Benchmark results on Loongson-3C6000 @ 2.20GHz:
goos: linux
goarch: loong64
pkg: golang.org/x/crypto/argon2
cpu: Loongson-3C6000/S @ 2200.00MHz
| old.bench | new.bench |
| sec/op | sec/op vs base |
Argon2i/_Time:_3_Memory:_32_MB,_Threads:_1 123.36m ± 0% 76.67m ± 0% -37.85% (p=0.000 n=10)
Argon2i/_Time:_4_Memory:_32_MB,_Threads:_1 163.7m ± 0% 101.3m ± 0% -38.09% (p=0.000 n=10)
Argon2i/_Time:_5_Memory:_32_MB,_Threads:_1 195.0m ± 0% 116.5m ± 8% -40.24% (p=0.000 n=10)
Argon2i/_Time:_3_Memory:_64_MB,_Threads:_4 259.4m ± 0% 165.3m ± 0% -36.28% (p=0.000 n=10)
Argon2i/_Time:_4_Memory:_64_MB,_Threads:_4 349.9m ± 0% 220.8m ± 0% -36.92% (p=0.000 n=10)
Argon2i/_Time:_5_Memory:_64_MB,_Threads:_4 437.6m ± 0% 276.0m ± 0% -36.92% (p=0.000 n=10)
Argon2d/_Time:_3,_Memory:_32_MB,_Threads:_1 116.34m ± 0% 72.07m ± 0% -38.06% (p=0.000 n=10)
Argon2d/_Time:_4,_Memory:_32_MB,_Threads:_1 154.42m ± 0% 95.28m ± 0% -38.30% (p=0.000 n=10)
Argon2d/_Time:_5,_Memory:_32_MB,_Threads:_1 192.4m ± 0% 115.9m ± 2% -39.73% (p=0.000 n=10)
Argon2d/_Time:_3,_Memory:_64_MB,_Threads:_4 254.4m ± 0% 165.2m ± 0% -35.06% (p=0.000 n=10)
Argon2d/_Time:_4,_Memory:_64_MB,_Threads:_4 345.5m ± 1% 221.0m ± 0% -36.04% (p=0.000 n=10)
Argon2d/_Time:_5,_Memory:_64_MB,_Threads:_4 432.1m ± 0% 276.2m ± 0% -36.09% (p=0.000 n=10)
Argon2id/_Time:_3,_Memory:_32_MB,_Threads:_1 116.49m ± 0% 72.38m ± 0% -37.86% (p=0.000 n=10)
Argon2id/_Time:_4,_Memory:_32_MB,_Threads:_1 154.59m ± 0% 95.71m ± 3% -38.09% (p=0.000 n=10)
Argon2id/_Time:_5,_Memory:_32_MB,_Threads:_1 192.5m ± 0% 115.0m ± 0% -40.25% (p=0.000 n=10)
Argon2id/_Time:_3,_Memory:_64_MB,_Threads:_4 255.6m ± 0% 165.7m ± 0% -35.18% (p=0.000 n=10)
Argon2id/_Time:_4,_Memory:_64_MB,_Threads:_4 345.4m ± 0% 221.5m ± 0% -35.87% (p=0.000 n=10)
Argon2id/_Time:_5,_Memory:_64_MB,_Threads:_4 431.9m ± 0% 276.6m ± 0% -35.96% (p=0.000 n=10)
geomean 227.7m 142.6m -37.40%
| old.bench | new.bench |
| B/op | B/op vs base |
Argon2i/_Time:_3_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_4_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_5_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_3_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_4_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_5_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_3,_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_4,_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_5,_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_3,_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_4,_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_5,_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_3,_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_4,_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_5,_Memory:_32_MB,_Threads:_1 32.00Mi ± 0% 32.00Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_3,_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_4,_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_5,_Memory:_64_MB,_Threads:_4 64.01Mi ± 0% 64.01Mi ± 0% ~ (p=1.000 n=10) ¹
geomean 45.26Mi 45.26Mi +0.00%
¹ all samples are equal
| old.bench | new.bench |
| allocs/op | allocs/op vs base |
Argon2i/_Time:_3_Memory:_32_MB,_Threads:_1 31.00 ± 0% 31.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_4_Memory:_32_MB,_Threads:_1 39.00 ± 0% 39.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_5_Memory:_32_MB,_Threads:_1 47.00 ± 0% 47.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_3_Memory:_64_MB,_Threads:_4 73.00 ± 0% 73.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_4_Memory:_64_MB,_Threads:_4 93.00 ± 0% 93.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2i/_Time:_5_Memory:_64_MB,_Threads:_4 113.0 ± 0% 113.0 ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_3,_Memory:_32_MB,_Threads:_1 31.00 ± 0% 31.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_4,_Memory:_32_MB,_Threads:_1 39.00 ± 0% 39.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_5,_Memory:_32_MB,_Threads:_1 47.00 ± 0% 47.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_3,_Memory:_64_MB,_Threads:_4 73.00 ± 0% 73.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_4,_Memory:_64_MB,_Threads:_4 93.00 ± 0% 93.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2d/_Time:_5,_Memory:_64_MB,_Threads:_4 113.0 ± 0% 113.0 ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_3,_Memory:_32_MB,_Threads:_1 31.00 ± 0% 31.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_4,_Memory:_32_MB,_Threads:_1 39.00 ± 0% 39.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_5,_Memory:_32_MB,_Threads:_1 47.00 ± 0% 47.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_3,_Memory:_64_MB,_Threads:_4 73.00 ± 0% 73.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_4,_Memory:_64_MB,_Threads:_4 93.00 ± 0% 93.00 ± 0% ~ (p=1.000 n=10) ¹
Argon2id/_Time:_5,_Memory:_64_MB,_Threads:_4 113.0 ± 0% 113.0 ± 0% ~ (p=1.000 n=10) ¹
geomean 59.32 59.32 +0.00%
¹ all samples are equal
Change-Id: Ia814057ddfdefbe1d23431fa366189ffe5852b96
Reviewed-on: https://go-review.googlesource.com/c/crypto/+/826304
Reviewed-by: Junyang Shao <shaojunyang@google.com>
LUCI-TryBot-Result: golang-scoped@luci-project-accounts.iam.gserviceaccount.com <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Cherry Mui <cherryyz@google.com>
50 lines
1.0 KiB
Go
50 lines
1.0 KiB
Go
// Copyright 2026 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.
|
|
|
|
//go:build loong64 && gc && !purego
|
|
|
|
package argon2
|
|
|
|
import "golang.org/x/sys/cpu"
|
|
|
|
func init() {
|
|
// useLSX (declared in blamka_generic.go) gates the LSX vector path.
|
|
// If the running CPU lacks LSX support, processBlockVX falls back
|
|
// to processBlockGeneric.
|
|
useLSX = cpu.Loong64.HasLSX
|
|
}
|
|
|
|
//go:noescape
|
|
func blamkaLOONG64(b *block)
|
|
|
|
//go:noescape
|
|
func mixBlocksVX(out, a, b, c *block)
|
|
|
|
//go:noescape
|
|
func xorBlocksVX(out, a, b, c *block)
|
|
|
|
func processBlock(out, in1, in2 *block) {
|
|
processBlockVX(out, in1, in2, false)
|
|
}
|
|
|
|
func processBlockXOR(out, in1, in2 *block) {
|
|
processBlockVX(out, in1, in2, true)
|
|
}
|
|
|
|
func processBlockVX(out, in1, in2 *block, xor bool) {
|
|
if !useLSX {
|
|
processBlockGeneric(out, in1, in2, xor)
|
|
return
|
|
}
|
|
|
|
var t block
|
|
mixBlocksVX(&t, in1, in2, &t)
|
|
blamkaLOONG64(&t)
|
|
if xor {
|
|
xorBlocksVX(out, in1, in2, &t)
|
|
} else {
|
|
mixBlocksVX(out, in1, in2, &t)
|
|
}
|
|
}
|