Inspired by Vectorization of ChaCha Stream Cipher https://eprint.iacr.org/2013/759.pdf name old time/op new time/op delta ChaCha20/32 690ns ± 0% 872ns ± 0% +26.38% (p=0.000 n=10+10) ChaCha20/63 750ns ± 0% 987ns ± 0% +31.53% (p=0.000 n=10+10) ChaCha20/64 674ns ± 0% 879ns ± 0% +30.42% (p=0.000 n=8+10) ChaCha20/256 2.28µs ± 0% 0.82µs ± 0% -64.13% (p=0.000 n=10+10) ChaCha20/1024 8.64µs ± 0% 2.92µs ± 0% -66.15% (p=0.000 n=9+9) ChaCha20/1350 11.9µs ± 0% 4.5µs ± 0% -62.51% (p=0.000 n=10+8) ChaCha20/65536 554µs ± 0% 181µs ± 0% -67.33% (p=0.000 n=10+10) name old speed new speed delta ChaCha20/32 46.3MB/s ± 0% 36.7MB/s ± 0% -20.87% (p=0.000 n=10+9) ChaCha20/63 83.9MB/s ± 0% 63.8MB/s ± 0% -23.97% (p=0.000 n=10+10) ChaCha20/64 94.9MB/s ± 0% 72.8MB/s ± 0% -23.31% (p=0.000 n=10+10) ChaCha20/256 112MB/s ± 0% 312MB/s ± 0% +178.74% (p=0.000 n=10+10) ChaCha20/1024 119MB/s ± 0% 350MB/s ± 0% +195.31% (p=0.000 n=10+9) ChaCha20/1350 114MB/s ± 0% 303MB/s ± 0% +166.73% (p=0.000 n=8+8) ChaCha20/65536 118MB/s ± 0% 362MB/s ± 0% +206.12% (p=0.000 n=10+10) Updates golang/go#22809 Change-Id: I487487faa2ae4ff29de6fd8eb1317740c2939c10 Reviewed-on: https://go-review.googlesource.com/c/107628 Reviewed-by: Filippo Valsorda <filippo@golang.org>
32 lines
745 B
Go
32 lines
745 B
Go
// Copyright 2018 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.
|
|
|
|
// +build go1.11
|
|
// +build !gccgo
|
|
|
|
package chacha20
|
|
|
|
const (
|
|
haveAsm = true
|
|
bufSize = 256
|
|
)
|
|
|
|
//go:noescape
|
|
func xorKeyStreamVX(dst, src []byte, key *[8]uint32, nonce *[3]uint32, counter *uint32)
|
|
|
|
func (c *Cipher) xorKeyStreamAsm(dst, src []byte) {
|
|
|
|
if len(src) >= bufSize {
|
|
xorKeyStreamVX(dst, src, &c.key, &c.nonce, &c.counter)
|
|
}
|
|
|
|
if len(src)%bufSize != 0 {
|
|
i := len(src) - len(src)%bufSize
|
|
c.buf = [bufSize]byte{}
|
|
copy(c.buf[:], src[i:])
|
|
xorKeyStreamVX(c.buf[:], c.buf[:], &c.key, &c.nonce, &c.counter)
|
|
c.len = bufSize - copy(dst[i:], c.buf[:len(src)%bufSize])
|
|
}
|
|
}
|