Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix #1111. #1112

Closed
wants to merge 2 commits into from
Closed

Fix #1111. #1112

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cdb2aab
Fix #1111.
ncruces Feb 9, 2023
4662e1e
Use another CPUID lib.
ncruces Feb 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions go.mod
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,3 +11,5 @@ retract (
v1.0.0-beta.2
v1.0.0-beta.1
)

require github.com/zcalusic/sysinfo v0.9.5
2 changes: 2 additions & 0 deletions go.sum
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
github.com/zcalusic/sysinfo v0.9.5 h1:ivoHyj9aIAYkwzo1+8QgJ5s4oeE6Etx9FmZtqa4wJjQ=
github.com/zcalusic/sysinfo v0.9.5/go.mod h1:Z/gPVufBrFc8X5sef3m6kkw3r3nlNFp+I6bvASfvBZQ=
19 changes: 16 additions & 3 deletions internal/engine/compiler/impl_amd64.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,8 @@ import (
"bytes"
"fmt"
"math"
"runtime"

"github.com/zcalusic/sysinfo/cpuid"

"github.com/tetratelabs/wazero/internal/asm"
"github.com/tetratelabs/wazero/internal/asm/amd64"
Expand Down Expand Up @@ -1151,14 +1152,26 @@ func (c *amd64Compiler) compileMulForFloats(instruction asm.Instruction) error {
return nil
}

func hasLZCNT() bool {
// https://www.amd.com/system/files/TechDocs/25481.pdf
const (
Fn8000_0001 = 0x8000_0001
ABM = 0x0400_0000 // ABM is the 5th bit, from the left, zero based, EDX register
EDX = 3
)
var out [4]uint32
cpuid.CPUID(&out, Fn8000_0001)
return out[EDX]&ABM != 0
}

// compileClz implements compiler.compileClz for the amd64 architecture.
func (c *amd64Compiler) compileClz(o *wazeroir.OperationClz) error {
target := c.locationStack.pop()
if err := c.compileEnsureOnRegister(target); err != nil {
return err
}

if runtime.GOOS != "darwin" && runtime.GOOS != "freebsd" {
if hasLZCNT() {
if o.Type == wazeroir.UnsignedInt32 {
c.assembler.CompileRegisterToRegister(amd64.LZCNTL, target.register, target.register)
} else {
Expand Down Expand Up @@ -1221,7 +1234,7 @@ func (c *amd64Compiler) compileCtz(o *wazeroir.OperationCtz) error {
return err
}

if runtime.GOOS != "darwin" && runtime.GOOS != "freebsd" {
if hasLZCNT() {
if o.Type == wazeroir.UnsignedInt32 {
c.assembler.CompileRegisterToRegister(amd64.TZCNTL, target.register, target.register)
} else {
Expand Down