOnNilArg0: true, symEffect: "Read"}, // load byte from arg0+auxint+aux. arg1=mem. Zero extend.
{name: "MOVBLSXload", argLength: 2, reg: gpload, asm: "MOVBLSX", aux: "SymOff", faultOnNilArg0: true, symEffect: "Read"}, // ditto, sign extend to int32
{name: "MOVWload", argLength: 2, reg: gpload, asm: "MOVWLZX", aux: "SymOff", typ: "UInt16", faultOnNilArg0: true, symEffect: "Read"}, // load 2 bytes from arg0+auxint+aux. arg1=mem. Zero extend.
{name: "MOVWLSXload", argLength: 2, reg: gpload, asm: "MOVWLSX", aux: "SymOff", faultOnNilArg0: true, symEffect: "Read"}, // ditto, sign extend to int32
{name: "MOVLload", argLength: 2, reg: gpload, asm: "MOVL", aux: "SymOff", typ: "UInt32", faultOnNilArg0: true, symEffect: "Read"}, // load 4 bytes from arg0+auxint+aux. arg1=mem. Zero extend.
{name: "MOVBstore", argLength: 3, reg: gpstore, asm: "MOVB", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store byte in arg1 to arg0+auxint+aux. arg2=mem
{name: "MOVWstore", argLength: 3, reg: gpstore, asm: "MOVW", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store 2 bytes in arg1 to arg0+auxint+aux. arg2=mem
{name: "MOVLstore", argLength: 3, reg: gpstore, asm: "MOVL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store 4 bytes in arg1 to arg0+auxint+aux. arg2=mem
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile: emit more compact 386 instructions ADDL/SUBL/ANDL/ORL/XORL can have a memory operand as destination, and this CL optimize the compiler to emit such instructions on 386 for more compact binary. Here is test report: 1. The total size of pkg/linux_386/ and pkg/tool/linux_386/ decreases about 14KB. (pkg/linux_386/cmd/compile/ and pkg/tool/linux_386/compile are excluded) 2. The go1 benchmark shows little change, excluding ±2% noise. name old time/op new time/op delta BinaryTree17-4 3.34s ± 2% 3.38s ± 2% +1.27% (p=0.000 n=40+39) Fannkuch11-4 3.55s ± 1% 3.51s ± 1% -1.33% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.3ns ± 3% 46.9ns ± 4% +1.41% (p=0.002 n=40+40) FmtFprintfString-4 80.8ns ± 3% 80.4ns ± 6% -0.54% (p=0.044 n=40+40) FmtFprintfInt-4 93.0ns ± 3% 92.2ns ± 4% -0.88% (p=0.007 n=39+40) FmtFprintfIntInt-4 144ns ± 5% 145ns ± 2% +0.78% (p=0.015 n=40+40) FmtFprintfPrefixedInt-4 184ns ± 2% 182ns ± 2% -1.06% (p=0.004 n=40+40) FmtFprintfFloat-4 415ns ± 4% 419ns ± 4% ~ (p=0.434 n=40+40) FmtManyArgs-4 615ns ± 3% 619ns ± 3% ~ (p=0.100 n=40+40) GobDecode-4 7.30ms ± 6% 7.36ms ± 6% ~ (p=0.074 n=40+40) GobEncode-4 7.10ms ± 6% 7.21ms ± 5% ~ (p=0.082 n=40+39) Gzip-4 364ms ± 3% 362ms ± 6% -0.71% (p=0.020 n=40+40) Gunzip-4 42.4ms ± 3% 42.2ms ± 3% ~ (p=0.303 n=40+40) HTTPClientServer-4 62.9µs ± 1% 62.9µs ± 1% ~ (p=0.768 n=38+39) JSONEncode-4 21.4ms ± 4% 21.5ms ± 5% ~ (p=0.210 n=40+40) JSONDecode-4 67.7ms ± 3% 67.9ms ± 4% ~ (p=0.713 n=40+40) Mandelbrot200-4 5.18ms ± 3% 5.21ms ± 3% +0.59% (p=0.021 n=40+40) GoParse-4 3.35ms ± 3% 3.34ms ± 2% ~ (p=0.996 n=40+40) RegexpMatchEasy0_32-4 98.5ns ± 5% 96.3ns ± 4% -2.15% (p=0.001 n=40+40) RegexpMatchEasy0_1K-4 851ns ± 4% 850ns ± 5% ~ (p=0.700 n=40+40) RegexpMatchEasy1_32-4 105ns ± 7% 107ns ± 4% +1.50% (p=0.017 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 5% 1.03µs ± 4% ~ (p=0.992 n=40+40) RegexpMatchMedium_32-4 130ns ± 6% 128ns ± 4% -1.66% (p=0.012 n=40+40) RegexpMatchMedium_1K-4 44.0µs ± 5% 43.6µs ± 3% ~ (p=0.704 n=40+40) RegexpMatchHard_32-4 2.29µs ± 3% 2.23µs ± 4% -2.38% (p=0.000 n=40+40) RegexpMatchHard_1K-4 69.0µs ± 3% 68.1µs ± 3% -1.28% (p=0.003 n=40+40) Revcomp-4 1.85s ± 2% 1.87s ± 3% +1.11% (p=0.000 n=40+40) Template-4 69.8ms ± 3% 69.6ms ± 3% ~ (p=0.125 n=40+40) TimeParse-4 442ns ± 5% 440ns ± 3% ~ (p=0.585 n=40+40) TimeFormat-4 419ns ± 3% 420ns ± 3% ~ (p=0.824 n=40+40) [Geo mean] 67.3µs 67.2µs -0.11% name old speed new speed delta GobDecode-4 105MB/s ± 6% 104MB/s ± 6% ~ (p=0.074 n=40+40) GobEncode-4 108MB/s ± 7% 107MB/s ± 5% ~ (p=0.080 n=40+39) Gzip-4 53.3MB/s ± 3% 53.7MB/s ± 6% +0.73% (p=0.021 n=40+40) Gunzip-4 458MB/s ± 3% 460MB/s ± 3% ~ (p=0.301 n=40+40) JSONEncode-4 90.8MB/s ± 4% 90.3MB/s ± 4% ~ (p=0.213 n=40+40) JSONDecode-4 28.7MB/s ± 3% 28.6MB/s ± 4% ~ (p=0.679 n=40+40) GoParse-4 17.3MB/s ± 3% 17.3MB/s ± 2% ~ (p=1.000 n=40+40) RegexpMatchEasy0_32-4 325MB/s ± 5% 333MB/s ± 4% +2.44% (p=0.000 n=40+38) RegexpMatchEasy0_1K-4 1.20GB/s ± 4% 1.21GB/s ± 5% ~ (p=0.684 n=40+40) RegexpMatchEasy1_32-4 303MB/s ± 7% 298MB/s ± 4% -1.52% (p=0.022 n=40+40) RegexpMatchEasy1_1K-4 995MB/s ± 5% 996MB/s ± 4% ~ (p=0.996 n=40+40) RegexpMatchMedium_32-4 7.67MB/s ± 6% 7.80MB/s ± 4% +1.68% (p=0.011 n=40+40) RegexpMatchMedium_1K-4 23.3MB/s ± 5% 23.5MB/s ± 3% ~ (p=0.697 n=40+40) RegexpMatchHard_32-4 14.0MB/s ± 3% 14.3MB/s ± 4% +2.43% (p=0.000 n=40+40) RegexpMatchHard_1K-4 14.8MB/s ± 3% 15.0MB/s ± 3% +1.30% (p=0.003 n=40+40) Revcomp-4 137MB/s ± 2% 136MB/s ± 3% -1.10% (p=0.000 n=40+40) Template-4 27.8MB/s ± 3% 27.9MB/s ± 3% ~ (p=0.128 n=40+40) [Geo mean] 79.6MB/s 79.9MB/s +0.28% Change-Id: I02a3efc125dc81e18fc8495eb2bf1bba59ab8733 Reviewed-on: https://go-review.googlesource.com/110157 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-04-29 10:42:14 +00:00
// direct binary-op on memory (read-modify-write)
cmd/compile: fix a bug in 386 backend The ADDLmodify/SUBLmodify/ANDLmodify/ORLmodify/XORLmodify should have clobberFlags set to true. Change-Id: Ie447d536db51334eddc70c00a722647282186a69 Reviewed-on: https://go-review.googlesource.com/122556 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-07-06 23:39:01 +00:00
{name: "ADDLmodify", argLength: 3, reg: gpstore, asm: "ADDL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+auxint+aux) += arg1, arg2=mem
{name: "SUBLmodify", argLength: 3, reg: gpstore, asm: "SUBL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+auxint+aux) -= arg1, arg2=mem
{name: "ANDLmodify", argLength: 3, reg: gpstore, asm: "ANDL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+auxint+aux) &= arg1, arg2=mem
{name: "ORLmodify", argLength: 3, reg: gpstore, asm: "ORL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+auxint+aux) |= arg1, arg2=mem
{name: "XORLmodify", argLength: 3, reg: gpstore, asm: "XORL", aux: "SymOff", typ: "Mem", faultOnNilArg0: true, clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+auxint+aux) ^= arg1, arg2=mem
cmd/compile: emit more compact 386 instructions ADDL/SUBL/ANDL/ORL/XORL can have a memory operand as destination, and this CL optimize the compiler to emit such instructions on 386 for more compact binary. Here is test report: 1. The total size of pkg/linux_386/ and pkg/tool/linux_386/ decreases about 14KB. (pkg/linux_386/cmd/compile/ and pkg/tool/linux_386/compile are excluded) 2. The go1 benchmark shows little change, excluding ±2% noise. name old time/op new time/op delta BinaryTree17-4 3.34s ± 2% 3.38s ± 2% +1.27% (p=0.000 n=40+39) Fannkuch11-4 3.55s ± 1% 3.51s ± 1% -1.33% (p=0.000 n=40+40) FmtFprintfEmpty-4 46.3ns ± 3% 46.9ns ± 4% +1.41% (p=0.002 n=40+40) FmtFprintfString-4 80.8ns ± 3% 80.4ns ± 6% -0.54% (p=0.044 n=40+40) FmtFprintfInt-4 93.0ns ± 3% 92.2ns ± 4% -0.88% (p=0.007 n=39+40) FmtFprintfIntInt-4 144ns ± 5% 145ns ± 2% +0.78% (p=0.015 n=40+40) FmtFprintfPrefixedInt-4 184ns ± 2% 182ns ± 2% -1.06% (p=0.004 n=40+40) FmtFprintfFloat-4 415ns ± 4% 419ns ± 4% ~ (p=0.434 n=40+40) FmtManyArgs-4 615ns ± 3% 619ns ± 3% ~ (p=0.100 n=40+40) GobDecode-4 7.30ms ± 6% 7.36ms ± 6% ~ (p=0.074 n=40+40) GobEncode-4 7.10ms ± 6% 7.21ms ± 5% ~ (p=0.082 n=40+39) Gzip-4 364ms ± 3% 362ms ± 6% -0.71% (p=0.020 n=40+40) Gunzip-4 42.4ms ± 3% 42.2ms ± 3% ~ (p=0.303 n=40+40) HTTPClientServer-4 62.9µs ± 1% 62.9µs ± 1% ~ (p=0.768 n=38+39) JSONEncode-4 21.4ms ± 4% 21.5ms ± 5% ~ (p=0.210 n=40+40) JSONDecode-4 67.7ms ± 3% 67.9ms ± 4% ~ (p=0.713 n=40+40) Mandelbrot200-4 5.18ms ± 3% 5.21ms ± 3% +0.59% (p=0.021 n=40+40) GoParse-4 3.35ms ± 3% 3.34ms ± 2% ~ (p=0.996 n=40+40) RegexpMatchEasy0_32-4 98.5ns ± 5% 96.3ns ± 4% -2.15% (p=0.001 n=40+40) RegexpMatchEasy0_1K-4 851ns ± 4% 850ns ± 5% ~ (p=0.700 n=40+40) RegexpMatchEasy1_32-4 105ns ± 7% 107ns ± 4% +1.50% (p=0.017 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 5% 1.03µs ± 4% ~ (p=0.992 n=40+40) RegexpMatchMedium_32-4 130ns ± 6% 128ns ± 4% -1.66% (p=0.012 n=40+40) RegexpMatchMedium_1K-4 44.0µs ± 5% 43.6µs ± 3% ~ (p=0.704 n=40+40) RegexpMatchHard_32-4 2.29µs ± 3% 2.23µs ± 4% -2.38% (p=0.000 n=40+40) RegexpMatchHard_1K-4 69.0µs ± 3% 68.1µs ± 3% -1.28% (p=0.003 n=40+40) Revcomp-4 1.85s ± 2% 1.87s ± 3% +1.11% (p=0.000 n=40+40) Template-4 69.8ms ± 3% 69.6ms ± 3% ~ (p=0.125 n=40+40) TimeParse-4 442ns ± 5% 440ns ± 3% ~ (p=0.585 n=40+40) TimeFormat-4 419ns ± 3% 420ns ± 3% ~ (p=0.824 n=40+40) [Geo mean] 67.3µs 67.2µs -0.11% name old speed new speed delta GobDecode-4 105MB/s ± 6% 104MB/s ± 6% ~ (p=0.074 n=40+40) GobEncode-4 108MB/s ± 7% 107MB/s ± 5% ~ (p=0.080 n=40+39) Gzip-4 53.3MB/s ± 3% 53.7MB/s ± 6% +0.73% (p=0.021 n=40+40) Gunzip-4 458MB/s ± 3% 460MB/s ± 3% ~ (p=0.301 n=40+40) JSONEncode-4 90.8MB/s ± 4% 90.3MB/s ± 4% ~ (p=0.213 n=40+40) JSONDecode-4 28.7MB/s ± 3% 28.6MB/s ± 4% ~ (p=0.679 n=40+40) GoParse-4 17.3MB/s ± 3% 17.3MB/s ± 2% ~ (p=1.000 n=40+40) RegexpMatchEasy0_32-4 325MB/s ± 5% 333MB/s ± 4% +2.44% (p=0.000 n=40+38) RegexpMatchEasy0_1K-4 1.20GB/s ± 4% 1.21GB/s ± 5% ~ (p=0.684 n=40+40) RegexpMatchEasy1_32-4 303MB/s ± 7% 298MB/s ± 4% -1.52% (p=0.022 n=40+40) RegexpMatchEasy1_1K-4 995MB/s ± 5% 996MB/s ± 4% ~ (p=0.996 n=40+40) RegexpMatchMedium_32-4 7.67MB/s ± 6% 7.80MB/s ± 4% +1.68% (p=0.011 n=40+40) RegexpMatchMedium_1K-4 23.3MB/s ± 5% 23.5MB/s ± 3% ~ (p=0.697 n=40+40) RegexpMatchHard_32-4 14.0MB/s ± 3% 14.3MB/s ± 4% +2.43% (p=0.000 n=40+40) RegexpMatchHard_1K-4 14.8MB/s ± 3% 15.0MB/s ± 3% +1.30% (p=0.003 n=40+40) Revcomp-4 137MB/s ± 2% 136MB/s ± 3% -1.10% (p=0.000 n=40+40) Template-4 27.8MB/s ± 3% 27.9MB/s ± 3% ~ (p=0.128 n=40+40) [Geo mean] 79.6MB/s 79.9MB/s +0.28% Change-Id: I02a3efc125dc81e18fc8495eb2bf1bba59ab8733 Reviewed-on: https://go-review.googlesource.com/110157 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
2018-04-29 10:42:14 +00:00
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
// direct binary-op on indexed memory (read-modify-write)
cmd/compile: indexed loads/stores can't be faultOnNilArg0 Because of the index, these ops can't guarantee faulting if arg0 is nil. Clean up the PPC64 index ops - they can't take a sym or an offset. Noticed while debugging #37881. I don't think it is the cause, but I guess there is a chance. Update #37881 Change-Id: Ic22925250bf7b1ba64e3cea1a65638bc4bab390c Reviewed-on: https://go-review.googlesource.com/c/go/+/224457 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-20 09:59:53 -07:00
{name: "ADDLmodifyidx4", argLength: 4, reg: gpstoreidx, asm: "ADDL", aux: "SymOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+arg1*4+auxint+aux) += arg2, arg3=mem
{name: "SUBLmodifyidx4", argLength: 4, reg: gpstoreidx, asm: "SUBL", aux: "SymOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+arg1*4+auxint+aux) -= arg2, arg3=mem
{name: "ANDLmodifyidx4", argLength: 4, reg: gpstoreidx, asm: "ANDL", aux: "SymOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+arg1*4+auxint+aux) &= arg2, arg3=mem
{name: "ORLmodifyidx4", argLength: 4, reg: gpstoreidx, asm: "ORL", aux: "SymOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+arg1*4+auxint+aux) |= arg2, arg3=mem
{name: "XORLmodifyidx4", argLength: 4, reg: gpstoreidx, asm: "XORL", aux: "SymOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // *(arg0+arg1*4+auxint+aux) ^= arg2, arg3=mem
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
cmd/compile: implement "OPC $imm, (mem)" for 386 New read-modify-write operations are introduced in this CL for 386. 1. The total size of pkg/linux_386 decreases about 10KB (excluding cmd/compile). 2. The go1 benchmark shows little regression. name old time/op new time/op delta BinaryTree17-4 3.32s ± 4% 3.29s ± 2% ~ (p=0.059 n=30+30) Fannkuch11-4 3.49s ± 1% 3.46s ± 1% -0.92% (p=0.001 n=30+30) FmtFprintfEmpty-4 47.7ns ± 2% 46.8ns ± 5% -1.93% (p=0.011 n=25+30) FmtFprintfString-4 79.5ns ± 7% 80.2ns ± 3% +0.89% (p=0.001 n=28+29) FmtFprintfInt-4 90.5ns ± 2% 92.1ns ± 2% +1.82% (p=0.014 n=22+30) FmtFprintfIntInt-4 141ns ± 1% 144ns ± 3% +2.23% (p=0.013 n=22+30) FmtFprintfPrefixedInt-4 183ns ± 2% 184ns ± 3% ~ (p=0.080 n=21+30) FmtFprintfFloat-4 409ns ± 3% 412ns ± 3% +0.83% (p=0.040 n=30+30) FmtManyArgs-4 597ns ± 6% 607ns ± 4% +1.71% (p=0.006 n=30+30) GobDecode-4 7.21ms ± 5% 7.18ms ± 6% ~ (p=0.665 n=30+30) GobEncode-4 7.17ms ± 6% 7.09ms ± 7% ~ (p=0.117 n=29+30) Gzip-4 413ms ± 4% 399ms ± 4% -3.48% (p=0.000 n=30+30) Gunzip-4 41.3ms ± 4% 41.7ms ± 3% +1.05% (p=0.011 n=30+30) HTTPClientServer-4 63.5µs ± 3% 62.9µs ± 2% -0.97% (p=0.017 n=30+27) JSONEncode-4 20.3ms ± 5% 20.1ms ± 5% -1.16% (p=0.004 n=30+30) JSONDecode-4 66.2ms ± 4% 67.7ms ± 4% +2.21% (p=0.000 n=30+30) Mandelbrot200-4 5.16ms ± 3% 5.18ms ± 3% ~ (p=0.123 n=30+30) GoParse-4 3.23ms ± 2% 3.27ms ± 2% +1.08% (p=0.006 n=30+30) RegexpMatchEasy0_32-4 98.9ns ± 5% 97.1ns ± 4% -1.83% (p=0.006 n=30+30) RegexpMatchEasy0_1K-4 842ns ± 3% 842ns ± 3% ~ (p=0.550 n=30+30) RegexpMatchEasy1_32-4 107ns ± 4% 105ns ± 4% -1.93% (p=0.012 n=30+30) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.04µs ± 4% ~ (p=0.304 n=30+30) RegexpMatchMedium_32-4 132ns ± 2% 129ns ± 4% -2.02% (p=0.000 n=21+30) RegexpMatchMedium_1K-4 44.1µs ± 4% 43.8µs ± 3% ~ (p=0.641 n=30+30) RegexpMatchHard_32-4 2.26µs ± 4% 2.23µs ± 4% -1.28% (p=0.023 n=30+30) RegexpMatchHard_1K-4 68.1µs ± 3% 68.6µs ± 4% ~ (p=0.089 n=30+30) Revcomp-4 1.85s ± 2% 1.84s ± 2% ~ (p=0.072 n=30+30) Template-4 69.2ms ± 3% 68.5ms ± 3% -1.04% (p=0.012 n=30+30) TimeParse-4 441ns ± 3% 446ns ± 4% +1.21% (p=0.001 n=30+30) TimeFormat-4 415ns ± 3% 415ns ± 3% ~ (p=0.436 n=30+30) [Geo mean] 67.0µs 66.9µs -0.17% name old speed new speed delta GobDecode-4 107MB/s ± 5% 107MB/s ± 6% ~ (p=0.663 n=30+30) GobEncode-4 107MB/s ± 6% 108MB/s ± 7% ~ (p=0.117 n=29+30) Gzip-4 47.0MB/s ± 4% 48.7MB/s ± 4% +3.61% (p=0.000 n=30+30) Gunzip-4 470MB/s ± 4% 466MB/s ± 4% -1.05% (p=0.011 n=30+30) JSONEncode-4 95.6MB/s ± 5% 96.7MB/s ± 5% +1.16% (p=0.005 n=30+30) JSONDecode-4 29.3MB/s ± 4% 28.7MB/s ± 4% -2.17% (p=0.000 n=30+30) GoParse-4 17.9MB/s ± 2% 17.7MB/s ± 2% -1.06% (p=0.007 n=30+30) RegexpMatchEasy0_32-4 323MB/s ± 5% 329MB/s ± 4% +1.93% (p=0.006 n=30+30) RegexpMatchEasy0_1K-4 1.22GB/s ± 3% 1.22GB/s ± 3% ~ (p=0.496 n=30+30) RegexpMatchEasy1_32-4 298MB/s ± 4% 303MB/s ± 4% +1.84% (p=0.017 n=30+30) RegexpMatchEasy1_1K-4 995MB/s ± 4% 989MB/s ± 4% ~ (p=0.307 n=30+30) RegexpMatchMedium_32-4 7.56MB/s ± 4% 7.74MB/s ± 4% +2.46% (p=0.000 n=22+30) RegexpMatchMedium_1K-4 23.2MB/s ± 4% 23.4MB/s ± 3% ~ (p=0.651 n=30+30) RegexpMatchHard_32-4 14.2MB/s ± 4% 14.3MB/s ± 4% +1.29% (p=0.021 n=30+30) RegexpMatchHard_1K-4 15.0MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.069 n=30+29) Revcomp-4 138MB/s ± 2% 138MB/s ± 2% ~ (p=0.072 n=30+30) Template-4 28.1MB/s ± 3% 28.4MB/s ± 3% +1.05% (p=0.012 n=30+30) [Geo mean] 79.7MB/s 80.2MB/s +0.60% Change-Id: I44a1dfc942c9a385904553c4fe1fa8e509c8aa31 Reviewed-on: https://go-review.googlesource.com/120916 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-06-26 02:58:54 +00:00
// direct binary-op on memory with a constant (read-modify-write)
{name: "ADDLconstmodify", argLength: 2, reg: gpstoreconst, asm: "ADDL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // add ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
{name: "ANDLconstmodify", argLength: 2, reg: gpstoreconst, asm: "ANDL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // and ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
{name: "ORLconstmodify", argLength: 2, reg: gpstoreconst, asm: "ORL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // or ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
{name: "XORLconstmodify", argLength: 2, reg: gpstoreconst, asm: "XORL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, faultOnNilArg0: true, symEffect: "Read,Write"}, // xor ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux, arg1=mem
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
// direct binary-op on indexed memory with a constant (read-modify-write)
cmd/compile: indexed loads/stores can't be faultOnNilArg0 Because of the index, these ops can't guarantee faulting if arg0 is nil. Clean up the PPC64 index ops - they can't take a sym or an offset. Noticed while debugging #37881. I don't think it is the cause, but I guess there is a chance. Update #37881 Change-Id: Ic22925250bf7b1ba64e3cea1a65638bc4bab390c Reviewed-on: https://go-review.googlesource.com/c/go/+/224457 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-20 09:59:53 -07:00
{name: "ADDLconstmodifyidx4", argLength: 3, reg: gpstoreconstidx, asm: "ADDL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // add ValAndOff(AuxInt).Val() to arg0+arg1*4+ValAndOff(AuxInt).Off()+aux, arg2=mem
{name: "ANDLconstmodifyidx4", argLength: 3, reg: gpstoreconstidx, asm: "ANDL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // and ValAndOff(AuxInt).Val() to arg0+arg1*4+ValAndOff(AuxInt).Off()+aux, arg2=mem
{name: "ORLconstmodifyidx4", argLength: 3, reg: gpstoreconstidx, asm: "ORL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // or ValAndOff(AuxInt).Val() to arg0+arg1*4+ValAndOff(AuxInt).Off()+aux, arg2=mem
{name: "XORLconstmodifyidx4", argLength: 3, reg: gpstoreconstidx, asm: "XORL", aux: "SymValAndOff", typ: "Mem", clobberFlags: true, symEffect: "Read,Write"}, // xor ValAndOff(AuxInt).Val() to arg0+arg1*4+ValAndOff(AuxInt).Off()+aux, arg2=mem
cmd/compile: add indexed form for several 386 instructions This CL implements indexed memory operands for the following instructions. (ADD|SUB|MUL|AND|OR|XOR)Lload -> (ADD|SUB|MUL|AND|OR|XOR)Lloadidx4 (ADD|SUB|AND|OR|XOR)Lmodify -> (ADD|SUB|AND|OR|XOR)Lmodifyidx4 (ADD|AND|OR|XOR)Lconstmodify -> (ADD|AND|OR|XOR)Lconstmodifyidx4 1. The total size of pkg/linux_386/ decreases about 2.5KB, excluding cmd/compile/ . 2. There is little regression in the go1 benchmark test, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.25s ± 3% 3.25s ± 3% ~ (p=0.218 n=40+40) Fannkuch11-4 3.53s ± 1% 3.53s ± 1% ~ (p=0.303 n=40+40) FmtFprintfEmpty-4 44.9ns ± 3% 45.6ns ± 3% +1.48% (p=0.030 n=40+36) FmtFprintfString-4 78.7ns ± 5% 80.1ns ± 7% ~ (p=0.217 n=36+40) FmtFprintfInt-4 90.2ns ± 6% 89.8ns ± 5% ~ (p=0.659 n=40+38) FmtFprintfIntInt-4 140ns ± 5% 141ns ± 5% +1.00% (p=0.027 n=40+40) FmtFprintfPrefixedInt-4 185ns ± 3% 183ns ± 3% ~ (p=0.104 n=40+40) FmtFprintfFloat-4 411ns ± 4% 406ns ± 3% -1.37% (p=0.005 n=40+40) FmtManyArgs-4 590ns ± 4% 598ns ± 4% +1.35% (p=0.008 n=40+40) GobDecode-4 7.16ms ± 5% 7.10ms ± 5% ~ (p=0.335 n=40+40) GobEncode-4 6.85ms ± 7% 6.74ms ± 9% ~ (p=0.058 n=38+40) Gzip-4 400ms ± 4% 399ms ± 2% -0.34% (p=0.003 n=40+33) Gunzip-4 41.4ms ± 3% 41.4ms ± 4% -0.12% (p=0.020 n=40+40) HTTPClientServer-4 64.1µs ± 4% 63.5µs ± 2% -1.07% (p=0.000 n=39+37) JSONEncode-4 15.9ms ± 2% 15.9ms ± 3% ~ (p=0.103 n=40+40) JSONDecode-4 62.2ms ± 4% 61.6ms ± 3% -0.98% (p=0.006 n=39+40) Mandelbrot200-4 5.18ms ± 3% 5.14ms ± 4% ~ (p=0.125 n=40+40) GoParse-4 3.29ms ± 2% 3.27ms ± 2% -0.66% (p=0.006 n=40+40) RegexpMatchEasy0_32-4 103ns ± 4% 103ns ± 4% ~ (p=0.632 n=40+40) RegexpMatchEasy0_1K-4 830ns ± 3% 828ns ± 3% ~ (p=0.563 n=40+40) RegexpMatchEasy1_32-4 113ns ± 4% 113ns ± 4% ~ (p=0.494 n=40+40) RegexpMatchEasy1_1K-4 1.03µs ± 4% 1.03µs ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 130ns ± 4% 129ns ± 3% ~ (p=0.458 n=40+40) RegexpMatchMedium_1K-4 39.4µs ± 3% 39.7µs ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 2.16µs ± 4% 2.15µs ± 4% ~ (p=0.137 n=40+40) RegexpMatchHard_1K-4 65.2µs ± 3% 65.4µs ± 4% ~ (p=0.160 n=40+40) Revcomp-4 1.87s ± 2% 1.87s ± 1% +0.17% (p=0.019 n=33+33) Template-4 69.4ms ± 3% 69.8ms ± 3% +0.60% (p=0.009 n=40+40) TimeParse-4 437ns ± 4% 438ns ± 4% ~ (p=0.234 n=40+40) TimeFormat-4 408ns ± 3% 408ns ± 3% ~ (p=0.904 n=40+40) [Geo mean] 65.7µs 65.6µs -0.08% name old speed new speed delta GobDecode-4 107MB/s ± 5% 108MB/s ± 5% ~ (p=0.336 n=40+40) GobEncode-4 112MB/s ± 6% 114MB/s ± 9% +1.95% (p=0.036 n=37+40) Gzip-4 48.5MB/s ± 4% 48.6MB/s ± 2% +0.28% (p=0.003 n=40+33) Gunzip-4 469MB/s ± 4% 469MB/s ± 4% +0.11% (p=0.021 n=40+40) JSONEncode-4 122MB/s ± 2% 122MB/s ± 3% ~ (p=0.105 n=40+40) JSONDecode-4 31.2MB/s ± 4% 31.5MB/s ± 4% +0.99% (p=0.007 n=39+40) GoParse-4 17.6MB/s ± 2% 17.7MB/s ± 2% +0.66% (p=0.007 n=40+40) RegexpMatchEasy0_32-4 310MB/s ± 4% 310MB/s ± 4% ~ (p=0.384 n=40+40) RegexpMatchEasy0_1K-4 1.23GB/s ± 3% 1.24GB/s ± 3% ~ (p=0.186 n=40+40) RegexpMatchEasy1_32-4 283MB/s ± 3% 281MB/s ± 4% ~ (p=0.855 n=40+40) RegexpMatchEasy1_1K-4 1.00GB/s ± 4% 1.00GB/s ± 4% ~ (p=0.665 n=40+40) RegexpMatchMedium_32-4 7.68MB/s ± 4% 7.73MB/s ± 3% ~ (p=0.359 n=40+40) RegexpMatchMedium_1K-4 26.0MB/s ± 3% 25.8MB/s ± 3% ~ (p=0.825 n=40+40) RegexpMatchHard_32-4 14.8MB/s ± 3% 14.9MB/s ± 4% ~ (p=0.136 n=40+40) RegexpMatchHard_1K-4 15.7MB/s ± 3% 15.7MB/s ± 4% ~ (p=0.150 n=40+40) Revcomp-4 136MB/s ± 1% 136MB/s ± 1% -0.09% (p=0.028 n=32+33) Template-4 28.0MB/s ± 3% 27.8MB/s ± 3% -0.59% (p=0.010 n=40+40) [Geo mean] 82.1MB/s 82.3MB/s +0.25% Change-Id: Ifa387a251056678326d3508aa02753b70bf7e5d0 Reviewed-on: https://go-review.googlesource.com/c/140303 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-10-06 13:13:48 +00:00
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// indexed loads/stores
cmd/compile: automatically handle commuting ops in rewrite rules Note that this is a redo of an undo of the original buggy CL 38666. We have lots of rewrite rules that vary only in the fact that we have 2 versions for the 2 different orderings of various commuting ops. For example: (ADDL x (MOVLconst [c])) -> (ADDLconst [c] x) (ADDL (MOVLconst [c]) x) -> (ADDLconst [c] x) It can get unwieldly quickly, especially when there is more than one commuting op in a rule. Our existing "fix" for this problem is to have rules that canonicalize the operations first. For example: (Eq64 x (Const64 <t> [c])) && x.Op != OpConst64 -> (Eq64 (Const64 <t> [c]) x) Subsequent rules can then assume if there is a constant arg to Eq64, it will be the first one. This fix kinda works, but it is fragile and only works when we remember to include the required extra rules. The fundamental problem is that the rule matcher doesn't know anything about commuting ops. This CL fixes that fact. We already have information about which ops commute. (The register allocator takes advantage of commutivity.) The rule generator now automatically generates multiple rules for a single source rule when there are commutative ops in the rule. We can now drop all of our almost-duplicate source-level rules and the canonicalization rules. I have some CLs in progress that will be a lot less verbose when the rule generator handles commutivity for me. I had to reorganize the load-combining rules a bit. The 8-way OR rules generated 128 different reorderings, which was causing the generator to put too much code in the rewrite*.go files (the big ones were going from 25K lines to 132K lines). Instead I reorganized the rules to combine pairs of loads at a time. The generated rule files are now actually a bit (5%) smaller. Make.bash times are ~unchanged. Compiler benchmarks are not observably different. Probably because we don't spend much compiler time in rule matching anyway. I've also done a pass over all of our ops adding commutative markings for ops which hadn't had them previously. Fixes #18292 Change-Id: Ic1c0e43fbf579539f459971625f69690c9ab8805 Reviewed-on: https://go-review.googlesource.com/38801 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-03-30 03:30:22 +00:00
{name: "MOVBloadidx1", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVBLZX", aux: "SymOff", symEffect: "Read"}, // load a byte from arg0+arg1+auxint+aux. arg2=mem
{name: "MOVWloadidx1", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVWLZX", aux: "SymOff", symEffect: "Read"}, // load 2 bytes from arg0+arg1+auxint+aux. arg2=mem
{name: "MOVWloadidx2", argLength: 3, reg: gploadidx, asm: "MOVWLZX", aux: "SymOff", symEffect: "Read"}, // load 2 bytes from arg0+2*arg1+auxint+aux. arg2=mem
{name: "MOVLloadidx1", argLength: 3, reg: gploadidx, commutative: true, asm: "MOVL", aux: "SymOff", symEffect: "Read"}, // load 4 bytes from arg0+arg1+auxint+aux. arg2=mem
{name: "MOVLloadidx4", argLength: 3, reg: gploadidx, asm: "MOVL", aux: "SymOff", symEffect: "Read"}, // load 4 bytes from arg0+4*arg1+auxint+aux. arg2=mem
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// TODO: sign-extending indexed loads
cmd/compile: automatically handle commuting ops in rewrite rules Note that this is a redo of an undo of the original buggy CL 38666. We have lots of rewrite rules that vary only in the fact that we have 2 versions for the 2 different orderings of various commuting ops. For example: (ADDL x (MOVLconst [c])) -> (ADDLconst [c] x) (ADDL (MOVLconst [c]) x) -> (ADDLconst [c] x) It can get unwieldly quickly, especially when there is more than one commuting op in a rule. Our existing "fix" for this problem is to have rules that canonicalize the operations first. For example: (Eq64 x (Const64 <t> [c])) && x.Op != OpConst64 -> (Eq64 (Const64 <t> [c]) x) Subsequent rules can then assume if there is a constant arg to Eq64, it will be the first one. This fix kinda works, but it is fragile and only works when we remember to include the required extra rules. The fundamental problem is that the rule matcher doesn't know anything about commuting ops. This CL fixes that fact. We already have information about which ops commute. (The register allocator takes advantage of commutivity.) The rule generator now automatically generates multiple rules for a single source rule when there are commutative ops in the rule. We can now drop all of our almost-duplicate source-level rules and the canonicalization rules. I have some CLs in progress that will be a lot less verbose when the rule generator handles commutivity for me. I had to reorganize the load-combining rules a bit. The 8-way OR rules generated 128 different reorderings, which was causing the generator to put too much code in the rewrite*.go files (the big ones were going from 25K lines to 132K lines). Instead I reorganized the rules to combine pairs of loads at a time. The generated rule files are now actually a bit (5%) smaller. Make.bash times are ~unchanged. Compiler benchmarks are not observably different. Probably because we don't spend much compiler time in rule matching anyway. I've also done a pass over all of our ops adding commutative markings for ops which hadn't had them previously. Fixes #18292 Change-Id: Ic1c0e43fbf579539f459971625f69690c9ab8805 Reviewed-on: https://go-review.googlesource.com/38801 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-03-30 03:30:22 +00:00
{name: "MOVBstoreidx1", argLength: 4, reg: gpstoreidx, commutative: true, asm: "MOVB", aux: "SymOff", symEffect: "Write"}, // store byte in arg2 to arg0+arg1+auxint+aux. arg3=mem
{name: "MOVWstoreidx1", argLength: 4, reg: gpstoreidx, commutative: true, asm: "MOVW", aux: "SymOff", symEffect: "Write"}, // store 2 bytes in arg2 to arg0+arg1+auxint+aux. arg3=mem
{name: "MOVWstoreidx2", argLength: 4, reg: gpstoreidx, asm: "MOVW", aux: "SymOff", symEffect: "Write"}, // store 2 bytes in arg2 to arg0+2*arg1+auxint+aux. arg3=mem
{name: "MOVLstoreidx1", argLength: 4, reg: gpstoreidx, commutative: true, asm: "MOVL", aux: "SymOff", symEffect: "Write"}, // store 4 bytes in arg2 to arg0+arg1+auxint+aux. arg3=mem
{name: "MOVLstoreidx4", argLength: 4, reg: gpstoreidx, asm: "MOVL", aux: "SymOff", symEffect: "Write"}, // store 4 bytes in arg2 to arg0+4*arg1+auxint+aux. arg3=mem
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// TODO: add size-mismatched indexed loads, like MOVBstoreidx4.
// For storeconst ops, the AuxInt field encodes both
// the value to store and an address offset of the store.
// Cast AuxInt to a ValAndOff to extract Val and Off fields.
cmd/compile/internal/ssa: populate SymEffects for SSA Ops Changes to ${GOARCH}Ops.go files were mechanically produced using github.com/mdempsky/ssa-symops, a one-off tool that inserts "SymEffect: X" elements by pattern matching against the Op names. Change-Id: Ibf3e481ffd588647f2a31662d72114b740ccbfcf Reviewed-on: https://go-review.googlesource.com/38084 Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-03-09 14:46:43 -08:00
{name: "MOVBstoreconst", argLength: 2, reg: gpstoreconst, asm: "MOVB", aux: "SymValAndOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store low byte of ValAndOff(AuxInt).Val() to arg0+ValAndOff(AuxInt).Off()+aux. arg1=mem
{name: "MOVWstoreconst", argLength: 2, reg: gpstoreconst, asm: "MOVW", aux: "SymValAndOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store low 2 bytes of ...
{name: "MOVLstoreconst", argLength: 2, reg: gpstoreconst, asm: "MOVL", aux: "SymValAndOff", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store low 4 bytes of ...
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
cmd/compile/internal/ssa: populate SymEffects for SSA Ops Changes to ${GOARCH}Ops.go files were mechanically produced using github.com/mdempsky/ssa-symops, a one-off tool that inserts "SymEffect: X" elements by pattern matching against the Op names. Change-Id: Ibf3e481ffd588647f2a31662d72114b740ccbfcf Reviewed-on: https://go-review.googlesource.com/38084 Run-TryBot: Matthew Dempsky <mdempsky@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-03-09 14:46:43 -08:00
{name: "MOVBstoreconstidx1", argLength: 3, reg: gpstoreconstidx, asm: "MOVB", aux: "SymValAndOff", typ: "Mem", symEffect: "Write"}, // store low byte of ValAndOff(AuxInt).Val() to arg0+1*arg1+ValAndOff(AuxInt).Off()+aux. arg2=mem
{name: "MOVWstoreconstidx1", argLength: 3, reg: gpstoreconstidx, asm: "MOVW", aux: "SymValAndOff", typ: "Mem", symEffect: "Write"}, // store low 2 bytes of ... arg1 ...
{name: "MOVWstoreconstidx2", argLength: 3, reg: gpstoreconstidx, asm: "MOVW", aux: "SymValAndOff", typ: "Mem", symEffect: "Write"}, // store low 2 bytes of ... 2*arg1 ...
{name: "MOVLstoreconstidx1", argLength: 3, reg: gpstoreconstidx, asm: "MOVL", aux: "SymValAndOff", typ: "Mem", symEffect: "Write"}, // store low 4 bytes of ... arg1 ...
{name: "MOVLstoreconstidx4", argLength: 3, reg: gpstoreconstidx, asm: "MOVL", aux: "SymValAndOff", typ: "Mem", symEffect: "Write"}, // store low 4 bytes of ... 4*arg1 ...
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
[dev.ssa] cmd/compile: more 386 port changes Fix up zero/move code, including duff calls and rep movs. Handle the new ops generated by dec64.rules. Fix constant shifts. Change-Id: I7d89194b29b04311bfafa0fd93b9f5644af04df9 Reviewed-on: https://go-review.googlesource.com/25033 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-07-18 15:52:59 -07:00
// arg0 = pointer to start of memory to zero
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// arg1 = value to store (will always be zero)
// arg2 = mem
// auxint = offset into duffzero code to start executing
// returns mem
{
name: "DUFFZERO",
aux: "Int64",
argLength: 3,
reg: regInfo{
[dev.ssa] cmd/compile: more 386 port changes Fix up zero/move code, including duff calls and rep movs. Handle the new ops generated by dec64.rules. Fix constant shifts. Change-Id: I7d89194b29b04311bfafa0fd93b9f5644af04df9 Reviewed-on: https://go-review.googlesource.com/25033 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-07-18 15:52:59 -07:00
inputs: []regMask{buildReg("DI"), buildReg("AX")},
[dev.ssa] cmd/compile: more fixes for 386 shared libraries Use the destination register for materializing the pc for GOT references also. See https://go-review.googlesource.com/c/25442/ The SSA backend assumes CX does not get clobbered for these instructions. Mark duffzero as clobbering CX. The linker needs to clobber CX to materialize the address to call. (This affects the non-shared-library duffzero also, but hopefully forbidding one register across duffzero won't be a big deal.) Hopefully this is all the cases where the linker is clobbering CX under the hood and SSA assumes it isn't. Change-Id: I080c938170193df57cd5ce1f2a956b68a34cc886 Reviewed-on: https://go-review.googlesource.com/26611 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Michael Hudson-Doyle <michael.hudson@canonical.com>
2016-08-09 13:58:06 -07:00
clobbers: buildReg("DI CX"),
// Note: CX is only clobbered when dynamic linking.
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
},
cmd/compile: remove nil check for Zero/Move on 386, AMD64, S390X Fixes #18003. Change-Id: Iadcc5c424c64badecfb5fdbd4dbd9197df56182c Reviewed-on: https://go-review.googlesource.com/33421 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2016-11-21 11:31:39 -05:00
faultOnNilArg0: true,
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
},
// arg0 = address of memory to zero
// arg1 = # of 4-byte words to zero
// arg2 = value to store (will always be zero)
// arg3 = mem
// returns mem
{
name: "REPSTOSL",
argLength: 4,
reg: regInfo{
inputs: []regMask{buildReg("DI"), buildReg("CX"), buildReg("AX")},
clobbers: buildReg("DI CX"),
},
cmd/compile: remove nil check for Zero/Move on 386, AMD64, S390X Fixes #18003. Change-Id: Iadcc5c424c64badecfb5fdbd4dbd9197df56182c Reviewed-on: https://go-review.googlesource.com/33421 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2016-11-21 11:31:39 -05:00
faultOnNilArg0: true,
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
},
cmd/compile: extend ssa.AuxCall to closure and interface calls Also introduce helper methods. Change-Id: I11a744ed002bae0ca9ebabba3206e1c14147e03d Reviewed-on: https://go-review.googlesource.com/c/go/+/239080 Trust: David Chase <drchase@google.com> Run-TryBot: David Chase <drchase@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-06-15 18:27:02 -04:00
{name: "CALLstatic", argLength: 1, reg: regInfo{clobbers: callerSave}, aux: "CallOff", clobberFlags: true, call: true}, // call static function aux.(*obj.LSym). arg0=mem, auxint=argsize, returns mem
cmd/compile: don't clobber LR for tail calls When doing a tail call the link register is live as the callee will directly return to the caller (of the function that does the tail call). Don't allocate or clobber the link register. Fixes #49032. Change-Id: I2d60f2354e5b6c14aa285c8983a9786687b90223 Reviewed-on: https://go-review.googlesource.com/c/go/+/358435 Trust: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com> Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com> TryBot-Result: Go Bot <gobot@golang.org>
2021-10-25 11:51:25 -04:00
{name: "CALLtail", argLength: 1, reg: regInfo{clobbers: callerSave}, aux: "CallOff", clobberFlags: true, call: true, tailCall: true}, // tail call static function aux.(*obj.LSym). arg0=mem, auxint=argsize, returns mem
cmd/compile: extend ssa.AuxCall to closure and interface calls Also introduce helper methods. Change-Id: I11a744ed002bae0ca9ebabba3206e1c14147e03d Reviewed-on: https://go-review.googlesource.com/c/go/+/239080 Trust: David Chase <drchase@google.com> Run-TryBot: David Chase <drchase@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-06-15 18:27:02 -04:00
{name: "CALLclosure", argLength: 3, reg: regInfo{inputs: []regMask{gpsp, buildReg("DX"), 0}, clobbers: callerSave}, aux: "CallOff", clobberFlags: true, call: true}, // call function via closure. arg0=codeptr, arg1=closure, arg2=mem, auxint=argsize, returns mem
{name: "CALLinter", argLength: 2, reg: regInfo{inputs: []regMask{gp}, clobbers: callerSave}, aux: "CallOff", clobberFlags: true, call: true}, // call fn by pointer. arg0=codeptr, arg1=mem, auxint=argsize, returns mem
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// arg0 = destination pointer
// arg1 = source pointer
// arg2 = mem
// auxint = offset from duffcopy symbol to call
// returns memory
{
name: "DUFFCOPY",
aux: "Int64",
argLength: 3,
reg: regInfo{
inputs: []regMask{buildReg("DI"), buildReg("SI")},
[dev.ssa] cmd/compile: remove flags from regMask Reg allocator skips flag-typed values. Flag allocator uses the type and whether the op has "clobberFlags" set. Tested on AMD64, ARM, ARM64, 386. Passed 'toolstash -cmp' on AMD64. PPC64 is coded blindly. Change-Id: Ib1cc27efecef6a1bb27f7d7ed035a582660d244f Reviewed-on: https://go-review.googlesource.com/25480 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-08-04 06:57:34 -04:00
clobbers: buildReg("DI SI CX"), // uses CX as a temporary
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
},
cmd/compile: remove nil check for Zero/Move on 386, AMD64, S390X Fixes #18003. Change-Id: Iadcc5c424c64badecfb5fdbd4dbd9197df56182c Reviewed-on: https://go-review.googlesource.com/33421 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2016-11-21 11:31:39 -05:00
clobberFlags: true,
faultOnNilArg0: true,
faultOnNilArg1: true,
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
},
// arg0 = destination pointer
// arg1 = source pointer
// arg2 = # of 8-byte words to copy
// arg3 = mem
// returns memory
{
name: "REPMOVSL",
argLength: 4,
reg: regInfo{
inputs: []regMask{buildReg("DI"), buildReg("SI"), buildReg("CX")},
clobbers: buildReg("DI SI CX"),
},
cmd/compile: remove nil check for Zero/Move on 386, AMD64, S390X Fixes #18003. Change-Id: Iadcc5c424c64badecfb5fdbd4dbd9197df56182c Reviewed-on: https://go-review.googlesource.com/33421 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2016-11-21 11:31:39 -05:00
faultOnNilArg0: true,
faultOnNilArg1: true,
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
},
// (InvertFlags (CMPL a b)) == (CMPL b a)
// So if we want (SETL (CMPL a b)) but we can't do that because a is a constant,
// then we do (SETL (InvertFlags (CMPL b a))) instead.
// Rewrites will convert this to (SETG (CMPL b a)).
// InvertFlags is a pseudo-op which can't appear in assembly output.
{name: "InvertFlags", argLength: 1}, // reverse direction of arg0
// Pseudo-ops
{name: "LoweredGetG", argLength: 1, reg: gp01}, // arg0=mem
// Scheduler ensures LoweredGetClosurePtr occurs only in entry block,
// and sorts it to the very beginning of the block to prevent other
// use of DX (the closure pointer)
cmd/compile/internal/ssa: note zero-width Ops Add a bool to opInfo to indicate if an Op never results in any instructions. This is a conservative approximation: some operations, like Copy, may or may not generate code depending on their arguments. I built the list by reading each arch's ssaGenValue function. Hopefully I got them all. Change-Id: I130b251b65f18208294e129bb7ddc3f91d57d31d Reviewed-on: https://go-review.googlesource.com/97957 Reviewed-by: Keith Randall <khr@golang.org>
2018-02-28 16:30:07 -05:00
{name: "LoweredGetClosurePtr", reg: regInfo{outputs: []regMask{buildReg("DX")}}, zeroWidth: true},
cmd/compile: add intrinsic for reading caller's pc First step towards removing the mandatory argument for getcallerpc, which solves certain problems for the runtime. This might also slightly improve performance. Intrinsic enabled on 386, amd64, amd64p32, runtime asm implementation removed on those architectures. Now-superfluous argument remains in getcallerpc signature (for a future CL; non-386/amd64 asm funcs ignore it). Added getcallerpc to the "not a real function" test in dcl.go, that story is a little odd with respect to unexported functions but that is not this CL. Fixes #17327. Change-Id: I5df1ad91f27ee9ac1f0dd88fa48f1329d6306c3e Reviewed-on: https://go-review.googlesource.com/31851 Run-TryBot: David Chase <drchase@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Austin Clements <austin@google.com>
2016-10-24 10:25:05 -04:00
// LoweredGetCallerPC evaluates to the PC to which its "caller" will return.
// I.e., if f calls g "calls" getcallerpc,
// the result should be the PC within f that g will return to.
// See runtime/stubs.go for a more detailed discussion.
cmd/compile: mark LoweredGetCallerPC rematerializeable The caller's PC is always available in the frame. We can just load it when needed, no need to spill. Change-Id: I9c0a525903e574bb4eec9fe53cbeb8c64321166a Reviewed-on: https://go-review.googlesource.com/70710 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2017-10-13 11:05:12 -04:00
{name: "LoweredGetCallerPC", reg: gp01, rematerializeable: true},
cmd/compile: add memory argument to GetCallerSP We need to make sure that when we get the stack pointer, we get it at the right time. V = GetCallerSP Call() W = GetCallerSP If Call causes a stack growth, then we will be in a situation where V != W. So it matters when GetCallerSP operations get scheduled. Add a memory argument to GetCallerSP so it can't be reordered with things like calls. Change-Id: I6cc801134c38e358c5a1ec0c09d38379a16a4184 Reviewed-on: https://go-review.googlesource.com/c/go/+/453515 Reviewed-by: Martin Möhrmann <moehrmann@google.com> Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: Martin Möhrmann <martin@golang.org> Reviewed-by: Robert Griesemer <gri@google.com> TryBot-Result: Gopher Robot <gobot@golang.org>
2022-11-26 15:03:51 -08:00
// LoweredGetCallerSP returns the SP of the caller of the current function. arg0=mem
{name: "LoweredGetCallerSP", argLength: 1, reg: gp01, rematerializeable: true},
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
//arg0=ptr,arg1=mem, returns void. Faults if ptr is nil.
cmd/compile: remove duplicate nilchecks Mark nil check operations as faulting if their arg is zero. This lets the late nilcheck pass remove duplicates. Fixes #17242. Change-Id: I4c9938d8a5a1e43edd85b4a66f0b34004860bcd9 Reviewed-on: https://go-review.googlesource.com/29952 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-09-27 14:39:27 -07:00
{name: "LoweredNilCheck", argLength: 2, reg: regInfo{inputs: []regMask{gpsp}}, clobberFlags: true, nilCheck: true, faultOnNilArg0: true},
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
runtime: buffered write barrier for 386 Updates #22460. Change-Id: I3c8e90fd6bcda7e28911036591873d63665aaca7 Reviewed-on: https://go-review.googlesource.com/92696 Run-TryBot: Austin Clements <austin@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2017-11-15 14:54:24 -08:00
// LoweredWB invokes runtime.gcWriteBarrier. arg0=destptr, arg1=srcptr, arg2=mem, aux=runtime.gcWriteBarrier
// It saves all GP registers if necessary, but may clobber others.
{name: "LoweredWB", argLength: 3, reg: regInfo{inputs: []regMask{buildReg("DI"), ax}, clobbers: callerSave &^ gp}, clobberFlags: true, aux: "Sym", symEffect: "None"},
cmd/compile,runtime: provide index information on bounds check failure A few examples (for accessing a slice of length 3): s[-1] runtime error: index out of range [-1] s[3] runtime error: index out of range [3] with length 3 s[-1:0] runtime error: slice bounds out of range [-1:] s[3:0] runtime error: slice bounds out of range [3:0] s[3:-1] runtime error: slice bounds out of range [:-1] s[3:4] runtime error: slice bounds out of range [:4] with capacity 3 s[0:3:4] runtime error: slice bounds out of range [::4] with capacity 3 Note that in cases where there are multiple things wrong with the indexes (e.g. s[3:-1]), we report one of those errors kind of arbitrarily, currently the rightmost one. An exhaustive set of examples is in issue30116[u].out in the CL. The message text has the same prefix as the old message text. That leads to slightly awkward phrasing but hopefully minimizes the chance that code depending on the error text will break. Increases the size of the go binary by 0.5% (amd64). The panic functions take arguments in registers in order to keep the size of the compiled code as small as possible. Fixes #30116 Change-Id: Idb99a827b7888822ca34c240eca87b7e44a04fdd Reviewed-on: https://go-review.googlesource.com/c/go/+/161477 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2019-02-06 14:12:36 -08:00
// There are three of these functions so that they can have three different register inputs.
// When we check 0 <= c <= cap (A), then 0 <= b <= c (B), then 0 <= a <= b (C), we want the
// default registers to match so we don't need to copy registers around unnecessarily.
cmd/compile: mark PanicBounds/Extend as calls PanicBounds and PanicExtend are lowered to runtime calls (with a non-Go ABI), but are not currently marked as calls. Since liveness analysis only emits stack maps at calls in the runtime, this means these panic call sites in the runtime won't get a stack map. These almost immediately turn into throws in the runtime, but there's still a chance they'll try to grow the stack first, which would lead to a different panic. To fix this, mark these operations as calls. Outside the runtime, we currently emit stack maps for everything that isn't an unsafe-point, so these panic calls get stack maps by default. However, we're about to move to emitting stack maps only at call sites, at which point this will start to matter outside the runtime as well. I confirmed that this has no effect on anything but PCDATA/FUNCDATA in runtime and net/http. For #36365. Change-Id: Ic5bb463fd152cc320c815dc04cf62005261ae169 Reviewed-on: https://go-review.googlesource.com/c/go/+/230539 Run-TryBot: Austin Clements <austin@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-27 15:58:16 -04:00
{name: "LoweredPanicBoundsA", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{dx, bx}}, typ: "Mem", call: true}, // arg0=idx, arg1=len, arg2=mem, returns memory. AuxInt contains report code (see PanicBounds in genericOps.go).
{name: "LoweredPanicBoundsB", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{cx, dx}}, typ: "Mem", call: true}, // arg0=idx, arg1=len, arg2=mem, returns memory. AuxInt contains report code (see PanicBounds in genericOps.go).
{name: "LoweredPanicBoundsC", argLength: 3, aux: "Int64", reg: regInfo{inputs: []regMask{ax, cx}}, typ: "Mem", call: true}, // arg0=idx, arg1=len, arg2=mem, returns memory. AuxInt contains report code (see PanicBounds in genericOps.go).
cmd/compile,runtime: provide index information on bounds check failure A few examples (for accessing a slice of length 3): s[-1] runtime error: index out of range [-1] s[3] runtime error: index out of range [3] with length 3 s[-1:0] runtime error: slice bounds out of range [-1:] s[3:0] runtime error: slice bounds out of range [3:0] s[3:-1] runtime error: slice bounds out of range [:-1] s[3:4] runtime error: slice bounds out of range [:4] with capacity 3 s[0:3:4] runtime error: slice bounds out of range [::4] with capacity 3 Note that in cases where there are multiple things wrong with the indexes (e.g. s[3:-1]), we report one of those errors kind of arbitrarily, currently the rightmost one. An exhaustive set of examples is in issue30116[u].out in the CL. The message text has the same prefix as the old message text. That leads to slightly awkward phrasing but hopefully minimizes the chance that code depending on the error text will break. Increases the size of the go binary by 0.5% (amd64). The panic functions take arguments in registers in order to keep the size of the compiled code as small as possible. Fixes #30116 Change-Id: Idb99a827b7888822ca34c240eca87b7e44a04fdd Reviewed-on: https://go-review.googlesource.com/c/go/+/161477 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2019-02-06 14:12:36 -08:00
// Extend ops are the same as Bounds ops except the indexes are 64-bit.
cmd/compile: mark PanicBounds/Extend as calls PanicBounds and PanicExtend are lowered to runtime calls (with a non-Go ABI), but are not currently marked as calls. Since liveness analysis only emits stack maps at calls in the runtime, this means these panic call sites in the runtime won't get a stack map. These almost immediately turn into throws in the runtime, but there's still a chance they'll try to grow the stack first, which would lead to a different panic. To fix this, mark these operations as calls. Outside the runtime, we currently emit stack maps for everything that isn't an unsafe-point, so these panic calls get stack maps by default. However, we're about to move to emitting stack maps only at call sites, at which point this will start to matter outside the runtime as well. I confirmed that this has no effect on anything but PCDATA/FUNCDATA in runtime and net/http. For #36365. Change-Id: Ic5bb463fd152cc320c815dc04cf62005261ae169 Reviewed-on: https://go-review.googlesource.com/c/go/+/230539 Run-TryBot: Austin Clements <austin@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-27 15:58:16 -04:00
{name: "LoweredPanicExtendA", argLength: 4, aux: "Int64", reg: regInfo{inputs: []regMask{si, dx, bx}}, typ: "Mem", call: true}, // arg0=idxHi, arg1=idxLo, arg2=len, arg3=mem, returns memory. AuxInt contains report code (see PanicExtend in genericOps.go).
{name: "LoweredPanicExtendB", argLength: 4, aux: "Int64", reg: regInfo{inputs: []regMask{si, cx, dx}}, typ: "Mem", call: true}, // arg0=idxHi, arg1=idxLo, arg2=len, arg3=mem, returns memory. AuxInt contains report code (see PanicExtend in genericOps.go).
{name: "LoweredPanicExtendC", argLength: 4, aux: "Int64", reg: regInfo{inputs: []regMask{si, ax, cx}}, typ: "Mem", call: true}, // arg0=idxHi, arg1=idxLo, arg2=len, arg3=mem, returns memory. AuxInt contains report code (see PanicExtend in genericOps.go).
cmd/compile,runtime: provide index information on bounds check failure A few examples (for accessing a slice of length 3): s[-1] runtime error: index out of range [-1] s[3] runtime error: index out of range [3] with length 3 s[-1:0] runtime error: slice bounds out of range [-1:] s[3:0] runtime error: slice bounds out of range [3:0] s[3:-1] runtime error: slice bounds out of range [:-1] s[3:4] runtime error: slice bounds out of range [:4] with capacity 3 s[0:3:4] runtime error: slice bounds out of range [::4] with capacity 3 Note that in cases where there are multiple things wrong with the indexes (e.g. s[3:-1]), we report one of those errors kind of arbitrarily, currently the rightmost one. An exhaustive set of examples is in issue30116[u].out in the CL. The message text has the same prefix as the old message text. That leads to slightly awkward phrasing but hopefully minimizes the chance that code depending on the error text will break. Increases the size of the go binary by 0.5% (amd64). The panic functions take arguments in registers in order to keep the size of the compiled code as small as possible. Fixes #30116 Change-Id: Idb99a827b7888822ca34c240eca87b7e44a04fdd Reviewed-on: https://go-review.googlesource.com/c/go/+/161477 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2019-02-06 14:12:36 -08:00
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
// Constant flag values. For any comparison, there are 5 possible
// outcomes: the three from the signed total order (<,==,>) and the
// three from the unsigned total order. The == cases overlap.
// Note: there's a sixth "unordered" outcome for floating-point
// comparisons, but we don't use such a beast yet.
// These ops are for temporary use by rewrite rules. They
// cannot appear in the generated assembly.
{name: "FlagEQ"}, // equal
{name: "FlagLT_ULT"}, // signed < and unsigned <
{name: "FlagLT_UGT"}, // signed < and unsigned >
{name: "FlagGT_UGT"}, // signed > and unsigned <
{name: "FlagGT_ULT"}, // signed > and unsigned >
[dev.ssa] cmd/compile: fix fp constant loads for 386+PIC In position-independent 386 code, loading floating-point constants from the constant pool requires two steps: materializing the address of the constant pool entry (requires calling a thunk) and then loading from that address. Before this CL, the materializing happened implicitly in CX, which clobbered that register. Change-Id: Id094e0fb2d3be211089f299e8f7c89c315de0a87 Reviewed-on: https://go-review.googlesource.com/26811 Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: David Crawshaw <crawshaw@golang.org> Reviewed-by: David Chase <drchase@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
2016-08-11 09:49:48 -07:00
// Special ops for PIC floating-point constants.
// MOVSXconst1 loads the address of the constant-pool entry into a register.
// MOVSXconst2 loads the constant from that address.
// MOVSXconst1 returns a pointer, but we type it as uint32 because it can never point to the Go heap.
{name: "MOVSSconst1", reg: gp01, typ: "UInt32", aux: "Float32"},
{name: "MOVSDconst1", reg: gp01, typ: "UInt32", aux: "Float64"},
{name: "MOVSSconst2", argLength: 1, reg: gpfp, asm: "MOVSS"},
{name: "MOVSDconst2", argLength: 1, reg: gpfp, asm: "MOVSD"},
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
}
var _386blocks = []blockData{
cmd/compile: allow multiple SSA block control values Control values are used to choose which successor of a block is jumped to. Typically a control value takes the form of a 'flags' value that represents the result of a comparison. Some architectures however use a variable in a register as a control value. Up until now we have managed with a single control value per block. However some architectures (e.g. s390x and riscv64) have combined compare-and-branch instructions that take two variables in registers as parameters. To generate these instructions we need to support 2 control values per block. This CL allows up to 2 control values to be used in a block in order to support the addition of compare-and-branch instructions. I have implemented s390x compare-and-branch instructions in a different CL. Passes toolstash-check -all. Results of compilebench: name old time/op new time/op delta Template 208ms ± 1% 209ms ± 1% ~ (p=0.289 n=20+20) Unicode 83.7ms ± 1% 83.3ms ± 3% -0.49% (p=0.017 n=18+18) GoTypes 748ms ± 1% 748ms ± 0% ~ (p=0.460 n=20+18) Compiler 3.47s ± 1% 3.48s ± 1% ~ (p=0.070 n=19+18) SSA 11.5s ± 1% 11.7s ± 1% +1.64% (p=0.000 n=19+18) Flate 130ms ± 1% 130ms ± 1% ~ (p=0.588 n=19+20) GoParser 160ms ± 1% 161ms ± 1% ~ (p=0.211 n=20+20) Reflect 465ms ± 1% 467ms ± 1% +0.42% (p=0.007 n=20+20) Tar 184ms ± 1% 185ms ± 2% ~ (p=0.087 n=18+20) XML 253ms ± 1% 253ms ± 1% ~ (p=0.377 n=20+18) LinkCompiler 769ms ± 2% 774ms ± 2% ~ (p=0.070 n=19+19) ExternalLinkCompiler 3.59s ±11% 3.68s ± 6% ~ (p=0.072 n=20+20) LinkWithoutDebugCompiler 446ms ± 5% 454ms ± 3% +1.79% (p=0.002 n=19+20) StdCmd 26.0s ± 2% 26.0s ± 2% ~ (p=0.799 n=20+20) name old user-time/op new user-time/op delta Template 238ms ± 5% 240ms ± 5% ~ (p=0.142 n=20+20) Unicode 105ms ±11% 106ms ±10% ~ (p=0.512 n=20+20) GoTypes 876ms ± 2% 873ms ± 4% ~ (p=0.647 n=20+19) Compiler 4.17s ± 2% 4.19s ± 1% ~ (p=0.093 n=20+18) SSA 13.9s ± 1% 14.1s ± 1% +1.45% (p=0.000 n=18+18) Flate 145ms ±13% 146ms ± 5% ~ (p=0.851 n=20+18) GoParser 185ms ± 5% 188ms ± 7% ~ (p=0.174 n=20+20) Reflect 534ms ± 3% 538ms ± 2% ~ (p=0.105 n=20+18) Tar 215ms ± 4% 211ms ± 9% ~ (p=0.079 n=19+20) XML 295ms ± 6% 295ms ± 5% ~ (p=0.968 n=20+20) LinkCompiler 832ms ± 4% 837ms ± 7% ~ (p=0.707 n=17+20) ExternalLinkCompiler 1.58s ± 8% 1.60s ± 4% ~ (p=0.296 n=20+19) LinkWithoutDebugCompiler 478ms ±12% 489ms ±10% ~ (p=0.429 n=20+20) name old object-bytes new object-bytes delta Template 559kB ± 0% 559kB ± 0% ~ (all equal) Unicode 216kB ± 0% 216kB ± 0% ~ (all equal) GoTypes 2.03MB ± 0% 2.03MB ± 0% ~ (all equal) Compiler 8.07MB ± 0% 8.07MB ± 0% -0.06% (p=0.000 n=20+20) SSA 27.1MB ± 0% 27.3MB ± 0% +0.89% (p=0.000 n=20+20) Flate 343kB ± 0% 343kB ± 0% ~ (all equal) GoParser 441kB ± 0% 441kB ± 0% ~ (all equal) Reflect 1.36MB ± 0% 1.36MB ± 0% ~ (all equal) Tar 487kB ± 0% 487kB ± 0% ~ (all equal) XML 632kB ± 0% 632kB ± 0% ~ (all equal) name old export-bytes new export-bytes delta Template 18.5kB ± 0% 18.5kB ± 0% ~ (all equal) Unicode 7.92kB ± 0% 7.92kB ± 0% ~ (all equal) GoTypes 35.0kB ± 0% 35.0kB ± 0% ~ (all equal) Compiler 109kB ± 0% 110kB ± 0% +0.72% (p=0.000 n=20+20) SSA 137kB ± 0% 138kB ± 0% +0.58% (p=0.000 n=20+20) Flate 4.89kB ± 0% 4.89kB ± 0% ~ (all equal) GoParser 8.49kB ± 0% 8.49kB ± 0% ~ (all equal) Reflect 11.4kB ± 0% 11.4kB ± 0% ~ (all equal) Tar 10.5kB ± 0% 10.5kB ± 0% ~ (all equal) XML 16.7kB ± 0% 16.7kB ± 0% ~ (all equal) name old text-bytes new text-bytes delta HelloSize 761kB ± 0% 761kB ± 0% ~ (all equal) CmdGoSize 10.8MB ± 0% 10.8MB ± 0% ~ (all equal) name old data-bytes new data-bytes delta HelloSize 10.7kB ± 0% 10.7kB ± 0% ~ (all equal) CmdGoSize 312kB ± 0% 312kB ± 0% ~ (all equal) name old bss-bytes new bss-bytes delta HelloSize 122kB ± 0% 122kB ± 0% ~ (all equal) CmdGoSize 146kB ± 0% 146kB ± 0% ~ (all equal) name old exe-bytes new exe-bytes delta HelloSize 1.13MB ± 0% 1.13MB ± 0% ~ (all equal) CmdGoSize 15.1MB ± 0% 15.1MB ± 0% ~ (all equal) Change-Id: I3cc2f9829a109543d9a68be4a21775d2d3e9801f Reviewed-on: https://go-review.googlesource.com/c/go/+/196557 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Daniel Martí <mvdan@mvdan.cc> Reviewed-by: Keith Randall <khr@golang.org>
2019-08-12 20:19:58 +01:00
{name: "EQ", controls: 1},
{name: "NE", controls: 1},
{name: "LT", controls: 1},
{name: "LE", controls: 1},
{name: "GT", controls: 1},
{name: "GE", controls: 1},
{name: "OS", controls: 1},
{name: "OC", controls: 1},
{name: "ULT", controls: 1},
{name: "ULE", controls: 1},
{name: "UGT", controls: 1},
{name: "UGE", controls: 1},
{name: "EQF", controls: 1},
{name: "NEF", controls: 1},
{name: "ORD", controls: 1}, // FP, ordered comparison (parity zero)
{name: "NAN", controls: 1}, // FP, unordered comparison (parity one)
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
}
archs = append(archs, arch{
name: "386",
pkg: "cmd/internal/obj/x86",
genfile: "../../x86/ssa.go",
ops: _386ops,
blocks: _386blocks,
regnames: regNames386,
gpregmask: gp,
fpregmask: fp,
framepointerreg: int8(num["BP"]),
cmd/compile: make link register allocatable in non-leaf functions We save and restore the link register in non-leaf functions because it is clobbered by CALLs. It is therefore available for general purpose use. Only enabled on s390x currently. The RC4 benchmarks in particular benefit from the extra register: name old speed new speed delta RC4_128 243MB/s ± 2% 341MB/s ± 2% +40.46% (p=0.008 n=5+5) RC4_1K 267MB/s ± 0% 359MB/s ± 1% +34.32% (p=0.008 n=5+5) RC4_8K 271MB/s ± 0% 362MB/s ± 0% +33.61% (p=0.008 n=5+5) Change-Id: Id23bff95e771da9425353da2f32668b8e34ba09f Reviewed-on: https://go-review.googlesource.com/30597 Reviewed-by: Cherry Zhang <cherryyz@google.com> Run-TryBot: Michael Munday <munday@ca.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
2016-10-06 15:06:45 -04:00
linkreg: -1, // not used
[dev.ssa] cmd/compile: initial 386 SSA port Basically just copied all the amd64 files, removed all the *Q ops, and rebuilt. Compiles fib successfully. Still need to do: - all the 64->32 bit op translations. - audit for instructions that aren't available on 386. - GO386=387? Update #16358 Change-Id: Ib8c684586416a554a527a5eefa0cff71424e36f5 Reviewed-on: https://go-review.googlesource.com/24912 Reviewed-by: Cherry Zhang <cherryyz@google.com>
2016-07-13 13:43:08 -07:00
})
go/printer, gofmt: handle raw string literals containing newlines better A raw string containing newlines breaks whatever columns structure has been established so far. Recognize the situation and force a new section of alignment with the first line break seen after the the raw string. Applied gofmt to src and misc. Fixes #9064. Change-Id: I961e94b529b1fd421908311f366b113e2ec9b7f0 Reviewed-on: https://go-review.googlesource.com/105040 Reviewed-by: Matthew Dempsky <mdempsky@google.com>
2018-04-05 16:04:56 -07:00
}
Reference in a new issue Copy permalink