go/src/cmd/compile/internal/ssa/config.go

421 lines
13 KiB
Go
Raw Normal View History

// Copyright 2015 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 ssa
import (
"cmd/compile/internal/abi"
"cmd/compile/internal/base"
"cmd/compile/internal/ir"
cmd/compile: change ssa.Type into *types.Type When package ssa was created, Type was in package gc. To avoid circular dependencies, we used an interface (ssa.Type) to represent type information in SSA. In the Go 1.9 cycle, gri extricated the Type type from package gc. As a result, we can now use it in package ssa. Now, instead of package types depending on package ssa, it is the other way. This is a more sensible dependency tree, and helps compiler performance a bit. Though this is a big CL, most of the changes are mechanical and uninteresting. Interesting bits: * Add new singleton globals to package types for the special SSA types Memory, Void, Invalid, Flags, and Int128. * Add two new Types, TSSA for the special types, and TTUPLE, for SSA tuple types. ssa.MakeTuple is now types.NewTuple. * Move type comparison result constants CMPlt, CMPeq, and CMPgt to package types. * We had picked the name "types" in our rules for the handy list of types provided by ssa.Config. That conflicted with the types package name, so change it to "typ". * Update the type comparison routine to handle tuples and special types inline. * Teach gc/fmt.go how to print special types. * We can now eliminate ElemTypes in favor of just Elem, and probably also some other duplicated Type methods designed to return ssa.Type instead of *types.Type. * The ssa tests were using their own dummy types, and they were not particularly careful about types in general. Of necessity, this CL switches them to use *types.Type; it does not make them more type-accurate. Unfortunately, using types.Type means initializing a bit of the types universe. This is prime for refactoring and improvement. This shrinks ssa.Value; it now fits in a smaller size class on 64 bit systems. This doesn't have a giant impact, though, since most Values are preallocated in a chunk. name old alloc/op new alloc/op delta Template 37.9MB ± 0% 37.7MB ± 0% -0.57% (p=0.000 n=10+8) Unicode 28.9MB ± 0% 28.7MB ± 0% -0.52% (p=0.000 n=10+10) GoTypes 110MB ± 0% 109MB ± 0% -0.88% (p=0.000 n=10+10) Flate 24.7MB ± 0% 24.6MB ± 0% -0.66% (p=0.000 n=10+10) GoParser 31.1MB ± 0% 30.9MB ± 0% -0.61% (p=0.000 n=10+9) Reflect 73.9MB ± 0% 73.4MB ± 0% -0.62% (p=0.000 n=10+8) Tar 25.8MB ± 0% 25.6MB ± 0% -0.77% (p=0.000 n=9+10) XML 41.2MB ± 0% 40.9MB ± 0% -0.80% (p=0.000 n=10+10) [Geo mean] 40.5MB 40.3MB -0.68% name old allocs/op new allocs/op delta Template 385k ± 0% 386k ± 0% ~ (p=0.356 n=10+9) Unicode 343k ± 1% 344k ± 0% ~ (p=0.481 n=10+10) GoTypes 1.16M ± 0% 1.16M ± 0% -0.16% (p=0.004 n=10+10) Flate 238k ± 1% 238k ± 1% ~ (p=0.853 n=10+10) GoParser 320k ± 0% 320k ± 0% ~ (p=0.720 n=10+9) Reflect 957k ± 0% 957k ± 0% ~ (p=0.460 n=10+8) Tar 252k ± 0% 252k ± 0% ~ (p=0.133 n=9+10) XML 400k ± 0% 400k ± 0% ~ (p=0.796 n=10+10) [Geo mean] 428k 428k -0.01% Removing all the interface calls helps non-trivially with CPU, though. name old time/op new time/op delta Template 178ms ± 4% 173ms ± 3% -2.90% (p=0.000 n=94+96) Unicode 85.0ms ± 4% 83.9ms ± 4% -1.23% (p=0.000 n=96+96) GoTypes 543ms ± 3% 528ms ± 3% -2.73% (p=0.000 n=98+96) Flate 116ms ± 3% 113ms ± 4% -2.34% (p=0.000 n=96+99) GoParser 144ms ± 3% 140ms ± 4% -2.80% (p=0.000 n=99+97) Reflect 344ms ± 3% 334ms ± 4% -3.02% (p=0.000 n=100+99) Tar 106ms ± 5% 103ms ± 4% -3.30% (p=0.000 n=98+94) XML 198ms ± 5% 192ms ± 4% -2.88% (p=0.000 n=92+95) [Geo mean] 178ms 173ms -2.65% name old user-time/op new user-time/op delta Template 229ms ± 5% 224ms ± 5% -2.36% (p=0.000 n=95+99) Unicode 107ms ± 6% 106ms ± 5% -1.13% (p=0.001 n=93+95) GoTypes 696ms ± 4% 679ms ± 4% -2.45% (p=0.000 n=97+99) Flate 137ms ± 4% 134ms ± 5% -2.66% (p=0.000 n=99+96) GoParser 176ms ± 5% 172ms ± 8% -2.27% (p=0.000 n=98+100) Reflect 430ms ± 6% 411ms ± 5% -4.46% (p=0.000 n=100+92) Tar 128ms ±13% 123ms ±13% -4.21% (p=0.000 n=100+100) XML 239ms ± 6% 233ms ± 6% -2.50% (p=0.000 n=95+97) [Geo mean] 220ms 213ms -2.76% Change-Id: I15c7d6268347f8358e75066dfdbd77db24e8d0c1 Reviewed-on: https://go-review.googlesource.com/42145 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-04-28 14:12:28 -07:00
"cmd/compile/internal/types"
"cmd/internal/obj"
"cmd/internal/src"
"internal/buildcfg"
)
// A Config holds readonly compilation information.
// It is created once, early during compilation,
// and shared across all compilations.
type Config struct {
arch string // "amd64", etc.
PtrSize int64 // 4 or 8; copy of cmd/internal/sys.Arch.PtrSize
RegSize int64 // 4 or 8; copy of cmd/internal/sys.Arch.RegSize
Types Types
lowerBlock blockRewriter // block lowering function, first round
lowerValue valueRewriter // value lowering function, first round
lateLowerBlock blockRewriter // block lowering function that needs to be run after the first round; only used on some architectures
lateLowerValue valueRewriter // value lowering function that needs to be run after the first round; only used on some architectures
splitLoad valueRewriter // function for splitting merged load ops; only used on some architectures
registers []Register // machine registers
gpRegMask regMask // general purpose integer register mask
fpRegMask regMask // floating point register mask
fp32RegMask regMask // floating point register mask
fp64RegMask regMask // floating point register mask
specialRegMask regMask // special register mask
intParamRegs []int8 // register numbers of integer param (in/out) registers
floatParamRegs []int8 // register numbers of floating param (in/out) registers
ABI1 *abi.ABIConfig // "ABIInternal" under development // TODO change comment when this becomes current
ABI0 *abi.ABIConfig
GCRegMap []*Register // garbage collector register map, by GC register index
FPReg int8 // register number of frame pointer, -1 if not used
LinkReg int8 // register number of link register if it is a general purpose register, -1 if not used
hasGReg bool // has hardware g register
ctxt *obj.Link // Generic arch information
optimize bool // Do optimization
noDuffDevice bool // Don't use Duff's device
useSSE bool // Use SSE for non-float operations
useAvg bool // Use optimizations that need Avg* operations
useHmul bool // Use optimizations that need Hmul* operations
SoftFloat bool //
Race bool // race detector enabled
BigEndian bool //
UseFMA bool // Use hardware FMA operation
unalignedOK bool // Unaligned loads/stores are ok
haveBswap64 bool // architecture implements Bswap64
haveBswap32 bool // architecture implements Bswap32
haveBswap16 bool // architecture implements Bswap16
}
type (
blockRewriter func(*Block) bool
valueRewriter func(*Value) bool
)
type Types struct {
cmd/compile: change ssa.Type into *types.Type When package ssa was created, Type was in package gc. To avoid circular dependencies, we used an interface (ssa.Type) to represent type information in SSA. In the Go 1.9 cycle, gri extricated the Type type from package gc. As a result, we can now use it in package ssa. Now, instead of package types depending on package ssa, it is the other way. This is a more sensible dependency tree, and helps compiler performance a bit. Though this is a big CL, most of the changes are mechanical and uninteresting. Interesting bits: * Add new singleton globals to package types for the special SSA types Memory, Void, Invalid, Flags, and Int128. * Add two new Types, TSSA for the special types, and TTUPLE, for SSA tuple types. ssa.MakeTuple is now types.NewTuple. * Move type comparison result constants CMPlt, CMPeq, and CMPgt to package types. * We had picked the name "types" in our rules for the handy list of types provided by ssa.Config. That conflicted with the types package name, so change it to "typ". * Update the type comparison routine to handle tuples and special types inline. * Teach gc/fmt.go how to print special types. * We can now eliminate ElemTypes in favor of just Elem, and probably also some other duplicated Type methods designed to return ssa.Type instead of *types.Type. * The ssa tests were using their own dummy types, and they were not particularly careful about types in general. Of necessity, this CL switches them to use *types.Type; it does not make them more type-accurate. Unfortunately, using types.Type means initializing a bit of the types universe. This is prime for refactoring and improvement. This shrinks ssa.Value; it now fits in a smaller size class on 64 bit systems. This doesn't have a giant impact, though, since most Values are preallocated in a chunk. name old alloc/op new alloc/op delta Template 37.9MB ± 0% 37.7MB ± 0% -0.57% (p=0.000 n=10+8) Unicode 28.9MB ± 0% 28.7MB ± 0% -0.52% (p=0.000 n=10+10) GoTypes 110MB ± 0% 109MB ± 0% -0.88% (p=0.000 n=10+10) Flate 24.7MB ± 0% 24.6MB ± 0% -0.66% (p=0.000 n=10+10) GoParser 31.1MB ± 0% 30.9MB ± 0% -0.61% (p=0.000 n=10+9) Reflect 73.9MB ± 0% 73.4MB ± 0% -0.62% (p=0.000 n=10+8) Tar 25.8MB ± 0% 25.6MB ± 0% -0.77% (p=0.000 n=9+10) XML 41.2MB ± 0% 40.9MB ± 0% -0.80% (p=0.000 n=10+10) [Geo mean] 40.5MB 40.3MB -0.68% name old allocs/op new allocs/op delta Template 385k ± 0% 386k ± 0% ~ (p=0.356 n=10+9) Unicode 343k ± 1% 344k ± 0% ~ (p=0.481 n=10+10) GoTypes 1.16M ± 0% 1.16M ± 0% -0.16% (p=0.004 n=10+10) Flate 238k ± 1% 238k ± 1% ~ (p=0.853 n=10+10) GoParser 320k ± 0% 320k ± 0% ~ (p=0.720 n=10+9) Reflect 957k ± 0% 957k ± 0% ~ (p=0.460 n=10+8) Tar 252k ± 0% 252k ± 0% ~ (p=0.133 n=9+10) XML 400k ± 0% 400k ± 0% ~ (p=0.796 n=10+10) [Geo mean] 428k 428k -0.01% Removing all the interface calls helps non-trivially with CPU, though. name old time/op new time/op delta Template 178ms ± 4% 173ms ± 3% -2.90% (p=0.000 n=94+96) Unicode 85.0ms ± 4% 83.9ms ± 4% -1.23% (p=0.000 n=96+96) GoTypes 543ms ± 3% 528ms ± 3% -2.73% (p=0.000 n=98+96) Flate 116ms ± 3% 113ms ± 4% -2.34% (p=0.000 n=96+99) GoParser 144ms ± 3% 140ms ± 4% -2.80% (p=0.000 n=99+97) Reflect 344ms ± 3% 334ms ± 4% -3.02% (p=0.000 n=100+99) Tar 106ms ± 5% 103ms ± 4% -3.30% (p=0.000 n=98+94) XML 198ms ± 5% 192ms ± 4% -2.88% (p=0.000 n=92+95) [Geo mean] 178ms 173ms -2.65% name old user-time/op new user-time/op delta Template 229ms ± 5% 224ms ± 5% -2.36% (p=0.000 n=95+99) Unicode 107ms ± 6% 106ms ± 5% -1.13% (p=0.001 n=93+95) GoTypes 696ms ± 4% 679ms ± 4% -2.45% (p=0.000 n=97+99) Flate 137ms ± 4% 134ms ± 5% -2.66% (p=0.000 n=99+96) GoParser 176ms ± 5% 172ms ± 8% -2.27% (p=0.000 n=98+100) Reflect 430ms ± 6% 411ms ± 5% -4.46% (p=0.000 n=100+92) Tar 128ms ±13% 123ms ±13% -4.21% (p=0.000 n=100+100) XML 239ms ± 6% 233ms ± 6% -2.50% (p=0.000 n=95+97) [Geo mean] 220ms 213ms -2.76% Change-Id: I15c7d6268347f8358e75066dfdbd77db24e8d0c1 Reviewed-on: https://go-review.googlesource.com/42145 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-04-28 14:12:28 -07:00
Bool *types.Type
Int8 *types.Type
Int16 *types.Type
Int32 *types.Type
Int64 *types.Type
UInt8 *types.Type
UInt16 *types.Type
UInt32 *types.Type
UInt64 *types.Type
Int *types.Type
Float32 *types.Type
Float64 *types.Type
UInt *types.Type
cmd/compile: change ssa.Type into *types.Type When package ssa was created, Type was in package gc. To avoid circular dependencies, we used an interface (ssa.Type) to represent type information in SSA. In the Go 1.9 cycle, gri extricated the Type type from package gc. As a result, we can now use it in package ssa. Now, instead of package types depending on package ssa, it is the other way. This is a more sensible dependency tree, and helps compiler performance a bit. Though this is a big CL, most of the changes are mechanical and uninteresting. Interesting bits: * Add new singleton globals to package types for the special SSA types Memory, Void, Invalid, Flags, and Int128. * Add two new Types, TSSA for the special types, and TTUPLE, for SSA tuple types. ssa.MakeTuple is now types.NewTuple. * Move type comparison result constants CMPlt, CMPeq, and CMPgt to package types. * We had picked the name "types" in our rules for the handy list of types provided by ssa.Config. That conflicted with the types package name, so change it to "typ". * Update the type comparison routine to handle tuples and special types inline. * Teach gc/fmt.go how to print special types. * We can now eliminate ElemTypes in favor of just Elem, and probably also some other duplicated Type methods designed to return ssa.Type instead of *types.Type. * The ssa tests were using their own dummy types, and they were not particularly careful about types in general. Of necessity, this CL switches them to use *types.Type; it does not make them more type-accurate. Unfortunately, using types.Type means initializing a bit of the types universe. This is prime for refactoring and improvement. This shrinks ssa.Value; it now fits in a smaller size class on 64 bit systems. This doesn't have a giant impact, though, since most Values are preallocated in a chunk. name old alloc/op new alloc/op delta Template 37.9MB ± 0% 37.7MB ± 0% -0.57% (p=0.000 n=10+8) Unicode 28.9MB ± 0% 28.7MB ± 0% -0.52% (p=0.000 n=10+10) GoTypes 110MB ± 0% 109MB ± 0% -0.88% (p=0.000 n=10+10) Flate 24.7MB ± 0% 24.6MB ± 0% -0.66% (p=0.000 n=10+10) GoParser 31.1MB ± 0% 30.9MB ± 0% -0.61% (p=0.000 n=10+9) Reflect 73.9MB ± 0% 73.4MB ± 0% -0.62% (p=0.000 n=10+8) Tar 25.8MB ± 0% 25.6MB ± 0% -0.77% (p=0.000 n=9+10) XML 41.2MB ± 0% 40.9MB ± 0% -0.80% (p=0.000 n=10+10) [Geo mean] 40.5MB 40.3MB -0.68% name old allocs/op new allocs/op delta Template 385k ± 0% 386k ± 0% ~ (p=0.356 n=10+9) Unicode 343k ± 1% 344k ± 0% ~ (p=0.481 n=10+10) GoTypes 1.16M ± 0% 1.16M ± 0% -0.16% (p=0.004 n=10+10) Flate 238k ± 1% 238k ± 1% ~ (p=0.853 n=10+10) GoParser 320k ± 0% 320k ± 0% ~ (p=0.720 n=10+9) Reflect 957k ± 0% 957k ± 0% ~ (p=0.460 n=10+8) Tar 252k ± 0% 252k ± 0% ~ (p=0.133 n=9+10) XML 400k ± 0% 400k ± 0% ~ (p=0.796 n=10+10) [Geo mean] 428k 428k -0.01% Removing all the interface calls helps non-trivially with CPU, though. name old time/op new time/op delta Template 178ms ± 4% 173ms ± 3% -2.90% (p=0.000 n=94+96) Unicode 85.0ms ± 4% 83.9ms ± 4% -1.23% (p=0.000 n=96+96) GoTypes 543ms ± 3% 528ms ± 3% -2.73% (p=0.000 n=98+96) Flate 116ms ± 3% 113ms ± 4% -2.34% (p=0.000 n=96+99) GoParser 144ms ± 3% 140ms ± 4% -2.80% (p=0.000 n=99+97) Reflect 344ms ± 3% 334ms ± 4% -3.02% (p=0.000 n=100+99) Tar 106ms ± 5% 103ms ± 4% -3.30% (p=0.000 n=98+94) XML 198ms ± 5% 192ms ± 4% -2.88% (p=0.000 n=92+95) [Geo mean] 178ms 173ms -2.65% name old user-time/op new user-time/op delta Template 229ms ± 5% 224ms ± 5% -2.36% (p=0.000 n=95+99) Unicode 107ms ± 6% 106ms ± 5% -1.13% (p=0.001 n=93+95) GoTypes 696ms ± 4% 679ms ± 4% -2.45% (p=0.000 n=97+99) Flate 137ms ± 4% 134ms ± 5% -2.66% (p=0.000 n=99+96) GoParser 176ms ± 5% 172ms ± 8% -2.27% (p=0.000 n=98+100) Reflect 430ms ± 6% 411ms ± 5% -4.46% (p=0.000 n=100+92) Tar 128ms ±13% 123ms ±13% -4.21% (p=0.000 n=100+100) XML 239ms ± 6% 233ms ± 6% -2.50% (p=0.000 n=95+97) [Geo mean] 220ms 213ms -2.76% Change-Id: I15c7d6268347f8358e75066dfdbd77db24e8d0c1 Reviewed-on: https://go-review.googlesource.com/42145 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-04-28 14:12:28 -07:00
Uintptr *types.Type
String *types.Type
BytePtr *types.Type // TODO: use unsafe.Pointer instead?
Int32Ptr *types.Type
UInt32Ptr *types.Type
IntPtr *types.Type
UintptrPtr *types.Type
Float32Ptr *types.Type
Float64Ptr *types.Type
BytePtrPtr *types.Type
}
// NewTypes creates and populates a Types.
func NewTypes() *Types {
t := new(Types)
t.SetTypPtrs()
return t
}
// SetTypPtrs populates t.
func (t *Types) SetTypPtrs() {
t.Bool = types.Types[types.TBOOL]
t.Int8 = types.Types[types.TINT8]
t.Int16 = types.Types[types.TINT16]
t.Int32 = types.Types[types.TINT32]
t.Int64 = types.Types[types.TINT64]
t.UInt8 = types.Types[types.TUINT8]
t.UInt16 = types.Types[types.TUINT16]
t.UInt32 = types.Types[types.TUINT32]
t.UInt64 = types.Types[types.TUINT64]
t.Int = types.Types[types.TINT]
t.Float32 = types.Types[types.TFLOAT32]
t.Float64 = types.Types[types.TFLOAT64]
t.UInt = types.Types[types.TUINT]
t.Uintptr = types.Types[types.TUINTPTR]
t.String = types.Types[types.TSTRING]
t.BytePtr = types.NewPtr(types.Types[types.TUINT8])
t.Int32Ptr = types.NewPtr(types.Types[types.TINT32])
t.UInt32Ptr = types.NewPtr(types.Types[types.TUINT32])
t.IntPtr = types.NewPtr(types.Types[types.TINT])
t.UintptrPtr = types.NewPtr(types.Types[types.TUINTPTR])
t.Float32Ptr = types.NewPtr(types.Types[types.TFLOAT32])
t.Float64Ptr = types.NewPtr(types.Types[types.TFLOAT64])
t.BytePtrPtr = types.NewPtr(types.NewPtr(types.Types[types.TUINT8]))
}
type Logger interface {
// Logf logs a message from the compiler.
Logf(string, ...interface{})
[dev.ssa] cmd/compile/ssa: separate logging, work in progress, and fatal errors The SSA implementation logs for three purposes: * debug logging * fatal errors * unimplemented features Separating these three uses lets us attempt an SSA implementation for all functions, not just _ssa functions. This turns the entire standard library into a compilation test, and makes it easy to figure out things like "how much coverage does SSA have now" and "what should we do next to get more coverage?". Functions called _ssa are still special. They log profusely by default and the output of the SSA implementation is used. For all other functions, logging is off, and the implementation is built and discarded, due to lack of support for the runtime. While we're here, fix a few minor bugs and add some extra Unimplementeds to allow all.bash to pass. As of now, SSA handles 20.79% of the functions in the standard library (689 of 3314). The top missing features are: 10.03% 2597 SSA unimplemented: zero for type error not implemented 7.79% 2016 SSA unimplemented: addr: bad op DOTPTR 7.33% 1898 SSA unimplemented: unhandled expr EQ 6.10% 1579 SSA unimplemented: unhandled expr OROR 4.91% 1271 SSA unimplemented: unhandled expr NE 4.49% 1163 SSA unimplemented: unhandled expr LROT 4.00% 1036 SSA unimplemented: unhandled expr LEN 3.56% 923 SSA unimplemented: unhandled stmt CALLFUNC 2.37% 615 SSA unimplemented: zero for type []byte not implemented 1.90% 492 SSA unimplemented: unhandled stmt CALLMETH 1.74% 450 SSA unimplemented: unhandled expr CALLINTER 1.74% 450 SSA unimplemented: unhandled expr DOT 1.71% 444 SSA unimplemented: unhandled expr ANDAND 1.65% 426 SSA unimplemented: unhandled expr CLOSUREVAR 1.54% 400 SSA unimplemented: unhandled expr CALLMETH 1.51% 390 SSA unimplemented: unhandled stmt SWITCH 1.47% 380 SSA unimplemented: unhandled expr CONV 1.33% 345 SSA unimplemented: addr: bad op * 1.30% 336 SSA unimplemented: unhandled OLITERAL 6 Change-Id: I4ca07951e276714dc13c31de28640aead17a1be7 Reviewed-on: https://go-review.googlesource.com/11160 Reviewed-by: Keith Randall <khr@golang.org>
2015-06-12 11:01:13 -07:00
// Log reports whether logging is not a no-op
// some logging calls account for more than a few heap allocations.
Log() bool
// Fatalf reports a compiler error and exits.
2016-12-15 17:17:01 -08:00
Fatalf(pos src.XPos, msg string, args ...interface{})
[dev.ssa] cmd/compile/ssa: separate logging, work in progress, and fatal errors The SSA implementation logs for three purposes: * debug logging * fatal errors * unimplemented features Separating these three uses lets us attempt an SSA implementation for all functions, not just _ssa functions. This turns the entire standard library into a compilation test, and makes it easy to figure out things like "how much coverage does SSA have now" and "what should we do next to get more coverage?". Functions called _ssa are still special. They log profusely by default and the output of the SSA implementation is used. For all other functions, logging is off, and the implementation is built and discarded, due to lack of support for the runtime. While we're here, fix a few minor bugs and add some extra Unimplementeds to allow all.bash to pass. As of now, SSA handles 20.79% of the functions in the standard library (689 of 3314). The top missing features are: 10.03% 2597 SSA unimplemented: zero for type error not implemented 7.79% 2016 SSA unimplemented: addr: bad op DOTPTR 7.33% 1898 SSA unimplemented: unhandled expr EQ 6.10% 1579 SSA unimplemented: unhandled expr OROR 4.91% 1271 SSA unimplemented: unhandled expr NE 4.49% 1163 SSA unimplemented: unhandled expr LROT 4.00% 1036 SSA unimplemented: unhandled expr LEN 3.56% 923 SSA unimplemented: unhandled stmt CALLFUNC 2.37% 615 SSA unimplemented: zero for type []byte not implemented 1.90% 492 SSA unimplemented: unhandled stmt CALLMETH 1.74% 450 SSA unimplemented: unhandled expr CALLINTER 1.74% 450 SSA unimplemented: unhandled expr DOT 1.71% 444 SSA unimplemented: unhandled expr ANDAND 1.65% 426 SSA unimplemented: unhandled expr CLOSUREVAR 1.54% 400 SSA unimplemented: unhandled expr CALLMETH 1.51% 390 SSA unimplemented: unhandled stmt SWITCH 1.47% 380 SSA unimplemented: unhandled expr CONV 1.33% 345 SSA unimplemented: addr: bad op * 1.30% 336 SSA unimplemented: unhandled OLITERAL 6 Change-Id: I4ca07951e276714dc13c31de28640aead17a1be7 Reviewed-on: https://go-review.googlesource.com/11160 Reviewed-by: Keith Randall <khr@golang.org>
2015-06-12 11:01:13 -07:00
// Warnl writes compiler messages in the form expected by "errorcheck" tests
2016-12-15 17:17:01 -08:00
Warnl(pos src.XPos, fmt_ string, args ...interface{})
// Forwards the Debug flags from gc
Debug_checknil() bool
}
type Frontend interface {
Logger
// StringData returns a symbol pointing to the given string's contents.
cmd/compile: start implementing strongly typed aux and auxint fields Right now the Aux and AuxInt fields of ssa.Values are typed as interface{} and int64, respectively. Each rule that uses these values must cast them to the type they actually are (*obj.LSym, or int32, or ValAndOff, etc.), use them, and then cast them back to interface{} or int64. We know for each opcode what the types of the Aux and AuxInt fields should be. So let's modify the rule generator to declare the types to be what we know they should be, autoconverting to and from the generic types for us. That way we can make the rules more type safe. It's difficult to make a single CL for this, so I've coopted the "=>" token to indicate a rule that is strongly typed. "->" rules are processed as before. That will let us migrate a few rules at a time in separate CLs. Hopefully we can reach a state where all rules are strongly typed and we can drop the distinction. This CL changes just a few rules to get a feel for what this transition would look like. I've decided not to put explicit types in the rules. I think it makes the rules somewhat clearer, but definitely more verbose. In particular, the passthrough rules that don't modify the fields in question are verbose for no real reason. Change-Id: I63a1b789ac5702e7caf7934cd49f784235d1d73d Reviewed-on: https://go-review.googlesource.com/c/go/+/190197 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2020-03-19 16:25:08 -07:00
StringData(string) *obj.LSym
cmd/compile: better job of naming compound types Compound AUTO types weren't named previously. That was because live variable analysis (plive.go) doesn't handle spilling to compound types. It can't handle them because there is no valid place to put VARDEFs when regalloc is spilling compound types. compound types = multiword builtin types: complex, string, slice, and interface. Instead, we split named AUTOs into individual one-word variables. For example, a string s gets split into a byte ptr s.ptr and an integer s.len. Those two variables can be spilled to / restored from independently. As a result, live variable analysis can handle them because they are one-word objects. This CL will change how AUTOs are described in DWARF information. Consider the code: func f(s string, i int) int { x := s[i:i+5] g() return lookup(x) } The old compiler would spill x to two consecutive slots on the stack, both named x (at offsets 0 and 8). The new compiler spills the pointer of x to a slot named x.ptr. It doesn't spill x.len at all, as it is a constant (5) and can be rematerialized for the call to lookup. So compound objects may not be spilled in their entirety, and even if they are they won't necessarily be contiguous. Such is the price of optimization. Re-enable live variable analysis tests. One test remains disabled, it fails because of #14904. Change-Id: I8ef2b5ab91e43a0d2136bfc231c05d100ec0b801 Reviewed-on: https://go-review.googlesource.com/21233 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-03-28 11:25:17 -07:00
// Given the name for a compound type, returns the name we should use
// for the parts of that compound type.
SplitSlot(parent *LocalSlot, suffix string, offset int64, t *types.Type) LocalSlot
cmd/compile: better job of naming compound types Compound AUTO types weren't named previously. That was because live variable analysis (plive.go) doesn't handle spilling to compound types. It can't handle them because there is no valid place to put VARDEFs when regalloc is spilling compound types. compound types = multiword builtin types: complex, string, slice, and interface. Instead, we split named AUTOs into individual one-word variables. For example, a string s gets split into a byte ptr s.ptr and an integer s.len. Those two variables can be spilled to / restored from independently. As a result, live variable analysis can handle them because they are one-word objects. This CL will change how AUTOs are described in DWARF information. Consider the code: func f(s string, i int) int { x := s[i:i+5] g() return lookup(x) } The old compiler would spill x to two consecutive slots on the stack, both named x (at offsets 0 and 8). The new compiler spills the pointer of x to a slot named x.ptr. It doesn't spill x.len at all, as it is a constant (5) and can be rematerialized for the call to lookup. So compound objects may not be spilled in their entirety, and even if they are they won't necessarily be contiguous. Such is the price of optimization. Re-enable live variable analysis tests. One test remains disabled, it fails because of #14904. Change-Id: I8ef2b5ab91e43a0d2136bfc231c05d100ec0b801 Reviewed-on: https://go-review.googlesource.com/21233 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2016-03-28 11:25:17 -07:00
// Syslook returns a symbol of the runtime function/variable with the
// given name.
Syslook(string) *obj.LSym
// UseWriteBarrier reports whether write barrier is enabled
UseWriteBarrier() bool
// Func returns the ir.Func of the function being compiled.
Func() *ir.Func
}
// NewConfig returns a new configuration object for the given architecture.
func NewConfig(arch string, types Types, ctxt *obj.Link, optimize, softfloat bool) *Config {
c := &Config{arch: arch, Types: types}
c.useAvg = true
c.useHmul = true
switch arch {
case "amd64":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockAMD64
c.lowerValue = rewriteValueAMD64
c.lateLowerBlock = rewriteBlockAMD64latelower
c.lateLowerValue = rewriteValueAMD64latelower
c.splitLoad = rewriteValueAMD64splitload
c.registers = registersAMD64[:]
c.gpRegMask = gpRegMaskAMD64
c.fpRegMask = fpRegMaskAMD64
c.specialRegMask = specialRegMaskAMD64
c.intParamRegs = paramIntRegAMD64
c.floatParamRegs = paramFloatRegAMD64
c.FPReg = framepointerRegAMD64
c.LinkReg = linkRegAMD64
c.hasGReg = true
c.unalignedOK = true
c.haveBswap64 = true
c.haveBswap32 = true
c.haveBswap16 = true
case "386":
c.PtrSize = 4
c.RegSize = 4
c.lowerBlock = rewriteBlock386
c.lowerValue = rewriteValue386
c.splitLoad = rewriteValue386splitload
c.registers = registers386[:]
c.gpRegMask = gpRegMask386
c.fpRegMask = fpRegMask386
c.FPReg = framepointerReg386
c.LinkReg = linkReg386
c.hasGReg = false
c.unalignedOK = true
c.haveBswap32 = true
c.haveBswap16 = true
case "arm":
c.PtrSize = 4
c.RegSize = 4
c.lowerBlock = rewriteBlockARM
c.lowerValue = rewriteValueARM
c.registers = registersARM[:]
c.gpRegMask = gpRegMaskARM
c.fpRegMask = fpRegMaskARM
c.FPReg = framepointerRegARM
c.LinkReg = linkRegARM
c.hasGReg = true
case "arm64":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockARM64
c.lowerValue = rewriteValueARM64
c.lateLowerBlock = rewriteBlockARM64latelower
cmd/compile: add late lower pass for last rules to run Usually optimization rules have corresponding priorities, some need to be run first, some run next, and some run last, which produces the best code. But currently our optimization rules have no priority, this CL adds a late lower pass that runs those rules that need to be run at last, such as split unreasonable constant folding. This pass can be seen as the second round of the lower pass. For example: func foo(a, b uint64) uint64 { d := a+0x1234568 d1 := b+0x1234568 return d&d1 } The code generated by the master branch: 0x0004 00004 ADD $19088744, R0, R2 // movz+movk+add 0x0010 00016 ADD $19088744, R1, R1 // movz+movk+add 0x001c 00028 AND R1, R2, R0 This is because the current constant folding optimization rules do not take into account the range of constants, causing the constant to be loaded repeatedly. This CL splits these unreasonable constants folding in the late lower pass. With this CL the generated code: 0x0004 00004 MOVD $19088744, R2 // movz+movk 0x000c 00012 ADD R0, R2, R3 0x0010 00016 ADD R1, R2, R1 0x0014 00020 AND R1, R3, R0 This CL also adds constant folding optimization for ADDS instruction. In addition, in order not to introduce the codegen regression, an optimization rule is added to change the addition of a negative number into a subtraction of a positive number. go1 benchmarks: name old time/op new time/op delta BinaryTree17-8 1.22s ± 1% 1.24s ± 0% +1.56% (p=0.008 n=5+5) Fannkuch11-8 1.54s ± 0% 1.53s ± 0% -0.69% (p=0.016 n=4+5) FmtFprintfEmpty-8 14.1ns ± 0% 14.1ns ± 0% ~ (p=0.079 n=4+5) FmtFprintfString-8 26.0ns ± 0% 26.1ns ± 0% +0.23% (p=0.008 n=5+5) FmtFprintfInt-8 32.3ns ± 0% 32.9ns ± 1% +1.72% (p=0.008 n=5+5) FmtFprintfIntInt-8 54.5ns ± 0% 55.5ns ± 0% +1.83% (p=0.008 n=5+5) FmtFprintfPrefixedInt-8 61.5ns ± 0% 62.0ns ± 0% +0.93% (p=0.008 n=5+5) FmtFprintfFloat-8 72.0ns ± 0% 73.6ns ± 0% +2.24% (p=0.008 n=5+5) FmtManyArgs-8 221ns ± 0% 224ns ± 0% +1.22% (p=0.008 n=5+5) GobDecode-8 1.91ms ± 0% 1.93ms ± 0% +0.98% (p=0.008 n=5+5) GobEncode-8 1.40ms ± 1% 1.39ms ± 0% -0.79% (p=0.032 n=5+5) Gzip-8 115ms ± 0% 117ms ± 1% +1.17% (p=0.008 n=5+5) Gunzip-8 19.4ms ± 1% 19.3ms ± 0% -0.71% (p=0.016 n=5+4) HTTPClientServer-8 27.0µs ± 0% 27.3µs ± 0% +0.80% (p=0.008 n=5+5) JSONEncode-8 3.36ms ± 1% 3.33ms ± 0% ~ (p=0.056 n=5+5) JSONDecode-8 17.5ms ± 2% 17.8ms ± 0% +1.71% (p=0.016 n=5+4) Mandelbrot200-8 2.29ms ± 0% 2.29ms ± 0% ~ (p=0.151 n=5+5) GoParse-8 1.35ms ± 1% 1.36ms ± 1% ~ (p=0.056 n=5+5) RegexpMatchEasy0_32-8 24.5ns ± 0% 24.5ns ± 0% ~ (p=0.444 n=4+5) RegexpMatchEasy0_1K-8 131ns ±11% 118ns ± 6% ~ (p=0.056 n=5+5) RegexpMatchEasy1_32-8 22.9ns ± 0% 22.9ns ± 0% ~ (p=0.905 n=4+5) RegexpMatchEasy1_1K-8 126ns ± 0% 127ns ± 0% ~ (p=0.063 n=4+5) RegexpMatchMedium_32-8 486ns ± 5% 483ns ± 0% ~ (p=0.381 n=5+4) RegexpMatchMedium_1K-8 15.4µs ± 1% 15.5µs ± 0% ~ (p=0.151 n=5+5) RegexpMatchHard_32-8 687ns ± 0% 686ns ± 0% ~ (p=0.103 n=5+5) RegexpMatchHard_1K-8 20.7µs ± 0% 20.7µs ± 1% ~ (p=0.151 n=5+5) Revcomp-8 175ms ± 2% 176ms ± 3% ~ (p=1.000 n=5+5) Template-8 20.4ms ± 6% 20.1ms ± 2% ~ (p=0.151 n=5+5) TimeParse-8 112ns ± 0% 113ns ± 0% +0.97% (p=0.016 n=5+4) TimeFormat-8 156ns ± 0% 145ns ± 0% -7.14% (p=0.029 n=4+4) Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da Reviewed-on: https://go-review.googlesource.com/c/go/+/425134 Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Eric Fang <eric.fang@arm.com>
2022-08-17 10:01:17 +00:00
c.lateLowerValue = rewriteValueARM64latelower
c.registers = registersARM64[:]
c.gpRegMask = gpRegMaskARM64
c.fpRegMask = fpRegMaskARM64
c.intParamRegs = paramIntRegARM64
c.floatParamRegs = paramFloatRegARM64
c.FPReg = framepointerRegARM64
c.LinkReg = linkRegARM64
c.hasGReg = true
c.unalignedOK = true
c.haveBswap64 = true
c.haveBswap32 = true
c.haveBswap16 = true
case "ppc64":
c.BigEndian = true
fallthrough
case "ppc64le":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockPPC64
c.lowerValue = rewriteValuePPC64
c.lateLowerBlock = rewriteBlockPPC64latelower
c.lateLowerValue = rewriteValuePPC64latelower
c.registers = registersPPC64[:]
c.gpRegMask = gpRegMaskPPC64
c.fpRegMask = fpRegMaskPPC64
c.specialRegMask = specialRegMaskPPC64
c.intParamRegs = paramIntRegPPC64
c.floatParamRegs = paramFloatRegPPC64
c.FPReg = framepointerRegPPC64
c.LinkReg = linkRegPPC64
c.hasGReg = true
c.unalignedOK = true
// Note: ppc64 has register bswap ops only when GOPPC64>=10.
// But it has bswap+load and bswap+store ops for all ppc64 variants.
// That is the sense we're using them here - they are only used
// in contexts where they can be merged with a load or store.
c.haveBswap64 = true
c.haveBswap32 = true
c.haveBswap16 = true
case "mips64":
c.BigEndian = true
fallthrough
case "mips64le":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockMIPS64
c.lowerValue = rewriteValueMIPS64
c.registers = registersMIPS64[:]
c.gpRegMask = gpRegMaskMIPS64
c.fpRegMask = fpRegMaskMIPS64
c.specialRegMask = specialRegMaskMIPS64
c.FPReg = framepointerRegMIPS64
c.LinkReg = linkRegMIPS64
c.hasGReg = true
case "loong64":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockLOONG64
c.lowerValue = rewriteValueLOONG64
c.registers = registersLOONG64[:]
c.gpRegMask = gpRegMaskLOONG64
c.fpRegMask = fpRegMaskLOONG64
cmd/compile, internal/buildcfg: enable regABI on loong64, and add loong64 in test func hasRegisterABI goos: linux goarch: loong64 pkg: test/bench/go1 cpu: Loongson-3A5000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Template 116.4m ± 1% 101.3m ± 0% -12.94% (p=0.000 n=20) Gzip 417.2m ± 0% 419.4m ± 0% +0.53% (p=0.000 n=20) Gunzip 87.41m ± 0% 84.61m ± 0% -3.20% (p=0.000 n=20) FmtFprintfEmpty 97.87n ± 0% 81.05n ± 0% -17.19% (p=0.000 n=20) FmtFprintfString 151.1n ± 0% 140.9n ± 0% -6.75% (p=0.000 n=20) FmtFprintfInt 155.6n ± 0% 143.0n ± 0% -8.10% (p=0.000 n=20) FmtFprintfIntInt 236.9n ± 0% 225.1n ± 0% -5.00% (p=0.000 n=20) FmtFprintfPrefixedInt 316.8n ± 0% 331.9n ± 0% +4.77% (p=0.000 n=20) FmtFprintfFloat 401.5n ± 0% 380.0n ± 0% -5.35% (p=0.000 n=20) FmtManyArgs 925.3n ± 0% 910.1n ± 0% -1.64% (p=0.000 n=20) BinaryTree17 14.04 ± 1% 12.84 ± 0% -8.52% (p=0.000 n=20) RegexpMatchEasy0_32 133.1n ± 0% 121.3n ± 0% -8.87% (p=0.000 n=20) RegexpMatchEasy0_1K 1.363µ ± 0% 1.337µ ± 0% -1.91% (p=0.000 n=20) RegexpMatchEasy1_32 162.7n ± 0% 152.6n ± 0% -6.24% (p=0.000 n=20) RegexpMatchEasy1_1K 1.505µ ± 0% 1.740µ ± 0% +15.61% (p=0.000 n=20) RegexpMatchMedium_32 1.429µ ± 0% 1.299µ ± 0% -9.10% (p=0.000 n=20) RegexpMatchMedium_1K 41.76µ ± 0% 38.16µ ± 0% -8.61% (p=0.000 n=20) RegexpMatchHard_32 2.094µ ± 0% 2.157µ ± 0% +3.01% (p=0.000 n=20) RegexpMatchHard_1K 63.25µ ± 0% 64.72µ ± 0% +2.33% (p=0.000 n=20) JSONEncode 18.00m ± 1% 17.46m ± 1% -3.05% (p=0.000 n=20) JSONDecode 79.49m ± 0% 72.42m ± 0% -8.89% (p=0.000 n=20) Revcomp 1.147 ± 0% 1.255 ± 0% +9.39% (p=0.000 n=20) Fannkuch11 3.623 ± 0% 3.410 ± 0% -5.87% (p=0.000 n=20) Fannkuch11 3.623 ± 0% 3.410 ± 0% -5.87% (p=0.000 n=20) GobDecode 14.26m ± 0% 12.92m ± 0% -9.36% (p=0.000 n=20) GobEncode 16.86m ± 1% 14.96m ± 0% -11.28% (p=0.000 n=20) GoParse 8.721m ± 0% 8.125m ± 1% -6.84% (p=0.000 n=20) Mandelbrot200 7.203m ± 0% 7.171m ± 0% -0.44% (p=0.000 n=20) HTTPClientServer 83.96µ ± 0% 80.83µ ± 0% -3.72% (p=0.000 n=20) TimeParse 415.3n ± 0% 389.1n ± 0% -6.31% (p=0.000 n=20) TimeFormat 506.4n ± 0% 495.9n ± 0% -2.06% (p=0.000 n=20) geomean 102.6µ 98.04µ -4.40% │ bench.old │ bench.new │ │ B/s │ B/s vs base │ Template 15.90Mi ± 1% 18.26Mi ± 0% +14.88% (p=0.000 n=20) Gzip 44.36Mi ± 0% 44.12Mi ± 0% -0.53% (p=0.000 n=20) Gunzip 211.7Mi ± 0% 218.7Mi ± 0% +3.31% (p=0.000 n=20) RegexpMatchEasy0_32 229.3Mi ± 0% 251.6Mi ± 0% +9.72% (p=0.000 n=20) RegexpMatchEasy0_1K 716.4Mi ± 0% 730.3Mi ± 0% +1.94% (p=0.000 n=20) RegexpMatchEasy1_32 187.6Mi ± 0% 200.0Mi ± 0% +6.64% (p=0.000 n=20) RegexpMatchEasy1_1K 649.1Mi ± 0% 561.3Mi ± 0% -13.52% (p=0.000 n=20) RegexpMatchMedium_32 21.35Mi ± 0% 23.50Mi ± 0% +10.05% (p=0.000 n=20) RegexpMatchMedium_1K 23.38Mi ± 0% 25.59Mi ± 0% +9.42% (p=0.000 n=20) RegexpMatchHard_32 14.57Mi ± 0% 14.14Mi ± 0% -2.95% (p=0.000 n=20) RegexpMatchHard_1K 15.44Mi ± 0% 15.09Mi ± 0% -2.29% (p=0.000 n=20) JSONEncode 102.8Mi ± 1% 106.0Mi ± 1% +3.15% (p=0.000 n=20) JSONDecode 23.28Mi ± 0% 25.55Mi ± 0% +9.75% (p=0.000 n=20) Revcomp 211.3Mi ± 0% 193.1Mi ± 0% -8.58% (p=0.000 n=20) GobDecode 51.34Mi ± 0% 56.64Mi ± 0% +10.33% (p=0.000 n=20) GobEncode 43.42Mi ± 1% 48.93Mi ± 0% +12.71% (p=0.000 n=20) GoParse 6.337Mi ± 0% 6.800Mi ± 1% +7.30% (p=0.000 n=20) geomean 61.24Mi 63.63Mi +3.91% Update #40724 Co-authored-by: Xiaolin Zhao <zhaoxiaolin@loongson.cn> Change-Id: I5993460da8c5926c70cb6fbe551b8e4655dea9d0 Reviewed-on: https://go-review.googlesource.com/c/go/+/521790 Reviewed-by: Meidan Li <limeidan@loongson.cn> Reviewed-by: Cherry Mui <cherryyz@google.com> Auto-Submit: David Chase <drchase@google.com> Run-TryBot: David Chase <drchase@google.com> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com>
2023-08-16 10:39:38 +08:00
c.intParamRegs = paramIntRegLOONG64
c.floatParamRegs = paramFloatRegLOONG64
c.FPReg = framepointerRegLOONG64
c.LinkReg = linkRegLOONG64
c.hasGReg = true
case "s390x":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockS390X
c.lowerValue = rewriteValueS390X
c.registers = registersS390X[:]
c.gpRegMask = gpRegMaskS390X
c.fpRegMask = fpRegMaskS390X
c.FPReg = framepointerRegS390X
c.LinkReg = linkRegS390X
c.hasGReg = true
c.noDuffDevice = true
c.BigEndian = true
c.unalignedOK = true
c.haveBswap64 = true
c.haveBswap32 = true
c.haveBswap16 = true // only for loads&stores, see ppc64 comment
case "mips":
c.BigEndian = true
fallthrough
case "mipsle":
c.PtrSize = 4
c.RegSize = 4
c.lowerBlock = rewriteBlockMIPS
c.lowerValue = rewriteValueMIPS
c.registers = registersMIPS[:]
c.gpRegMask = gpRegMaskMIPS
c.fpRegMask = fpRegMaskMIPS
c.specialRegMask = specialRegMaskMIPS
c.FPReg = framepointerRegMIPS
c.LinkReg = linkRegMIPS
c.hasGReg = true
c.noDuffDevice = true
case "riscv64":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockRISCV64
c.lowerValue = rewriteValueRISCV64
c.lateLowerBlock = rewriteBlockRISCV64latelower
c.lateLowerValue = rewriteValueRISCV64latelower
c.registers = registersRISCV64[:]
c.gpRegMask = gpRegMaskRISCV64
c.fpRegMask = fpRegMaskRISCV64
c.intParamRegs = paramIntRegRISCV64
c.floatParamRegs = paramFloatRegRISCV64
c.FPReg = framepointerRegRISCV64
c.hasGReg = true
case "wasm":
c.PtrSize = 8
c.RegSize = 8
c.lowerBlock = rewriteBlockWasm
c.lowerValue = rewriteValueWasm
c.registers = registersWasm[:]
c.gpRegMask = gpRegMaskWasm
c.fpRegMask = fpRegMaskWasm
c.fp32RegMask = fp32RegMaskWasm
c.fp64RegMask = fp64RegMaskWasm
c.FPReg = framepointerRegWasm
c.LinkReg = linkRegWasm
c.hasGReg = true
c.noDuffDevice = true
c.useAvg = false
c.useHmul = false
default:
ctxt.Diag("arch %s not implemented", arch)
}
c.ctxt = ctxt
c.optimize = optimize
c.useSSE = true
c.UseFMA = true
c.SoftFloat = softfloat
if softfloat {
c.floatParamRegs = nil // no FP registers in softfloat mode
}
c.ABI0 = abi.NewABIConfig(0, 0, ctxt.Arch.FixedFrameSize, 0)
c.ABI1 = abi.NewABIConfig(len(c.intParamRegs), len(c.floatParamRegs), ctxt.Arch.FixedFrameSize, 1)
// On Plan 9, floating point operations are not allowed in note handler.
if buildcfg.GOOS == "plan9" {
// Don't use FMA on Plan 9
c.UseFMA = false
// Don't use Duff's device and SSE on Plan 9 AMD64.
if arch == "amd64" {
c.noDuffDevice = true
c.useSSE = false
}
}
if ctxt.Flag_shared {
// LoweredWB is secretly a CALL and CALLs on 386 in
// shared mode get rewritten by obj6.go to go through
// the GOT, which clobbers BX.
opcodeTable[Op386LoweredWB].reg.clobbers |= 1 << 3 // BX
}
// Create the GC register map index.
// TODO: This is only used for debug printing. Maybe export config.registers?
gcRegMapSize := int16(0)
for _, r := range c.registers {
if r.gcNum+1 > gcRegMapSize {
gcRegMapSize = r.gcNum + 1
}
}
c.GCRegMap = make([]*Register, gcRegMapSize)
for i, r := range c.registers {
if r.gcNum != -1 {
c.GCRegMap[r.gcNum] = &c.registers[i]
}
}
return c
}
func (c *Config) Ctxt() *obj.Link { return c.ctxt }
func (c *Config) haveByteSwap(size int64) bool {
switch size {
case 8:
return c.haveBswap64
case 4:
return c.haveBswap32
case 2:
return c.haveBswap16
default:
base.Fatalf("bad size %d\n", size)
return false
}
}