aboutsummaryrefslogtreecommitdiff
path: root/src/internal/cpu/cpu_x86.go
AgeCommit message (Collapse)Author
2026-01-28cmd/compile, simd: capture VAES instructions and fix AVX512VAES featureJunyang Shao
The code previously filters out VAES-only instructions, this CL added them back. This CL added the VAES feature check following the Intel xed data: XED_ISA_SET_VAES: vaes.7.0.ecx.9 # avx.1.0.ecx.28 This CL also found out that the old AVX512VAES feature check is not checking the correct bits, it also fixes it: XED_ISA_SET_AVX512_VAES_128: vaes.7.0.ecx.9 aes.1.0.ecx.25 avx512f.7.0.ebx.16 avx512vl.7.0.ebx.31 XED_ISA_SET_AVX512_VAES_256: vaes.7.0.ecx.9 aes.1.0.ecx.25 avx512f.7.0.ebx.16 avx512vl.7.0.ebx.31 XED_ISA_SET_AVX512_VAES_512: vaes.7.0.ecx.9 aes.1.0.ecx.25 avx512f.7.0.ebx.16 It restricts to the most strict common set - includes avx512vl for even 512-bits although it doesn't requires it. Change-Id: I4e2f72b312fd2411589fbc12f9ee5c63c09c2e9a Reviewed-on: https://go-review.googlesource.com/c/go/+/738500 Reviewed-by: Cherry Mui <cherryyz@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
2026-01-13simd/archsimd: 128- and 256-bit FMA operations do not require AVX-512Austin Clements
Currently, all FMA operations are marked as requiring AVX512, even on smaller vector widths. This is happening because the narrower FMA operations are marked as extension "FMA" in the XED. Since this extension doesn't start with "AVX", we filter them out very early in the XED process. However, this is just a quirk of naming: the FMA feature depends on the AVX feature, so it is part of AVX, even if it doesn't say so on the tin. Fix this by accepting the FMA extension and adding FMA to the table of CPU features. We also tweak internal/cpu slightly do it correctly enforces that the logical FMA feature depends on both the FMA and AVX CPUID flags. This actually *deletes* a lot of generated code because we no longer need the AVX-512 encoding of these 128- and 256-bit operations. Change-Id: I744a18d0be888f536ac034fe88b110347622be7e Reviewed-on: https://go-review.googlesource.com/c/go/+/736160 Auto-Submit: Austin Clements <austin@google.com> Reviewed-by: Junyang Shao <shaojunyang@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-on: https://go-review.googlesource.com/c/go/+/736201 Reviewed-by: Austin Clements <austin@google.com>
2025-12-18internal/cpu: repair VNNI feature checkDavid Chase
This is a pain to test. Also the original test was never executed, because it was wrong. It looks like processors that might lack this features include Intel 11th generation and AMD Zen 4. These might or might not have bit 2 set in the 7th cpuid "leaf" (SM4) which is what the incorrect test was checking; the bug is triggered by ^VNNI & SM4. Apparently the SM4 bit is not usually set, else we would have seen a test failure. The "Lion Cove" microarchitecture (Arrow Lake, Lunar Lake) appears to trigger this problem, it's not clear if there are others. It was hard to verify this from online information. Fixes #76881. Change-Id: I21be6b4f47134d81e89799b0f06f89fcb6563264 Reviewed-on: https://go-review.googlesource.com/c/go/+/731240 TryBot-Bypass: David Chase <drchase@google.com> Reviewed-by: Cherry Mui <cherryyz@google.com>
2025-09-30[dev.simd] cmd/compile, simd: add AES instructionsJunyang Shao
AVXAES is a composite feature set, Intel did listed it as "AVXAES" in the XED data instead of separating them. The tests will be in the next CL. Change-Id: I89c97261f2228b2fdafb48f63e82ef6239bdd5ca Reviewed-on: https://go-review.googlesource.com/c/go/+/706055 LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: David Chase <drchase@google.com>
2025-09-02[dev.simd] internal/cpu: report AVX1 and 2 as supported on macOS 15 Rosetta 2Cherry Mui
Apparently, on macOS 15 or newer, Rosetta 2 supports AVX1 and 2. However, neither CPUID nor the Apple-recommended sysctl says it has AVX. If AVX is used without checking the CPU feature, it may run fine without SIGILL, but the runtime doesn't know AVX is available therefore save and restore its states. This may lead to value corruption. Check if we are running under Rosetta 2 on macOS 15 or newer. If so, report AVX1 and 2 as supported. Change-Id: Ib981379405b1ae28faa378f051096827d760a4cc Reviewed-on: https://go-review.googlesource.com/c/go/+/700055 Reviewed-by: David Chase <drchase@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Junyang Shao <shaojunyang@google.com>
2025-08-14[dev.simd] all: merge master (924fe98) into dev.simdCherry Mui
Conflicts: - src/cmd/compile/internal/amd64/ssa.go - src/cmd/compile/internal/ssa/expand_calls.go - src/cmd/compile/internal/ssagen/ssa.go - src/internal/buildcfg/exp.go - src/internal/cpu/cpu.go - src/internal/cpu/cpu_x86.go - src/runtime/mkpreempt.go - src/runtime/preempt_amd64.go - src/runtime/preempt_amd64.s Merge List: + 2025-08-14 924fe98902 cmd/internal/obj/riscv: add encoding for compressed riscv64 instructions + 2025-08-13 320df537cc cmd/compile: emit classify instructions for infinity tests on riscv64 + 2025-08-13 ca66f907dd cmd/compile: use generated loops instead of DUFFCOPY on amd64 + 2025-08-13 4b1800e476 encoding/json/v2: cleanup error constructors + 2025-08-13 af8870708b encoding/json/v2: fix incorrect marshaling of NaN in float64 any + 2025-08-13 0a75e5a07b encoding/json/v2: fix wrong type with cyclic marshal error in map[string]any + 2025-08-13 de9b6f9875 cmd/pprof: update vendored github.com/google/pprof + 2025-08-13 674c5f0edd os/exec: fix incorrect expansion of ".." in LookPath on plan9 + 2025-08-13 9bbea0f21a cmd/compile: during regalloc, fixedreg values are always available + 2025-08-13 08eef97500 runtime/trace: fix documentation typo + 2025-08-13 2fe5d51d04 internal/trace: fix wrong scope for Event.Range or EvGCSweepActive + 2025-08-13 9fcb87c352 cmd/compile: teach prove about len's & cap's max based on the element size + 2025-08-13 9763ece873 cmd/compile: absorb NEGV into branch on loong64 + 2025-08-13 f10a82b76f all: update vendored dependencies [generated] + 2025-08-13 3bea95b277 cmd/link/internal/ld: remove OpenBSD buildid workaround + 2025-08-12 90b7d7aaa2 cmd/compile/internal: optimize multiplication use new operation 'ADDshiftLLV' on loong64 + 2025-08-12 1b263fc604 runtime/race: restore previous version of LLVM TSAN on macOS + 2025-08-12 b266318cf7 cmd/compile/internal/ssa: use BEQ/BNE to optimize the combination of XOR and EQ/NE on loong64 + 2025-08-12 adbf59525c internal/runtime/gc/scan: avoid -1 index when cache sizes unavailable + 2025-08-12 4e182db5fc Revert "cmd/compile: use generated loops instead of DUFFCOPY on amd64" + 2025-08-12 d2b3c1a504 internal/trace: clarify which StateTransition events have stacks + 2025-08-12 f63e12d0e0 internal/trace: fix Sync.ClockSnapshot comment + 2025-08-12 8e317da77d internal/trace: remove unused StateTransition.id field + 2025-08-12 f67d8ff34a internal/trace/tracev2: adjust comment for consistency + 2025-08-12 fe4d445c36 internal/trace/tracev2: fix EvSTWBegin comment to include stack ID + 2025-08-12 750789fab7 internal/trace/internal/testgen: fix missing stacks nframes arg + 2025-08-12 889ab74169 internal/runtime/gc/scan: import scan kernel from gclab [green tea] + 2025-08-12 182336bf05 net/http: fix data race in client + 2025-08-12 f04421ea9a cmd/compile: soften test for 74788 + 2025-08-12 28aa529c99 cmd/compile: use generated loops instead of DUFFZERO on arm64 + 2025-08-12 ec9e1176c3 cmd/compile: use generated loops instead of DUFFCOPY on amd64 + 2025-08-12 d0a64f7969 Revert "cmd/compile/internal/ssa: Use transitive properties for len/cap" + 2025-08-12 00a7bdcb55 all: delete aliastypeparams GOEXPERIMENT + 2025-08-11 74421a305b Revert "cmd/compile: allow multi-field structs to be stored directly in interfaces" + 2025-08-11 c31359138c Revert "cmd/compile: allow StructSelect [x] of interface data fields for x>0" + 2025-08-11 7248995b60 Revert "cmd/compile: allow more args in StructMake folding rule" + 2025-08-11 caf9fc3ccd Revert "reflect: handle zero-sized fields of directly-stored structures correctly" + 2025-08-11 ce3f3e2ae7 cmd/link/internal/ld, internal/syscall/unix: use posix_fallocate on netbsd + 2025-08-11 3dbef65bf3 database/sql: allow drivers to override Scan behavior + 2025-08-11 2b804abf07 net: context aware Dialer.Dial functions + 2025-08-11 6abfe7b0de cmd/dist: require Go 1.24.6 as minimum bootstrap toolchain + 2025-08-11 691af6ca28 encoding/json: fix Indent trailing whitespace regression in goexperiment.jsonv2 + 2025-08-11 925149da20 net/http: add example for CrossOriginProtection + 2025-08-11 cf4af0b2f3 encoding/json/v2: fix UnmarshalDecode regression with EOF + 2025-08-11 b096ddb9ea internal/runtime/maps: loop invariant code motion with h2(hash) by hand + 2025-08-11 a2431776eb net, os, file/filepath, syscall: use slices.Equal in tests + 2025-08-11 a7f05b38f7 cmd/compile: convert branch with zero to more optimal branch zero on loong64 + 2025-08-11 1718828c81 internal/sync: warn about incorrect unsafe usage in HashTrieMap + 2025-08-11 084c0f8494 cmd/compile: allow InlMark operations to be speculatively executed + 2025-08-10 a62f72f7a7 cmd/compile/internal/ssa: optimise more branches with SGTconst/SGTUconst on loong64 + 2025-08-08 fbac94a799 internal/sync: rename Store parameter from old to new + 2025-08-08 317be4cfeb cmd/compile/internal/staticinit: remove deadcode + 2025-08-08 bce5601cbb cmd/go: fix fips doc link + 2025-08-08 777d76c4f2 text/template: use sync.OnceValue for builtinFuncs + 2025-08-08 0201524c52 math: remove redundant infinity tests + 2025-08-08 dcc77f9e3c cmd/go: fix get -tool when multiple packages are provided + 2025-08-08 c7b85e9ddc all: update blog link + 2025-08-08 a8dd771e13 crypto/tls: check if quic conn can send session ticket + 2025-08-08 bdb2d50fdf net: fix WriteMsgUDPAddrPort addr handling on IPv4 sockets + 2025-08-08 768c51e368 internal/runtime/maps: remove unused var bitsetDeleted + 2025-08-08 b3388569a1 reflect: handle zero-sized fields of directly-stored structures correctly + 2025-08-08 d83b16fcb8 internal/bytealg: vector implementation of compare for riscv64 + 2025-08-07 dd3abf6bc5 internal/bytealg: optimize Index/IndexString on loong64 + 2025-08-07 73ff6d1480 cmd/internal/obj/loong64: change the immediate range of ALSL{W/WU/V} + 2025-08-07 f3606b0825 cmd/compile/internal/ssa: fix typo in LOONG64Ops.go comment + 2025-08-07 ee7bb8969a cmd/internal/obj/loong64: add support for FSEL instruction + 2025-08-07 1f7ffca171 time: skip TestLongAdjustTimers on plan9 (too slow) + 2025-08-06 8282b72d62 runtime/race: update darwin race syso + 2025-08-06 dc54d7b607 all: remove support for windows/arm + 2025-08-06 e0a1ea431c cmd/compile: make panicBounds stack frame smaller on ppc64 + 2025-08-06 2747f925dd debug/macho: support reading imported symbols without LC_DYSYMTAB + 2025-08-06 025d36917c cmd/internal/testdir: pass -buildid to link command + 2025-08-06 f53dcb6280 cmd/internal/testdir: unify link command + 2025-08-06 a3895fe9f1 database/sql: avoid closing Rows while scan is in progress + 2025-08-06 608e9fac90 go/types, types2: flip on position tracing + 2025-08-06 72e8237cc1 cmd/compile: allow more args in StructMake folding rule + 2025-08-06 3406a617d9 internal/bytealg: vector implementation of indexbyte for riscv64 + 2025-08-06 75ea2d05c0 internal/bytealg: vector implementation of equal for riscv64 + 2025-08-05 17a8be7117 crypto/sha512: use const table for key loading on loong64 + 2025-08-05 dda9d780e2 crypto/sha256: use const table for key loading on loong64 + 2025-08-05 5defe8ebb3 internal/chacha8rand: replace WORD with instruction VMOVQ + 2025-08-05 4c7362e41c cmd/internal/obj/loong64: add new instructions ALSL{W/WU/V} for loong64 + 2025-08-05 a552737418 cmd/compile: fold negation into multiplication on loong64 + 2025-08-05 e1fd4faf91 runtime: fix godoc comment for inVDSOPage + 2025-08-05 bcd25c79aa cmd/compile: allow StructSelect [x] of interface data fields for x>0 + 2025-08-05 b0945a54b5 cmd/dist, internal/platform: mark freebsd/riscv64 broken + 2025-08-05 55d961b202 runtime: save AVX2 and AVX-512 state on asynchronous preemption + 2025-08-05 af0c4fe2ca runtime: save scalar registers off stack in amd64 async preemption + 2025-08-05 e73afaae69 internal/cpu: add AVX-512-CD and DQ, and derived "basic AVX-512" + 2025-08-05 cef381ba60 runtime: eliminate global state in mkpreempt.go + 2025-08-05 c0025d5e0b go/parser: correct comment in expectedErrors + 2025-08-05 4ee0df8c46 cmd: remove dead code + 2025-08-05 a2c45f0eb1 runtime: test VDSO symbol hash values + 2025-08-05 cd55f86b8d cmd/compile: allow multi-field structs to be stored directly in interfaces + 2025-08-05 21ab0128b6 cmd/compile: remove support for old-style bounds check calls + 2025-08-05 802d056c78 cmd/compile: move ppc64 over to new bounds check strategy + 2025-08-05 a3295df873 cmd/compile/internal/ssa: Use transitive properties for len/cap + 2025-08-05 bd082857a5 doc: fix typo in go memory model doc + 2025-08-05 2b622b05a9 cmd/compile: remove isUintXPowerOfTwo functions + 2025-08-05 72147ffa75 cmd/compile: simplify isUintXPowerOfTwo implementation + 2025-08-05 26da1199eb cmd/compile: make isUint{32,64}PowerOfTwo implementations clearer + 2025-08-05 5ab9f23977 cmd/compile, runtime: add checkptr instrumentation for unsafe.Add + 2025-08-05 fcc036f03b cmd/compile: optimise float <-> int register moves on riscv64 Change-Id: Ie94f29d9b0cc14a52a536866f5abaef27b5c52d7
2025-08-12internal/runtime/gc/scan: import scan kernel from gclab [green tea]Michael Anthony Knyszek
This change imports the AVX512 GC scanning kernel from CL 593938 into a new package, internal/runtime/gc/scan. Credit to Austin Clements for most of this work. I did some cleanup, added support for more size classes to the expanders, and added more testing. I also restructured the code to make it easier and clearer to add new scan kernels for new architectures. For #73581. Change-Id: I76bcbc889fa6cad73ba0084620fae084a5912e6b Cq-Include-Trybots: luci.golang.try:gotip-linux-amd64_avx512,gotip-linux-amd64_avx512-greenteagc Reviewed-on: https://go-review.googlesource.com/c/go/+/655280 LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Auto-Submit: Michael Knyszek <mknyszek@google.com> Reviewed-by: Michael Pratt <mpratt@google.com>
2025-08-05internal/cpu: add AVX-512-CD and DQ, and derived "basic AVX-512"Austin Clements
This adds detection for the CD and DQ sub-features of x86 AVX-512. Building on these, we also add a "derived" AVX-512 feature that bundles together the basic usable subset of subfeatures. Despite the F in AVX-512-F standing for "foundation", AVX-512-F+BW+DQ+VL together really form the basic usable subset of AVX-512 functionality. These have also all been supported together by almost every CPU, and are guaranteed by GOAMD64=v4, so there's little point in separating them out. This is a cherry-pick of CL 680899 from the dev.simd branch. Change-Id: I34356502bd1853ba2372e48db0b10d55cffe07a1 Reviewed-on: https://go-review.googlesource.com/c/go/+/693396 Reviewed-by: Cherry Mui <cherryyz@google.com> Auto-Submit: Austin Clements <austin@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
2025-08-04[dev.simd] all: merge master (7a1679d) into dev.simdCherry Mui
Conflicts: - src/cmd/compile/internal/amd64/ssa.go - src/cmd/compile/internal/ssa/rewriteAMD64.go - src/internal/buildcfg/exp.go - src/internal/cpu/cpu.go - src/internal/cpu/cpu_x86.go - src/internal/goexperiment/flags.go Merge List: + 2025-08-04 7a1679d7ae cmd/compile: move s390x over to new bounds check strategy + 2025-08-04 95693816a5 cmd/compile: move riscv64 over to new bounds check strategy + 2025-08-04 d7bd7773eb go/parser: remove safePos + 2025-08-04 4b6cbc377f cmd/cgo/internal/test: use (syntactic) constant for C array bound + 2025-08-03 b2960e3580 cmd/internal/obj/loong64: add {V,XV}{BITCLR/BITSET/BITREV}[I].{B/H/W/D} instructions support + 2025-08-03 abeeef1c08 cmd/compile/internal/test: fix typo in comments + 2025-08-03 d44749b65b cmd/internal/obj/loong64: add [X]VLDREPL.{B/H/W/D} instructions support + 2025-08-03 d6beda863e runtime: add reference to debugPinnerV1 + 2025-08-01 4ab1aec007 cmd/go: modload should use a read-write lock to improve concurrency + 2025-08-01 e666972a67 runtime: deduplicate Windows stdcall + 2025-08-01 ef40549786 runtime,syscall: move loadlibrary and getprocaddress to syscall + 2025-08-01 336931a4ca cmd/go: use os.Rename to move files on Windows + 2025-08-01 eef5f8d930 cmd/compile: enforce that locals are always accessed with SP base register + 2025-08-01 e071617222 cmd/compile: optimize multiplication rules on loong64 + 2025-07-31 eb7f515c4d cmd/compile: use generated loops instead of DUFFZERO on amd64 + 2025-07-31 c0ee2fd4e3 cmd/go: explicitly reject module paths "go" and "toolchain" + 2025-07-30 a4d99770c0 runtime/metrics: add cleanup and finalizer queue metrics + 2025-07-30 70a2ff7648 runtime: add cgo call benchmark + 2025-07-30 69338a335a cmd/go/internal/gover: fix ModIsPrerelease for toolchain versions + 2025-07-30 cedf63616a cmd/compile: add floating point min/max intrinsics on s390x + 2025-07-30 82a1921c3b all: remove redundant Swiss prefixes + 2025-07-30 2ae059ccaf all: remove GOEXPERIMENT=swissmap + 2025-07-30 cc571dab91 cmd/compile: deduplicate instructions when rewrite func results + 2025-07-30 2174a7936c crypto/tls: use standard chacha20-poly1305 cipher suite names + 2025-07-30 8330fb48a6 cmd/compile: move mips32 over to new bounds check strategy + 2025-07-30 9f9d7b50e8 cmd/compile: move mips64 over to new bounds check strategy + 2025-07-30 5216fd570e cmd/compile: move loong64 over to new bounds check strategy + 2025-07-30 89a0af86b8 cmd/compile: allow ops to specify clobbering input registers + 2025-07-30 5e94d72158 cmd/compile: simplify zerorange on arm64 + 2025-07-30 8cd85e602a cmd/compile: check domination of loop return in both controls + 2025-07-30 cefaed0de0 reflect: fix noswiss builder + 2025-07-30 3aa1b00081 regexp: fix compiling alternate patterns of different fold case literals + 2025-07-30 b1e933d955 cmd/compile: avoid extending when already sufficiently masked on loong64 + 2025-07-29 880ca333d7 cmd/compile: removing log2uint32 function + 2025-07-29 1513661dc3 cmd/compile: simplify logX implementations + 2025-07-29 bd94ae8903 cmd/compile: use unsigned power-of-two detector for unsigned mod + 2025-07-29 f3582fc80e cmd/compile: add unsigned power-of-two detector + 2025-07-29 f7d167fe71 internal/abi: move direct/indirect flag from Kind to TFlag + 2025-07-29 e0b07dc22e os/exec: fix incorrect expansion of "", "." and ".." in LookPath + 2025-07-29 25816d401c internal/goexperiment: delete RangeFunc goexperiment + 2025-07-29 7961bf71f8 internal/goexperiment: delete CacheProg goexperiment + 2025-07-29 e15a14c4dd sync: remove synchashtriemap GOEXPERIMENT + 2025-07-29 7dccd6395c cmd/compile: move arm32 over to new bounds check strategy + 2025-07-29 d79405a344 runtime: only deduct assist credit for arenas during GC + 2025-07-29 19a086f716 cmd/go/internal/telemetrystats: count goexperiments + 2025-07-29 aa95ab8215 image: fix formatting of godoc link + 2025-07-29 4c854b7a3e crypto/elliptic: change a variable name that have the same name as keywords + 2025-07-28 b10eb1d042 cmd/compile: simplify zerorange on amd64 + 2025-07-28 f8eae7a3c3 os/user: fix tests to pass on non-english Windows + 2025-07-28 0984264471 internal/poll: remove msg field from Windows' poll.operation + 2025-07-28 d7b4114346 internal/poll: remove rsan field from Windows' poll.operation + 2025-07-28 361b1ab41f internal/poll: remove sa field from Windows' poll.operation + 2025-07-28 9b6bd64e46 internal/poll: remove qty and flags fields from Windows' poll.operation + 2025-07-28 cd3655a824 internal/runtime/maps: fix spelling errors in comments + 2025-07-28 d5dc36af45 runtime: remove openbsd/mips64 related code + 2025-07-28 64ba72474d errors: omit redundant nil check in type assertion for Join + 2025-07-28 e151db3e06 all: omit unnecessary type conversions + 2025-07-28 4569255f8c cmd/compile: cleanup SelectN rules by indexing into args + 2025-07-28 94645d2413 cmd/compile: rewrite cmov(x, x, cond) into x + 2025-07-28 10c5cf68d4 net/http: add proper panic message + 2025-07-28 46b5839231 test/codegen: fix failing condmove wasm tests + 2025-07-28 98f301cf68 runtime,syscall: move SyscallX implementations from runtime to syscall + 2025-07-28 c7ed3a1c5a internal/runtime/syscall/windows: factor out code from runtime + 2025-07-28 e81eac19d3 hash/crc32: fix incorrect checksums with avx512+race + 2025-07-25 6fbad4be75 cmd/compile: remove no-longer-necessary call to calculateDepths + 2025-07-25 5045fdd8ff cmd/compile: fix containsUnavoidableCall computation + 2025-07-25 d28b27cd8e go/types, types2: use nil to represent incomplete explicit aliases + 2025-07-25 7b53d8d06e cmd/compile/internal/types2: add loaded state between loader calls and constraint expansion + 2025-07-25 374e3be2eb os/user: user random name for the test user account + 2025-07-25 1aa154621d runtime: rename scanobject to scanObject + 2025-07-25 41b429881a runtime: duplicate scanobject in greentea and non-greentea files + 2025-07-25 aeb256e98a cmd/compile: remove unused arg from gorecover + 2025-07-25 08376e1a9c runtime: iterate through inlinings when processing recover() + 2025-07-25 c76c3abc54 encoding/json: fix truncated Token error regression in goexperiment.jsonv2 + 2025-07-25 ebdbfccd98 encoding/json/jsontext: preserve buffer capacity in Encoder.Reset + 2025-07-25 91c4f0ccd5 reflect: avoid a bounds check in stack-constrained code + 2025-07-24 3636ced112 encoding/json: fix extra data regression under goexperiment.jsonv2 + 2025-07-24 a6eec8bdc7 encoding/json: reduce error text regressions under goexperiment.jsonv2 + 2025-07-24 0fa88dec1e time: remove redundant uint32 conversion in split + 2025-07-24 ada30b8248 internal/buildcfg: add ability to get GORISCV64 variable in GOGOARCH + 2025-07-24 6f6c6c5782 cmd/internal/obj: rip out argp adjustment for wrapper frames + 2025-07-24 7b50024330 runtime: detect successful recovers differently + 2025-07-24 7b9de668bd unicode/utf8: skip ahead during ascii runs in Valid/ValidString + 2025-07-24 076eae436e cmd/compile: move amd64 and 386 over to new bounds check strategy + 2025-07-24 f703dc5bef cmd/compile: add missing StringLen rule in prove + 2025-07-24 394d0bee8d cmd/compile: move arm64 over to new bounds check strategy + 2025-07-24 3024785b92 cmd/compile,runtime: remember idx+len for bounds check failure with less code + 2025-07-24 741a19ab41 runtime: move bounds check constants to internal/abi + 2025-07-24 ce05ad448f cmd/compile: rewrite condselects into doublings and halvings + 2025-07-24 fcd28070fe cmd/compile: add opt branchelim to rewrite some CondSelect into math + 2025-07-24 f32cf8e4b0 cmd/compile: learn transitive proofs for safe unsigned subs + 2025-07-24 d574856482 cmd/compile: learn transitive proofs for safe negative signed adds + 2025-07-24 1a72920f09 cmd/compile: learn transitive proofs for safe positive signed adds + 2025-07-24 e5f202bb60 cmd/compile: learn transitive proofs for safe unsigned adds + 2025-07-24 bd80f74bc1 cmd/compile: fold shift through AND for slice operations + 2025-07-24 5c45fe1385 internal/runtime/syscall: rename to internal/runtime/syscall/linux + 2025-07-24 592c2db868 cmd/compile: improve loopRotate to handle nested loops + 2025-07-24 dcb479c2f9 cmd/compile: optimize slice bounds checking with SUB/SUBconst comparisons + 2025-07-24 f11599b0b9 internal/poll: remove handle field from Windows' poll.operation + 2025-07-24 f7432e0230 internal/poll: remove fd field from Windows' poll.operation + 2025-07-24 e84ed38641 runtime: add benchmark for small-size memmory operation + 2025-07-24 18dbe5b941 hash/crc32: add AVX512 IEEE CRC32 calculation + 2025-07-24 c641900f72 cmd/compile: prefer base.Fatalf to panic in dwarfgen + 2025-07-24 d71d8aeafd cmd/internal/obj/s390x: add MVCLE instruction + 2025-07-24 b6cf1d94dc runtime: optimize memclr on mips64x + 2025-07-24 a8edd99479 runtime: improvement in memclr for s390x + 2025-07-24 bd04f65511 internal/runtime/exithook: fix a typo + 2025-07-24 5c8624a396 cmd/internal/goobj: make error output clear + 2025-07-24 44d73dfb4e cmd/go/internal/doc: clean up after merge with cmd/internal/doc + 2025-07-24 bd446662dd cmd/internal/doc: merge with cmd/go/internal/doc + 2025-07-24 da8b50c830 cmd/doc: delete + 2025-07-24 6669aa3b14 runtime: randomize heap base address + 2025-07-24 26338a7f69 cmd/compile: use better fatal message for staticValue1 + 2025-07-24 8587ba272e cmd/cgo: compare malloc return value to NULL instead of literal 0 + 2025-07-24 cae45167b7 go/types, types2: better error messages for certain type mismatches + 2025-07-24 2ddf542e4c cmd/compile: use ,ok return idiom for sparsemap.get + 2025-07-24 6505fcbd0a cmd/compile: use generics for sparse map + 2025-07-24 14f5eb7812 cmd/api: rerun updategolden + 2025-07-24 52b6d7f67a runtime: drop NetBSD kernel bug sysmon workaround fixed in NetBSD 9.2 + 2025-07-24 1ebebf1cc1 cmd/go: clean should respect workspaces + 2025-07-24 6536a93547 encoding/json/jsontext: preserve buffer capacity in Decoder.Reset + 2025-07-24 efc37e97c0 cmd/go: always return the cached path from go tool -n + 2025-07-23 98a031193b runtime: check TestUsingVDSO ExitError type assertion + 2025-07-23 6bb42997c8 doc/next: initialize + 2025-07-23 2696a11a97 internal/goversion: update Version to 1.26 + 2025-07-23 489868f776 cmd/link: scope test to linux & net.sendFile + 2025-07-22 71c2bf5513 cmd/compile: fix loclist for heap return vars without optimizations + 2025-07-22 c74399e7f5 net: correct comment for ListenConfig.ListenPacket + 2025-07-22 4ed9943b26 all: go fmt + 2025-07-22 1aaf7422f1 cmd/internal/objabi: remove redundant word in comment + 2025-07-21 d5ec0815e6 runtime: relax TestMemoryLimitNoGCPercent a bit + 2025-07-21 f7cc61e7d7 cmd/compile: for arm64 epilog, do SP increment with a single instruction + 2025-07-21 5dac42363b runtime: fix asan wrapper for riscv64 + 2025-07-21 e5502e0959 cmd/go: check subcommand properties + 2025-07-19 2363897932 cmd/internal/obj: enable got pcrel itype in fips140 for riscv64 + 2025-07-19 e32255fcc0 cmd/compile/internal/ssa: restrict architectures for TestDebugLines_74576 + 2025-07-18 0451816430 os: revert the use of AddCleanup to close files and roots + 2025-07-18 34b70684ba go/types: infer correct type for y in append(bytes, y...) + 2025-07-17 66536242fc cmd/compile/internal/escape: improve DWARF .debug_line numbering for literal rewriting optimizations + 2025-07-16 385000b004 runtime: fix idle time double-counting bug + 2025-07-16 f506ad2644 cmd/compile/internal/escape: speed up analyzing some functions with many closures + 2025-07-16 9c507e7942 cmd/link, runtime: on Wasm, put only function index in method table and func table + 2025-07-16 9782dcfd16 runtime: use 32-bit function index on Wasm + 2025-07-16 c876bf9346 cmd/internal/obj/wasm: use 64-bit instructions for indirect calls + 2025-07-15 b4309ece66 cmd/internal/doc: upgrade godoc pkgsite to 01b046e + 2025-07-15 75a19dbcd7 runtime: use memclrNoHeapPointers to clear inline mark bits + 2025-07-15 6d4a91c7a5 runtime: only clear inline mark bits on span alloc if necessary + 2025-07-15 0c6296ab12 runtime: have mergeInlineMarkBits also clear the inline mark bits + 2025-07-15 397d2117ec runtime: merge inline mark bits with gcmarkBits 8 bytes at a time + 2025-07-15 7dceabd3be runtime/maps: fix typo in group.go comment (instrinsified -> intrinsified) + 2025-07-15 d826bf4d74 os: remove useless error check + 2025-07-14 bb07e55aff runtime: expand GOMAXPROCS documentation + 2025-07-14 9159cd4ec6 encoding/json: decompose legacy options + 2025-07-14 c6556b8eb3 encoding/json/v2: add security section to doc + 2025-07-11 6ebb5f56d9 runtime: gofmt after CL 643897 and CL 662455 + 2025-07-11 1e48ca7020 encoding/json: remove legacy option to EscapeInvalidUTF8 + 2025-07-11 a0a99cb22b encoding/json/v2: report wrapped io.ErrUnexpectedEOF + 2025-07-11 9d04122d24 crypto/rsa: drop contradictory promise to keep PublicKey modulus secret + 2025-07-11 1ca23682dd crypto/rsa: fix documentation formatting + 2025-07-11 4bc3373c8e runtime: turn off large memmove tests under asan/msan Change-Id: I1e32d964eba770b85421efb86b305a2242f24466
2025-07-24hash/crc32: add AVX512 IEEE CRC32 calculationKlaus Post
Benchmark: goos: windows goarch: amd64 pkg: hash/crc32 cpu: AMD Ryzen 9 9950X 16-Core Processor benchmark old MB/s new MB/s speedup BenchmarkCRC32/poly=IEEE/size=15/align=0-32 1081.48 1089.42 1.01x BenchmarkCRC32/poly=IEEE/size=15/align=1-32 1085.87 1082.61 1.00x BenchmarkCRC32/poly=IEEE/size=40/align=0-32 2756.33 2752.37 1.00x BenchmarkCRC32/poly=IEEE/size=40/align=1-32 2758.27 2756.99 1.00x BenchmarkCRC32/poly=IEEE/size=512/align=0-32 18133.44 18076.52 1.00x BenchmarkCRC32/poly=IEEE/size=512/align=1-32 18151.05 18055.41 0.99x BenchmarkCRC32/poly=IEEE/size=1kB/align=0-32 19902.93 48581.07 2.44x BenchmarkCRC32/poly=IEEE/size=1kB/align=1-32 19966.99 48393.25 2.42x BenchmarkCRC32/poly=IEEE/size=4kB/align=0-32 21690.33 51679.25 2.38x BenchmarkCRC32/poly=IEEE/size=4kB/align=1-32 21655.30 51731.22 2.39x BenchmarkCRC32/poly=IEEE/size=32kB/align=0-32 22046.57 46406.90 2.10x BenchmarkCRC32/poly=IEEE/size=32kB/align=1-32 21986.22 46250.66 2.10x AVX512 are enabled above 1KB input size. This rather high limit is due to AVX512 may be slower to ramp up than the regular SSE4 implementation for smaller inputs. This is not reflected in the benchmarks, since consecutive calls means the CPU is "hot". The 'HasAVX512VPCLMULQDQ' name mirrors the one in golang.org/x/sys/cpu Change-Id: Id23685d8e3cc412b6d397a7d70056844bdb79271 Change-Id: Id23685d8e3cc412b6d397a7d70056844bdb79271 GitHub-Last-Rev: 6639f07b9febc7c96a7f3b402a2fd60f7be5e154 GitHub-Pull-Request: golang/go#74701 Reviewed-on: https://go-review.googlesource.com/c/go/+/689435 Reviewed-by: Keith Randall <khr@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Michael Knyszek <mknyszek@google.com> Auto-Submit: Keith Randall <khr@golang.org> Auto-Submit: Michael Knyszek <mknyszek@google.com> Reviewed-by: Keith Randall <khr@golang.org>
2025-07-21[dev.simd] simd, internal/cpu: support more AVX CPU Feature checksJunyang Shao
This CL adds more checks, it also changes HasAVX512GFNI to be exactly checking GFNI instead of being a virtual feature. This CL copies its logic from x/sys/arch. Change-Id: I4612b0409b8a3518928300562ae08bcf123d53a7 Reviewed-on: https://go-review.googlesource.com/c/go/+/688276 LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: David Chase <drchase@google.com>
2025-07-01[dev.simd] internal/cpu: add GFNI feature checkJunyang Shao
This CL amends HasAVX512 flag with GFNI check. This is needed because our SIMD API supports Galois Field operations. Change-Id: I3e957b7b2215d2b7b6b8a7a0ca3e2e60d453b2e5 Reviewed-on: https://go-review.googlesource.com/c/go/+/685295 Reviewed-by: David Chase <drchase@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
2025-06-13[dev.simd] internal/cpu: add AVX-512-CD and DQ, and derived "basic AVX-512"Austin Clements
This adds detection for the CD and DQ sub-features of x86 AVX-512. Building on these, we also add a "derived" AVX-512 feature that bundles together the basic usable subset of subfeatures. Despite the F in AVX-512-F standing for "foundation", AVX-512-F+BW+DQ+VL together really form the basic usable subset of AVX-512 functionality. These have also all been supported together by almost every CPU, and are guaranteed by GOAMD64=v4, so there's little point in separating them out. Change-Id: I34356502bd1853ba2372e48db0b10d55cffe07a1 Reviewed-on: https://go-review.googlesource.com/c/go/+/680899 Reviewed-by: Cherry Mui <cherryyz@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
2024-07-22runtime: add ERMS-based memmove support for modern CPU platformsTangYang
The current memmove implementation uses REP MOVSB to copy data larger than 2KB when the useAVXmemmove global variable is false and the CPU supports the ERMS feature. This feature is currently only enabled on CPUs in the Sandy Bridge (Client) , Sandy Bridge (Server), Ivy Bridge (Client), and Ivy Bridge (Server) microarchitectures. For modern Intel CPU microarchitectures that support the ERMS feature, such as Ice Lake (Server), Sapphire Rapids , REP MOVSB achieves better performance than the AVX-based copy currently implemented in memmove. Benchstat result: goos: linux goarch: amd64 pkg: runtime cpu: Intel(R) Xeon(R) Gold 6348 CPU @ 2.60GHz │ ./old.txt │ ./new.txt │ │ sec/op │ sec/op vs base │ Memmove/2048-2 25.24n ± 0% 24.27n ± 0% -3.84% (p=0.000 n=10) Memmove/4096-2 44.87n ± 0% 33.16n ± 1% -26.11% (p=0.000 n=10) geomean 33.65n 28.37n -15.71% │ ./old.txt │ ./new.txt │ │ B/s │ B/s vs base │ Memmove/2048-2 75.56Gi ± 0% 78.59Gi ± 0% +4.02% (p=0.000 n=10) Memmove/4096-2 85.01Gi ± 0% 115.05Gi ± 1% +35.34% (p=0.000 n=10) geomean 80.14Gi 95.09Gi +18.65% Fixes #66958 Change-Id: I1fafd1b51a16752f83ac15047cf3b29422a79d5d GitHub-Last-Rev: 89cf5af32b1b41e1499282058656a8a5c7aed359 GitHub-Pull-Request: golang/go#66959 Reviewed-on: https://go-review.googlesource.com/c/go/+/580735 LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Keith Randall <khr@google.com> Reviewed-by: Keith Randall <khr@golang.org> Auto-Submit: Keith Randall <khr@golang.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2024-05-22internal/cpu: remove unused const cpuid_SSE2Tobias Klauser
It's unused since CL 344350. Change-Id: I1aacb9d3db6798aa7013a58603112894e2281002 Reviewed-on: https://go-review.googlesource.com/c/go/+/587035 Auto-Submit: Tobias Klauser <tobias.klauser@gmail.com> Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Ian Lance Taylor <iant@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
2023-11-15internal/cpu: detect support of AVX512Achille Roussel
Extracts changes from that were submitted in other CLs to enable AVX512 detection, notably: - https://go-review.googlesource.com/c/go/+/271521 - https://go-review.googlesource.com/c/go/+/379394 - https://go-review.googlesource.com/c/go/+/502476 This change adds properties to the cpu.X86 fields to enable runtime detection of AVX512, and the hasAVX512F, hasAVX512BW, and hasAVX512VL macros to support bypassing runtime checks in assembly code when GOAMD64=v4 is set. Change-Id: Ia7c3f22f1e66bf1de575aba522cb0d0a55ce791f Reviewed-on: https://go-review.googlesource.com/c/go/+/536257 Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Martin Möhrmann <martin@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Auto-Submit: Martin Möhrmann <martin@golang.org> Reviewed-by: Keith Randall <khr@google.com> Run-TryBot: Martin Möhrmann <moehrmann@google.com> Commit-Queue: Martin Möhrmann <martin@golang.org> Reviewed-by: Martin Möhrmann <moehrmann@google.com>
2022-08-15internal/cpu: detect sha-ni instruction support for AMD64ted
addresses proposal #53084 required by sha-256 change list developed for #50543 Change-Id: I5454d746fce069a7a4993d70dc5b0a5544f8eeaf Reviewed-on: https://go-review.googlesource.com/c/go/+/408794 Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: Martin Möhrmann <moehrmann@google.com> Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Keith Randall <khr@google.com> Run-TryBot: Keith Randall <khr@google.com>
2022-03-14internal/cpu: disallow disabling options that are required for microarchKeith Randall
e.g., if GOAMD64=v3, don't allow GODEBUG=cpu.XXX=off for XXX which are required for v3. Change-Id: Ib58a4c8b13c5464ba476448ba44bbb261218787c Reviewed-on: https://go-review.googlesource.com/c/go/+/391694 Trust: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gopher Robot <gobot@golang.org> Reviewed-by: Martin Möhrmann <martin@golang.org>
2021-10-28all: go fix -fix=buildtag std cmd (except for bootstrap deps, vendor)Russ Cox
When these packages are released as part of Go 1.18, Go 1.16 will no longer be supported, so we can remove the +build tags in these files. Ran go fix -fix=buildtag std cmd and then reverted the bootstrapDirs as defined in src/cmd/dist/buildtool.go, which need to continue to build with Go 1.4 for now. Also reverted src/vendor and src/cmd/vendor, which will need to be updated in their own repos first. Manual changes in runtime/pprof/mprof_test.go to adjust line numbers. For #41184. Change-Id: Ic0f93f7091295b6abc76ed5cd6e6746e1280861e Reviewed-on: https://go-review.googlesource.com/c/go/+/344955 Trust: Russ Cox <rsc@golang.org> Run-TryBot: Russ Cox <rsc@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Bryan C. Mills <bcmills@google.com>
2021-08-23all: replace runtime SSE2 detection with GO386 settingMartin Möhrmann
When GO386=sse2 we can assume sse2 to be present without a runtime check. If GO386=softfloat is set we can avoid the usage of SSE2 even if detected. This might cause a memcpy, memclr and bytealg slowdown of Go binaries compiled with softfloat on machines that support SSE2. Such setups are rare and should use GO386=sse2 instead if performance matters. On targets that support SSE2 we avoid the runtime overhead of dynamic cpu feature dispatch. The removal of runtime sse2 checks also allows to simplify internal/cpu further by removing handling of the required feature option as a followup after this CL. Change-Id: I90a853a8853a405cb665497c6d1a86556947ba17 Reviewed-on: https://go-review.googlesource.com/c/go/+/344350 Trust: Martin Möhrmann <martin@golang.org> Run-TryBot: Martin Möhrmann <martin@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2021-08-23runtime: use RDTSCP for instruction stream serialized read of TSCMartin Möhrmann
To measure all instructions having been completed before reading the time stamp counter with RDTSC an instruction sequence that has instruction stream serializing properties which guarantee waiting until all previous instructions have been executed is needed. This does not necessary mean to wait for all stores to be globally visible. This CL aims to remove vendor specific logic for determining the instruction sequence with CPU feature flag checks that are CPU vendor independent. For intel LFENCE has the wanted properties at least since it was introduced together with SSE2 support. On AMD instruction stream serializing LFENCE is supported by setting an MSR C001_1029[1]=1 on AMD family 10h/12h/14h/15h/16h/17h processors. AMD family 0Fh/11h processors support LFENCE as serializing always. AMD plans support for this MSR and access to this bit for all future processors. Source: https://developer.amd.com/wp-content/resources/Managing-Speculation-on-AMD-Processors.pdf Reading the MSR to determine LFENCE properties is not always possible or reliable (hypervisors). The Linux kernel is relying on serializing LFENCE on AMD CPUs since a commit in July 2019: https://lkml.org/lkml/2019/7/22/295 and the MSR C001_1029 to enable serialization has been set by default with the Spectre v1 mitigations. Using an MFENCE on AMD is waiting on previous instructions having been executed but in addition also flushes store buffers. To align the serialization properties without runtime detection of CPU manufacturers we can use the newer RDTSCP instruction which waits until all previous instructions have been executed. RDTSCP is available on Intel since around 2008 and on AMD CPUs since around 2006. Support for RDTSCP can be checked independently of manufacturer by checking CPUID bits. Using RDTSCP is the default in Linux to read TSC in program order when the instruction is available. https://github.com/torvalds/linux/blob/e22ce8eb631bdc47a4a4ea7ecf4e4ba499db4f93/arch/x86/include/asm/msr.h#L231 Change-Id: Ifa841843b9abb2816f8f0754a163ebf01385306d Reviewed-on: https://go-review.googlesource.com/c/go/+/344429 Reviewed-by: Keith Randall <khr@golang.org> Trust: Martin Möhrmann <martin@golang.org> Run-TryBot: Martin Möhrmann <martin@golang.org> TryBot-Result: Go Bot <gobot@golang.org>
2021-02-20all: go fmt std cmd (but revert vendor)Russ Cox
Make all our package sources use Go 1.17 gofmt format (adding //go:build lines). Part of //go:build change (#41184). See https://golang.org/design/draft-gobuild Change-Id: Ia0534360e4957e58cd9a18429c39d0e32a6addb4 Reviewed-on: https://go-review.googlesource.com/c/go/+/294430 Trust: Russ Cox <rsc@golang.org> Run-TryBot: Russ Cox <rsc@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Jason A. Donenfeld <Jason@zx2c4.com> Reviewed-by: Ian Lance Taylor <iant@golang.org>
2020-12-03internal/cpu: disable FMA when OSXSAVE is not enabled on x86Martin Möhrmann
All instructions in the FMA extension on x86 are VEX prefixed. VEX prefixed instructions generally require OSXSAVE to be enabled. The execution of FMA instructions emitted by the Go compiler on amd64 will generate an invalid opcode exception if OSXSAVE is not enabled. Fixes #41022 Change-Id: I49881630e7195c804110a2bd81b5bec8cac31ba8 Reviewed-on: https://go-review.googlesource.com/c/go/+/274479 Trust: Martin Möhrmann <moehrmann@google.com> Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2020-10-20testing: print cpu type as label for benchmarksMartin Möhrmann
Supports 386 and amd64 architectures on all operating systems. Example output: $ go test -bench=.* goos: darwin goarch: amd64 pkg: strconv cpu: Intel(R) Core(TM) i7-3520M CPU @ 2.90GHz BenchmarkAtof64Decimal-4 24431032 46.8 ns/op ... As the displayed CPU information is only used for information purposes it is lazily initialized when needed using the new internal/sysinfo package. This allows internal/cpu to stay without dependencies and avoid initialization costs when the CPU information is not needed as the new code to query the CPU name in internal/cpu can be dead code eliminated if not used. Fixes #39214 Change-Id: I77ae5c5d2fed6b28fa78dd45075f9f0a6a7f1bfd Reviewed-on: https://go-review.googlesource.com/c/go/+/263804 Trust: Martin Möhrmann <moehrmann@google.com> Reviewed-by: Keith Randall <khr@golang.org>
2019-10-10all: remove nacl (part 3, more amd64p32)Brad Fitzpatrick
Part 1: CL 199499 (GOOS nacl) Part 2: CL 200077 (amd64p32 files, toolchain) Part 3: stuff that arguably should've been part of Part 2, but I forgot one of my grep patterns when splitting the original CL up into two parts. This one might also have interesting stuff to resurrect for any future x32 ABI support. Updates #30439 Change-Id: I2b4143374a253a003666f3c69e776b7e456bdb9c Reviewed-on: https://go-review.googlesource.com/c/go/+/200318 Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Ian Lance Taylor <iant@golang.org>
2018-10-24internal/cpu: add options and warnings for required cpu featuresMartin Möhrmann
Updates #27218 Change-Id: I8603f3a639cdd9ee201c4f1566692e5b88877fc4 Reviewed-on: https://go-review.googlesource.com/c/144107 Run-TryBot: Martin Möhrmann <martisch@uos.de> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-10-15internal/cpu: add invalid option warnings and support to enable cpu featuresMartin Möhrmann
This CL adds the ability to enable the cpu feature FEATURE by specifying FEATURE=on in GODEBUGCPU. Syntax support to enable cpu features is useful in combination with a preceeding all=off to disable all but some specific cpu features. Example: GODEBUGCPU=all=off,sse3=on This CL implements printing of warnings for invalid GODEBUGCPU settings: - requests enabling features that are not supported with the current CPU - specifying values different than 'on' or 'off' for a feature - settings for unkown cpu feature names Updates #27218 Change-Id: Ic13e5c4c35426a390c50eaa4bd2a408ef2ee21be Reviewed-on: https://go-review.googlesource.com/c/141800 Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2018-08-24internal/cpu: add a CacheLinePadSize constantMartin Möhrmann
The new constant CacheLinePadSize can be used to compute best effort alignment of structs to cache lines. e.g. the runtime can use this in the locktab definition: var locktab [57]struct { l spinlock pad [cpu.CacheLinePadSize - unsafe.Sizeof(spinlock{})]byte } Change-Id: I86f6fbfc5ee7436f742776a7d4a99a1d54ffccc8 Reviewed-on: https://go-review.googlesource.com/131237 Reviewed-by: Ian Lance Taylor <iant@golang.org> Run-TryBot: Ian Lance Taylor <iant@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org>
2018-05-22internal/cpu: add experiment to disable CPU features with GODEBUGCPUMartin Möhrmann
Needs the go compiler to be build with GOEXPERIMENT=debugcpu to be active. The GODEBUGCPU environment variable can be used to disable usage of specific processor features in the Go standard library. This is useful for testing and benchmarking different code paths that are guarded by internal/cpu variable checks. Use of processor features can not be enabled through GODEBUGCPU. To disable usage of AVX and SSE41 cpu features on GOARCH amd64 use: GODEBUGCPU=avx=0,sse41=0 The special "all" option can be used to disable all options: GODEBUGCPU=all=0 Updates #12805 Updates #15403 Change-Id: I699c2e6f74d98472b6fb4b1e5ffbf29b15697aab Reviewed-on: https://go-review.googlesource.com/91737 Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-10internal/cpu: align capability definitions for x86 with other architecturesMartin Möhrmann
Use constant masks and align the definition of isSet with arm64 and ppc64x. Change-Id: I0c6eae30da5e3ce797cde0dab4a39855d4d245d9 Reviewed-on: https://go-review.googlesource.com/94759 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-10internal/cpu,runtime: call cpu.initialize before alginitMeng Zhuo
runtime.alginit needs runtime/support_{aes,ssse3,sse41} feature flag to init aeshash function but internal/cpu.init not be called yet. This CL will call internal/cpu.initialize before runtime.alginit, so that we can move all cpu features related code to internal/cpu. Change-Id: I00b8e403ace3553f8c707563d95f27dade0bc853 Reviewed-on: https://go-review.googlesource.com/104636 Reviewed-by: Tobias Klauser <tobias.klauser@gmail.com> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org> Run-TryBot: Tobias Klauser <tobias.klauser@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org>
2017-11-02cmd/internal/obj/x86: add ADX extensionIlya Tocar
Add support for ADX cpuid bit detection and all instructions, implied by that bit (ADOX/ADCX). They are useful for rsa and math/big in general. Change-Id: Idaa93303ead48fd18b9b3da09b3e79de2f7e2193 Reviewed-on: https://go-review.googlesource.com/74850 Run-TryBot: Ilya Tocar <ilya.tocar@intel.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2017-09-11internal/cpu: add support for x86 FMA cpu feature detectionMartin Möhrmann
Change-Id: I88ea39de01b07e6afa1c187c0df6a258da4aa8e4 Reviewed-on: https://go-review.googlesource.com/62650 Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2017-08-08internal/cpu: fix style nit in variable nameMartin Möhrmann
Consistent with similar change of style in the crypto repository: http://golang.org/cl/43511 Change-Id: Ib158c52a2649dcbbe9eb92f2bdb9d289e0dcc7bf Reviewed-on: https://go-review.googlesource.com/53474 Reviewed-by: Han-Wen Nienhuys <hanwen@google.com> Reviewed-by: Avelino <t@avelino.xxx> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2017-05-10internal/cpu: new package to detect cpu featuresMartin Möhrmann
Implements detection of x86 cpu features that are used in the go standard library. Changes all standard library packages to use the new cpu package instead of using runtime internal variables to check x86 cpu features. Updates: #15403 Change-Id: I2999a10cb4d9ec4863ffbed72f4e021a1dbc4bb9 Reviewed-on: https://go-review.googlesource.com/41476 Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org>
generated by cgit v1.3 (git 2.53.0) at 2026-04-16 03:27:56 +0000