mirror of
https://github.com/golang/go.git
synced 2025-12-08 06:10:04 +00:00
This CL implements the compiler support for calling the buffered write barrier added by the previous CL. Since the buffered write barrier is only implemented on amd64 right now, this still supports the old, eager write barrier as well. There's little overhead to supporting both and this way a few tests in test/fixedbugs that expect to have liveness maps at write barrier calls can easily opt-in to the old, eager barrier. This significantly improves the performance of the write barrier: name old time/op new time/op delta WriteBarrier-12 73.5ns ±20% 19.2ns ±27% -73.90% (p=0.000 n=19+18) It also reduces the size of binaries because the write barrier call is more compact: name old object-bytes new object-bytes delta Template 398k ± 0% 393k ± 0% -1.14% (p=0.008 n=5+5) Unicode 208k ± 0% 206k ± 0% -1.00% (p=0.008 n=5+5) GoTypes 1.18M ± 0% 1.15M ± 0% -2.00% (p=0.008 n=5+5) Compiler 4.05M ± 0% 3.88M ± 0% -4.26% (p=0.008 n=5+5) SSA 8.25M ± 0% 8.11M ± 0% -1.59% (p=0.008 n=5+5) Flate 228k ± 0% 224k ± 0% -1.83% (p=0.008 n=5+5) GoParser 295k ± 0% 284k ± 0% -3.62% (p=0.008 n=5+5) Reflect 1.00M ± 0% 0.99M ± 0% -0.70% (p=0.008 n=5+5) Tar 339k ± 0% 333k ± 0% -1.67% (p=0.008 n=5+5) XML 404k ± 0% 395k ± 0% -2.10% (p=0.008 n=5+5) [Geo mean] 704k 690k -2.00% name old exe-bytes new exe-bytes delta HelloSize 1.05M ± 0% 1.04M ± 0% -1.55% (p=0.008 n=5+5) https://perf.golang.org/search?q=upload:20171027.1 (Amusingly, this also reduces compiler allocations by 0.75%, which, combined with the better write barrier, speeds up the compiler overall by 2.10%. See the perf link.) It slightly improves the performance of most of the go1 benchmarks and improves the performance of the x/benchmarks: name old time/op new time/op delta BinaryTree17-12 2.40s ± 1% 2.47s ± 1% +2.69% (p=0.000 n=19+19) Fannkuch11-12 2.95s ± 0% 2.95s ± 0% +0.21% (p=0.000 n=20+19) FmtFprintfEmpty-12 41.8ns ± 4% 41.4ns ± 2% -1.03% (p=0.014 n=20+20) FmtFprintfString-12 68.7ns ± 2% 67.5ns ± 1% -1.75% (p=0.000 n=20+17) FmtFprintfInt-12 79.0ns ± 3% 77.1ns ± 1% -2.40% (p=0.000 n=19+17) FmtFprintfIntInt-12 127ns ± 1% 123ns ± 3% -3.42% (p=0.000 n=20+20) FmtFprintfPrefixedInt-12 152ns ± 1% 150ns ± 1% -1.02% (p=0.000 n=18+17) FmtFprintfFloat-12 211ns ± 1% 209ns ± 0% -0.99% (p=0.000 n=20+16) FmtManyArgs-12 500ns ± 0% 496ns ± 0% -0.73% (p=0.000 n=17+20) GobDecode-12 6.44ms ± 1% 6.53ms ± 0% +1.28% (p=0.000 n=20+19) GobEncode-12 5.46ms ± 0% 5.46ms ± 1% ~ (p=0.550 n=19+20) Gzip-12 220ms ± 1% 216ms ± 0% -1.75% (p=0.000 n=19+19) Gunzip-12 38.8ms ± 0% 38.6ms ± 0% -0.30% (p=0.000 n=18+19) HTTPClientServer-12 79.0µs ± 1% 78.2µs ± 1% -1.01% (p=0.000 n=20+20) JSONEncode-12 11.9ms ± 0% 11.9ms ± 0% -0.29% (p=0.000 n=20+19) JSONDecode-12 52.6ms ± 0% 52.2ms ± 0% -0.68% (p=0.000 n=19+20) Mandelbrot200-12 3.69ms ± 0% 3.68ms ± 0% -0.36% (p=0.000 n=20+20) GoParse-12 3.13ms ± 1% 3.18ms ± 1% +1.67% (p=0.000 n=19+20) RegexpMatchEasy0_32-12 73.2ns ± 1% 72.3ns ± 1% -1.19% (p=0.000 n=19+18) RegexpMatchEasy0_1K-12 241ns ± 0% 239ns ± 0% -0.83% (p=0.000 n=17+16) RegexpMatchEasy1_32-12 68.6ns ± 1% 69.0ns ± 1% +0.47% (p=0.015 n=18+16) RegexpMatchEasy1_1K-12 364ns ± 0% 361ns ± 0% -0.67% (p=0.000 n=16+17) RegexpMatchMedium_32-12 104ns ± 1% 103ns ± 1% -0.79% (p=0.001 n=20+15) RegexpMatchMedium_1K-12 33.8µs ± 3% 34.0µs ± 2% ~ (p=0.267 n=20+19) RegexpMatchHard_32-12 1.64µs ± 1% 1.62µs ± 2% -1.25% (p=0.000 n=19+18) RegexpMatchHard_1K-12 49.2µs ± 0% 48.7µs ± 1% -0.93% (p=0.000 n=19+18) Revcomp-12 391ms ± 5% 396ms ± 7% ~ (p=0.154 n=19+19) Template-12 63.1ms ± 0% 59.5ms ± 0% -5.76% (p=0.000 n=18+19) TimeParse-12 307ns ± 0% 306ns ± 0% -0.39% (p=0.000 n=19+17) TimeFormat-12 325ns ± 0% 323ns ± 0% -0.50% (p=0.000 n=19+19) [Geo mean] 47.3µs 46.9µs -0.67% https://perf.golang.org/search?q=upload:20171026.1 name old time/op new time/op delta Garbage/benchmem-MB=64-12 2.25ms ± 1% 2.20ms ± 1% -2.31% (p=0.000 n=18+18) HTTP-12 12.6µs ± 0% 12.6µs ± 0% -0.72% (p=0.000 n=18+17) JSON-12 11.0ms ± 0% 11.0ms ± 1% -0.68% (p=0.000 n=17+19) https://perf.golang.org/search?q=upload:20171026.2 Updates #14951. Updates #22460. Change-Id: Id4c0932890a1d41020071bec73b8522b1367d3e7 Reviewed-on: https://go-review.googlesource.com/73712 Run-TryBot: Austin Clements <austin@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
298 lines
6.1 KiB
Go
298 lines
6.1 KiB
Go
// Copyright 2009 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/compile/internal/ssa"
|
|
"cmd/compile/internal/types"
|
|
"cmd/internal/obj"
|
|
"cmd/internal/src"
|
|
"sync"
|
|
)
|
|
|
|
const (
|
|
BADWIDTH = types.BADWIDTH
|
|
maxStackVarSize = 10 * 1024 * 1024
|
|
)
|
|
|
|
// isRuntimePkg reports whether p is package runtime.
|
|
func isRuntimePkg(p *types.Pkg) bool {
|
|
if compiling_runtime && p == localpkg {
|
|
return true
|
|
}
|
|
return p.Path == "runtime"
|
|
}
|
|
|
|
// The Class of a variable/function describes the "storage class"
|
|
// of a variable or function. During parsing, storage classes are
|
|
// called declaration contexts.
|
|
type Class uint8
|
|
|
|
//go:generate stringer -type=Class
|
|
const (
|
|
Pxxx Class = iota // no class; used during ssa conversion to indicate pseudo-variables
|
|
PEXTERN // global variable
|
|
PAUTO // local variables
|
|
PAUTOHEAP // local variable or parameter moved to heap
|
|
PPARAM // input arguments
|
|
PPARAMOUT // output results
|
|
PFUNC // global function
|
|
|
|
PDISCARD // discard during parse of duplicate import
|
|
// Careful: Class is stored in three bits in Node.flags.
|
|
// Adding a new Class will overflow that.
|
|
)
|
|
|
|
func init() {
|
|
if PDISCARD != 7 {
|
|
panic("PDISCARD changed; does all Class values still fit in three bits?")
|
|
}
|
|
}
|
|
|
|
// note this is the runtime representation
|
|
// of the compilers arrays.
|
|
//
|
|
// typedef struct
|
|
// { // must not move anything
|
|
// uchar array[8]; // pointer to data
|
|
// uchar nel[4]; // number of elements
|
|
// uchar cap[4]; // allocated number of elements
|
|
// } Array;
|
|
var array_array int // runtime offsetof(Array,array) - same for String
|
|
|
|
var array_nel int // runtime offsetof(Array,nel) - same for String
|
|
|
|
var array_cap int // runtime offsetof(Array,cap)
|
|
|
|
var sizeof_Array int // runtime sizeof(Array)
|
|
|
|
// note this is the runtime representation
|
|
// of the compilers strings.
|
|
//
|
|
// typedef struct
|
|
// { // must not move anything
|
|
// uchar array[8]; // pointer to data
|
|
// uchar nel[4]; // number of elements
|
|
// } String;
|
|
var sizeof_String int // runtime sizeof(String)
|
|
|
|
var pragcgobuf string
|
|
|
|
var outfile string
|
|
var linkobj string
|
|
var dolinkobj bool
|
|
|
|
// nerrors is the number of compiler errors reported
|
|
// since the last call to saveerrors.
|
|
var nerrors int
|
|
|
|
// nsavederrors is the total number of compiler errors
|
|
// reported before the last call to saveerrors.
|
|
var nsavederrors int
|
|
|
|
var nsyntaxerrors int
|
|
|
|
var decldepth int32
|
|
|
|
var safemode bool
|
|
|
|
var nolocalimports bool
|
|
|
|
var Debug [256]int
|
|
|
|
var debugstr string
|
|
|
|
var Debug_checknil int
|
|
var Debug_typeassert int
|
|
|
|
var localpkg *types.Pkg // package being compiled
|
|
|
|
var inimport bool // set during import
|
|
|
|
var itabpkg *types.Pkg // fake pkg for itab entries
|
|
|
|
var itablinkpkg *types.Pkg // fake package for runtime itab entries
|
|
|
|
var Runtimepkg *types.Pkg // fake package runtime
|
|
|
|
var racepkg *types.Pkg // package runtime/race
|
|
|
|
var msanpkg *types.Pkg // package runtime/msan
|
|
|
|
var unsafepkg *types.Pkg // package unsafe
|
|
|
|
var trackpkg *types.Pkg // fake package for field tracking
|
|
|
|
var mappkg *types.Pkg // fake package for map zero value
|
|
var zerosize int64
|
|
|
|
var myimportpath string
|
|
|
|
var localimport string
|
|
|
|
var asmhdr string
|
|
|
|
var simtype [NTYPE]types.EType
|
|
|
|
var (
|
|
isforw [NTYPE]bool
|
|
isInt [NTYPE]bool
|
|
isFloat [NTYPE]bool
|
|
isComplex [NTYPE]bool
|
|
issimple [NTYPE]bool
|
|
)
|
|
|
|
var (
|
|
okforeq [NTYPE]bool
|
|
okforadd [NTYPE]bool
|
|
okforand [NTYPE]bool
|
|
okfornone [NTYPE]bool
|
|
okforcmp [NTYPE]bool
|
|
okforbool [NTYPE]bool
|
|
okforcap [NTYPE]bool
|
|
okforlen [NTYPE]bool
|
|
okforarith [NTYPE]bool
|
|
okforconst [NTYPE]bool
|
|
)
|
|
|
|
var (
|
|
okfor [OEND][]bool
|
|
iscmp [OEND]bool
|
|
)
|
|
|
|
var minintval [NTYPE]*Mpint
|
|
|
|
var maxintval [NTYPE]*Mpint
|
|
|
|
var minfltval [NTYPE]*Mpflt
|
|
|
|
var maxfltval [NTYPE]*Mpflt
|
|
|
|
var xtop []*Node
|
|
|
|
var exportlist []*Node
|
|
|
|
var importlist []*Node // imported functions and methods with inlinable bodies
|
|
|
|
var (
|
|
funcsymsmu sync.Mutex // protects funcsyms and associated package lookups (see func funcsym)
|
|
funcsyms []*types.Sym
|
|
)
|
|
|
|
var dclcontext Class // PEXTERN/PAUTO
|
|
|
|
var Curfn *Node
|
|
|
|
var Widthptr int
|
|
|
|
var Widthreg int
|
|
|
|
var nblank *Node
|
|
|
|
var typecheckok bool
|
|
|
|
var compiling_runtime bool
|
|
|
|
// Compiling the standard library
|
|
var compiling_std bool
|
|
|
|
var compiling_wrappers bool
|
|
|
|
var use_writebarrier bool
|
|
|
|
var pure_go bool
|
|
|
|
var flag_installsuffix string
|
|
|
|
var flag_race bool
|
|
|
|
var flag_msan bool
|
|
|
|
var flagDWARF bool
|
|
|
|
// Whether we are adding any sort of code instrumentation, such as
|
|
// when the race detector is enabled.
|
|
var instrumenting bool
|
|
|
|
// Whether we are tracking lexical scopes for DWARF.
|
|
var trackScopes bool
|
|
|
|
var debuglive int
|
|
|
|
var Ctxt *obj.Link
|
|
|
|
var writearchive bool
|
|
|
|
var Nacl bool
|
|
|
|
var nodfp *Node
|
|
|
|
var disable_checknil int
|
|
|
|
var autogeneratedPos src.XPos
|
|
|
|
// interface to back end
|
|
|
|
type Arch struct {
|
|
LinkArch *obj.LinkArch
|
|
|
|
REGSP int
|
|
MAXWIDTH int64
|
|
Use387 bool // should 386 backend use 387 FP instructions instead of sse2.
|
|
|
|
PadFrame func(int64) int64
|
|
ZeroRange func(*Progs, *obj.Prog, int64, int64, *uint32) *obj.Prog
|
|
Ginsnop func(*Progs)
|
|
|
|
// SSAMarkMoves marks any MOVXconst ops that need to avoid clobbering flags.
|
|
SSAMarkMoves func(*SSAGenState, *ssa.Block)
|
|
|
|
// SSAGenValue emits Prog(s) for the Value.
|
|
SSAGenValue func(*SSAGenState, *ssa.Value)
|
|
|
|
// SSAGenBlock emits end-of-block Progs. SSAGenValue should be called
|
|
// for all values in the block before SSAGenBlock.
|
|
SSAGenBlock func(s *SSAGenState, b, next *ssa.Block)
|
|
|
|
// ZeroAuto emits code to zero the given auto stack variable.
|
|
// ZeroAuto must not use any non-temporary registers.
|
|
// ZeroAuto will only be called for variables which contain a pointer.
|
|
ZeroAuto func(*Progs, *Node)
|
|
}
|
|
|
|
var thearch Arch
|
|
|
|
var (
|
|
staticbytes,
|
|
zerobase *Node
|
|
|
|
Newproc,
|
|
Deferproc,
|
|
Deferreturn,
|
|
Duffcopy,
|
|
Duffzero,
|
|
panicindex,
|
|
panicslice,
|
|
panicdivide,
|
|
growslice,
|
|
panicdottypeE,
|
|
panicdottypeI,
|
|
panicnildottype,
|
|
assertE2I,
|
|
assertE2I2,
|
|
assertI2I,
|
|
assertI2I2,
|
|
goschedguarded,
|
|
writeBarrier,
|
|
writebarrierptr,
|
|
gcWriteBarrier,
|
|
typedmemmove,
|
|
typedmemclr,
|
|
Udiv *obj.LSym
|
|
|
|
// GO386=387
|
|
ControlWord64trunc,
|
|
ControlWord32 *obj.LSym
|
|
)
|