Skip to content

G
Geth-Modification
Unverified Commit 1bccafe5 authored by Péter Szilágyi's avatar Péter Szilágyi
Browse files
Options

core/vm, crypto/blake2b: add SSE, AVX and AVX2 code

parent 2890f060
Show whitespace changes
Inline Side-by-side
Showing with 2560 additions and 55 deletions
core/vm/contracts.go
View file @ 1bccafe5
......@@ -438,63 +438,60 @@ func (c *bn256PairingByzantium) Run(input []byte) ([]byte, error) {
type blake2F struct{}
func (c *blake2F) RequiredGas(input []byte) uint64 {
// If the input is malformed, we can't calculate the gas, return 0 and let the
// actual call choke and fault.
if len(input) != blake2FInputLength {
// Input is malformed, we can't read the number of rounds.
// Precompile can't be executed so we set its price to 0.
return 0
}
rounds := binary.BigEndian.Uint32(input[0:4])
return uint64(rounds)
return uint64(binary.BigEndian.Uint32(input[0:4]))
}
const blake2FInputLength = 213
const blake2FFinalBlockBytes = byte(1)
const blake2FNonFinalBlockBytes = byte(0)
var errBlake2FIncorrectInputLength = errors.New(
"input length for Blake2 F precompile should be exactly 213 bytes",
const (
blake2FInputLength = 213
blake2FFinalBlockBytes = byte(1)
blake2FNonFinalBlockBytes = byte(0)
)
var errBlake2FIncorrectFinalBlockIndicator = errors.New(
"incorrect final block indicator flag",
var (
errBlake2FInvalidInputLength = errors.New("invalid input length")
errBlake2FInvalidFinalFlag = errors.New("invalid final flag")
)
func (c *blake2F) Run(input []byte) ([]byte, error) {
// Make sure the input is valid (correct lenth and final flag)
if len(input) != blake2FInputLength {
return nil, errBlake2FIncorrectInputLength
return nil, errBlake2FInvalidInputLength
}
if input[212] != blake2FNonFinalBlockBytes && input[212] != blake2FFinalBlockBytes {
return nil, errBlake2FIncorrectFinalBlockIndicator
return nil, errBlake2FInvalidFinalFlag
}
// Parse the input into the Blake2b call parameters
var (
rounds = binary.BigEndian.Uint32(input[0:4])
final = (input[212] == blake2FFinalBlockBytes)
rounds := binary.BigEndian.Uint32(input[0:4])
var h [8]uint64
h [8]uint64
m [16]uint64
t [2]uint64
)
for i := 0; i < 8; i++ {
offset := 4 + i*8
h[i] = binary.LittleEndian.Uint64(input[offset : offset+8])
}
var m [16]uint64
for i := 0; i < 16; i++ {
offset := 68 + i*8
m[i] = binary.LittleEndian.Uint64(input[offset : offset+8])
}
var t [2]uint64
t[0] = binary.LittleEndian.Uint64(input[196:204])
t[1] = binary.LittleEndian.Uint64(input[204:212])
f := (input[212] == blake2FFinalBlockBytes)
// Execute the compression function, extract and return the result
blake2b.F(&h, m, t, final, rounds)
blake2b.F(&h, m, t, f, rounds)
var output [64]byte
output := make([]byte, 64)
for i := 0; i < 8; i++ {
offset := i * 8
binary.LittleEndian.PutUint64(output[offset:offset+8], h[i])
}
return output[:], nil
return output, nil
}
core/vm/contracts_test.go
View file @ 1bccafe5
......@@ -349,22 +349,22 @@ var bn256PairingTests = []precompiledTest{
var blake2FMalformedInputTests = []precompiledFailureTest{
{
input: "",
expectedError: errBlake2FIncorrectInputLength,
expectedError: errBlake2FInvalidInputLength,
name: "vector 0: empty input",
},
{
input: "00000c48c9bdf267e6096a3ba7ca8485ae67bb2bf894fe72f36e3cf1361d5f3af54fa5d182e6ad7f520e511f6c3e2b8c68059b6bbd41fbabd9831f79217e1319cde05b61626300000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000300000000000000000000000000000001",
expectedError: errBlake2FIncorrectInputLength,
expectedError: errBlake2FInvalidInputLength,
name: "vector 1: less than 213 bytes input",
},
{
input: "000000000c48c9bdf267e6096a3ba7ca8485ae67bb2bf894fe72f36e3cf1361d5f3af54fa5d182e6ad7f520e511f6c3e2b8c68059b6bbd41fbabd9831f79217e1319cde05b61626300000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000300000000000000000000000000000001",
expectedError: errBlake2FIncorrectInputLength,
expectedError: errBlake2FInvalidInputLength,
name: "vector 2: more than 213 bytes input",
},
{
input: "0000000c48c9bdf267e6096a3ba7ca8485ae67bb2bf894fe72f36e3cf1361d5f3af54fa5d182e6ad7f520e511f6c3e2b8c68059b6bbd41fbabd9831f79217e1319cde05b61626300000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000300000000000000000000000000000002",
expectedError: errBlake2FIncorrectFinalBlockIndicator,
expectedError: errBlake2FInvalidFinalFlag,
name: "vector 3: malformed final block indicator flag",
},
}
......@@ -391,6 +391,11 @@ var blake2FTests = []precompiledTest{
expected: "b63a380cb2897d521994a85234ee2c181b5f844d2c624c002677e9703449d2fba551b3a8333bcdf5f2f7e08993d53923de3d64fcc68c034e717b9293fed7a421",
name: "vector 7",
},
{
input: "007A120048c9bdf267e6096a3ba7ca8485ae67bb2bf894fe72f36e3cf1361d5f3af54fa5d182e6ad7f520e511f6c3e2b8c68059b6bbd41fbabd9831f79217e1319cde05b61626300000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000300000000000000000000000000000001",
expected: "6d2ce9e534d50e18ff866ae92d70cceba79bbcd14c63819fe48752c8aca87a4bb7dcc230d22a4047f0486cfcfb50a17b24b2899eb8fca370f22240adb5170189",
name: "vector 8",
},
}
func testPrecompiled(addr string, test precompiledTest, t *testing.T) {
......
crypto/blake2b/blake2b.go 0 → 100644
View file @ 1bccafe5
// Copyright 2016 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.
// Package blake2b implements the BLAKE2b hash algorithm defined by RFC 7693
// and the extendable output function (XOF) BLAKE2Xb.
//
// For a detailed specification of BLAKE2b see https://blake2.net/blake2.pdf
// and for BLAKE2Xb see https://blake2.net/blake2x.pdf
//
// If you aren't sure which function you need, use BLAKE2b (Sum512 or New512).
// If you need a secret-key MAC (message authentication code), use the New512
// function with a non-nil key.
//
// BLAKE2X is a construction to compute hash values larger than 64 bytes. It
// can produce hash values between 0 and 4 GiB.
package blake2b
import (
"encoding/binary"
"errors"
"hash"
)
const (
// The blocksize of BLAKE2b in bytes.
BlockSize = 128
// The hash size of BLAKE2b-512 in bytes.
Size = 64
// The hash size of BLAKE2b-384 in bytes.
Size384 = 48
// The hash size of BLAKE2b-256 in bytes.
Size256 = 32
)
var (
useAVX2 bool
useAVX bool
useSSE4 bool
)
var (
errKeySize = errors.New("blake2b: invalid key size")
errHashSize = errors.New("blake2b: invalid hash size")
)
var iv = [8]uint64{
0x6a09e667f3bcc908, 0xbb67ae8584caa73b, 0x3c6ef372fe94f82b, 0xa54ff53a5f1d36f1,
0x510e527fade682d1, 0x9b05688c2b3e6c1f, 0x1f83d9abfb41bd6b, 0x5be0cd19137e2179,
}
// Sum512 returns the BLAKE2b-512 checksum of the data.
func Sum512(data []byte) [Size]byte {
var sum [Size]byte
checkSum(&sum, Size, data)
return sum
}
// Sum384 returns the BLAKE2b-384 checksum of the data.
func Sum384(data []byte) [Size384]byte {
var sum [Size]byte
var sum384 [Size384]byte
checkSum(&sum, Size384, data)
copy(sum384[:], sum[:Size384])
return sum384
}
// Sum256 returns the BLAKE2b-256 checksum of the data.
func Sum256(data []byte) [Size256]byte {
var sum [Size]byte
var sum256 [Size256]byte
checkSum(&sum, Size256, data)
copy(sum256[:], sum[:Size256])
return sum256
}
// New512 returns a new hash.Hash computing the BLAKE2b-512 checksum. A non-nil
// key turns the hash into a MAC. The key must be between zero and 64 bytes long.
func New512(key []byte) (hash.Hash, error) { return newDigest(Size, key) }
// New384 returns a new hash.Hash computing the BLAKE2b-384 checksum. A non-nil
// key turns the hash into a MAC. The key must be between zero and 64 bytes long.
func New384(key []byte) (hash.Hash, error) { return newDigest(Size384, key) }
// New256 returns a new hash.Hash computing the BLAKE2b-256 checksum. A non-nil
// key turns the hash into a MAC. The key must be between zero and 64 bytes long.
func New256(key []byte) (hash.Hash, error) { return newDigest(Size256, key) }
// New returns a new hash.Hash computing the BLAKE2b checksum with a custom length.
// A non-nil key turns the hash into a MAC. The key must be between zero and 64 bytes long.
// The hash size can be a value between 1 and 64 but it is highly recommended to use
// values equal or greater than:
// - 32 if BLAKE2b is used as a hash function (The key is zero bytes long).
// - 16 if BLAKE2b is used as a MAC function (The key is at least 16 bytes long).
// When the key is nil, the returned hash.Hash implements BinaryMarshaler
// and BinaryUnmarshaler for state (de)serialization as documented by hash.Hash.
func New(size int, key []byte) (hash.Hash, error) { return newDigest(size, key) }
// F is a compression function for BLAKE2b. It takes as an argument the state
// vector `h`, message block vector `m`, offset counter `t`, final block indicator
// flag `f`, and number of rounds `rounds`. The state vector provided as the first
// parameter is modified by the function.
func F(h *[8]uint64, m [16]uint64, c [2]uint64, final bool, rounds uint32) {
var flag uint64
if final {
flag = 0xFFFFFFFFFFFFFFFF
}
f(h, &m, c[0], c[1], flag, uint64(rounds))
}
func newDigest(hashSize int, key []byte) (*digest, error) {
if hashSize < 1 || hashSize > Size {
return nil, errHashSize
}
if len(key) > Size {
return nil, errKeySize
}
d := &digest{
size: hashSize,
keyLen: len(key),
}
copy(d.key[:], key)
d.Reset()
return d, nil
}
func checkSum(sum *[Size]byte, hashSize int, data []byte) {
h := iv
h[0] ^= uint64(hashSize) | (1 << 16) | (1 << 24)
var c [2]uint64
if length := len(data); length > BlockSize {
n := length &^ (BlockSize - 1)
if length == n {
n -= BlockSize
}
hashBlocks(&h, &c, 0, data[:n])
data = data[n:]
}
var block [BlockSize]byte
offset := copy(block[:], data)
remaining := uint64(BlockSize - offset)
if c[0] < remaining {
c[1]--
}
c[0] -= remaining
hashBlocks(&h, &c, 0xFFFFFFFFFFFFFFFF, block[:])
for i, v := range h[:(hashSize+7)/8] {
binary.LittleEndian.PutUint64(sum[8*i:], v)
}
}
func hashBlocks(h *[8]uint64, c *[2]uint64, flag uint64, blocks []byte) {
var m [16]uint64
c0, c1 := c[0], c[1]
for i := 0; i < len(blocks); {
c0 += BlockSize
if c0 < BlockSize {
c1++
}
for j := range m {
m[j] = binary.LittleEndian.Uint64(blocks[i:])
i += 8
}
f(h, &m, c0, c1, flag, 12)
}
c[0], c[1] = c0, c1
}
type digest struct {
h [8]uint64
c [2]uint64
size int
block [BlockSize]byte
offset int
key [BlockSize]byte
keyLen int
}
const (
magic = "b2b"
marshaledSize = len(magic) + 8*8 + 2*8 + 1 + BlockSize + 1
)
func (d *digest) MarshalBinary() ([]byte, error) {
if d.keyLen != 0 {
return nil, errors.New("crypto/blake2b: cannot marshal MACs")
}
b := make([]byte, 0, marshaledSize)
b = append(b, magic...)
for i := 0; i < 8; i++ {
b = appendUint64(b, d.h[i])
}
b = appendUint64(b, d.c[0])
b = appendUint64(b, d.c[1])
// Maximum value for size is 64
b = append(b, byte(d.size))
b = append(b, d.block[:]...)
b = append(b, byte(d.offset))
return b, nil
}
func (d *digest) UnmarshalBinary(b []byte) error {
if len(b) < len(magic) || string(b[:len(magic)]) != magic {
return errors.New("crypto/blake2b: invalid hash state identifier")
}
if len(b) != marshaledSize {
return errors.New("crypto/blake2b: invalid hash state size")
}
b = b[len(magic):]
for i := 0; i < 8; i++ {
b, d.h[i] = consumeUint64(b)
}
b, d.c[0] = consumeUint64(b)
b, d.c[1] = consumeUint64(b)
d.size = int(b[0])
b = b[1:]
copy(d.block[:], b[:BlockSize])
b = b[BlockSize:]
d.offset = int(b[0])
return nil
}
func (d *digest) BlockSize() int { return BlockSize }
func (d *digest) Size() int { return d.size }
func (d *digest) Reset() {
d.h = iv
d.h[0] ^= uint64(d.size) | (uint64(d.keyLen) << 8) | (1 << 16) | (1 << 24)
d.offset, d.c[0], d.c[1] = 0, 0, 0
if d.keyLen > 0 {
d.block = d.key
d.offset = BlockSize
}
}
func (d *digest) Write(p []byte) (n int, err error) {
n = len(p)
if d.offset > 0 {
remaining := BlockSize - d.offset
if n <= remaining {
d.offset += copy(d.block[d.offset:], p)
return
}
copy(d.block[d.offset:], p[:remaining])
hashBlocks(&d.h, &d.c, 0, d.block[:])
d.offset = 0
p = p[remaining:]
}
if length := len(p); length > BlockSize {
nn := length &^ (BlockSize - 1)
if length == nn {
nn -= BlockSize
}
hashBlocks(&d.h, &d.c, 0, p[:nn])
p = p[nn:]
}
if len(p) > 0 {
d.offset += copy(d.block[:], p)
}
return
}
func (d *digest) Sum(sum []byte) []byte {
var hash [Size]byte
d.finalize(&hash)
return append(sum, hash[:d.size]...)
}
func (d *digest) finalize(hash *[Size]byte) {
var block [BlockSize]byte
copy(block[:], d.block[:d.offset])
remaining := uint64(BlockSize - d.offset)
c := d.c
if c[0] < remaining {
c[1]--
}
c[0] -= remaining
h := d.h
hashBlocks(&h, &c, 0xFFFFFFFFFFFFFFFF, block[:])
for i, v := range h {
binary.LittleEndian.PutUint64(hash[8*i:], v)
}
}
func appendUint64(b []byte, x uint64) []byte {
var a [8]byte
binary.BigEndian.PutUint64(a[:], x)
return append(b, a[:]...)
}
func appendUint32(b []byte, x uint32) []byte {
var a [4]byte
binary.BigEndian.PutUint32(a[:], x)
return append(b, a[:]...)
}
func consumeUint64(b []byte) ([]byte, uint64) {
x := binary.BigEndian.Uint64(b)
return b[8:], x
}
func consumeUint32(b []byte) ([]byte, uint32) {
x := binary.BigEndian.Uint32(b)
return b[4:], x
}
crypto/blake2b/blake2bAVX2_amd64.go 0 → 100644
View file @ 1bccafe5
// Copyright 2016 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 go1.7,amd64,!gccgo,!appengine
package blake2b
import "golang.org/x/sys/cpu"
func init() {
useAVX2 = cpu.X86.HasAVX2
useAVX = cpu.X86.HasAVX
useSSE4 = cpu.X86.HasSSE41
}
//go:noescape
func fAVX2(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
//go:noescape
func fAVX(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
//go:noescape
func fSSE4(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
func f(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64) {
switch {
case useAVX2:
fAVX2(h, m, c0, c1, flag, rounds)
case useAVX:
fAVX(h, m, c0, c1, flag, rounds)
case useSSE4:
fSSE4(h, m, c0, c1, flag, rounds)
default:
fGeneric(h, m, c0, c1, flag, rounds)
}
}
crypto/blake2b/blake2bAVX2_amd64.s 0 → 100644
View file @ 1bccafe5
// Copyright 2016 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 go1.7,amd64,!gccgo,!appengine
#include "textflag.h"
DATA ·AVX2_iv0<>+0x00(SB)/8, $0x6a09e667f3bcc908
DATA ·AVX2_iv0<>+0x08(SB)/8, $0xbb67ae8584caa73b
DATA ·AVX2_iv0<>+0x10(SB)/8, $0x3c6ef372fe94f82b
DATA ·AVX2_iv0<>+0x18(SB)/8, $0xa54ff53a5f1d36f1
GLOBL ·AVX2_iv0<>(SB), (NOPTR+RODATA), $32
DATA ·AVX2_iv1<>+0x00(SB)/8, $0x510e527fade682d1
DATA ·AVX2_iv1<>+0x08(SB)/8, $0x9b05688c2b3e6c1f
DATA ·AVX2_iv1<>+0x10(SB)/8, $0x1f83d9abfb41bd6b
DATA ·AVX2_iv1<>+0x18(SB)/8, $0x5be0cd19137e2179
GLOBL ·AVX2_iv1<>(SB), (NOPTR+RODATA), $32
DATA ·AVX2_c40<>+0x00(SB)/8, $0x0201000706050403
DATA ·AVX2_c40<>+0x08(SB)/8, $0x0a09080f0e0d0c0b
DATA ·AVX2_c40<>+0x10(SB)/8, $0x0201000706050403
DATA ·AVX2_c40<>+0x18(SB)/8, $0x0a09080f0e0d0c0b
GLOBL ·AVX2_c40<>(SB), (NOPTR+RODATA), $32
DATA ·AVX2_c48<>+0x00(SB)/8, $0x0100070605040302
DATA ·AVX2_c48<>+0x08(SB)/8, $0x09080f0e0d0c0b0a
DATA ·AVX2_c48<>+0x10(SB)/8, $0x0100070605040302
DATA ·AVX2_c48<>+0x18(SB)/8, $0x09080f0e0d0c0b0a
GLOBL ·AVX2_c48<>(SB), (NOPTR+RODATA), $32
DATA ·AVX_iv0<>+0x00(SB)/8, $0x6a09e667f3bcc908
DATA ·AVX_iv0<>+0x08(SB)/8, $0xbb67ae8584caa73b
GLOBL ·AVX_iv0<>(SB), (NOPTR+RODATA), $16
DATA ·AVX_iv1<>+0x00(SB)/8, $0x3c6ef372fe94f82b
DATA ·AVX_iv1<>+0x08(SB)/8, $0xa54ff53a5f1d36f1
GLOBL ·AVX_iv1<>(SB), (NOPTR+RODATA), $16
DATA ·AVX_iv2<>+0x00(SB)/8, $0x510e527fade682d1
DATA ·AVX_iv2<>+0x08(SB)/8, $0x9b05688c2b3e6c1f
GLOBL ·AVX_iv2<>(SB), (NOPTR+RODATA), $16
DATA ·AVX_iv3<>+0x00(SB)/8, $0x1f83d9abfb41bd6b
DATA ·AVX_iv3<>+0x08(SB)/8, $0x5be0cd19137e2179
GLOBL ·AVX_iv3<>(SB), (NOPTR+RODATA), $16
DATA ·AVX_c40<>+0x00(SB)/8, $0x0201000706050403
DATA ·AVX_c40<>+0x08(SB)/8, $0x0a09080f0e0d0c0b
GLOBL ·AVX_c40<>(SB), (NOPTR+RODATA), $16
DATA ·AVX_c48<>+0x00(SB)/8, $0x0100070605040302
DATA ·AVX_c48<>+0x08(SB)/8, $0x09080f0e0d0c0b0a
GLOBL ·AVX_c48<>(SB), (NOPTR+RODATA), $16
#define VPERMQ_0x39_Y1_Y1 BYTE $0xc4; BYTE $0xe3; BYTE $0xfd; BYTE $0x00; BYTE $0xc9; BYTE $0x39
#define VPERMQ_0x93_Y1_Y1 BYTE $0xc4; BYTE $0xe3; BYTE $0xfd; BYTE $0x00; BYTE $0xc9; BYTE $0x93
#define VPERMQ_0x4E_Y2_Y2 BYTE $0xc4; BYTE $0xe3; BYTE $0xfd; BYTE $0x00; BYTE $0xd2; BYTE $0x4e
#define VPERMQ_0x93_Y3_Y3 BYTE $0xc4; BYTE $0xe3; BYTE $0xfd; BYTE $0x00; BYTE $0xdb; BYTE $0x93
#define VPERMQ_0x39_Y3_Y3 BYTE $0xc4; BYTE $0xe3; BYTE $0xfd; BYTE $0x00; BYTE $0xdb; BYTE $0x39
#define ROUND_AVX2(m0, m1, m2, m3, t, c40, c48) \
VPADDQ m0, Y0, Y0; \
VPADDQ Y1, Y0, Y0; \
VPXOR Y0, Y3, Y3; \
VPSHUFD $-79, Y3, Y3; \
VPADDQ Y3, Y2, Y2; \
VPXOR Y2, Y1, Y1; \
VPSHUFB c40, Y1, Y1; \
VPADDQ m1, Y0, Y0; \
VPADDQ Y1, Y0, Y0; \
VPXOR Y0, Y3, Y3; \
VPSHUFB c48, Y3, Y3; \
VPADDQ Y3, Y2, Y2; \
VPXOR Y2, Y1, Y1; \
VPADDQ Y1, Y1, t; \
VPSRLQ $63, Y1, Y1; \
VPXOR t, Y1, Y1; \
VPERMQ_0x39_Y1_Y1; \
VPERMQ_0x4E_Y2_Y2; \
VPERMQ_0x93_Y3_Y3; \
VPADDQ m2, Y0, Y0; \
VPADDQ Y1, Y0, Y0; \
VPXOR Y0, Y3, Y3; \
VPSHUFD $-79, Y3, Y3; \
VPADDQ Y3, Y2, Y2; \
VPXOR Y2, Y1, Y1; \
VPSHUFB c40, Y1, Y1; \
VPADDQ m3, Y0, Y0; \
VPADDQ Y1, Y0, Y0; \
VPXOR Y0, Y3, Y3; \
VPSHUFB c48, Y3, Y3; \
VPADDQ Y3, Y2, Y2; \
VPXOR Y2, Y1, Y1; \
VPADDQ Y1, Y1, t; \
VPSRLQ $63, Y1, Y1; \
VPXOR t, Y1, Y1; \
VPERMQ_0x39_Y3_Y3; \
VPERMQ_0x4E_Y2_Y2; \
VPERMQ_0x93_Y1_Y1
#define VMOVQ_SI_X11_0 BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x1E
#define VMOVQ_SI_X12_0 BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x26
#define VMOVQ_SI_X13_0 BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x2E
#define VMOVQ_SI_X14_0 BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x36
#define VMOVQ_SI_X15_0 BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x3E
#define VMOVQ_SI_X11(n) BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x5E; BYTE $n
#define VMOVQ_SI_X12(n) BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x66; BYTE $n
#define VMOVQ_SI_X13(n) BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x6E; BYTE $n
#define VMOVQ_SI_X14(n) BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x76; BYTE $n
#define VMOVQ_SI_X15(n) BYTE $0xC5; BYTE $0x7A; BYTE $0x7E; BYTE $0x7E; BYTE $n
#define VPINSRQ_1_SI_X11_0 BYTE $0xC4; BYTE $0x63; BYTE $0xA1; BYTE $0x22; BYTE $0x1E; BYTE $0x01
#define VPINSRQ_1_SI_X12_0 BYTE $0xC4; BYTE $0x63; BYTE $0x99; BYTE $0x22; BYTE $0x26; BYTE $0x01
#define VPINSRQ_1_SI_X13_0 BYTE $0xC4; BYTE $0x63; BYTE $0x91; BYTE $0x22; BYTE $0x2E; BYTE $0x01
#define VPINSRQ_1_SI_X14_0 BYTE $0xC4; BYTE $0x63; BYTE $0x89; BYTE $0x22; BYTE $0x36; BYTE $0x01
#define VPINSRQ_1_SI_X15_0 BYTE $0xC4; BYTE $0x63; BYTE $0x81; BYTE $0x22; BYTE $0x3E; BYTE $0x01
#define VPINSRQ_1_SI_X11(n) BYTE $0xC4; BYTE $0x63; BYTE $0xA1; BYTE $0x22; BYTE $0x5E; BYTE $n; BYTE $0x01
#define VPINSRQ_1_SI_X12(n) BYTE $0xC4; BYTE $0x63; BYTE $0x99; BYTE $0x22; BYTE $0x66; BYTE $n; BYTE $0x01
#define VPINSRQ_1_SI_X13(n) BYTE $0xC4; BYTE $0x63; BYTE $0x91; BYTE $0x22; BYTE $0x6E; BYTE $n; BYTE $0x01
#define VPINSRQ_1_SI_X14(n) BYTE $0xC4; BYTE $0x63; BYTE $0x89; BYTE $0x22; BYTE $0x76; BYTE $n; BYTE $0x01
#define VPINSRQ_1_SI_X15(n) BYTE $0xC4; BYTE $0x63; BYTE $0x81; BYTE $0x22; BYTE $0x7E; BYTE $n; BYTE $0x01
#define VMOVQ_R8_X15 BYTE $0xC4; BYTE $0x41; BYTE $0xF9; BYTE $0x6E; BYTE $0xF8
#define VPINSRQ_1_R9_X15 BYTE $0xC4; BYTE $0x43; BYTE $0x81; BYTE $0x22; BYTE $0xF9; BYTE $0x01
// load msg: Y12 = (i0, i1, i2, i3)
// i0, i1, i2, i3 must not be 0
#define LOAD_MSG_AVX2_Y12(i0, i1, i2, i3) \
VMOVQ_SI_X12(i0*8); \
VMOVQ_SI_X11(i2*8); \
VPINSRQ_1_SI_X12(i1*8); \
VPINSRQ_1_SI_X11(i3*8); \
VINSERTI128 $1, X11, Y12, Y12
// load msg: Y13 = (i0, i1, i2, i3)
// i0, i1, i2, i3 must not be 0
#define LOAD_MSG_AVX2_Y13(i0, i1, i2, i3) \
VMOVQ_SI_X13(i0*8); \
VMOVQ_SI_X11(i2*8); \
VPINSRQ_1_SI_X13(i1*8); \
VPINSRQ_1_SI_X11(i3*8); \
VINSERTI128 $1, X11, Y13, Y13
// load msg: Y14 = (i0, i1, i2, i3)
// i0, i1, i2, i3 must not be 0
#define LOAD_MSG_AVX2_Y14(i0, i1, i2, i3) \
VMOVQ_SI_X14(i0*8); \
VMOVQ_SI_X11(i2*8); \
VPINSRQ_1_SI_X14(i1*8); \
VPINSRQ_1_SI_X11(i3*8); \
VINSERTI128 $1, X11, Y14, Y14
// load msg: Y15 = (i0, i1, i2, i3)
// i0, i1, i2, i3 must not be 0
#define LOAD_MSG_AVX2_Y15(i0, i1, i2, i3) \
VMOVQ_SI_X15(i0*8); \
VMOVQ_SI_X11(i2*8); \
VPINSRQ_1_SI_X15(i1*8); \
VPINSRQ_1_SI_X11(i3*8); \
VINSERTI128 $1, X11, Y15, Y15
#define LOAD_MSG_AVX2_0_2_4_6_1_3_5_7_8_10_12_14_9_11_13_15() \
VMOVQ_SI_X12_0; \
VMOVQ_SI_X11(4*8); \
VPINSRQ_1_SI_X12(2*8); \
VPINSRQ_1_SI_X11(6*8); \
VINSERTI128 $1, X11, Y12, Y12; \
LOAD_MSG_AVX2_Y13(1, 3, 5, 7); \
LOAD_MSG_AVX2_Y14(8, 10, 12, 14); \
LOAD_MSG_AVX2_Y15(9, 11, 13, 15)
#define LOAD_MSG_AVX2_14_4_9_13_10_8_15_6_1_0_11_5_12_2_7_3() \
LOAD_MSG_AVX2_Y12(14, 4, 9, 13); \
LOAD_MSG_AVX2_Y13(10, 8, 15, 6); \
VMOVQ_SI_X11(11*8); \
VPSHUFD $0x4E, 0*8(SI), X14; \
VPINSRQ_1_SI_X11(5*8); \
VINSERTI128 $1, X11, Y14, Y14; \
LOAD_MSG_AVX2_Y15(12, 2, 7, 3)
#define LOAD_MSG_AVX2_11_12_5_15_8_0_2_13_10_3_7_9_14_6_1_4() \
VMOVQ_SI_X11(5*8); \
VMOVDQU 11*8(SI), X12; \
VPINSRQ_1_SI_X11(15*8); \
VINSERTI128 $1, X11, Y12, Y12; \
VMOVQ_SI_X13(8*8); \
VMOVQ_SI_X11(2*8); \
VPINSRQ_1_SI_X13_0; \
VPINSRQ_1_SI_X11(13*8); \
VINSERTI128 $1, X11, Y13, Y13; \
LOAD_MSG_AVX2_Y14(10, 3, 7, 9); \
LOAD_MSG_AVX2_Y15(14, 6, 1, 4)
#define LOAD_MSG_AVX2_7_3_13_11_9_1_12_14_2_5_4_15_6_10_0_8() \
LOAD_MSG_AVX2_Y12(7, 3, 13, 11); \
LOAD_MSG_AVX2_Y13(9, 1, 12, 14); \
LOAD_MSG_AVX2_Y14(2, 5, 4, 15); \
VMOVQ_SI_X15(6*8); \
VMOVQ_SI_X11_0; \
VPINSRQ_1_SI_X15(10*8); \
VPINSRQ_1_SI_X11(8*8); \
VINSERTI128 $1, X11, Y15, Y15
#define LOAD_MSG_AVX2_9_5_2_10_0_7_4_15_14_11_6_3_1_12_8_13() \
LOAD_MSG_AVX2_Y12(9, 5, 2, 10); \
VMOVQ_SI_X13_0; \
VMOVQ_SI_X11(4*8); \
VPINSRQ_1_SI_X13(7*8); \
VPINSRQ_1_SI_X11(15*8); \
VINSERTI128 $1, X11, Y13, Y13; \
LOAD_MSG_AVX2_Y14(14, 11, 6, 3); \
LOAD_MSG_AVX2_Y15(1, 12, 8, 13)
#define LOAD_MSG_AVX2_2_6_0_8_12_10_11_3_4_7_15_1_13_5_14_9() \
VMOVQ_SI_X12(2*8); \
VMOVQ_SI_X11_0; \
VPINSRQ_1_SI_X12(6*8); \
VPINSRQ_1_SI_X11(8*8); \
VINSERTI128 $1, X11, Y12, Y12; \
LOAD_MSG_AVX2_Y13(12, 10, 11, 3); \
LOAD_MSG_AVX2_Y14(4, 7, 15, 1); \
LOAD_MSG_AVX2_Y15(13, 5, 14, 9)
#define LOAD_MSG_AVX2_12_1_14_4_5_15_13_10_0_6_9_8_7_3_2_11() \
LOAD_MSG_AVX2_Y12(12, 1, 14, 4); \
LOAD_MSG_AVX2_Y13(5, 15, 13, 10); \
VMOVQ_SI_X14_0; \
VPSHUFD $0x4E, 8*8(SI), X11; \
VPINSRQ_1_SI_X14(6*8); \
VINSERTI128 $1, X11, Y14, Y14; \
LOAD_MSG_AVX2_Y15(7, 3, 2, 11)
#define LOAD_MSG_AVX2_13_7_12_3_11_14_1_9_5_15_8_2_0_4_6_10() \
LOAD_MSG_AVX2_Y12(13, 7, 12, 3); \
LOAD_MSG_AVX2_Y13(11, 14, 1, 9); \
LOAD_MSG_AVX2_Y14(5, 15, 8, 2); \
VMOVQ_SI_X15_0; \
VMOVQ_SI_X11(6*8); \
VPINSRQ_1_SI_X15(4*8); \
VPINSRQ_1_SI_X11(10*8); \
VINSERTI128 $1, X11, Y15, Y15
#define LOAD_MSG_AVX2_6_14_11_0_15_9_3_8_12_13_1_10_2_7_4_5() \
VMOVQ_SI_X12(6*8); \
VMOVQ_SI_X11(11*8); \
VPINSRQ_1_SI_X12(14*8); \
VPINSRQ_1_SI_X11_0; \
VINSERTI128 $1, X11, Y12, Y12; \
LOAD_MSG_AVX2_Y13(15, 9, 3, 8); \
VMOVQ_SI_X11(1*8); \
VMOVDQU 12*8(SI), X14; \
VPINSRQ_1_SI_X11(10*8); \
VINSERTI128 $1, X11, Y14, Y14; \
VMOVQ_SI_X15(2*8); \
VMOVDQU 4*8(SI), X11; \
VPINSRQ_1_SI_X15(7*8); \
VINSERTI128 $1, X11, Y15, Y15
#define LOAD_MSG_AVX2_10_8_7_1_2_4_6_5_15_9_3_13_11_14_12_0() \
LOAD_MSG_AVX2_Y12(10, 8, 7, 1); \
VMOVQ_SI_X13(2*8); \
VPSHUFD $0x4E, 5*8(SI), X11; \
VPINSRQ_1_SI_X13(4*8); \
VINSERTI128 $1, X11, Y13, Y13; \
LOAD_MSG_AVX2_Y14(15, 9, 3, 13); \
VMOVQ_SI_X15(11*8); \
VMOVQ_SI_X11(12*8); \
VPINSRQ_1_SI_X15(14*8); \
VPINSRQ_1_SI_X11_0; \
VINSERTI128 $1, X11, Y15, Y15
// func fAVX2(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
TEXT ·fAVX2(SB), 4, $64-48 // frame size = 32 + 32 byte alignment
MOVQ h+0(FP), AX
MOVQ m+8(FP), SI
MOVQ c0+16(FP), R8
MOVQ c1+24(FP), R9
MOVQ flag+32(FP), CX
MOVQ rounds+40(FP), BX
MOVQ SP, DX
MOVQ SP, R10
ADDQ $31, R10
ANDQ $~31, R10
MOVQ R10, SP
MOVQ CX, 16(SP)
XORQ CX, CX
MOVQ CX, 24(SP)
VMOVDQU ·AVX2_c40<>(SB), Y4
VMOVDQU ·AVX2_c48<>(SB), Y5
VMOVDQU 0(AX), Y8
VMOVDQU 32(AX), Y9
VMOVDQU ·AVX2_iv0<>(SB), Y6
VMOVDQU ·AVX2_iv1<>(SB), Y7
MOVQ R8, 0(SP)
MOVQ R9, 8(SP)
VMOVDQA Y8, Y0
VMOVDQA Y9, Y1
VMOVDQA Y6, Y2
VPXOR 0(SP), Y7, Y3
loop:
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_0_2_4_6_1_3_5_7_8_10_12_14_9_11_13_15()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_14_4_9_13_10_8_15_6_1_0_11_5_12_2_7_3()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_11_12_5_15_8_0_2_13_10_3_7_9_14_6_1_4()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_7_3_13_11_9_1_12_14_2_5_4_15_6_10_0_8()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_9_5_2_10_0_7_4_15_14_11_6_3_1_12_8_13()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_2_6_0_8_12_10_11_3_4_7_15_1_13_5_14_9()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_12_1_14_4_5_15_13_10_0_6_9_8_7_3_2_11()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_13_7_12_3_11_14_1_9_5_15_8_2_0_4_6_10()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_6_14_11_0_15_9_3_8_12_13_1_10_2_7_4_5()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
SUBQ $1, BX; JCS done
LOAD_MSG_AVX2_10_8_7_1_2_4_6_5_15_9_3_13_11_14_12_0()
ROUND_AVX2(Y12, Y13, Y14, Y15, Y10, Y4, Y5)
JMP loop
done:
VPXOR Y0, Y8, Y8
VPXOR Y1, Y9, Y9
VPXOR Y2, Y8, Y8
VPXOR Y3, Y9, Y9
VMOVDQU Y8, 0(AX)
VMOVDQU Y9, 32(AX)
VZEROUPPER
MOVQ DX, SP
RET
#define VPUNPCKLQDQ_X2_X2_X15 BYTE $0xC5; BYTE $0x69; BYTE $0x6C; BYTE $0xFA
#define VPUNPCKLQDQ_X3_X3_X15 BYTE $0xC5; BYTE $0x61; BYTE $0x6C; BYTE $0xFB
#define VPUNPCKLQDQ_X7_X7_X15 BYTE $0xC5; BYTE $0x41; BYTE $0x6C; BYTE $0xFF
#define VPUNPCKLQDQ_X13_X13_X15 BYTE $0xC4; BYTE $0x41; BYTE $0x11; BYTE $0x6C; BYTE $0xFD
#define VPUNPCKLQDQ_X14_X14_X15 BYTE $0xC4; BYTE $0x41; BYTE $0x09; BYTE $0x6C; BYTE $0xFE
#define VPUNPCKHQDQ_X15_X2_X2 BYTE $0xC4; BYTE $0xC1; BYTE $0x69; BYTE $0x6D; BYTE $0xD7
#define VPUNPCKHQDQ_X15_X3_X3 BYTE $0xC4; BYTE $0xC1; BYTE $0x61; BYTE $0x6D; BYTE $0xDF
#define VPUNPCKHQDQ_X15_X6_X6 BYTE $0xC4; BYTE $0xC1; BYTE $0x49; BYTE $0x6D; BYTE $0xF7
#define VPUNPCKHQDQ_X15_X7_X7 BYTE $0xC4; BYTE $0xC1; BYTE $0x41; BYTE $0x6D; BYTE $0xFF
#define VPUNPCKHQDQ_X15_X3_X2 BYTE $0xC4; BYTE $0xC1; BYTE $0x61; BYTE $0x6D; BYTE $0xD7
#define VPUNPCKHQDQ_X15_X7_X6 BYTE $0xC4; BYTE $0xC1; BYTE $0x41; BYTE $0x6D; BYTE $0xF7
#define VPUNPCKHQDQ_X15_X13_X3 BYTE $0xC4; BYTE $0xC1; BYTE $0x11; BYTE $0x6D; BYTE $0xDF
#define VPUNPCKHQDQ_X15_X13_X7 BYTE $0xC4; BYTE $0xC1; BYTE $0x11; BYTE $0x6D; BYTE $0xFF
#define SHUFFLE_AVX() \
VMOVDQA X6, X13; \
VMOVDQA X2, X14; \
VMOVDQA X4, X6; \
VPUNPCKLQDQ_X13_X13_X15; \
VMOVDQA X5, X4; \
VMOVDQA X6, X5; \
VPUNPCKHQDQ_X15_X7_X6; \
VPUNPCKLQDQ_X7_X7_X15; \
VPUNPCKHQDQ_X15_X13_X7; \
VPUNPCKLQDQ_X3_X3_X15; \
VPUNPCKHQDQ_X15_X2_X2; \
VPUNPCKLQDQ_X14_X14_X15; \
VPUNPCKHQDQ_X15_X3_X3; \
#define SHUFFLE_AVX_INV() \
VMOVDQA X2, X13; \
VMOVDQA X4, X14; \
VPUNPCKLQDQ_X2_X2_X15; \
VMOVDQA X5, X4; \
VPUNPCKHQDQ_X15_X3_X2; \
VMOVDQA X14, X5; \
VPUNPCKLQDQ_X3_X3_X15; \
VMOVDQA X6, X14; \
VPUNPCKHQDQ_X15_X13_X3; \
VPUNPCKLQDQ_X7_X7_X15; \
VPUNPCKHQDQ_X15_X6_X6; \
VPUNPCKLQDQ_X14_X14_X15; \
VPUNPCKHQDQ_X15_X7_X7; \
#define HALF_ROUND_AVX(v0, v1, v2, v3, v4, v5, v6, v7, m0, m1, m2, m3, t0, c40, c48) \
VPADDQ m0, v0, v0; \
VPADDQ v2, v0, v0; \
VPADDQ m1, v1, v1; \
VPADDQ v3, v1, v1; \
VPXOR v0, v6, v6; \
VPXOR v1, v7, v7; \
VPSHUFD $-79, v6, v6; \
VPSHUFD $-79, v7, v7; \
VPADDQ v6, v4, v4; \
VPADDQ v7, v5, v5; \
VPXOR v4, v2, v2; \
VPXOR v5, v3, v3; \
VPSHUFB c40, v2, v2; \
VPSHUFB c40, v3, v3; \
VPADDQ m2, v0, v0; \
VPADDQ v2, v0, v0; \
VPADDQ m3, v1, v1; \
VPADDQ v3, v1, v1; \
VPXOR v0, v6, v6; \
VPXOR v1, v7, v7; \
VPSHUFB c48, v6, v6; \
VPSHUFB c48, v7, v7; \
VPADDQ v6, v4, v4; \
VPADDQ v7, v5, v5; \
VPXOR v4, v2, v2; \
VPXOR v5, v3, v3; \
VPADDQ v2, v2, t0; \
VPSRLQ $63, v2, v2; \
VPXOR t0, v2, v2; \
VPADDQ v3, v3, t0; \
VPSRLQ $63, v3, v3; \
VPXOR t0, v3, v3
// load msg: X12 = (i0, i1), X13 = (i2, i3), X14 = (i4, i5), X15 = (i6, i7)
// i0, i1, i2, i3, i4, i5, i6, i7 must not be 0
#define LOAD_MSG_AVX(i0, i1, i2, i3, i4, i5, i6, i7) \
VMOVQ_SI_X12(i0*8); \
VMOVQ_SI_X13(i2*8); \
VMOVQ_SI_X14(i4*8); \
VMOVQ_SI_X15(i6*8); \
VPINSRQ_1_SI_X12(i1*8); \
VPINSRQ_1_SI_X13(i3*8); \
VPINSRQ_1_SI_X14(i5*8); \
VPINSRQ_1_SI_X15(i7*8)
// load msg: X12 = (0, 2), X13 = (4, 6), X14 = (1, 3), X15 = (5, 7)
#define LOAD_MSG_AVX_0_2_4_6_1_3_5_7() \
VMOVQ_SI_X12_0; \
VMOVQ_SI_X13(4*8); \
VMOVQ_SI_X14(1*8); \
VMOVQ_SI_X15(5*8); \
VPINSRQ_1_SI_X12(2*8); \
VPINSRQ_1_SI_X13(6*8); \
VPINSRQ_1_SI_X14(3*8); \
VPINSRQ_1_SI_X15(7*8)
// load msg: X12 = (1, 0), X13 = (11, 5), X14 = (12, 2), X15 = (7, 3)
#define LOAD_MSG_AVX_1_0_11_5_12_2_7_3() \
VPSHUFD $0x4E, 0*8(SI), X12; \
VMOVQ_SI_X13(11*8); \
VMOVQ_SI_X14(12*8); \
VMOVQ_SI_X15(7*8); \
VPINSRQ_1_SI_X13(5*8); \
VPINSRQ_1_SI_X14(2*8); \
VPINSRQ_1_SI_X15(3*8)
// load msg: X12 = (11, 12), X13 = (5, 15), X14 = (8, 0), X15 = (2, 13)
#define LOAD_MSG_AVX_11_12_5_15_8_0_2_13() \
VMOVDQU 11*8(SI), X12; \
VMOVQ_SI_X13(5*8); \
VMOVQ_SI_X14(8*8); \
VMOVQ_SI_X15(2*8); \
VPINSRQ_1_SI_X13(15*8); \
VPINSRQ_1_SI_X14_0; \
VPINSRQ_1_SI_X15(13*8)
// load msg: X12 = (2, 5), X13 = (4, 15), X14 = (6, 10), X15 = (0, 8)
#define LOAD_MSG_AVX_2_5_4_15_6_10_0_8() \
VMOVQ_SI_X12(2*8); \
VMOVQ_SI_X13(4*8); \
VMOVQ_SI_X14(6*8); \
VMOVQ_SI_X15_0; \
VPINSRQ_1_SI_X12(5*8); \
VPINSRQ_1_SI_X13(15*8); \
VPINSRQ_1_SI_X14(10*8); \
VPINSRQ_1_SI_X15(8*8)
// load msg: X12 = (9, 5), X13 = (2, 10), X14 = (0, 7), X15 = (4, 15)
#define LOAD_MSG_AVX_9_5_2_10_0_7_4_15() \
VMOVQ_SI_X12(9*8); \
VMOVQ_SI_X13(2*8); \
VMOVQ_SI_X14_0; \
VMOVQ_SI_X15(4*8); \
VPINSRQ_1_SI_X12(5*8); \
VPINSRQ_1_SI_X13(10*8); \
VPINSRQ_1_SI_X14(7*8); \
VPINSRQ_1_SI_X15(15*8)
// load msg: X12 = (2, 6), X13 = (0, 8), X14 = (12, 10), X15 = (11, 3)
#define LOAD_MSG_AVX_2_6_0_8_12_10_11_3() \
VMOVQ_SI_X12(2*8); \
VMOVQ_SI_X13_0; \
VMOVQ_SI_X14(12*8); \
VMOVQ_SI_X15(11*8); \
VPINSRQ_1_SI_X12(6*8); \
VPINSRQ_1_SI_X13(8*8); \
VPINSRQ_1_SI_X14(10*8); \
VPINSRQ_1_SI_X15(3*8)
// load msg: X12 = (0, 6), X13 = (9, 8), X14 = (7, 3), X15 = (2, 11)
#define LOAD_MSG_AVX_0_6_9_8_7_3_2_11() \
MOVQ 0*8(SI), X12; \
VPSHUFD $0x4E, 8*8(SI), X13; \
MOVQ 7*8(SI), X14; \
MOVQ 2*8(SI), X15; \
VPINSRQ_1_SI_X12(6*8); \
VPINSRQ_1_SI_X14(3*8); \
VPINSRQ_1_SI_X15(11*8)
// load msg: X12 = (6, 14), X13 = (11, 0), X14 = (15, 9), X15 = (3, 8)
#define LOAD_MSG_AVX_6_14_11_0_15_9_3_8() \
MOVQ 6*8(SI), X12; \
MOVQ 11*8(SI), X13; \
MOVQ 15*8(SI), X14; \
MOVQ 3*8(SI), X15; \
VPINSRQ_1_SI_X12(14*8); \
VPINSRQ_1_SI_X13_0; \
VPINSRQ_1_SI_X14(9*8); \
VPINSRQ_1_SI_X15(8*8)
// load msg: X12 = (5, 15), X13 = (8, 2), X14 = (0, 4), X15 = (6, 10)
#define LOAD_MSG_AVX_5_15_8_2_0_4_6_10() \
MOVQ 5*8(SI), X12; \
MOVQ 8*8(SI), X13; \
MOVQ 0*8(SI), X14; \
MOVQ 6*8(SI), X15; \
VPINSRQ_1_SI_X12(15*8); \
VPINSRQ_1_SI_X13(2*8); \
VPINSRQ_1_SI_X14(4*8); \
VPINSRQ_1_SI_X15(10*8)
// load msg: X12 = (12, 13), X13 = (1, 10), X14 = (2, 7), X15 = (4, 5)
#define LOAD_MSG_AVX_12_13_1_10_2_7_4_5() \
VMOVDQU 12*8(SI), X12; \
MOVQ 1*8(SI), X13; \
MOVQ 2*8(SI), X14; \
VPINSRQ_1_SI_X13(10*8); \
VPINSRQ_1_SI_X14(7*8); \
VMOVDQU 4*8(SI), X15
// load msg: X12 = (15, 9), X13 = (3, 13), X14 = (11, 14), X15 = (12, 0)
#define LOAD_MSG_AVX_15_9_3_13_11_14_12_0() \
MOVQ 15*8(SI), X12; \
MOVQ 3*8(SI), X13; \
MOVQ 11*8(SI), X14; \
MOVQ 12*8(SI), X15; \
VPINSRQ_1_SI_X12(9*8); \
VPINSRQ_1_SI_X13(13*8); \
VPINSRQ_1_SI_X14(14*8); \
VPINSRQ_1_SI_X15_0
// func fAVX(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
TEXT ·fAVX(SB), 4, $24-48 // frame size = 8 + 16 byte alignment
MOVQ h+0(FP), AX
MOVQ m+8(FP), SI
MOVQ c0+16(FP), R8
MOVQ c1+24(FP), R9
MOVQ flag+32(FP), CX
MOVQ rounds+40(FP), BX
MOVQ SP, BP
MOVQ SP, R10
ADDQ $15, R10
ANDQ $~15, R10
MOVQ R10, SP
VMOVDQU ·AVX_c40<>(SB), X0
VMOVDQU ·AVX_c48<>(SB), X1
VMOVDQA X0, X8
VMOVDQA X1, X9
VMOVDQU ·AVX_iv3<>(SB), X0
VMOVDQA X0, 0(SP)
XORQ CX, 0(SP) // 0(SP) = ·AVX_iv3 ^ (CX || 0)
VMOVDQU 0(AX), X10
VMOVDQU 16(AX), X11
VMOVDQU 32(AX), X2
VMOVDQU 48(AX), X3
VMOVQ_R8_X15
VPINSRQ_1_R9_X15
VMOVDQA X10, X0
VMOVDQA X11, X1
VMOVDQU ·AVX_iv0<>(SB), X4
VMOVDQU ·AVX_iv1<>(SB), X5
VMOVDQU ·AVX_iv2<>(SB), X6
VPXOR X15, X6, X6
VMOVDQA 0(SP), X7
loop:
SUBQ $1, BX; JCS done
LOAD_MSG_AVX_0_2_4_6_1_3_5_7()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX(8, 10, 12, 14, 9, 11, 13, 15)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX(14, 4, 9, 13, 10, 8, 15, 6)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX_1_0_11_5_12_2_7_3()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX_11_12_5_15_8_0_2_13()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX(10, 3, 7, 9, 14, 6, 1, 4)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX(7, 3, 13, 11, 9, 1, 12, 14)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX_2_5_4_15_6_10_0_8()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX_9_5_2_10_0_7_4_15()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX(14, 11, 6, 3, 1, 12, 8, 13)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX_2_6_0_8_12_10_11_3()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX(4, 7, 15, 1, 13, 5, 14, 9)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX(12, 1, 14, 4, 5, 15, 13, 10)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX_0_6_9_8_7_3_2_11()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX(13, 7, 12, 3, 11, 14, 1, 9)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX_5_15_8_2_0_4_6_10()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX_6_14_11_0_15_9_3_8()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX_12_13_1_10_2_7_4_5()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
SUBQ $1, BX; JCS done
LOAD_MSG_AVX(10, 8, 7, 1, 2, 4, 6, 5)
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX()
LOAD_MSG_AVX_15_9_3_13_11_14_12_0()
HALF_ROUND_AVX(X0, X1, X2, X3, X4, X5, X6, X7, X12, X13, X14, X15, X15, X8, X9)
SHUFFLE_AVX_INV()
JMP loop
done:
VMOVDQU 32(AX), X14
VMOVDQU 48(AX), X15
VPXOR X0, X10, X10
VPXOR X1, X11, X11
VPXOR X2, X14, X14
VPXOR X3, X15, X15
VPXOR X4, X10, X10
VPXOR X5, X11, X11
VPXOR X6, X14, X2
VPXOR X7, X15, X3
VMOVDQU X2, 32(AX)
VMOVDQU X3, 48(AX)
VMOVDQU X10, 0(AX)
VMOVDQU X11, 16(AX)
VZEROUPPER
MOVQ BP, SP
RET
crypto/blake2b/blake2b_amd64.go 0 → 100644
View file @ 1bccafe5
// Copyright 2016 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 !go1.7,amd64,!gccgo,!appengine
package blake2b
import "golang.org/x/sys/cpu"
func init() {
useSSE4 = cpu.X86.HasSSE41
}
//go:noescape
func fSSE4(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
func f(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64) {
if useSSE4 {
fSSE4(h, m, c0, c1, flag, rounds)
} else {
fGeneric(h, m, c0, c1, flag, rounds)
}
}
crypto/blake2b/blake2b_amd64.s 0 → 100644
View file @ 1bccafe5
// Copyright 2016 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 amd64,!gccgo,!appengine
#include "textflag.h"
DATA ·iv0<>+0x00(SB)/8, $0x6a09e667f3bcc908
DATA ·iv0<>+0x08(SB)/8, $0xbb67ae8584caa73b
GLOBL ·iv0<>(SB), (NOPTR+RODATA), $16
DATA ·iv1<>+0x00(SB)/8, $0x3c6ef372fe94f82b
DATA ·iv1<>+0x08(SB)/8, $0xa54ff53a5f1d36f1
GLOBL ·iv1<>(SB), (NOPTR+RODATA), $16
DATA ·iv2<>+0x00(SB)/8, $0x510e527fade682d1
DATA ·iv2<>+0x08(SB)/8, $0x9b05688c2b3e6c1f
GLOBL ·iv2<>(SB), (NOPTR+RODATA), $16
DATA ·iv3<>+0x00(SB)/8, $0x1f83d9abfb41bd6b
DATA ·iv3<>+0x08(SB)/8, $0x5be0cd19137e2179
GLOBL ·iv3<>(SB), (NOPTR+RODATA), $16
DATA ·c40<>+0x00(SB)/8, $0x0201000706050403
DATA ·c40<>+0x08(SB)/8, $0x0a09080f0e0d0c0b
GLOBL ·c40<>(SB), (NOPTR+RODATA), $16
DATA ·c48<>+0x00(SB)/8, $0x0100070605040302
DATA ·c48<>+0x08(SB)/8, $0x09080f0e0d0c0b0a
GLOBL ·c48<>(SB), (NOPTR+RODATA), $16
#define SHUFFLE(v2, v3, v4, v5, v6, v7, t1, t2) \
MOVO v4, t1; \
MOVO v5, v4; \
MOVO t1, v5; \
MOVO v6, t1; \
PUNPCKLQDQ v6, t2; \
PUNPCKHQDQ v7, v6; \
PUNPCKHQDQ t2, v6; \
PUNPCKLQDQ v7, t2; \
MOVO t1, v7; \
MOVO v2, t1; \
PUNPCKHQDQ t2, v7; \
PUNPCKLQDQ v3, t2; \
PUNPCKHQDQ t2, v2; \
PUNPCKLQDQ t1, t2; \
PUNPCKHQDQ t2, v3
#define SHUFFLE_INV(v2, v3, v4, v5, v6, v7, t1, t2) \
MOVO v4, t1; \
MOVO v5, v4; \
MOVO t1, v5; \
MOVO v2, t1; \
PUNPCKLQDQ v2, t2; \
PUNPCKHQDQ v3, v2; \
PUNPCKHQDQ t2, v2; \
PUNPCKLQDQ v3, t2; \
MOVO t1, v3; \
MOVO v6, t1; \
PUNPCKHQDQ t2, v3; \
PUNPCKLQDQ v7, t2; \
PUNPCKHQDQ t2, v6; \
PUNPCKLQDQ t1, t2; \
PUNPCKHQDQ t2, v7
#define HALF_ROUND(v0, v1, v2, v3, v4, v5, v6, v7, m0, m1, m2, m3, t0, c40, c48) \
PADDQ m0, v0; \
PADDQ m1, v1; \
PADDQ v2, v0; \
PADDQ v3, v1; \
PXOR v0, v6; \
PXOR v1, v7; \
PSHUFD $0xB1, v6, v6; \
PSHUFD $0xB1, v7, v7; \
PADDQ v6, v4; \
PADDQ v7, v5; \
PXOR v4, v2; \
PXOR v5, v3; \
PSHUFB c40, v2; \
PSHUFB c40, v3; \
PADDQ m2, v0; \
PADDQ m3, v1; \
PADDQ v2, v0; \
PADDQ v3, v1; \
PXOR v0, v6; \
PXOR v1, v7; \
PSHUFB c48, v6; \
PSHUFB c48, v7; \
PADDQ v6, v4; \
PADDQ v7, v5; \
PXOR v4, v2; \
PXOR v5, v3; \
MOVOU v2, t0; \
PADDQ v2, t0; \
PSRLQ $63, v2; \
PXOR t0, v2; \
MOVOU v3, t0; \
PADDQ v3, t0; \
PSRLQ $63, v3; \
PXOR t0, v3
#define LOAD_MSG(m0, m1, m2, m3, i0, i1, i2, i3, i4, i5, i6, i7) \
MOVQ i0*8(SI), m0; \
PINSRQ $1, i1*8(SI), m0; \
MOVQ i2*8(SI), m1; \
PINSRQ $1, i3*8(SI), m1; \
MOVQ i4*8(SI), m2; \
PINSRQ $1, i5*8(SI), m2; \
MOVQ i6*8(SI), m3; \
PINSRQ $1, i7*8(SI), m3
// func fSSE4(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64)
TEXT ·fSSE4(SB), 4, $24-48 // frame size = 8 + 16 byte alignment
MOVQ h+0(FP), AX
MOVQ m+8(FP), SI
MOVQ c0+16(FP), R8
MOVQ c1+24(FP), R9
MOVQ flag+32(FP), CX
MOVQ rounds+40(FP), BX
MOVQ SP, BP
MOVQ SP, R10
ADDQ $15, R10
ANDQ $~15, R10
MOVQ R10, SP
MOVOU ·iv3<>(SB), X0
MOVO X0, 0(SP)
XORQ CX, 0(SP) // 0(SP) = ·iv3 ^ (CX || 0)
MOVOU ·c40<>(SB), X13
MOVOU ·c48<>(SB), X14
MOVOU 0(AX), X12
MOVOU 16(AX), X15
MOVQ R8, X8
PINSRQ $1, R9, X8
MOVO X12, X0
MOVO X15, X1
MOVOU 32(AX), X2
MOVOU 48(AX), X3
MOVOU ·iv0<>(SB), X4
MOVOU ·iv1<>(SB), X5
MOVOU ·iv2<>(SB), X6
PXOR X8, X6
MOVO 0(SP), X7
loop:
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 0, 2, 4, 6, 1, 3, 5, 7)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 8, 10, 12, 14, 9, 11, 13, 15)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 14, 4, 9, 13, 10, 8, 15, 6)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 1, 0, 11, 5, 12, 2, 7, 3)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 11, 12, 5, 15, 8, 0, 2, 13)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 10, 3, 7, 9, 14, 6, 1, 4)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 7, 3, 13, 11, 9, 1, 12, 14)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 2, 5, 4, 15, 6, 10, 0, 8)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 9, 5, 2, 10, 0, 7, 4, 15)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 14, 11, 6, 3, 1, 12, 8, 13)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 2, 6, 0, 8, 12, 10, 11, 3)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 4, 7, 15, 1, 13, 5, 14, 9)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 12, 1, 14, 4, 5, 15, 13, 10)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 0, 6, 9, 8, 7, 3, 2, 11)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 13, 7, 12, 3, 11, 14, 1, 9)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 5, 15, 8, 2, 0, 4, 6, 10)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 6, 14, 11, 0, 15, 9, 3, 8)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 12, 13, 1, 10, 2, 7, 4, 5)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
SUBQ $1, BX; JCS done
LOAD_MSG(X8, X9, X10, X11, 10, 8, 7, 1, 2, 4, 6, 5)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE(X2, X3, X4, X5, X6, X7, X8, X9)
LOAD_MSG(X8, X9, X10, X11, 15, 9, 3, 13, 11, 14, 12, 0)
HALF_ROUND(X0, X1, X2, X3, X4, X5, X6, X7, X8, X9, X10, X11, X11, X13, X14)
SHUFFLE_INV(X2, X3, X4, X5, X6, X7, X8, X9)
JMP loop
done:
MOVOU 32(AX), X10
MOVOU 48(AX), X11
PXOR X0, X12
PXOR X1, X15
PXOR X2, X10
PXOR X3, X11
PXOR X4, X12
PXOR X5, X15
PXOR X6, X10
PXOR X7, X11
MOVOU X10, 32(AX)
MOVOU X11, 48(AX)
MOVOU X12, 0(AX)
MOVOU X15, 16(AX)
MOVQ BP, SP
RET
crypto/blake2b/f_test.go → crypto/blake2b/blake2b_f_test.go
View file @ 1bccafe5
package blake2b
import (
"encoding/binary"
"encoding/hex"
"fmt"
"reflect"
"testing"
......@@ -14,11 +12,10 @@ func TestF(t *testing.T) {
//toEthereumTestCase(test)
h := test.hIn
F(&h, test.m, test.c, test.f, test.rounds)
if !reflect.DeepEqual(test.hOut, h) {
t.Errorf("Unexpected result\nExpected: [%v]\nActual: [%v]\n", test.hOut, h)
t.Errorf("Unexpected result\nExpected: [%#x]\nActual: [%#x]\n", test.hOut, h)
}
})
}
......@@ -60,50 +57,3 @@ var testVectorsF = []testVector{
},
},
}
// toEthereumTestCase transforms F test vector into test vector format used by
// go-ethereum precompiles
func toEthereumTestCase(vector testVector) {
var memory [213]byte
// 4 bytes for rounds
binary.BigEndian.PutUint32(memory[0:4], uint32(vector.rounds))
// for h (512 bits = 64 bytes)
for i := 0; i < 8; i++ {
offset := 4 + i*8
binary.LittleEndian.PutUint64(memory[offset:offset+8], vector.hIn[i])
}
// for m (1024 bits = 128 bytes)
for i := 0; i < 16; i++ {
offset := 68 + i*8
binary.LittleEndian.PutUint64(memory[offset:offset+8], vector.m[i])
}
// 8 bytes for t[0], 8 bytes for t[1]
binary.LittleEndian.PutUint64(memory[196:204], vector.c[0])
binary.LittleEndian.PutUint64(memory[204:212], vector.c[1])
// 1 byte for f
if vector.f {
memory[212] = 1
}
fmt.Printf("input: \"%v\"\n", hex.EncodeToString(memory[:]))
var result [64]byte
binary.LittleEndian.PutUint64(result[0:8], vector.hOut[0])
binary.LittleEndian.PutUint64(result[8:16], vector.hOut[1])
binary.LittleEndian.PutUint64(result[16:24], vector.hOut[2])
binary.LittleEndian.PutUint64(result[24:32], vector.hOut[3])
binary.LittleEndian.PutUint64(result[32:40], vector.hOut[4])
binary.LittleEndian.PutUint64(result[40:48], vector.hOut[5])
binary.LittleEndian.PutUint64(result[48:56], vector.hOut[6])
binary.LittleEndian.PutUint64(result[56:64], vector.hOut[7])
fmt.Printf("expected: \"%v\"\n", hex.EncodeToString(result[:]))
}
crypto/blake2b/f.go → crypto/blake2b/blake2b_generic.go
View file @ 1bccafe5
......@@ -2,21 +2,13 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Modified by The Keep Network Authors to adjust
// to EIP-152 precompile format.
package blake2b
import (
"encoding/binary"
"math/bits"
)
// IV is an initialization vector for BLAKE2b
var IV = [8]uint64{
0x6a09e667f3bcc908, 0xbb67ae8584caa73b, 0x3c6ef372fe94f82b, 0xa54ff53a5f1d36f1,
0x510e527fade682d1, 0x9b05688c2b3e6c1f, 0x1f83d9abfb41bd6b, 0x5be0cd19137e2179,
}
// the precomputed values for BLAKE2b
// there are 10 16-byte arrays - one for each round
// the entries are calculated from the sigma constants.
......@@ -33,24 +25,33 @@ var precomputed = [10][16]byte{
{10, 8, 7, 1, 2, 4, 6, 5, 15, 9, 3, 13, 11, 14, 12, 0},
}
// F is a compression function for BLAKE2b. It takes as an argument the state
// vector `h`, message block vector `m`, offset counter `t`, final
// block indicator flag `f`, and number of rounds `rounds`. The state vector
// provided as the first parameter is modified by the function.
func F(h *[8]uint64, m [16]uint64, c [2]uint64, f bool, rounds uint32) {
func hashBlocksGeneric(h *[8]uint64, c *[2]uint64, flag uint64, blocks []byte) {
var m [16]uint64
c0, c1 := c[0], c[1]
for i := 0; i < len(blocks); {
c0 += BlockSize
if c0 < BlockSize {
c1++
}
for j := range m {
m[j] = binary.LittleEndian.Uint64(blocks[i:])
i += 8
}
fGeneric(h, &m, c0, c1, flag, 12)
}
c[0], c[1] = c0, c1
}
func fGeneric(h *[8]uint64, m *[16]uint64, c0, c1 uint64, flag uint64, rounds uint64) {
v0, v1, v2, v3, v4, v5, v6, v7 := h[0], h[1], h[2], h[3], h[4], h[5], h[6], h[7]
v8, v9, v10, v11, v12, v13, v14, v15 := IV[0], IV[1], IV[2], IV[3], IV[4], IV[5], IV[6], IV[7]
v8, v9, v10, v11, v12, v13, v14, v15 := iv[0], iv[1], iv[2], iv[3], iv[4], iv[5], iv[6], iv[7]
v12 ^= c0
v13 ^= c1
v14 ^= flag
if f {
v14 ^= 0xffffffffffffffff
}
for j := uint32(0); j < rounds; j++ {
s := &(precomputed[j%10])
for i := 0; i < int(rounds); i++ {
s := &(precomputed[i%10])
v0 += m[s[0]]
v0 += v4
......@@ -167,9 +168,7 @@ func F(h *[8]uint64, m [16]uint64, c [2]uint64, f bool, rounds uint32) {
v9 += v14
v4 ^= v9
v4 = bits.RotateLeft64(v4, -63)
}
h[0] ^= v0 ^ v8
h[1] ^= v1 ^ v9
h[2] ^= v2 ^ v10
......
crypto/blake2b/blake2b_ref.go 0 → 100644
View file @ 1bccafe5
// Copyright 2016 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 !amd64 appengine gccgo
package blake2b
func hashBlocks(h *[8]uint64, c *[2]uint64, flag uint64, blocks []byte) {
hashBlocksGeneric(h, c, flag, blocks)
}
func f(h *[8]uint64, m [16]uint64, c0, c1 uint64, flag uint64, rounds int) {
fGeneric(h, m, c0, c1, flag, rounds)
}
crypto/blake2b/blake2b_test.go 0 → 100644
View file @ 1bccafe5
This source diff could not be displayed because it is too large. You can view the blob instead.
crypto/blake2b/blake2x.go 0 → 100644
View file @ 1bccafe5
// Copyright 2017 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.
package blake2b
import (
"encoding/binary"
"errors"
"io"
)
// XOF defines the interface to hash functions that
// support arbitrary-length output.
type XOF interface {
// Write absorbs more data into the hash's state. It panics if called
// after Read.
io.Writer
// Read reads more output from the hash. It returns io.EOF if the limit
// has been reached.
io.Reader
// Clone returns a copy of the XOF in its current state.
Clone() XOF
// Reset resets the XOF to its initial state.
Reset()
}
// OutputLengthUnknown can be used as the size argument to NewXOF to indicate
// the length of the output is not known in advance.
const OutputLengthUnknown = 0
// magicUnknownOutputLength is a magic value for the output size that indicates
// an unknown number of output bytes.
const magicUnknownOutputLength = (1 << 32) - 1
// maxOutputLength is the absolute maximum number of bytes to produce when the
// number of output bytes is unknown.
const maxOutputLength = (1 << 32) * 64
// NewXOF creates a new variable-output-length hash. The hash either produce a
// known number of bytes (1 <= size < 2**32-1), or an unknown number of bytes
// (size == OutputLengthUnknown). In the latter case, an absolute limit of
// 256GiB applies.
//
// A non-nil key turns the hash into a MAC. The key must between
// zero and 32 bytes long.
func NewXOF(size uint32, key []byte) (XOF, error) {
if len(key) > Size {
return nil, errKeySize
}
if size == magicUnknownOutputLength {
// 2^32-1 indicates an unknown number of bytes and thus isn't a
// valid length.
return nil, errors.New("blake2b: XOF length too large")
}
if size == OutputLengthUnknown {
size = magicUnknownOutputLength
}
x := &xof{
d: digest{
size: Size,
keyLen: len(key),
},
length: size,
}
copy(x.d.key[:], key)
x.Reset()
return x, nil
}
type xof struct {
d digest
length uint32
remaining uint64
cfg, root, block [Size]byte
offset int
nodeOffset uint32
readMode bool
}
func (x *xof) Write(p []byte) (n int, err error) {
if x.readMode {
panic("blake2b: write to XOF after read")
}
return x.d.Write(p)
}
func (x *xof) Clone() XOF {
clone := *x
return &clone
}
func (x *xof) Reset() {
x.cfg[0] = byte(Size)
binary.LittleEndian.PutUint32(x.cfg[4:], uint32(Size)) // leaf length
binary.LittleEndian.PutUint32(x.cfg[12:], x.length) // XOF length
x.cfg[17] = byte(Size) // inner hash size
x.d.Reset()
x.d.h[1] ^= uint64(x.length) << 32
x.remaining = uint64(x.length)
if x.remaining == magicUnknownOutputLength {
x.remaining = maxOutputLength
}
x.offset, x.nodeOffset = 0, 0
x.readMode = false
}
func (x *xof) Read(p []byte) (n int, err error) {
if !x.readMode {
x.d.finalize(&x.root)
x.readMode = true
}
if x.remaining == 0 {
return 0, io.EOF
}
n = len(p)
if uint64(n) > x.remaining {
n = int(x.remaining)
p = p[:n]
}
if x.offset > 0 {
blockRemaining := Size - x.offset
if n < blockRemaining {
x.offset += copy(p, x.block[x.offset:])
x.remaining -= uint64(n)
return
}
copy(p, x.block[x.offset:])
p = p[blockRemaining:]
x.offset = 0
x.remaining -= uint64(blockRemaining)
}
for len(p) >= Size {
binary.LittleEndian.PutUint32(x.cfg[8:], x.nodeOffset)
x.nodeOffset++
x.d.initConfig(&x.cfg)
x.d.Write(x.root[:])
x.d.finalize(&x.block)
copy(p, x.block[:])
p = p[Size:]
x.remaining -= uint64(Size)
}
if todo := len(p); todo > 0 {
if x.remaining < uint64(Size) {
x.cfg[0] = byte(x.remaining)
}
binary.LittleEndian.PutUint32(x.cfg[8:], x.nodeOffset)
x.nodeOffset++
x.d.initConfig(&x.cfg)
x.d.Write(x.root[:])
x.d.finalize(&x.block)
x.offset = copy(p, x.block[:todo])
x.remaining -= uint64(todo)
}
return
}
func (d *digest) initConfig(cfg *[Size]byte) {
d.offset, d.c[0], d.c[1] = 0, 0, 0
for i := range d.h {
d.h[i] = iv[i] ^ binary.LittleEndian.Uint64(cfg[i*8:])
}
}
crypto/blake2b/register.go 0 → 100644
View file @ 1bccafe5
// Copyright 2017 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 go1.9
package blake2b
import (
"crypto"
"hash"
)
func init() {
newHash256 := func() hash.Hash {
h, _ := New256(nil)
return h
}
newHash384 := func() hash.Hash {
h, _ := New384(nil)
return h
}
newHash512 := func() hash.Hash {
h, _ := New512(nil)
return h
}
crypto.RegisterHash(crypto.BLAKE2b_256, newHash256)
crypto.RegisterHash(crypto.BLAKE2b_384, newHash384)
crypto.RegisterHash(crypto.BLAKE2b_512, newHash512)
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment