From 4598a8d3651b3543ea323b9fc6bf8dd954dc3a5d Mon Sep 17 00:00:00 2001 From: thesyncim Date: Sat, 31 Oct 2026 19:08:12 +0000 Subject: [PATCH 1/4] ci: install qemu-user on ubuntu-26.04 runners ubuntu-latest is now ubuntu-26.04, which has no qemu-user-static package, so every run fails at the install step and skips the arm64 tsvc run, the golden check, fmt and lint. qemu-user ships the static emulators there; link qemu-aarch64-static to it when the name is missing, as the Makefile runs that name. --- .github/workflows/test.yml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml index ba31cc9..efe0baa 100644 --- a/.github/workflows/test.yml +++ b/.github/workflows/test.yml @@ -61,8 +61,13 @@ jobs: - name: Test tsvc (amd64, SIMD) run: make tsvc-test - - name: Install qemu-user-static - run: sudo apt-get update && sudo apt-get install -y qemu-user-static + # ubuntu-26.04 has no qemu-user-static: qemu-user ships the static + # emulators there, without the -static names the Makefile runs. + - name: Install qemu-user + run: | + sudo apt-get update && sudo apt-get install -y qemu-user + command -v qemu-aarch64-static || sudo ln -s "$(command -v qemu-aarch64)" /usr/local/bin/qemu-aarch64-static + qemu-aarch64-static --version - name: Test tsvc (arm64, qemu) run: make tsvc-test-qemu-arm64 From c5557360f5e080f9bdf5ca1c52272089b81b61dd Mon Sep 17 00:00:00 2001 From: thesyncim Date: Sat, 31 Oct 2026 20:49:40 +0000 Subject: [PATCH 2/4] go.mod: update golang.org/x/tools to read Go tip's export data Go tip writes export data in iexport version 4, which encodes float constants exactly. x/tools v0.51.0, and the v0.52.0 release, read only up to version 3, so on tip go/packages fails for every package: cannot import "math" (unstable iexport format version 4, just rebuild compiler and std library), export data is newer version - update tool and every script that runs loopvec fails in the tip job. x/tools master reads version 4 (golang/tools@966056e2637c). Update to it until a release includes it. The pinned toolchain is unaffected. --- go.mod | 10 +++++----- go.sum | 24 ++++++++++++------------ 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/go.mod b/go.mod index ed04302..9457290 100644 --- a/go.mod +++ b/go.mod @@ -3,7 +3,7 @@ module github.com/mauri870/loopvec go 1.27.1 require ( - golang.org/x/tools v0.51.0 + golang.org/x/tools v0.52.1-0.20261030190145-0f433775b36d rsc.io/script v0.0.2 ) @@ -207,10 +207,10 @@ require ( go.uber.org/zap v1.27.0 // indirect go.yaml.in/yaml/v3 v3.0.5 // indirect golang.org/x/exp/typeparams v0.0.0-20260811152304-ee035b5b010f // indirect - golang.org/x/mod v0.41.0 // indirect - golang.org/x/sync v0.23.0 // indirect - golang.org/x/sys v0.48.0 // indirect - golang.org/x/telemetry v0.0.0-20260924152758-ed294f943157 // indirect + golang.org/x/mod v0.42.0 // indirect + golang.org/x/sync v0.24.0 // indirect + golang.org/x/sys v0.49.0 // indirect + golang.org/x/telemetry v0.0.0-20261009151841-97e8ea77aa2a // indirect golang.org/x/text v0.41.0 // indirect google.golang.org/protobuf v1.36.12 // indirect gopkg.in/ini.v1 v1.67.0 // indirect diff --git a/go.sum b/go.sum index 04c2946..bb2b241 100644 --- a/go.sum +++ b/go.sum @@ -688,8 +688,8 @@ golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA= golang.org/x/mod v0.6.0-dev.0.20220106191415-9b9b3d81d5e3/go.mod h1:3p9vT2HGsQu2K1YbXdKPJLVgG5VJdoTa1poYQBtP1AY= golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= -golang.org/x/mod v0.41.0 h1:qJmnOUb4YB+FsEuM3HcWucdZASCPGhsX6uljO6pog0c= -golang.org/x/mod v0.41.0/go.mod h1:Ek9pY8RKWXwsWvd3rQiHYtMqkjSUV+s1Rj7j4H5Ur6o= +golang.org/x/mod v0.42.0 h1:ICeL3t2L30ljSPHHxDnR4fqVcBt/zR2zJAb9juavmQg= +golang.org/x/mod v0.42.0/go.mod h1:u5fzIrRInkL8MaO1cbRkUHT64v303YIT5KEqpNr7jRs= golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= @@ -724,8 +724,8 @@ golang.org/x/net v0.0.0-20210525063256-abc453219eb5/go.mod h1:9nx3DQGgdP8bBQD5qx golang.org/x/net v0.0.0-20211015210444-4f30a5c0130f/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y= golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= -golang.org/x/net v0.59.0 h1:5zfYln+w5XCxwrnMMJPufRgNoXEaGxl0wo5GqPXyues= -golang.org/x/net v0.59.0/go.mod h1:2DA/G1UfVbCpQPeWTmMPGY7Cs2PkBkwu743bVX5PIVg= +golang.org/x/net v0.61.0 h1:RR+6j/BTBCrggOLugxa+66R8FvoN6MHlzDlZIbN9YFw= +golang.org/x/net v0.61.0/go.mod h1:WgDCOTH8iwtB66T4/GfI94AHo/hhdb7Hah9NDseQfiI= golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw= golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw= @@ -745,8 +745,8 @@ golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJ golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= -golang.org/x/sync v0.23.0 h1:KameEIfc1IkluZyXWLn39Wd4tURc6GbCiISGiZm2bQk= -golang.org/x/sync v0.23.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0= +golang.org/x/sync v0.24.0 h1:iqiDrGoDgyuvAKrhLQthUEzU/R378N78gXbBjxed7oA= +golang.org/x/sync v0.24.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0= golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= @@ -790,10 +790,10 @@ golang.org/x/sys v0.0.0-20220114195835-da31bd327af9/go.mod h1:oPkhp1MJrh7nUepCBc golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo= -golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og= -golang.org/x/telemetry v0.0.0-20260924152758-ed294f943157 h1:DftxASHKl6JolFPqoN+2WrFO53JvkHwRXvFqf8gsivA= -golang.org/x/telemetry v0.0.0-20260924152758-ed294f943157/go.mod h1:i+ivNqjDnTF3WTElsdk5g9V5DTSBYgdNo7xTU9SDwYA= +golang.org/x/sys v0.49.0 h1:XbzkgYJHdqh/8m2Uu0W/dQv8nktxx4BFHp1M0gROTXA= +golang.org/x/sys v0.49.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og= +golang.org/x/telemetry v0.0.0-20261009151841-97e8ea77aa2a h1:wnveMBKHwx8/nIb8WYT5P9vtefdXOvIWxzycCkc5n6Q= +golang.org/x/telemetry v0.0.0-20261009151841-97e8ea77aa2a/go.mod h1:i+ivNqjDnTF3WTElsdk5g9V5DTSBYgdNo7xTU9SDwYA= golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= @@ -857,8 +857,8 @@ golang.org/x/tools v0.1.1-0.20210302220138-2ac05c832e1a/go.mod h1:9bzcO0MWcOuT0t golang.org/x/tools v0.1.10/go.mod h1:Uh6Zz+xoGYZom868N8YTex3t7RhtHDBrE8Gzo9bV56E= golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= -golang.org/x/tools v0.51.0 h1:k4Xc/1Om9jwkBJBo4NVLMSARBoWtK10mx+W5BnXCeAI= -golang.org/x/tools v0.51.0/go.mod h1:9eEncMayCV6zRMGhR5eZEC2iBx98qWcF1HZ9Z7wJOoA= +golang.org/x/tools v0.52.1-0.20261030190145-0f433775b36d h1:F5ot9G6RM6pgx3TTdKF6IZa2nocit4tcsrVQlq4Zh5w= +golang.org/x/tools v0.52.1-0.20261030190145-0f433775b36d/go.mod h1:ItcP5UNaVGG+Yc4eIYmaFLNJ4soEopkx5Y2d4lcEurs= golang.org/x/tools/go/expect v0.1.1-deprecated h1:jpBZDwmgPhXsKZC6WhL20P4b/wmnpsEAGHaNy0n/rJM= golang.org/x/tools/go/expect v0.1.1-deprecated/go.mod h1:eihoPOH+FgIqa3FpoTwguz/bVUSGBlGQU67vpBeOrBY= golang.org/x/tools/go/packages/packagestest v0.1.1-deprecated h1:1h2MnaIAIXISqTFKdENegdpAgUXz6NrPEsbIeWaBRvM= From 808d0ec4dfb3fa2b94f079c1002d1a7b07efacd1 Mon Sep 17 00:00:00 2001 From: thesyncim Date: Sat, 31 Oct 2026 21:29:58 +0000 Subject: [PATCH 3/4] Makefile: test against go1.27.3 go1.27.3 is the latest 1.27 release. Its simd package is the same as go1.27.1's, so the capability table only changes in its header, and the -methods crash (golang/go#80657) is still there, as flag_methods_ice.txt checks. go.mod keeps go 1.27.1: that is the first release whose simd package loopvec's output compiles against (go1.27.0's ShiftAllRight takes a uint8). --- BUGS.md | 6 +++--- Makefile | 2 +- internal/loopir/caps_gen.go | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/BUGS.md b/BUGS.md index 843087e..55231c5 100644 --- a/BUGS.md +++ b/BUGS.md @@ -2,11 +2,11 @@ loopvec rewrites code to use `GOEXPERIMENT=simd`, which is new, so most of what it hits is in the Go toolchain. This file lists the Go issues that affect loopvec. "tip" means -gotip, "1.27.1" is the release toolchain loopvec is tested against. +gotip, "1.27.3" is the release toolchain loopvec is tested against. | Issue | Status | Affects | loopvec's answer | |---|---|---|---| -| [#80657](https://github.com/golang/go/issues/80657) simd in a method: internal compiler error | fixed on tip (CL 839405), still crashes on 1.27.1 | `-methods` | methods are skipped unless `-methods` is passed | +| [#80657](https://github.com/golang/go/issues/80657) simd in a method: internal compiler error | fixed on tip (CL 839405), still crashes on 1.27.3 | `-methods` | methods are skipped unless `-methods` is passed | | [#80835](https://github.com/golang/go/issues/80835) legacy SSE encodings in functions using simd cause AVX-SSE transition penalties | open, fix pending (CLs 825145, 825146, in tip) | speed of any scalar float code that runs after a rewritten loop, in the same function or another | none; the portable `simd` package has no `ClearAVXUpperBits` | | [#81844](https://github.com/golang/go/issues/81844) blank identifier parameters rejected | fixed on tip (CL 841145) | every rewrite of a function with a `_` parameter | the generated file renames them `_p0`, `_p1`, ... | | [#81845](https://github.com/golang/go/issues/81845) calls left unresolved when inlined into a package initializer | closed as a duplicate of [#80689](https://github.com/golang/go/issues/80689), which is open | loops in package-level `var x = func() {...}()` | not rewritten (the generated initializer fails to link), see `package_initializer_no_rewrite.txt` and `toolexec_package_initializer.txt` | @@ -19,7 +19,7 @@ gotip, "1.27.1" is the release toolchain loopvec is tested against. A function with a receiver that contains simd code failed to compile with `internal compiler error: missing Types entry`. loopvec does not rewrite loops in methods -by default; `-methods` turns it on. The fix is on tip. On 1.27.1 the crash is still there, +by default; `-methods` turns it on. The fix is on tip. On 1.27.3 the crash is still there, and `flag_methods_ice.txt` pins it, so that test starts failing when the pinned toolchain gets the fix. Reported by someone else; the fix is [CL 839405](https://go.dev/cl/839405). diff --git a/Makefile b/Makefile index b4226b3..3804653 100644 --- a/Makefile +++ b/Makefile @@ -1,4 +1,4 @@ -export GOTOOLCHAIN ?= go1.27.1 +export GOTOOLCHAIN ?= go1.27.3 .DEFAULT_GOAL := build diff --git a/internal/loopir/caps_gen.go b/internal/loopir/caps_gen.go index bccacfa..ba7ddff 100644 --- a/internal/loopir/caps_gen.go +++ b/internal/loopir/caps_gen.go @@ -1,4 +1,4 @@ -// Code generated by capsgen from the simd package of go1.27.1. DO NOT EDIT. +// Code generated by capsgen from the simd package of go1.27.3. DO NOT EDIT. package loopir From 93bfd0147cef73930165ad0d6884baee5c7c27c0 Mon Sep 17 00:00:00 2001 From: thesyncim Date: Sat, 31 Oct 2026 19:52:18 +0000 Subject: [PATCH 4/4] testdata: compare NaN results with the same machine's scalar build abs_sqrt.txt, activation_temp.txt and invariant_call.txt compare both builds with testmain/output, which was recorded on amd64. A NaN that an operation creates (the square root of a negative number, 0 times infinity) has the sign bit set on amd64 and clear on arm64, so on arm64 the scalar program itself does not match the recording and the scripts fail before the simd build runs. The recording is now compared only on amd64. On every target the simd build is compared with the scalar build of the same machine, which is the property these scripts check: the rewrite produces the same bits the scalar loop does there. --- testdata/abs_sqrt.txt | 11 +++++++++-- testdata/activation_temp.txt | 11 +++++++++-- testdata/invariant_call.txt | 11 +++++++++-- 3 files changed, 27 insertions(+), 6 deletions(-) diff --git a/testdata/abs_sqrt.txt b/testdata/abs_sqrt.txt index fa05a04..d6368e2 100644 --- a/testdata/abs_sqrt.txt +++ b/testdata/abs_sqrt.txt @@ -4,9 +4,15 @@ # float32. The inputs include -0, infinities, NaNs, and negative numbers, and the # output is compared bit for bit. +# testmain/output was recorded on amd64: a NaN that an operation creates (the square +# root of a negative number, 0 times infinity) has the sign bit set there and clear +# on arm64, so the recording is compared only on amd64, and on every target the +# simd build is compared with the scalar build of the same machine. + # The scalar program is the reference behavior. exec go run ./testmain -cmp stdout testmain/output +[GOARCH:amd64] cmp stdout testmain/output +cp stdout scalar.out cp ops.go ops.go.orig loopvec -split . @@ -18,7 +24,8 @@ cmp ops.go ops.go.guarded # The simd build must behave identically. env GOEXPERIMENT=simd exec go run ./testmain -cmp stdout testmain/output +[GOARCH:amd64] cmp stdout testmain/output +cmp stdout scalar.out -- go.mod -- module example.com/test diff --git a/testdata/activation_temp.txt b/testdata/activation_temp.txt index dc2f51b..5526f8d 100644 --- a/testdata/activation_temp.txt +++ b/testdata/activation_temp.txt @@ -4,8 +4,14 @@ # if/else if, then use it. Results must match the scalar loop bit for bit, NaN, # infinities and signed zeros included. +# testmain/output was recorded on amd64: a NaN that an operation creates (the square +# root of a negative number, 0 times infinity) has the sign bit set there and clear +# on arm64, so the recording is compared only on amd64, and on every target the +# simd build is compared with the scalar build of the same machine. + exec go run ./testmain -cmp stdout testmain/output +[GOARCH:amd64] cmp stdout testmain/output +cp stdout scalar.out cp ops.go ops.go.orig loopvec -split . @@ -16,7 +22,8 @@ cmp ops.go ops.go.guarded env GOEXPERIMENT=simd exec go run ./testmain -cmp stdout testmain/output +[GOARCH:amd64] cmp stdout testmain/output +cmp stdout scalar.out -- go.mod -- module example.com/test diff --git a/testdata/invariant_call.txt b/testdata/invariant_call.txt index 903e7ab..3f1fcf5 100644 --- a/testdata/invariant_call.txt +++ b/testdata/invariant_call.txt @@ -3,8 +3,14 @@ # the call is evaluated once before the loop. The results must match the scalar loop # bit for bit, which is the only way to compare NaN and negative zero. +# testmain/output was recorded on amd64: a NaN that an operation creates (the square +# root of a negative number, 0 times infinity) has the sign bit set there and clear +# on arm64, so the recording is compared only on amd64, and on every target the +# simd build is compared with the scalar build of the same machine. + exec go run ./testmain -cmp stdout testmain/output +[GOARCH:amd64] cmp stdout testmain/output +cp stdout scalar.out cp ops.go ops.go.orig loopvec -split . @@ -15,7 +21,8 @@ cmp ops.go ops.go.guarded env GOEXPERIMENT=simd exec go run ./testmain -cmp stdout testmain/output +[GOARCH:amd64] cmp stdout testmain/output +cmp stdout scalar.out -- go.mod -- module example.com/test