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

478 lines
11 KiB
Go
Raw Normal View History

// 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/internal/bio"
"cmd/internal/obj"
)
const (
UINF = 100
BADWIDTH = -1000000000
MaxStackVarSize = 10 * 1024 * 1024
)
type Pkg struct {
Name string // package name, e.g. "sys"
Path string // string literal used in import statement, e.g. "runtime/internal/sys"
Pathsym *Sym
Prefix string // escaped path for use in symbol table
Imported bool // export data of this package was parsed
Exported bool // import line written in export data
Direct bool // imported directly
Safe bool // whether the package is marked as safe
Syms map[string]*Sym
}
// Sym represents an object name. Most commonly, this is a Go identifier naming
// an object declared within a package, but Syms are also used to name internal
// synthesized objects.
//
// As a special exception, field and method names that are exported use the Sym
// associated with localpkg instead of the package that declared them. This
// allows using Sym pointer equality to test for Go identifier uniqueness when
// handling selector expressions.
type Sym struct {
Flags SymFlags
Link *Sym
Importdef *Pkg // where imported definition was found
Linkname string // link name
// saved and restored by dcopy
Pkg *Pkg
Name string // variable name
Def *Node // definition: ONAME OTYPE OPACK or OLITERAL
Block int32 // blocknumber to catch redeclaration
Lastlineno int32 // last declaration for diagnostic
Label *Label // corresponding label (ephemeral)
Origpkg *Pkg // original package for . import
Lsym *obj.LSym
Fsym *Sym // funcsym
}
type Label struct {
Sym *Sym
Def *Node
Use []*Node
// for use during gen
Gotopc *obj.Prog // pointer to unresolved gotos
Labelpc *obj.Prog // pointer to code
Breakpc *obj.Prog // pointer to code
Continpc *obj.Prog // pointer to code
Used bool
}
type SymFlags uint8
const (
SymExport SymFlags = 1 << iota // to be exported
SymPackage
SymExported // already written out by export
SymUniq
SymSiggen
SymAsm
SymAlgGen
)
// 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
const (
Pxxx Class = iota
PEXTERN // global variable
PAUTO // local variables
PPARAM // input arguments
PPARAMOUT // output results
PPARAMREF // closure variable reference
PFUNC // global function
PDISCARD // discard during parse of duplicate import
PHEAP = 1 << 7 // an extra bit to identify an escaped variable
)
// 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 infile string
var outfile string
var bout *bio.Writer
var nerrors int
var nsavederrors int
var nsyntaxerrors int
var decldepth int32
var safemode int
var nolocalimports int
var Debug [256]int
var debugstr string
var Debug_checknil int
var Debug_typeassert int
var localpkg *Pkg // package being compiled
var importpkg *Pkg // package being imported
cmd/compile: optimize remaining convT2I calls See #14874 Updates #6853 This change adds a compiler optimization for non pointer shaped convT2I. Since itab symbols are now emitted by the compiler, the itab address can be passed directly to convT2I instead of passing the iface type and a cache pointer argument. Compilebench results for the 5-commits series ending here: name old time/op new time/op delta Template 336ms ± 4% 344ms ± 4% +2.61% (p=0.027 n=9+8) Unicode 165ms ± 6% 173ms ± 7% +5.11% (p=0.014 n=9+9) GoTypes 1.09s ± 1% 1.06s ± 2% -3.29% (p=0.000 n=9+9) Compiler 5.09s ±10% 4.75s ±10% -6.64% (p=0.011 n=10+10) MakeBash 31.1s ± 5% 30.3s ± 3% ~ (p=0.089 n=10+10) name old text-bytes new text-bytes delta HelloSize 558k ± 0% 558k ± 0% +0.02% (p=0.000 n=10+10) CmdGoSize 6.24M ± 0% 6.11M ± 0% -2.11% (p=0.000 n=10+10) name old data-bytes new data-bytes delta HelloSize 3.66k ± 0% 3.74k ± 0% +2.41% (p=0.000 n=10+10) CmdGoSize 134k ± 0% 162k ± 0% +20.76% (p=0.000 n=10+10) name old bss-bytes new bss-bytes delta HelloSize 126k ± 0% 126k ± 0% ~ (all samples are equal) CmdGoSize 149k ± 0% 146k ± 0% -2.17% (p=0.000 n=10+10) name old exe-bytes new exe-bytes delta HelloSize 924k ± 0% 924k ± 0% +0.05% (p=0.000 n=10+10) CmdGoSize 9.77M ± 0% 9.62M ± 0% -1.47% (p=0.000 n=10+10) Change-Id: Ib230ddc04988824035c32287ae544a965fedd344 Reviewed-on: https://go-review.googlesource.com/20902 Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: David Crawshaw <crawshaw@golang.org> Run-TryBot: Michel Lespinasse <walken@google.com>
2016-03-18 17:21:33 -07:00
var itabpkg *Pkg // fake pkg for itab entries
var itablinkpkg *Pkg // fake package for runtime itab entries
var Runtimepkg *Pkg // package runtime
var racepkg *Pkg // package runtime/race
var msanpkg *Pkg // package runtime/msan
var typepkg *Pkg // fake package for runtime type info (headers)
var typelinkpkg *Pkg // fake package for runtime type info (data)
var unsafepkg *Pkg // package unsafe
var trackpkg *Pkg // fake package for field tracking
var Tptr EType // either TPTR32 or TPTR64
var myimportpath string
var localimport string
var asmhdr string
var Simtype [NTYPE]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 funcsyms []*Node
var dclcontext Class // PEXTERN/PAUTO
var incannedimport int
var statuniqgen int // name generator for static temps
var iota_ int32
var lastconst []*Node
var lasttype *Node
var Maxarg int64
var Stksize int64 // stack size for current frame
var stkptrsize int64 // prefix of stack containing pointers
var hasdefer bool // flag that curfn has defer statement
var Curfn *Node
var Widthptr int
var Widthint int
var Widthreg int
var nblank *Node
var Funcdepth int32
var typecheckok bool
var compiling_runtime int
var compiling_wrappers int
var use_writebarrier int
var pure_go int
var flag_installsuffix string
var flag_race int
var flag_msan int
var flag_largemodel int
// Whether we are adding any sort of code instrumentation, such as
// when the race detector is enabled.
var instrumenting bool
var debuglive int
var Ctxt *obj.Link
var writearchive int
var bstdout *bio.Writer
var Nacl bool
var continpc *obj.Prog
var breakpc *obj.Prog
var Pc *obj.Prog
var nodfp *Node
var Disable_checknil int
// interface to back end
const (
// Pseudo-op, like TEXT, GLOBL, TYPE, PCDATA, FUNCDATA.
Pseudo = 1 << 1
// There's nothing to say about the instruction,
// but it's still okay to see.
OK = 1 << 2
// Size of right-side write, or right-side read if no write.
SizeB = 1 << 3
SizeW = 1 << 4
SizeL = 1 << 5
SizeQ = 1 << 6
SizeF = 1 << 7
SizeD = 1 << 8
// Left side (Prog.from): address taken, read, write.
LeftAddr = 1 << 9
LeftRead = 1 << 10
LeftWrite = 1 << 11
// Register in middle (Prog.reg); only ever read. (arm, ppc64)
RegRead = 1 << 12
CanRegRead = 1 << 13
// Right side (Prog.to): address taken, read, write.
RightAddr = 1 << 14
RightRead = 1 << 15
RightWrite = 1 << 16
// Instruction kinds
Move = 1 << 17 // straight move
Conv = 1 << 18 // size conversion
Cjmp = 1 << 19 // conditional jump
Break = 1 << 20 // breaks control flow (no fallthrough)
Call = 1 << 21 // function call
Jump = 1 << 22 // jump
Skip = 1 << 23 // data instruction
// Set, use, or kill of carry bit.
// Kill means we never look at the carry bit after this kind of instruction.
// Originally for understanding ADC, RCR, and so on, but now also
// tracks set, use, and kill of the zero and overflow bits as well.
// TODO rename to {Set,Use,Kill}Flags
SetCarry = 1 << 24
UseCarry = 1 << 25
KillCarry = 1 << 26
// Special cases for register use. (amd64, 386)
ShiftCX = 1 << 27 // possible shift by CX
ImulAXDX = 1 << 28 // possible multiply into DX:AX
// Instruction updates whichever of from/to is type D_OREG. (ppc64)
PostInc = 1 << 29
)
type Arch struct {
LinkArch *obj.LinkArch
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
REGSP int
REGCTXT int
REGCALLX int // BX
REGCALLX2 int // AX
REGRETURN int // AX
REGMIN int
REGMAX int
REGZERO int // architectural zero register, if available
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
FREGMIN int
FREGMAX int
MAXWIDTH int64
ReservedRegs []int
AddIndex func(*Node, int64, *Node) bool // optional
Betypeinit func()
Bgen_float func(*Node, bool, int, *obj.Prog) // optional
Cgen64 func(*Node, *Node) // only on 32-bit systems
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
Cgenindex func(*Node, *Node, bool) *obj.Prog
Cgen_bmul func(Op, *Node, *Node, *Node) bool
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_float func(*Node, *Node) // optional
Cgen_hmul func(*Node, *Node, *Node)
Cgen_shift func(Op, bool, *Node, *Node, *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
Clearfat func(*Node)
Cmp64 func(*Node, *Node, Op, int, *obj.Prog) // only on 32-bit systems
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
Defframe func(*obj.Prog)
Dodiv func(Op, *Node, *Node, *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
Excise func(*Flow)
Expandchecks func(*obj.Prog)
cmd/internal/gc: inline runtime.getg This more closely restores what the old C runtime did. (In C, g was an 'extern register' with the same effective implementation as in this CL.) On a late 2012 MacBookPro10,2, best of 5 old vs best of 5 new: benchmark old ns/op new ns/op delta BenchmarkBinaryTree17 4981312777 4463426605 -10.40% BenchmarkFannkuch11 3046495712 3006819428 -1.30% BenchmarkFmtFprintfEmpty 89.3 79.8 -10.64% BenchmarkFmtFprintfString 284 262 -7.75% BenchmarkFmtFprintfInt 282 262 -7.09% BenchmarkFmtFprintfIntInt 480 448 -6.67% BenchmarkFmtFprintfPrefixedInt 382 358 -6.28% BenchmarkFmtFprintfFloat 529 486 -8.13% BenchmarkFmtManyArgs 1849 1773 -4.11% BenchmarkGobDecode 12835963 11794385 -8.11% BenchmarkGobEncode 10527170 10288422 -2.27% BenchmarkGzip 436109569 438422516 +0.53% BenchmarkGunzip 110121663 109843648 -0.25% BenchmarkHTTPClientServer 81930 85446 +4.29% BenchmarkJSONEncode 24638574 24280603 -1.45% BenchmarkJSONDecode 93022423 85753546 -7.81% BenchmarkMandelbrot200 4703899 4735407 +0.67% BenchmarkGoParse 5319853 5086843 -4.38% BenchmarkRegexpMatchEasy0_32 151 151 +0.00% BenchmarkRegexpMatchEasy0_1K 452 453 +0.22% BenchmarkRegexpMatchEasy1_32 131 132 +0.76% BenchmarkRegexpMatchEasy1_1K 761 722 -5.12% BenchmarkRegexpMatchMedium_32 228 224 -1.75% BenchmarkRegexpMatchMedium_1K 63751 64296 +0.85% BenchmarkRegexpMatchHard_32 3188 3238 +1.57% BenchmarkRegexpMatchHard_1K 95396 96756 +1.43% BenchmarkRevcomp 661587262 687107364 +3.86% BenchmarkTemplate 108312598 104008540 -3.97% BenchmarkTimeParse 453 459 +1.32% BenchmarkTimeFormat 475 441 -7.16% The garbage benchmark from the benchmarks subrepo gets 2.6% faster as well. Change-Id: I320aeda332db81012688b26ffab23f6581c59cfa Reviewed-on: https://go-review.googlesource.com/8460 Reviewed-by: Rick Hudson <rlh@golang.org> Run-TryBot: Rick Hudson <rlh@golang.org> Reviewed-by: Austin Clements <austin@google.com>
2015-04-03 12:23:28 -04:00
Getg func(*Node)
Gins func(obj.As, *Node, *Node) *obj.Prog
// Ginscmp generates code comparing n1 to n2 and jumping away if op is satisfied.
// The returned prog should be Patch'ed with the jump target.
// If op is not satisfied, code falls through to the next emitted instruction.
// Likely is the branch prediction hint: +1 for likely, -1 for unlikely, 0 for no opinion.
//
// Ginscmp must be able to handle all kinds of arguments for n1 and n2,
// not just simple registers, although it can assume that there are no
// function calls needed during the evaluation, and on 32-bit systems
// the values are guaranteed not to be 64-bit values, so no in-memory
// temporaries are necessary.
Ginscmp func(op Op, t *Type, n1, n2 *Node, likely int) *obj.Prog
cmd/internal/gc, cmd/6g: generate boolean values without jumps Use SETcc instructions instead of Jcc to generate boolean values. This generates shorter, jump-free code, which may in turn enable other peephole optimizations. For example, given func f(i, j int) bool { return i == j } Before "".f t=1 size=32 value=0 args=0x18 locals=0x0 0x0000 00000 (x.go:3) TEXT "".f(SB), $0-24 0x0000 00000 (x.go:3) FUNCDATA $0, gclocals·b4c25e9b09fd0cf9bb429dcefe91c353(SB) 0x0000 00000 (x.go:3) FUNCDATA $1, gclocals·33cdeccccebe80329f1fdbee7f5874cb(SB) 0x0000 00000 (x.go:4) MOVQ "".i+8(FP), BX 0x0005 00005 (x.go:4) MOVQ "".j+16(FP), BP 0x000a 00010 (x.go:4) CMPQ BX, BP 0x000d 00013 (x.go:4) JEQ 21 0x000f 00015 (x.go:4) MOVB $0, "".~r2+24(FP) 0x0014 00020 (x.go:4) RET 0x0015 00021 (x.go:4) MOVB $1, "".~r2+24(FP) 0x001a 00026 (x.go:4) JMP 20 After "".f t=1 size=32 value=0 args=0x18 locals=0x0 0x0000 00000 (x.go:3) TEXT "".f(SB), $0-24 0x0000 00000 (x.go:3) FUNCDATA $0, gclocals·b4c25e9b09fd0cf9bb429dcefe91c353(SB) 0x0000 00000 (x.go:3) FUNCDATA $1, gclocals·33cdeccccebe80329f1fdbee7f5874cb(SB) 0x0000 00000 (x.go:4) MOVQ "".i+8(FP), BX 0x0005 00005 (x.go:4) MOVQ "".j+16(FP), BP 0x000a 00010 (x.go:4) CMPQ BX, BP 0x000d 00013 (x.go:4) SETEQ "".~r2+24(FP) 0x0012 00018 (x.go:4) RET regexp benchmarks, best of 12 runs: benchmark old ns/op new ns/op delta BenchmarkNotOnePassShortB 782 733 -6.27% BenchmarkLiteral 180 171 -5.00% BenchmarkNotLiteral 2855 2721 -4.69% BenchmarkMatchHard_32 2672 2557 -4.30% BenchmarkMatchHard_1K 80182 76732 -4.30% BenchmarkMatchEasy1_32M 76440180 73304748 -4.10% BenchmarkMatchEasy1_32K 68798 66350 -3.56% BenchmarkAnchoredLongMatch 482 465 -3.53% BenchmarkMatchEasy1_1M 2373042 2292692 -3.39% BenchmarkReplaceAll 2776 2690 -3.10% BenchmarkNotOnePassShortA 1397 1360 -2.65% BenchmarkMatchClass_InRange 3842 3742 -2.60% BenchmarkMatchEasy0_32 125 122 -2.40% BenchmarkMatchEasy0_32K 11414 11164 -2.19% BenchmarkMatchEasy0_1K 668 654 -2.10% BenchmarkAnchoredShortMatch 260 255 -1.92% BenchmarkAnchoredLiteralShortNonMatch 164 161 -1.83% BenchmarkOnePassShortB 623 612 -1.77% BenchmarkOnePassShortA 801 788 -1.62% BenchmarkMatchClass 4094 4033 -1.49% BenchmarkMatchEasy0_32M 14078800 13890704 -1.34% BenchmarkMatchHard_32K 4095844 4045820 -1.22% BenchmarkMatchEasy1_1K 1663 1643 -1.20% BenchmarkMatchHard_1M 131261708 129708215 -1.18% BenchmarkMatchHard_32M 4210112412 4169292003 -0.97% BenchmarkMatchMedium_32K 2460752 2438611 -0.90% BenchmarkMatchEasy0_1M 422914 419672 -0.77% BenchmarkMatchMedium_1M 78581121 78040160 -0.69% BenchmarkMatchMedium_32M 2515287278 2498464906 -0.67% BenchmarkMatchMedium_32 1754 1746 -0.46% BenchmarkMatchMedium_1K 52105 52106 +0.00% BenchmarkAnchoredLiteralLongNonMatch 185 185 +0.00% BenchmarkMatchEasy1_32 107 107 +0.00% BenchmarkOnePassLongNotPrefix 505 505 +0.00% BenchmarkOnePassLongPrefix 147 147 +0.00% The godoc binary is ~0.12% smaller after this CL. Updates #5729. toolstash -cmp passes for all architectures other than amd64 and amd64p32. Other architectures can be done in follow-up CLs. Change-Id: I0e167e259274b722958567fc0af83a17ca002da7 Reviewed-on: https://go-review.googlesource.com/2284 Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-08 09:54:15 -07:00
// Ginsboolval inserts instructions to convert the result
// of a just-completed comparison to a boolean value.
// The first argument is the conditional jump instruction
// corresponding to the desired value.
// The second argument is the destination.
// If not present, Ginsboolval will be emulated with jumps.
Ginsboolval func(obj.As, *Node)
Ginscon func(obj.As, int64, *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
Ginsnop func()
Gmove func(*Node, *Node)
Igenindex func(*Node, *Node, bool) *obj.Prog
Peep func(*obj.Prog)
Proginfo func(*obj.Prog) // fills in Prog.Info
Regtyp func(*obj.Addr) bool
Sameaddr func(*obj.Addr, *obj.Addr) bool
Smallindir func(*obj.Addr, *obj.Addr) bool
Stackaddr func(*obj.Addr) bool
Blockcopy func(*Node, *Node, int64, int64, int64)
Sudoaddable func(obj.As, *Node, *obj.Addr) bool
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
Sudoclean func()
Excludedregs func() uint64
RtoB func(int) uint64
FtoB func(int) uint64
BtoR func(uint64) int
BtoF func(uint64) int
Optoas func(Op, *Type) obj.As
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
Doregbits func(int) uint64
Regnames func(*int) []string
Use387 bool // should 8g use 387 FP instructions instead of sse2.
// SSARegToReg maps ssa register numbers to obj register numbers.
SSARegToReg []int16
// 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)
}
var pcloc int32
var Thearch Arch
var Newproc *Node
var Deferproc *Node
var Deferreturn *Node
var Panicindex *Node
var panicslice *Node
var panicdivide *Node
var throwreturn *Node
var growslice *Node
var writebarrierptr *Node
var typedmemmove *Node
var panicdottype *Node