aboutsummaryrefslogtreecommitdiff
path: root/src/runtime
diff options
context:
space:
mode:
Diffstat (limited to 'src/runtime')
-rw-r--r--src/runtime/asm_amd64.s6
-rw-r--r--src/runtime/cpuflags.go3
-rw-r--r--src/runtime/cpuflags_amd64_test.go19
-rw-r--r--src/runtime/export_test.go2
-rw-r--r--src/runtime/mkpreempt.go2
-rw-r--r--src/runtime/os_darwin.go15
-rw-r--r--src/runtime/panic.go7
-rw-r--r--src/runtime/preempt_amd64.go16
-rw-r--r--src/runtime/preempt_amd64.s64
-rw-r--r--src/runtime/proc.go3
-rw-r--r--src/runtime/race_amd64.s3
-rw-r--r--src/runtime/sys_darwin_amd64.s3
-rw-r--r--src/runtime/sys_dragonfly_amd64.s3
-rw-r--r--src/runtime/sys_freebsd_amd64.s6
-rw-r--r--src/runtime/sys_linux_amd64.s6
-rw-r--r--src/runtime/sys_netbsd_amd64.s3
-rw-r--r--src/runtime/sys_openbsd_amd64.s3
-rw-r--r--src/runtime/sys_windows_amd64.s3
-rw-r--r--src/runtime/testdata/testprog/cpuflags_amd64.go18
-rw-r--r--src/runtime/testdata/testprog/cpuflags_amd64.s9
20 files changed, 173 insertions, 21 deletions
diff --git a/src/runtime/asm_amd64.s b/src/runtime/asm_amd64.s
index f4244f6e06..7c746803a8 100644
--- a/src/runtime/asm_amd64.s
+++ b/src/runtime/asm_amd64.s
@@ -1049,6 +1049,9 @@ needm:
// there's no need to handle that. Clear R14 so that there's
// a bad value in there, in case needm tries to use it.
XORPS X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
XORQ R14, R14
MOVQ $runtime·needAndBindM<ABIInternal>(SB), AX
CALL AX
@@ -1746,6 +1749,9 @@ TEXT ·sigpanic0(SB),NOSPLIT,$0-0
get_tls(R14)
MOVQ g(R14), R14
XORPS X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
JMP ·sigpanic<ABIInternal>(SB)
// gcWriteBarrier informs the GC about heap pointer writes.
diff --git a/src/runtime/cpuflags.go b/src/runtime/cpuflags.go
index 6452364b68..67ed081ef6 100644
--- a/src/runtime/cpuflags.go
+++ b/src/runtime/cpuflags.go
@@ -28,9 +28,10 @@ const (
var (
// Set in runtime.cpuinit.
// TODO: deprecate these; use internal/cpu directly.
+ x86HasAVX bool
+ x86HasFMA bool
x86HasPOPCNT bool
x86HasSSE41 bool
- x86HasFMA bool
armHasVFPv4 bool
diff --git a/src/runtime/cpuflags_amd64_test.go b/src/runtime/cpuflags_amd64_test.go
new file mode 100644
index 0000000000..f238e7fdf2
--- /dev/null
+++ b/src/runtime/cpuflags_amd64_test.go
@@ -0,0 +1,19 @@
+// Copyright 2025 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 runtime_test
+
+import (
+ "runtime"
+ "testing"
+)
+
+func TestHasAVX(t *testing.T) {
+ t.Parallel()
+ output := runTestProg(t, "testprog", "CheckAVX")
+ ok := output == "OK\n"
+ if *runtime.X86HasAVX != ok {
+ t.Fatalf("x86HasAVX: %v, CheckAVX got:\n%s", *runtime.X86HasAVX, output)
+ }
+}
diff --git a/src/runtime/export_test.go b/src/runtime/export_test.go
index 2db8add7e4..6e0360aaca 100644
--- a/src/runtime/export_test.go
+++ b/src/runtime/export_test.go
@@ -1978,6 +1978,8 @@ func TraceStack(gp *G, tab *TraceStackTable) {
traceStack(0, gp, (*traceStackTable)(tab))
}
+var X86HasAVX = &x86HasAVX
+
var DebugDecorateMappings = &debug.decoratemappings
func SetVMANameSupported() bool { return setVMANameSupported() }
diff --git a/src/runtime/mkpreempt.go b/src/runtime/mkpreempt.go
index dc951cd9a9..ca1c6e4a0e 100644
--- a/src/runtime/mkpreempt.go
+++ b/src/runtime/mkpreempt.go
@@ -402,7 +402,7 @@ func genAMD64(g *gen) {
// Create layouts for X, Y, and Z registers.
const (
numXRegs = 16
- numZRegs = 16 // TODO: If we start using upper registers, change to 32
+ numZRegs = 32
numKRegs = 8
)
lZRegs := layout{sp: xReg} // Non-GP registers
diff --git a/src/runtime/os_darwin.go b/src/runtime/os_darwin.go
index c908809c81..79cd2997c7 100644
--- a/src/runtime/os_darwin.go
+++ b/src/runtime/os_darwin.go
@@ -162,11 +162,22 @@ func sysctlbynameInt32(name []byte) (int32, int32) {
return ret, out
}
-//go:linkname internal_cpu_getsysctlbyname internal/cpu.getsysctlbyname
-func internal_cpu_getsysctlbyname(name []byte) (int32, int32) {
+func sysctlbynameBytes(name, out []byte) int32 {
+ nout := uintptr(len(out))
+ ret := sysctlbyname(&name[0], &out[0], &nout, nil, 0)
+ return ret
+}
+
+//go:linkname internal_cpu_sysctlbynameInt32 internal/cpu.sysctlbynameInt32
+func internal_cpu_sysctlbynameInt32(name []byte) (int32, int32) {
return sysctlbynameInt32(name)
}
+//go:linkname internal_cpu_sysctlbynameBytes internal/cpu.sysctlbynameBytes
+func internal_cpu_sysctlbynameBytes(name, out []byte) int32 {
+ return sysctlbynameBytes(name, out)
+}
+
const (
_CTL_HW = 6
_HW_NCPU = 3
diff --git a/src/runtime/panic.go b/src/runtime/panic.go
index 89b0614f67..d467e9305d 100644
--- a/src/runtime/panic.go
+++ b/src/runtime/panic.go
@@ -341,6 +341,13 @@ func panicmemAddr(addr uintptr) {
panic(errorAddressString{msg: "invalid memory address or nil pointer dereference", addr: addr})
}
+var simdImmError = error(errorString("out-of-range immediate for simd intrinsic"))
+
+func panicSimdImm() {
+ panicCheck2("simd immediate error")
+ panic(simdImmError)
+}
+
// Create a new deferred function fn, which has no arguments and results.
// The compiler turns a defer statement into a call to this.
func deferproc(fn func()) {
diff --git a/src/runtime/preempt_amd64.go b/src/runtime/preempt_amd64.go
index 88c0ddd34a..78dec40e1f 100644
--- a/src/runtime/preempt_amd64.go
+++ b/src/runtime/preempt_amd64.go
@@ -19,6 +19,22 @@ type xRegs struct {
Z13 [64]byte
Z14 [64]byte
Z15 [64]byte
+ Z16 [64]byte
+ Z17 [64]byte
+ Z18 [64]byte
+ Z19 [64]byte
+ Z20 [64]byte
+ Z21 [64]byte
+ Z22 [64]byte
+ Z23 [64]byte
+ Z24 [64]byte
+ Z25 [64]byte
+ Z26 [64]byte
+ Z27 [64]byte
+ Z28 [64]byte
+ Z29 [64]byte
+ Z30 [64]byte
+ Z31 [64]byte
K0 uint64
K1 uint64
K2 uint64
diff --git a/src/runtime/preempt_amd64.s b/src/runtime/preempt_amd64.s
index c35de7f3b7..a5b949a242 100644
--- a/src/runtime/preempt_amd64.s
+++ b/src/runtime/preempt_amd64.s
@@ -95,14 +95,30 @@ saveAVX512:
VMOVDQU64 Z13, 832(AX)
VMOVDQU64 Z14, 896(AX)
VMOVDQU64 Z15, 960(AX)
- KMOVQ K0, 1024(AX)
- KMOVQ K1, 1032(AX)
- KMOVQ K2, 1040(AX)
- KMOVQ K3, 1048(AX)
- KMOVQ K4, 1056(AX)
- KMOVQ K5, 1064(AX)
- KMOVQ K6, 1072(AX)
- KMOVQ K7, 1080(AX)
+ VMOVDQU64 Z16, 1024(AX)
+ VMOVDQU64 Z17, 1088(AX)
+ VMOVDQU64 Z18, 1152(AX)
+ VMOVDQU64 Z19, 1216(AX)
+ VMOVDQU64 Z20, 1280(AX)
+ VMOVDQU64 Z21, 1344(AX)
+ VMOVDQU64 Z22, 1408(AX)
+ VMOVDQU64 Z23, 1472(AX)
+ VMOVDQU64 Z24, 1536(AX)
+ VMOVDQU64 Z25, 1600(AX)
+ VMOVDQU64 Z26, 1664(AX)
+ VMOVDQU64 Z27, 1728(AX)
+ VMOVDQU64 Z28, 1792(AX)
+ VMOVDQU64 Z29, 1856(AX)
+ VMOVDQU64 Z30, 1920(AX)
+ VMOVDQU64 Z31, 1984(AX)
+ KMOVQ K0, 2048(AX)
+ KMOVQ K1, 2056(AX)
+ KMOVQ K2, 2064(AX)
+ KMOVQ K3, 2072(AX)
+ KMOVQ K4, 2080(AX)
+ KMOVQ K5, 2088(AX)
+ KMOVQ K6, 2096(AX)
+ KMOVQ K7, 2104(AX)
JMP preempt
preempt:
CALL ·asyncPreempt2(SB)
@@ -153,14 +169,30 @@ restoreAVX2:
VMOVDQU 0(AX), Y0
JMP restoreGPs
restoreAVX512:
- KMOVQ 1080(AX), K7
- KMOVQ 1072(AX), K6
- KMOVQ 1064(AX), K5
- KMOVQ 1056(AX), K4
- KMOVQ 1048(AX), K3
- KMOVQ 1040(AX), K2
- KMOVQ 1032(AX), K1
- KMOVQ 1024(AX), K0
+ KMOVQ 2104(AX), K7
+ KMOVQ 2096(AX), K6
+ KMOVQ 2088(AX), K5
+ KMOVQ 2080(AX), K4
+ KMOVQ 2072(AX), K3
+ KMOVQ 2064(AX), K2
+ KMOVQ 2056(AX), K1
+ KMOVQ 2048(AX), K0
+ VMOVDQU64 1984(AX), Z31
+ VMOVDQU64 1920(AX), Z30
+ VMOVDQU64 1856(AX), Z29
+ VMOVDQU64 1792(AX), Z28
+ VMOVDQU64 1728(AX), Z27
+ VMOVDQU64 1664(AX), Z26
+ VMOVDQU64 1600(AX), Z25
+ VMOVDQU64 1536(AX), Z24
+ VMOVDQU64 1472(AX), Z23
+ VMOVDQU64 1408(AX), Z22
+ VMOVDQU64 1344(AX), Z21
+ VMOVDQU64 1280(AX), Z20
+ VMOVDQU64 1216(AX), Z19
+ VMOVDQU64 1152(AX), Z18
+ VMOVDQU64 1088(AX), Z17
+ VMOVDQU64 1024(AX), Z16
VMOVDQU64 960(AX), Z15
VMOVDQU64 896(AX), Z14
VMOVDQU64 832(AX), Z13
diff --git a/src/runtime/proc.go b/src/runtime/proc.go
index 62e79e74e2..58fb4bd681 100644
--- a/src/runtime/proc.go
+++ b/src/runtime/proc.go
@@ -763,9 +763,10 @@ func cpuinit(env string) {
// to guard execution of instructions that can not be assumed to be always supported.
switch GOARCH {
case "386", "amd64":
+ x86HasAVX = cpu.X86.HasAVX
+ x86HasFMA = cpu.X86.HasFMA
x86HasPOPCNT = cpu.X86.HasPOPCNT
x86HasSSE41 = cpu.X86.HasSSE41
- x86HasFMA = cpu.X86.HasFMA
case "arm":
armHasVFPv4 = cpu.ARM.HasVFPv4
diff --git a/src/runtime/race_amd64.s b/src/runtime/race_amd64.s
index e19118bd54..23f2e59e3d 100644
--- a/src/runtime/race_amd64.s
+++ b/src/runtime/race_amd64.s
@@ -456,6 +456,9 @@ call:
// Back to Go world, set special registers.
// The g register (R14) is preserved in C.
XORPS X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
RET
// C->Go callback thunk that allows to call runtime·racesymbolize from C code.
diff --git a/src/runtime/sys_darwin_amd64.s b/src/runtime/sys_darwin_amd64.s
index 99d67a9cfd..e4e1216d56 100644
--- a/src/runtime/sys_darwin_amd64.s
+++ b/src/runtime/sys_darwin_amd64.s
@@ -177,6 +177,9 @@ TEXT runtime·sigtramp(SB),NOSPLIT|TOPFRAME|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
diff --git a/src/runtime/sys_dragonfly_amd64.s b/src/runtime/sys_dragonfly_amd64.s
index a223c2cf76..84bf326aad 100644
--- a/src/runtime/sys_dragonfly_amd64.s
+++ b/src/runtime/sys_dragonfly_amd64.s
@@ -228,6 +228,9 @@ TEXT runtime·sigtramp(SB),NOSPLIT|TOPFRAME|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
diff --git a/src/runtime/sys_freebsd_amd64.s b/src/runtime/sys_freebsd_amd64.s
index 977ea093d2..a1fa3a6fa2 100644
--- a/src/runtime/sys_freebsd_amd64.s
+++ b/src/runtime/sys_freebsd_amd64.s
@@ -265,6 +265,9 @@ TEXT runtime·sigtramp(SB),NOSPLIT|TOPFRAME|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
@@ -290,6 +293,9 @@ TEXT runtime·sigprofNonGoWrapper<>(SB),NOSPLIT|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
diff --git a/src/runtime/sys_linux_amd64.s b/src/runtime/sys_linux_amd64.s
index 941f70b0e8..02505c2fb0 100644
--- a/src/runtime/sys_linux_amd64.s
+++ b/src/runtime/sys_linux_amd64.s
@@ -340,6 +340,9 @@ TEXT runtime·sigtramp(SB),NOSPLIT|TOPFRAME|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
@@ -365,6 +368,9 @@ TEXT runtime·sigprofNonGoWrapper<>(SB),NOSPLIT|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
diff --git a/src/runtime/sys_netbsd_amd64.s b/src/runtime/sys_netbsd_amd64.s
index 2f1ddcdc89..edc7f3d6ee 100644
--- a/src/runtime/sys_netbsd_amd64.s
+++ b/src/runtime/sys_netbsd_amd64.s
@@ -310,6 +310,9 @@ TEXT runtime·sigtramp(SB),NOSPLIT|TOPFRAME|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
diff --git a/src/runtime/sys_openbsd_amd64.s b/src/runtime/sys_openbsd_amd64.s
index ff0bc2416a..734dfe6478 100644
--- a/src/runtime/sys_openbsd_amd64.s
+++ b/src/runtime/sys_openbsd_amd64.s
@@ -64,6 +64,9 @@ TEXT runtime·sigtramp(SB),NOSPLIT|TOPFRAME|NOFRAME,$0
get_tls(R12)
MOVQ g(R12), R14
PXOR X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
// Reserve space for spill slots.
NOP SP // disable vet stack checking
diff --git a/src/runtime/sys_windows_amd64.s b/src/runtime/sys_windows_amd64.s
index e438599910..b0b4d3cce6 100644
--- a/src/runtime/sys_windows_amd64.s
+++ b/src/runtime/sys_windows_amd64.s
@@ -32,6 +32,9 @@ TEXT sigtramp<>(SB),NOSPLIT,$0-0
// R14 is cleared in case there's a non-zero value in there
// if called from a non-go thread.
XORPS X15, X15
+ CMPB internal∕cpu·X86+const_offsetX86HasAVX(SB), $1
+ JNE 2(PC)
+ VXORPS X15, X15, X15
XORQ R14, R14
get_tls(AX)
diff --git a/src/runtime/testdata/testprog/cpuflags_amd64.go b/src/runtime/testdata/testprog/cpuflags_amd64.go
new file mode 100644
index 0000000000..d53eacbe99
--- /dev/null
+++ b/src/runtime/testdata/testprog/cpuflags_amd64.go
@@ -0,0 +1,18 @@
+// Copyright 2025 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 main
+
+import "fmt"
+
+func init() {
+ register("CheckAVX", CheckAVX)
+}
+
+func CheckAVX() {
+ checkAVX()
+ fmt.Println("OK")
+}
+
+func checkAVX()
diff --git a/src/runtime/testdata/testprog/cpuflags_amd64.s b/src/runtime/testdata/testprog/cpuflags_amd64.s
new file mode 100644
index 0000000000..1610c5729a
--- /dev/null
+++ b/src/runtime/testdata/testprog/cpuflags_amd64.s
@@ -0,0 +1,9 @@
+// Copyright 2025 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.
+
+#include "textflag.h"
+
+TEXT ·checkAVX(SB), NOSPLIT|NOFRAME, $0-0
+ VXORPS X1, X2, X3
+ RET
generated by cgit v1.3 (git 2.53.0) at 2026-04-16 01:27:47 +0000