go/src/cmd/compile/internal/gc/pgen.go

543 lines
12 KiB
Go
Raw Normal View History

// Copyright 2011 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 gc
import (
"cmd/internal/obj"
"crypto/md5"
"fmt"
"strings"
)
// "Portable" code generation.
var makefuncdatasym_nsym int32
func makefuncdatasym(namefmt string, funcdatakind int64) *Sym {
var nod Node
sym := Lookupf(namefmt, makefuncdatasym_nsym)
makefuncdatasym_nsym++
pnod := newname(sym)
pnod.Class = PEXTERN
Nodconst(&nod, Types[TINT32], funcdatakind)
Thearch.Gins(obj.AFUNCDATA, &nod, pnod)
return sym
}
// gvardef inserts a VARDEF for n into the instruction stream.
// VARDEF is an annotation for the liveness analysis, marking a place
// where a complete initialization (definition) of a variable begins.
// Since the liveness analysis can see initialization of single-word
// variables quite easy, gvardef is usually only called for multi-word
// or 'fat' variables, those satisfying isfat(n->type).
// However, gvardef is also called when a non-fat variable is initialized
// via a block move; the only time this happens is when you have
// return f()
// for a function with multiple return values exactly matching the return
// types of the current function.
//
// A 'VARDEF x' annotation in the instruction stream tells the liveness
// analysis to behave as though the variable x is being initialized at that
// point in the instruction stream. The VARDEF must appear before the
// actual (multi-instruction) initialization, and it must also appear after
// any uses of the previous value, if any. For example, if compiling:
//
// x = x[1:]
//
// it is important to generate code like:
//
// base, len, cap = pieces of x[1:]
// VARDEF x
// x = {base, len, cap}
//
// If instead the generated code looked like:
//
// VARDEF x
// base, len, cap = pieces of x[1:]
// x = {base, len, cap}
//
// then the liveness analysis would decide the previous value of x was
// unnecessary even though it is about to be used by the x[1:] computation.
// Similarly, if the generated code looked like:
//
// base, len, cap = pieces of x[1:]
// x = {base, len, cap}
// VARDEF x
//
// then the liveness analysis will not preserve the new value of x, because
// the VARDEF appears to have "overwritten" it.
//
// VARDEF is a bit of a kludge to work around the fact that the instruction
// stream is working on single-word values but the liveness analysis
// wants to work on individual variables, which might be multi-word
// aggregates. It might make sense at some point to look into letting
// the liveness analysis work on single-word values as well, although
// there are complications around interface values, slices, and strings,
// all of which cannot be treated as individual words.
//
// VARKILL is the opposite of VARDEF: it marks a value as no longer needed,
// even if its address has been taken. That is, a VARKILL annotation asserts
// that its argument is certainly dead, for use when the liveness analysis
// would not otherwise be able to deduce that fact.
func gvardefx(n *Node, as int) {
if n == nil {
Fatal("gvardef nil")
}
if n.Op != ONAME {
Yyerror("gvardef %v; %v", Oconv(int(n.Op), obj.FmtSharp), n)
return
}
switch n.Class {
case PAUTO, PPARAM, PPARAMOUT:
Thearch.Gins(as, nil, n)
}
}
func Gvardef(n *Node) {
gvardefx(n, obj.AVARDEF)
}
func gvarkill(n *Node) {
gvardefx(n, obj.AVARKILL)
}
func removevardef(firstp *obj.Prog) {
for p := firstp; p != nil; p = p.Link {
for p.Link != nil && (p.Link.As == obj.AVARDEF || p.Link.As == obj.AVARKILL) {
p.Link = p.Link.Link
}
if p.To.Type == obj.TYPE_BRANCH {
for p.To.Val.(*obj.Prog) != nil && (p.To.Val.(*obj.Prog).As == obj.AVARDEF || p.To.Val.(*obj.Prog).As == obj.AVARKILL) {
p.To.Val = p.To.Val.(*obj.Prog).Link
}
}
}
}
func gcsymdup(s *Sym) {
ls := Linksym(s)
if len(ls.R) > 0 {
Fatal("cannot rosymdup %s with relocations", ls.Name)
}
ls.Name = fmt.Sprintf("gclocals·%x", md5.Sum(ls.P))
ls.Dupok = 1
}
func emitptrargsmap() {
sym := Lookup(fmt.Sprintf("%s.args_stackmap", Curfn.Nname.Sym.Name))
nptr := int(Curfn.Type.Argwid / int64(Widthptr))
bv := bvalloc(int32(nptr) * 2)
nbitmap := 1
if Curfn.Type.Outtuple > 0 {
nbitmap = 2
}
off := duint32(sym, 0, uint32(nbitmap))
off = duint32(sym, off, uint32(bv.n))
var xoffset int64
if Curfn.Type.Thistuple > 0 {
xoffset = 0
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss The bitmaps were 2 bits per pointer because we needed to distinguish scalar, pointer, multiword, and we used the leftover value to distinguish uninitialized from scalar, even though the garbage collector (GC) didn't care. Now that there are no multiword structures from the GC's point of view, cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not. The GC assumes the same layout for stack frames and for the maps describing the global data and bss sections, so change them all in one CL. The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since the 2-bit representation lives (at least for now) in some of the reflect data. Because these stack frame bitmaps are stored directly in the rodata in the binary, this CL reduces the size of the 6g binary by about 1.1%. Performance change is basically a wash, but using less memory, and smaller binaries, and enables other bitmap reductions. name old mean new mean delta BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005) BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001) BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141) BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001) BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095) BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008) BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014) BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364) BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010) BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368) BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484) BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543) BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000) BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023) BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126) BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975) BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153) BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597) BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804) BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881) BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561) BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000) BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000) BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000) BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000) BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019) BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000) BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025) BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000) BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000) BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305) BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000) BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465) BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075) BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337) BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291) BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507) BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313) BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312) BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000) BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007) BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670) BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828) BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392) BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813) BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000) BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000) BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000) BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985) BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320) BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799) BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667) BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001) BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000) BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011) BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185) BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001) BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000) BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000) BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000) BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979) BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777) BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771) BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004) BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004) BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000) BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081) BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027) BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022) BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064) BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001) BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007) BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143) BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278) BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252) BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003) BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581) BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002) BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879) BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257) BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678) BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000) BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000) BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000) BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000) BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000) BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000) BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767) BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347) BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793) Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9 Reviewed-on: https://go-review.googlesource.com/9406 Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 22:45:57 -04:00
onebitwalktype1(getthisx(Curfn.Type), &xoffset, bv)
}
if Curfn.Type.Intuple > 0 {
xoffset = 0
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss The bitmaps were 2 bits per pointer because we needed to distinguish scalar, pointer, multiword, and we used the leftover value to distinguish uninitialized from scalar, even though the garbage collector (GC) didn't care. Now that there are no multiword structures from the GC's point of view, cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not. The GC assumes the same layout for stack frames and for the maps describing the global data and bss sections, so change them all in one CL. The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since the 2-bit representation lives (at least for now) in some of the reflect data. Because these stack frame bitmaps are stored directly in the rodata in the binary, this CL reduces the size of the 6g binary by about 1.1%. Performance change is basically a wash, but using less memory, and smaller binaries, and enables other bitmap reductions. name old mean new mean delta BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005) BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001) BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141) BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001) BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095) BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008) BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014) BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364) BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010) BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368) BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484) BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543) BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000) BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023) BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126) BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975) BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153) BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597) BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804) BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881) BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561) BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000) BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000) BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000) BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000) BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019) BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000) BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025) BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000) BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000) BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305) BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000) BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465) BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075) BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337) BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291) BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507) BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313) BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312) BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000) BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007) BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670) BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828) BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392) BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813) BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000) BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000) BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000) BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985) BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320) BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799) BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667) BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001) BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000) BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011) BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185) BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001) BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000) BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000) BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000) BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979) BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777) BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771) BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004) BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004) BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000) BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081) BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027) BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022) BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064) BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001) BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007) BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143) BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278) BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252) BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003) BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581) BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002) BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879) BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257) BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678) BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000) BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000) BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000) BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000) BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000) BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000) BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767) BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347) BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793) Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9 Reviewed-on: https://go-review.googlesource.com/9406 Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 22:45:57 -04:00
onebitwalktype1(getinargx(Curfn.Type), &xoffset, bv)
}
for j := 0; int32(j) < bv.n; j += 32 {
off = duint32(sym, off, bv.b[j/32])
}
if Curfn.Type.Outtuple > 0 {
xoffset = 0
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss The bitmaps were 2 bits per pointer because we needed to distinguish scalar, pointer, multiword, and we used the leftover value to distinguish uninitialized from scalar, even though the garbage collector (GC) didn't care. Now that there are no multiword structures from the GC's point of view, cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not. The GC assumes the same layout for stack frames and for the maps describing the global data and bss sections, so change them all in one CL. The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since the 2-bit representation lives (at least for now) in some of the reflect data. Because these stack frame bitmaps are stored directly in the rodata in the binary, this CL reduces the size of the 6g binary by about 1.1%. Performance change is basically a wash, but using less memory, and smaller binaries, and enables other bitmap reductions. name old mean new mean delta BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005) BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001) BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141) BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001) BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095) BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008) BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014) BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364) BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010) BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368) BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484) BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543) BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000) BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023) BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126) BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975) BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153) BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597) BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804) BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881) BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561) BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000) BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000) BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000) BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000) BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019) BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000) BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025) BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000) BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000) BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305) BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000) BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465) BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075) BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337) BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291) BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507) BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313) BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312) BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000) BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007) BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670) BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828) BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392) BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813) BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000) BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000) BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000) BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985) BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320) BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799) BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667) BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001) BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000) BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011) BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185) BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001) BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000) BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000) BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000) BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979) BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777) BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771) BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004) BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004) BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000) BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081) BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027) BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022) BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064) BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001) BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007) BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143) BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278) BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252) BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003) BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581) BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002) BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879) BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257) BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678) BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000) BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000) BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000) BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000) BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000) BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000) BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767) BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347) BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793) Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9 Reviewed-on: https://go-review.googlesource.com/9406 Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 22:45:57 -04:00
onebitwalktype1(getoutargx(Curfn.Type), &xoffset, bv)
for j := 0; int32(j) < bv.n; j += 32 {
off = duint32(sym, off, bv.b[j/32])
}
}
ggloblsym(sym, int32(off), obj.RODATA|obj.LOCAL)
}
// Sort the list of stack variables. Autos after anything else,
// within autos, unused after used, within used, things with
// pointers first, zeroed things first, and then decreasing size.
// Because autos are laid out in decreasing addresses
// on the stack, pointers first, zeroed things first and decreasing size
// really means, in memory, things with pointers needing zeroing at
// the top of the stack and increasing in size.
// Non-autos sort on offset.
func cmpstackvar(a *Node, b *Node) int {
if a.Class != b.Class {
if a.Class == PAUTO {
return +1
}
return -1
}
if a.Class != PAUTO {
if a.Xoffset < b.Xoffset {
return -1
}
if a.Xoffset > b.Xoffset {
return +1
}
return 0
}
if a.Used != b.Used {
return obj.Bool2int(b.Used) - obj.Bool2int(a.Used)
}
ap := obj.Bool2int(haspointers(a.Type))
bp := obj.Bool2int(haspointers(b.Type))
if ap != bp {
return bp - ap
}
ap = obj.Bool2int(a.Name.Needzero)
bp = obj.Bool2int(b.Name.Needzero)
if ap != bp {
return bp - ap
}
if a.Type.Width < b.Type.Width {
return +1
}
if a.Type.Width > b.Type.Width {
return -1
}
return stringsCompare(a.Sym.Name, b.Sym.Name)
}
// stkdelta records the stack offset delta for a node
// during the compaction of the stack frame to remove
// unused stack slots.
var stkdelta = map[*Node]int64{}
// TODO(lvd) find out where the PAUTO/OLITERAL nodes come from.
func allocauto(ptxt *obj.Prog) {
Stksize = 0
stkptrsize = 0
if Curfn.Func.Dcl == nil {
return
}
// Mark the PAUTO's unused.
for ll := Curfn.Func.Dcl; ll != nil; ll = ll.Next {
if ll.N.Class == PAUTO {
ll.N.Used = false
}
}
markautoused(ptxt)
listsort(&Curfn.Func.Dcl, cmpstackvar)
// Unused autos are at the end, chop 'em off.
ll := Curfn.Func.Dcl
n := ll.N
if n.Class == PAUTO && n.Op == ONAME && !n.Used {
// No locals used at all
Curfn.Func.Dcl = nil
fixautoused(ptxt)
return
}
for ll := Curfn.Func.Dcl; ll.Next != nil; ll = ll.Next {
n = ll.Next.N
if n.Class == PAUTO && n.Op == ONAME && !n.Used {
ll.Next = nil
Curfn.Func.Dcl.End = ll
break
}
}
// Reassign stack offsets of the locals that are still there.
var w int64
for ll := Curfn.Func.Dcl; ll != nil; ll = ll.Next {
n = ll.N
if n.Class != PAUTO || n.Op != ONAME {
continue
}
dowidth(n.Type)
w = n.Type.Width
if w >= Thearch.MAXWIDTH || w < 0 {
Fatal("bad width")
}
Stksize += w
Stksize = Rnd(Stksize, int64(n.Type.Align))
if haspointers(n.Type) {
stkptrsize = Stksize
}
if Thearch.Thechar == '5' || Thearch.Thechar == '7' || Thearch.Thechar == '9' {
Stksize = Rnd(Stksize, int64(Widthptr))
}
if Stksize >= 1<<31 {
setlineno(Curfn)
Yyerror("stack frame too large (>2GB)")
}
stkdelta[n] = -Stksize - n.Xoffset
}
Stksize = Rnd(Stksize, int64(Widthreg))
stkptrsize = Rnd(stkptrsize, int64(Widthreg))
fixautoused(ptxt)
// The debug information needs accurate offsets on the symbols.
for ll := Curfn.Func.Dcl; ll != nil; ll = ll.Next {
if ll.N.Class != PAUTO || ll.N.Op != ONAME {
continue
}
ll.N.Xoffset += stkdelta[ll.N]
delete(stkdelta, ll.N)
}
}
func Cgen_checknil(n *Node) {
if Disable_checknil != 0 {
return
}
// Ideally we wouldn't see any integer types here, but we do.
if n.Type == nil || (!Isptr[n.Type.Etype] && !Isint[n.Type.Etype] && n.Type.Etype != TUNSAFEPTR) {
Dump("checknil", n)
Fatal("bad checknil")
}
if ((Thearch.Thechar == '5' || Thearch.Thechar == '7' || Thearch.Thechar == '9') && n.Op != OREGISTER) || !n.Addable || n.Op == OLITERAL {
var reg Node
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
Regalloc(&reg, Types[Tptr], n)
Cgen(n, &reg)
Thearch.Gins(obj.ACHECKNIL, &reg, nil)
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
Regfree(&reg)
return
}
Thearch.Gins(obj.ACHECKNIL, n, nil)
}
func compile(fn *Node) {
if Newproc == nil {
Newproc = Sysfunc("newproc")
Deferproc = Sysfunc("deferproc")
Deferreturn = Sysfunc("deferreturn")
Panicindex = Sysfunc("panicindex")
panicslice = Sysfunc("panicslice")
throwreturn = Sysfunc("throwreturn")
}
lno := setlineno(fn)
Curfn = fn
dowidth(Curfn.Type)
var oldstksize int64
var nod1 Node
var ptxt *obj.Prog
var pl *obj.Plist
var p *obj.Prog
var n *Node
var nam *Node
var gcargs *Sym
var gclocals *Sym
if fn.Nbody == nil {
if pure_go != 0 || strings.HasPrefix(fn.Nname.Sym.Name, "init.") {
Yyerror("missing function body for %q", fn.Nname.Sym.Name)
goto ret
}
if Debug['A'] != 0 {
goto ret
}
emitptrargsmap()
goto ret
}
saveerrors()
// set up domain for labels
clearlabels()
if Curfn.Type.Outnamed != 0 {
// add clearing of the output parameters
var save Iter
t := Structfirst(&save, Getoutarg(Curfn.Type))
for t != nil {
if t.Nname != nil {
n = Nod(OAS, t.Nname, nil)
typecheck(&n, Etop)
Curfn.Nbody = concat(list1(n), Curfn.Nbody)
}
t = structnext(&save)
}
}
order(Curfn)
if nerrors != 0 {
goto ret
}
Hasdefer = 0
walk(Curfn)
if nerrors != 0 {
goto ret
}
if flag_race != 0 {
racewalk(Curfn)
}
if nerrors != 0 {
goto ret
}
continpc = nil
breakpc = nil
pl = newplist()
pl.Name = Linksym(Curfn.Nname.Sym)
setlineno(Curfn)
Nodconst(&nod1, Types[TINT32], 0)
nam = Curfn.Nname
if isblank(nam) {
nam = nil
}
ptxt = Thearch.Gins(obj.ATEXT, nam, &nod1)
ptxt.From3 = new(obj.Addr)
if fn.Func.Dupok {
ptxt.From3.Offset |= obj.DUPOK
}
if fn.Func.Wrapper {
ptxt.From3.Offset |= obj.WRAPPER
}
if fn.Func.Needctxt {
ptxt.From3.Offset |= obj.NEEDCTXT
}
if fn.Func.Nosplit {
ptxt.From3.Offset |= obj.NOSPLIT
}
// Clumsy but important.
// See test/recover.go for test cases and src/reflect/value.go
// for the actual functions being considered.
if myimportpath != "" && myimportpath == "reflect" {
if Curfn.Nname.Sym.Name == "callReflect" || Curfn.Nname.Sym.Name == "callMethod" {
ptxt.From3.Offset |= obj.WRAPPER
}
}
Afunclit(&ptxt.From, Curfn.Nname)
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
ginit()
gcargs = makefuncdatasym("gcargs·%d", obj.FUNCDATA_ArgsPointerMaps)
gclocals = makefuncdatasym("gclocals·%d", obj.FUNCDATA_LocalsPointerMaps)
for t := Curfn.Paramfld; t != nil; t = t.Down {
gtrack(tracksym(t.Type))
}
for l := fn.Func.Dcl; l != nil; l = l.Next {
n = l.N
if n.Op != ONAME { // might be OTYPE or OLITERAL
continue
}
switch n.Class {
case PAUTO, PPARAM, PPARAMOUT:
Nodconst(&nod1, Types[TUINTPTR], l.N.Type.Width)
p = Thearch.Gins(obj.ATYPE, l.N, &nod1)
p.From.Gotype = Linksym(ngotype(l.N))
}
}
Genlist(Curfn.Func.Enter)
Genlist(Curfn.Nbody)
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
gclean()
checklabels()
if nerrors != 0 {
goto ret
}
if Curfn.Func.Endlineno != 0 {
lineno = Curfn.Func.Endlineno
}
if Curfn.Type.Outtuple != 0 {
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
Ginscall(throwreturn, 0)
}
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
ginit()
// TODO: Determine when the final cgen_ret can be omitted. Perhaps always?
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
cgen_ret(nil)
if Hasdefer != 0 {
// deferreturn pretends to have one uintptr argument.
// Reserve space for it so stack scanner is happy.
if Maxarg < int64(Widthptr) {
Maxarg = int64(Widthptr)
}
}
cmd/internal/gc: move cgen, regalloc, et al to portable code This CL moves the bulk of the code that has been copy-and-pasted since the initial 386 port back into a shared place, cutting 5 copies to 1. The motivation here is not cleanup per se but instead to reduce the cost of introducing changes in shared concepts like regalloc or general expression evaluation. For example, a change after this one will implement x.(*T) without a call into the runtime. This CL makes that followup work 5x easier. The single copy still has more special cases for architecture details than I'd like, but having them called out explicitly like this at least opens the door to generalizing the conditions and smoothing out the distinctions in the future. This is a LARGE CL. I started by trying to pull in one function at a time in a sequence of CLs and it became clear that everything was so interrelated that it had to be moved as a whole. Apologies for the size. It is not clear how many more releases this code will matter for; eventually it will be replaced by Keith's SSA work. But as noted above, the deduplication was necessary to reduce the cost of working on the current code while we have it. Passes tests on amd64, 386, arm, and ppc64le. Can build arm64 binaries but not tested there. Being able to build binaries means it is probably very close. Change-Id: I735977f04c0614f80215fb12966dfe9bbd1f5861 Reviewed-on: https://go-review.googlesource.com/7853 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2015-03-18 17:26:36 -04:00
gclean()
if nerrors != 0 {
goto ret
}
Pc.As = obj.ARET // overwrite AEND
Pc.Lineno = lineno
fixjmp(ptxt)
if Debug['N'] == 0 || Debug['R'] != 0 || Debug['P'] != 0 {
regopt(ptxt)
nilopt(ptxt)
}
Thearch.Expandchecks(ptxt)
oldstksize = Stksize
allocauto(ptxt)
if false {
fmt.Printf("allocauto: %d to %d\n", oldstksize, int64(Stksize))
}
setlineno(Curfn)
if int64(Stksize)+Maxarg > 1<<31 {
Yyerror("stack frame too large (>2GB)")
goto ret
}
// Emit garbage collection symbols.
liveness(Curfn, ptxt, gcargs, gclocals)
gcsymdup(gcargs)
gcsymdup(gclocals)
Thearch.Defframe(ptxt)
if Debug['f'] != 0 {
frame(0)
}
// Remove leftover instrumentation from the instruction stream.
removevardef(ptxt)
ret:
lineno = lno
}