// +build amd64 // // Minimalist Object Storage, (C) 2015 Minio, Inc. // // Licensed under the Apache License, Version 2.0 (the "License"); // you may not use this file except in compliance with the License. // You may obtain a copy of the License at // // http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. // Software block transform are provided by The Go Authors: // Copyright 2009 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 of // Golang project: // https://github.com/golang/go/blob/master/LICENSE package sha256 // #cgo CFLAGS: -DHAS_SSE41 -DHAS_AVX -DHAS_AVX2 // #include <stdint.h> // void sha256_transform_ssse3 (const char *input_data, uint32_t *digest, unsigned long num_blks); // void sha256_transform_avx (const char *input_data, uint32_t *digest, unsigned long num_blks); // void sha256_transform_rorx (const char *input_data, uint32_t *digest, unsigned long num_blks); import "C" import "unsafe" func blockSSE(dig *digest, p []byte) { C.sha256_transform_ssse3((*C.char)(unsafe.Pointer(&p[0])), (*C.uint32_t)(unsafe.Pointer(&dig.h[0])), (C.ulong)(len(p)/64)) } func blockAVX(dig *digest, p []byte) { C.sha256_transform_avx((*C.char)(unsafe.Pointer(&p[0])), (*C.uint32_t)(unsafe.Pointer(&dig.h[0])), (C.ulong)(len(p)/64)) } func blockAVX2(dig *digest, p []byte) { C.sha256_transform_rorx((*C.char)(unsafe.Pointer(&p[0])), (*C.uint32_t)(unsafe.Pointer(&dig.h[0])), (C.ulong)(len(p)/64)) } func blockSoftware(dig *digest, p []byte) { var w [64]uint32 h0, h1, h2, h3, h4, h5, h6, h7 := dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] for len(p) >= chunk { // Can interlace the computation of w with the // rounds below if needed for speed. for i := 0; i < 16; i++ { j := i * 4 w[i] = uint32(p[j])<<24 | uint32(p[j+1])<<16 | uint32(p[j+2])<<8 | uint32(p[j+3]) } for i := 16; i < 64; i++ { v1 := w[i-2] t1 := (v1>>17 | v1<<(32-17)) ^ (v1>>19 | v1<<(32-19)) ^ (v1 >> 10) v2 := w[i-15] t2 := (v2>>7 | v2<<(32-7)) ^ (v2>>18 | v2<<(32-18)) ^ (v2 >> 3) w[i] = t1 + w[i-7] + t2 + w[i-16] } a, b, c, d, e, f, g, h := h0, h1, h2, h3, h4, h5, h6, h7 for i := 0; i < 64; i++ { t1 := h + ((e>>6 | e<<(32-6)) ^ (e>>11 | e<<(32-11)) ^ (e>>25 | e<<(32-25))) + ((e & f) ^ (^e & g)) + _K[i] + w[i] t2 := ((a>>2 | a<<(32-2)) ^ (a>>13 | a<<(32-13)) ^ (a>>22 | a<<(32-22))) + ((a & b) ^ (a & c) ^ (b & c)) h = g g = f f = e e = d + t1 d = c c = b b = a a = t1 + t2 } h0 += a h1 += b h2 += c h3 += d h4 += e h5 += f h6 += g h7 += h p = p[chunk:] } dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] = h0, h1, h2, h3, h4, h5, h6, h7 } var _K = []uint32{ 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da, 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070, 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2, }