math/big: arm64 assembly code for shlVU is incorrect

[ALTree]

The TestFloat64SpecialCases test in math/big (ratconv_test.go) is currently broken on the android/arm64 builder, with log:

https://build.golang.org/log/fbc581637a0375532f0d819ae67bc9b9abbe8ba9

Breakage started at e4ba400 (math/big: accept non-decimal floats with Rat.SetString).

cc @griesemer

[griesemer]

Hm. It's only broken on android-arm-wikofever. @eliasnaur, it looks like you're the owner of that builder. Is there anything special about that arm device? It's a Cortex-A53 CPU?

[eliasnaur]

I don't think it's a special device, other than it being an Android phone.

The test also broke on darwin/arm64 (iPhone):

https://build.golang.org/log/0b86dd35833a34f28785d335153946ed9a5a3691

which I assume uses an entirely different CPU.

[griesemer]

Indeed, and that appears to be an iPhone 7+. Interesting.

[griesemer]

Here's a smaller test case: https://play.golang.org/p/7OUzcEgoVGk

In the playground, and elsewhere, running this code produces the correct result:

r = 1/100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 (true)
len(r) = 308
f = 1e-305 (false)
e = 1e-305

On android-arm-wikofever (and presumably darwin/arm64) we get:

r = 1/96541187637860552075819821540903887880024095043179244007497829804714413865809870901655967120022719342752763287637146850362464306041721929996152029995888654682648990460561537640800770715572834310810731676381392326036599721803873644105423265719091992037347983408132957025607386110373485836090285769528130906264626714751533056 (true)
len(r) = 325
f = 1e-323 (false)
e = 1e-305

That is the fraction is completely wrong.

[griesemer]

The fraction is correct for 1e-164, and then wrong for 1e165.

[gopherbot]

Change https://golang.org/cl/169721 mentions this issue: math/big: temporarily disable buggy shlVU assembly for arm64

[griesemer]

I've tracked this down a bit more. Here is a stand-alone test file (to be added to the math/big test files) that exposes the problem:

package big

import (
	"strings"
	"testing"
)

func TestSHLVU(t *testing.T) {
	// compute 10^n via 5^n << n
	const n = 165
	p := nat(nil).expNN(nat{5}, nat{n}, nil)
	p = p.shl(p, uint(n)) // <<< this doesn't work using ·shlVU
	// p = nat(nil).shl(p, uint(n)) // <<< this works

	got := string(p.utoa(10))
	want := "1" + strings.Repeat("0", n)
	if got != want {
		t.Errorf("got  %s\nwant %s\n", got, want)
	}
}

When run with the ·shlVU assembly routine (in arith_arm64.s) enabled, this test fails on arm:

$ gomote run -path '$PATH,$WORKDIR/go/bin' $MOTE go/bin/go test -run SHLVU ../src/math/big
go_android_exec: adb wait-for-device exec-out while [[ -z $(getprop sys.boot_completed) ]]; do sleep 1; done;
go_android_exec: adb push /var/folders/f6/d2bhfqss2716nxm8gkv1fmb80000gn/T/workdir-host-darwin-amd64-eliasnaur-android/tmp/go-build825267701/b001/big.test /data/local/tmp/go_android_exec/big.test-89906/big.test
[  1%] /data/local/tmp/go_android_exec/big.test-89906/big.test
...
[100%] /data/local/tmp/go_android_exec/big.test-89906/big.test
/var/folders/f6/d2bhfqss2716nxm8gkv1fmb80000gn/T/workdir-host-darwin-amd64-eliasnaur-android/tmp/go-build825267701/b001/big.test: 1 file pushed. 10.1 MB/s (6329512 bytes in 0.597s)
go_android_exec: adb exec-out export TMPDIR="/data/local/tmp/go_android_exec/big.test-89906"; export GOROOT="/data/local/tmp/go_android_exec/goroot"; export GOPATH="/data/local/tmp/go_android_exec/big.test-89906/gopath"; export CGO_ENABLED=0; export GOPROXY=; export GOCACHE="/data/local/tmp/go_android_exec/gocache"; export PATH=$PATH:"/data/local/tmp/go_android_exec/goroot/bin"; cd "/data/local/tmp/go_android_exec/goroot/src/math/big"; '/data/local/tmp/go_android_exec/big.test-89906/big.test' -test.run=SHLVU; echo -n exitcode=$?
--- FAIL: TestSHLVU (0.00s)
    shl_test.go:18: got  999999999999999999999999999999999999997461262869164377797676543286813257059020658007941683889923711150197932805888983316150450477342246492361833965695145908050591744
        want 1000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
FAIL
exitcode=1go_android_exec: adb exec-out rm -rf /data/local/tmp/go_android_exec/big.test-89906
FAIL	math/big	0.988s
Error running run: exit status 1

When the assembly routine is disabled, the code works fine.

When the assembly routine is enabled but the test case is tweaked slightly such that it uses a nat(nil) receiver rather than p, then the code also seems to work. This is likely an indicator as to what might be wrong with the assembly code.

When fixing this, one should also look into ·shrVU and verify that it doesn't suffer from the same problem.

cc: @erifan @josharian who seem to have written some of this code

[josharian]

Looks like this routine was written by @erifan. The problem is definitely not obvious at a first read through the code. Let me know if you'd like me to take a closer look; otherwise, I will (tentatively) leave this for @erifan.