2018-03-09 08:23:35 +08:00
|
|
|
//====- SHA1.cpp - Private copy of the SHA1 implementation ---*- C++ -* ======//
|
2016-04-01 12:30:16 +08:00
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
SHA1: unroll loop in hashBlock.
This code is taken from public domain.
https://github.com/jsonn/src/blob/trunk/common/lib/libc/hash/sha1/sha1.c
I wrote a sha1 command and ran it on my Xeon E5-2680 v2 2.80GHz machine.
Here is a result. The new hash function is 37% faster than before.
Performance counter stats for './llvm-sha1-old /ssd/build/bin/lld' (10 runs):
6640.503687 task-clock (msec) # 1.001 CPUs utilized ( +- 0.03% )
54 context-switches # 0.008 K/sec ( +- 5.03% )
5 cpu-migrations # 0.001 K/sec ( +- 31.73% )
183,803 page-faults # 0.028 M/sec ( +- 0.00% )
18,527,954,113 cycles # 2.790 GHz ( +- 0.03% )
4,993,237,485 stalled-cycles-frontend # 26.95% frontend cycles idle ( +- 0.11% )
<not supported> stalled-cycles-backend
50,217,149,423 instructions # 2.71 insns per cycle
# 0.10 stalled cycles per insn ( +- 0.00% )
6,094,322,337 branches # 917.750 M/sec ( +- 0.00% )
11,778,239 branch-misses # 0.19% of all branches ( +- 0.01% )
6.634017401 seconds time elapsed ( +- 0.03% )
Performance counter stats for './llvm-sha1-new /ssd/build/bin/lld' (10 runs):
4167.062720 task-clock (msec) # 1.001 CPUs utilized ( +- 0.02% )
52 context-switches # 0.012 K/sec ( +- 16.45% )
7 cpu-migrations # 0.002 K/sec ( +- 32.20% )
183,804 page-faults # 0.044 M/sec ( +- 0.00% )
11,626,611,958 cycles # 2.790 GHz ( +- 0.02% )
4,491,897,976 stalled-cycles-frontend # 38.63% frontend cycles idle ( +- 0.05% )
<not supported> stalled-cycles-backend
24,320,180,617 instructions # 2.09 insns per cycle
# 0.18 stalled cycles per insn ( +- 0.00% )
1,574,674,576 branches # 377.886 M/sec ( +- 0.00% )
11,769,693 branch-misses # 0.75% of all branches ( +- 0.00% )
4.163251552 seconds time elapsed ( +- 0.02% )
Differential Revision: https://reviews.llvm.org/D26890
llvm-svn: 287473
2016-11-20 09:03:22 +08:00
|
|
|
//
|
2016-04-01 12:30:16 +08:00
|
|
|
// This code is taken from public domain
|
SHA1: unroll loop in hashBlock.
This code is taken from public domain.
https://github.com/jsonn/src/blob/trunk/common/lib/libc/hash/sha1/sha1.c
I wrote a sha1 command and ran it on my Xeon E5-2680 v2 2.80GHz machine.
Here is a result. The new hash function is 37% faster than before.
Performance counter stats for './llvm-sha1-old /ssd/build/bin/lld' (10 runs):
6640.503687 task-clock (msec) # 1.001 CPUs utilized ( +- 0.03% )
54 context-switches # 0.008 K/sec ( +- 5.03% )
5 cpu-migrations # 0.001 K/sec ( +- 31.73% )
183,803 page-faults # 0.028 M/sec ( +- 0.00% )
18,527,954,113 cycles # 2.790 GHz ( +- 0.03% )
4,993,237,485 stalled-cycles-frontend # 26.95% frontend cycles idle ( +- 0.11% )
<not supported> stalled-cycles-backend
50,217,149,423 instructions # 2.71 insns per cycle
# 0.10 stalled cycles per insn ( +- 0.00% )
6,094,322,337 branches # 917.750 M/sec ( +- 0.00% )
11,778,239 branch-misses # 0.19% of all branches ( +- 0.01% )
6.634017401 seconds time elapsed ( +- 0.03% )
Performance counter stats for './llvm-sha1-new /ssd/build/bin/lld' (10 runs):
4167.062720 task-clock (msec) # 1.001 CPUs utilized ( +- 0.02% )
52 context-switches # 0.012 K/sec ( +- 16.45% )
7 cpu-migrations # 0.002 K/sec ( +- 32.20% )
183,804 page-faults # 0.044 M/sec ( +- 0.00% )
11,626,611,958 cycles # 2.790 GHz ( +- 0.02% )
4,491,897,976 stalled-cycles-frontend # 38.63% frontend cycles idle ( +- 0.05% )
<not supported> stalled-cycles-backend
24,320,180,617 instructions # 2.09 insns per cycle
# 0.18 stalled cycles per insn ( +- 0.00% )
1,574,674,576 branches # 377.886 M/sec ( +- 0.00% )
11,769,693 branch-misses # 0.75% of all branches ( +- 0.00% )
4.163251552 seconds time elapsed ( +- 0.02% )
Differential Revision: https://reviews.llvm.org/D26890
llvm-svn: 287473
2016-11-20 09:03:22 +08:00
|
|
|
// (http://oauth.googlecode.com/svn/code/c/liboauth/src/sha1.c and
|
|
|
|
// http://cvsweb.netbsd.org/bsdweb.cgi/src/common/lib/libc/hash/sha1/sha1.c?rev=1.6)
|
2016-04-01 12:30:16 +08:00
|
|
|
// and modified by wrapping it in a C++ interface for LLVM,
|
|
|
|
// and removing unnecessary code.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "llvm/Support/SHA1.h"
|
2016-04-18 17:17:29 +08:00
|
|
|
#include "llvm/ADT/ArrayRef.h"
|
2017-06-06 19:49:48 +08:00
|
|
|
#include "llvm/Support/Host.h"
|
2016-04-06 04:19:49 +08:00
|
|
|
using namespace llvm;
|
2016-04-01 12:30:16 +08:00
|
|
|
|
2016-04-06 04:45:04 +08:00
|
|
|
#include <stdint.h>
|
|
|
|
#include <string.h>
|
|
|
|
|
2016-04-01 13:12:24 +08:00
|
|
|
#if defined(BYTE_ORDER) && defined(BIG_ENDIAN) && BYTE_ORDER == BIG_ENDIAN
|
2016-04-01 12:30:16 +08:00
|
|
|
#define SHA_BIG_ENDIAN
|
|
|
|
#endif
|
|
|
|
|
2016-11-20 09:15:56 +08:00
|
|
|
static uint32_t rol(uint32_t Number, int Bits) {
|
|
|
|
return (Number << Bits) | (Number >> (32 - Bits));
|
2016-11-20 09:13:22 +08:00
|
|
|
}
|
SHA1: unroll loop in hashBlock.
This code is taken from public domain.
https://github.com/jsonn/src/blob/trunk/common/lib/libc/hash/sha1/sha1.c
I wrote a sha1 command and ran it on my Xeon E5-2680 v2 2.80GHz machine.
Here is a result. The new hash function is 37% faster than before.
Performance counter stats for './llvm-sha1-old /ssd/build/bin/lld' (10 runs):
6640.503687 task-clock (msec) # 1.001 CPUs utilized ( +- 0.03% )
54 context-switches # 0.008 K/sec ( +- 5.03% )
5 cpu-migrations # 0.001 K/sec ( +- 31.73% )
183,803 page-faults # 0.028 M/sec ( +- 0.00% )
18,527,954,113 cycles # 2.790 GHz ( +- 0.03% )
4,993,237,485 stalled-cycles-frontend # 26.95% frontend cycles idle ( +- 0.11% )
<not supported> stalled-cycles-backend
50,217,149,423 instructions # 2.71 insns per cycle
# 0.10 stalled cycles per insn ( +- 0.00% )
6,094,322,337 branches # 917.750 M/sec ( +- 0.00% )
11,778,239 branch-misses # 0.19% of all branches ( +- 0.01% )
6.634017401 seconds time elapsed ( +- 0.03% )
Performance counter stats for './llvm-sha1-new /ssd/build/bin/lld' (10 runs):
4167.062720 task-clock (msec) # 1.001 CPUs utilized ( +- 0.02% )
52 context-switches # 0.012 K/sec ( +- 16.45% )
7 cpu-migrations # 0.002 K/sec ( +- 32.20% )
183,804 page-faults # 0.044 M/sec ( +- 0.00% )
11,626,611,958 cycles # 2.790 GHz ( +- 0.02% )
4,491,897,976 stalled-cycles-frontend # 38.63% frontend cycles idle ( +- 0.05% )
<not supported> stalled-cycles-backend
24,320,180,617 instructions # 2.09 insns per cycle
# 0.18 stalled cycles per insn ( +- 0.00% )
1,574,674,576 branches # 377.886 M/sec ( +- 0.00% )
11,769,693 branch-misses # 0.75% of all branches ( +- 0.00% )
4.163251552 seconds time elapsed ( +- 0.02% )
Differential Revision: https://reviews.llvm.org/D26890
llvm-svn: 287473
2016-11-20 09:03:22 +08:00
|
|
|
|
|
|
|
static uint32_t blk0(uint32_t *Buf, int I) { return Buf[I]; }
|
|
|
|
|
|
|
|
static uint32_t blk(uint32_t *Buf, int I) {
|
|
|
|
Buf[I & 15] = rol(Buf[(I + 13) & 15] ^ Buf[(I + 8) & 15] ^ Buf[(I + 2) & 15] ^
|
|
|
|
Buf[I & 15],
|
|
|
|
1);
|
|
|
|
return Buf[I & 15];
|
|
|
|
}
|
|
|
|
|
|
|
|
static void r0(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
|
|
|
|
int I, uint32_t *Buf) {
|
|
|
|
E += ((B & (C ^ D)) ^ D) + blk0(Buf, I) + 0x5A827999 + rol(A, 5);
|
|
|
|
B = rol(B, 30);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void r1(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
|
|
|
|
int I, uint32_t *Buf) {
|
|
|
|
E += ((B & (C ^ D)) ^ D) + blk(Buf, I) + 0x5A827999 + rol(A, 5);
|
|
|
|
B = rol(B, 30);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void r2(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
|
|
|
|
int I, uint32_t *Buf) {
|
|
|
|
E += (B ^ C ^ D) + blk(Buf, I) + 0x6ED9EBA1 + rol(A, 5);
|
|
|
|
B = rol(B, 30);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void r3(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
|
|
|
|
int I, uint32_t *Buf) {
|
|
|
|
E += (((B | C) & D) | (B & C)) + blk(Buf, I) + 0x8F1BBCDC + rol(A, 5);
|
|
|
|
B = rol(B, 30);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void r4(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
|
|
|
|
int I, uint32_t *Buf) {
|
|
|
|
E += (B ^ C ^ D) + blk(Buf, I) + 0xCA62C1D6 + rol(A, 5);
|
|
|
|
B = rol(B, 30);
|
|
|
|
}
|
|
|
|
|
2016-04-01 12:30:16 +08:00
|
|
|
/* code */
|
|
|
|
#define SHA1_K0 0x5a827999
|
|
|
|
#define SHA1_K20 0x6ed9eba1
|
|
|
|
#define SHA1_K40 0x8f1bbcdc
|
|
|
|
#define SHA1_K60 0xca62c1d6
|
|
|
|
|
|
|
|
#define SEED_0 0x67452301
|
|
|
|
#define SEED_1 0xefcdab89
|
|
|
|
#define SEED_2 0x98badcfe
|
|
|
|
#define SEED_3 0x10325476
|
|
|
|
#define SEED_4 0xc3d2e1f0
|
|
|
|
|
|
|
|
void SHA1::init() {
|
|
|
|
InternalState.State[0] = SEED_0;
|
|
|
|
InternalState.State[1] = SEED_1;
|
|
|
|
InternalState.State[2] = SEED_2;
|
|
|
|
InternalState.State[3] = SEED_3;
|
|
|
|
InternalState.State[4] = SEED_4;
|
|
|
|
InternalState.ByteCount = 0;
|
|
|
|
InternalState.BufferOffset = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void SHA1::hashBlock() {
|
SHA1: unroll loop in hashBlock.
This code is taken from public domain.
https://github.com/jsonn/src/blob/trunk/common/lib/libc/hash/sha1/sha1.c
I wrote a sha1 command and ran it on my Xeon E5-2680 v2 2.80GHz machine.
Here is a result. The new hash function is 37% faster than before.
Performance counter stats for './llvm-sha1-old /ssd/build/bin/lld' (10 runs):
6640.503687 task-clock (msec) # 1.001 CPUs utilized ( +- 0.03% )
54 context-switches # 0.008 K/sec ( +- 5.03% )
5 cpu-migrations # 0.001 K/sec ( +- 31.73% )
183,803 page-faults # 0.028 M/sec ( +- 0.00% )
18,527,954,113 cycles # 2.790 GHz ( +- 0.03% )
4,993,237,485 stalled-cycles-frontend # 26.95% frontend cycles idle ( +- 0.11% )
<not supported> stalled-cycles-backend
50,217,149,423 instructions # 2.71 insns per cycle
# 0.10 stalled cycles per insn ( +- 0.00% )
6,094,322,337 branches # 917.750 M/sec ( +- 0.00% )
11,778,239 branch-misses # 0.19% of all branches ( +- 0.01% )
6.634017401 seconds time elapsed ( +- 0.03% )
Performance counter stats for './llvm-sha1-new /ssd/build/bin/lld' (10 runs):
4167.062720 task-clock (msec) # 1.001 CPUs utilized ( +- 0.02% )
52 context-switches # 0.012 K/sec ( +- 16.45% )
7 cpu-migrations # 0.002 K/sec ( +- 32.20% )
183,804 page-faults # 0.044 M/sec ( +- 0.00% )
11,626,611,958 cycles # 2.790 GHz ( +- 0.02% )
4,491,897,976 stalled-cycles-frontend # 38.63% frontend cycles idle ( +- 0.05% )
<not supported> stalled-cycles-backend
24,320,180,617 instructions # 2.09 insns per cycle
# 0.18 stalled cycles per insn ( +- 0.00% )
1,574,674,576 branches # 377.886 M/sec ( +- 0.00% )
11,769,693 branch-misses # 0.75% of all branches ( +- 0.00% )
4.163251552 seconds time elapsed ( +- 0.02% )
Differential Revision: https://reviews.llvm.org/D26890
llvm-svn: 287473
2016-11-20 09:03:22 +08:00
|
|
|
uint32_t A = InternalState.State[0];
|
|
|
|
uint32_t B = InternalState.State[1];
|
|
|
|
uint32_t C = InternalState.State[2];
|
|
|
|
uint32_t D = InternalState.State[3];
|
|
|
|
uint32_t E = InternalState.State[4];
|
|
|
|
|
|
|
|
// 4 rounds of 20 operations each. Loop unrolled.
|
|
|
|
r0(A, B, C, D, E, 0, InternalState.Buffer.L);
|
|
|
|
r0(E, A, B, C, D, 1, InternalState.Buffer.L);
|
|
|
|
r0(D, E, A, B, C, 2, InternalState.Buffer.L);
|
|
|
|
r0(C, D, E, A, B, 3, InternalState.Buffer.L);
|
|
|
|
r0(B, C, D, E, A, 4, InternalState.Buffer.L);
|
|
|
|
r0(A, B, C, D, E, 5, InternalState.Buffer.L);
|
|
|
|
r0(E, A, B, C, D, 6, InternalState.Buffer.L);
|
|
|
|
r0(D, E, A, B, C, 7, InternalState.Buffer.L);
|
|
|
|
r0(C, D, E, A, B, 8, InternalState.Buffer.L);
|
|
|
|
r0(B, C, D, E, A, 9, InternalState.Buffer.L);
|
|
|
|
r0(A, B, C, D, E, 10, InternalState.Buffer.L);
|
|
|
|
r0(E, A, B, C, D, 11, InternalState.Buffer.L);
|
|
|
|
r0(D, E, A, B, C, 12, InternalState.Buffer.L);
|
|
|
|
r0(C, D, E, A, B, 13, InternalState.Buffer.L);
|
|
|
|
r0(B, C, D, E, A, 14, InternalState.Buffer.L);
|
|
|
|
r0(A, B, C, D, E, 15, InternalState.Buffer.L);
|
|
|
|
r1(E, A, B, C, D, 16, InternalState.Buffer.L);
|
|
|
|
r1(D, E, A, B, C, 17, InternalState.Buffer.L);
|
|
|
|
r1(C, D, E, A, B, 18, InternalState.Buffer.L);
|
|
|
|
r1(B, C, D, E, A, 19, InternalState.Buffer.L);
|
|
|
|
|
|
|
|
r2(A, B, C, D, E, 20, InternalState.Buffer.L);
|
|
|
|
r2(E, A, B, C, D, 21, InternalState.Buffer.L);
|
|
|
|
r2(D, E, A, B, C, 22, InternalState.Buffer.L);
|
|
|
|
r2(C, D, E, A, B, 23, InternalState.Buffer.L);
|
|
|
|
r2(B, C, D, E, A, 24, InternalState.Buffer.L);
|
|
|
|
r2(A, B, C, D, E, 25, InternalState.Buffer.L);
|
|
|
|
r2(E, A, B, C, D, 26, InternalState.Buffer.L);
|
|
|
|
r2(D, E, A, B, C, 27, InternalState.Buffer.L);
|
|
|
|
r2(C, D, E, A, B, 28, InternalState.Buffer.L);
|
|
|
|
r2(B, C, D, E, A, 29, InternalState.Buffer.L);
|
|
|
|
r2(A, B, C, D, E, 30, InternalState.Buffer.L);
|
|
|
|
r2(E, A, B, C, D, 31, InternalState.Buffer.L);
|
|
|
|
r2(D, E, A, B, C, 32, InternalState.Buffer.L);
|
|
|
|
r2(C, D, E, A, B, 33, InternalState.Buffer.L);
|
|
|
|
r2(B, C, D, E, A, 34, InternalState.Buffer.L);
|
|
|
|
r2(A, B, C, D, E, 35, InternalState.Buffer.L);
|
|
|
|
r2(E, A, B, C, D, 36, InternalState.Buffer.L);
|
|
|
|
r2(D, E, A, B, C, 37, InternalState.Buffer.L);
|
|
|
|
r2(C, D, E, A, B, 38, InternalState.Buffer.L);
|
|
|
|
r2(B, C, D, E, A, 39, InternalState.Buffer.L);
|
|
|
|
|
|
|
|
r3(A, B, C, D, E, 40, InternalState.Buffer.L);
|
|
|
|
r3(E, A, B, C, D, 41, InternalState.Buffer.L);
|
|
|
|
r3(D, E, A, B, C, 42, InternalState.Buffer.L);
|
|
|
|
r3(C, D, E, A, B, 43, InternalState.Buffer.L);
|
|
|
|
r3(B, C, D, E, A, 44, InternalState.Buffer.L);
|
|
|
|
r3(A, B, C, D, E, 45, InternalState.Buffer.L);
|
|
|
|
r3(E, A, B, C, D, 46, InternalState.Buffer.L);
|
|
|
|
r3(D, E, A, B, C, 47, InternalState.Buffer.L);
|
|
|
|
r3(C, D, E, A, B, 48, InternalState.Buffer.L);
|
|
|
|
r3(B, C, D, E, A, 49, InternalState.Buffer.L);
|
|
|
|
r3(A, B, C, D, E, 50, InternalState.Buffer.L);
|
|
|
|
r3(E, A, B, C, D, 51, InternalState.Buffer.L);
|
|
|
|
r3(D, E, A, B, C, 52, InternalState.Buffer.L);
|
|
|
|
r3(C, D, E, A, B, 53, InternalState.Buffer.L);
|
|
|
|
r3(B, C, D, E, A, 54, InternalState.Buffer.L);
|
|
|
|
r3(A, B, C, D, E, 55, InternalState.Buffer.L);
|
|
|
|
r3(E, A, B, C, D, 56, InternalState.Buffer.L);
|
|
|
|
r3(D, E, A, B, C, 57, InternalState.Buffer.L);
|
|
|
|
r3(C, D, E, A, B, 58, InternalState.Buffer.L);
|
|
|
|
r3(B, C, D, E, A, 59, InternalState.Buffer.L);
|
|
|
|
|
|
|
|
r4(A, B, C, D, E, 60, InternalState.Buffer.L);
|
|
|
|
r4(E, A, B, C, D, 61, InternalState.Buffer.L);
|
|
|
|
r4(D, E, A, B, C, 62, InternalState.Buffer.L);
|
|
|
|
r4(C, D, E, A, B, 63, InternalState.Buffer.L);
|
|
|
|
r4(B, C, D, E, A, 64, InternalState.Buffer.L);
|
|
|
|
r4(A, B, C, D, E, 65, InternalState.Buffer.L);
|
|
|
|
r4(E, A, B, C, D, 66, InternalState.Buffer.L);
|
|
|
|
r4(D, E, A, B, C, 67, InternalState.Buffer.L);
|
|
|
|
r4(C, D, E, A, B, 68, InternalState.Buffer.L);
|
|
|
|
r4(B, C, D, E, A, 69, InternalState.Buffer.L);
|
|
|
|
r4(A, B, C, D, E, 70, InternalState.Buffer.L);
|
|
|
|
r4(E, A, B, C, D, 71, InternalState.Buffer.L);
|
|
|
|
r4(D, E, A, B, C, 72, InternalState.Buffer.L);
|
|
|
|
r4(C, D, E, A, B, 73, InternalState.Buffer.L);
|
|
|
|
r4(B, C, D, E, A, 74, InternalState.Buffer.L);
|
|
|
|
r4(A, B, C, D, E, 75, InternalState.Buffer.L);
|
|
|
|
r4(E, A, B, C, D, 76, InternalState.Buffer.L);
|
|
|
|
r4(D, E, A, B, C, 77, InternalState.Buffer.L);
|
|
|
|
r4(C, D, E, A, B, 78, InternalState.Buffer.L);
|
|
|
|
r4(B, C, D, E, A, 79, InternalState.Buffer.L);
|
|
|
|
|
|
|
|
InternalState.State[0] += A;
|
|
|
|
InternalState.State[1] += B;
|
|
|
|
InternalState.State[2] += C;
|
|
|
|
InternalState.State[3] += D;
|
|
|
|
InternalState.State[4] += E;
|
2016-04-01 12:30:16 +08:00
|
|
|
}
|
|
|
|
|
2016-11-20 09:15:56 +08:00
|
|
|
void SHA1::addUncounted(uint8_t Data) {
|
2016-04-01 12:30:16 +08:00
|
|
|
#ifdef SHA_BIG_ENDIAN
|
2016-11-20 09:15:56 +08:00
|
|
|
InternalState.Buffer.C[InternalState.BufferOffset] = Data;
|
2016-04-01 12:30:16 +08:00
|
|
|
#else
|
2016-11-20 09:15:56 +08:00
|
|
|
InternalState.Buffer.C[InternalState.BufferOffset ^ 3] = Data;
|
2016-04-01 12:30:16 +08:00
|
|
|
#endif
|
SHA1: unroll loop in hashBlock.
This code is taken from public domain.
https://github.com/jsonn/src/blob/trunk/common/lib/libc/hash/sha1/sha1.c
I wrote a sha1 command and ran it on my Xeon E5-2680 v2 2.80GHz machine.
Here is a result. The new hash function is 37% faster than before.
Performance counter stats for './llvm-sha1-old /ssd/build/bin/lld' (10 runs):
6640.503687 task-clock (msec) # 1.001 CPUs utilized ( +- 0.03% )
54 context-switches # 0.008 K/sec ( +- 5.03% )
5 cpu-migrations # 0.001 K/sec ( +- 31.73% )
183,803 page-faults # 0.028 M/sec ( +- 0.00% )
18,527,954,113 cycles # 2.790 GHz ( +- 0.03% )
4,993,237,485 stalled-cycles-frontend # 26.95% frontend cycles idle ( +- 0.11% )
<not supported> stalled-cycles-backend
50,217,149,423 instructions # 2.71 insns per cycle
# 0.10 stalled cycles per insn ( +- 0.00% )
6,094,322,337 branches # 917.750 M/sec ( +- 0.00% )
11,778,239 branch-misses # 0.19% of all branches ( +- 0.01% )
6.634017401 seconds time elapsed ( +- 0.03% )
Performance counter stats for './llvm-sha1-new /ssd/build/bin/lld' (10 runs):
4167.062720 task-clock (msec) # 1.001 CPUs utilized ( +- 0.02% )
52 context-switches # 0.012 K/sec ( +- 16.45% )
7 cpu-migrations # 0.002 K/sec ( +- 32.20% )
183,804 page-faults # 0.044 M/sec ( +- 0.00% )
11,626,611,958 cycles # 2.790 GHz ( +- 0.02% )
4,491,897,976 stalled-cycles-frontend # 38.63% frontend cycles idle ( +- 0.05% )
<not supported> stalled-cycles-backend
24,320,180,617 instructions # 2.09 insns per cycle
# 0.18 stalled cycles per insn ( +- 0.00% )
1,574,674,576 branches # 377.886 M/sec ( +- 0.00% )
11,769,693 branch-misses # 0.75% of all branches ( +- 0.00% )
4.163251552 seconds time elapsed ( +- 0.02% )
Differential Revision: https://reviews.llvm.org/D26890
llvm-svn: 287473
2016-11-20 09:03:22 +08:00
|
|
|
|
2016-04-01 12:30:16 +08:00
|
|
|
InternalState.BufferOffset++;
|
|
|
|
if (InternalState.BufferOffset == BLOCK_LENGTH) {
|
|
|
|
hashBlock();
|
|
|
|
InternalState.BufferOffset = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-11-20 09:15:56 +08:00
|
|
|
void SHA1::writebyte(uint8_t Data) {
|
2016-04-01 12:30:16 +08:00
|
|
|
++InternalState.ByteCount;
|
2016-11-20 09:15:56 +08:00
|
|
|
addUncounted(Data);
|
2016-04-01 12:30:16 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void SHA1::update(ArrayRef<uint8_t> Data) {
|
|
|
|
for (auto &C : Data)
|
|
|
|
writebyte(C);
|
|
|
|
}
|
|
|
|
|
|
|
|
void SHA1::pad() {
|
2016-04-01 13:12:24 +08:00
|
|
|
// Implement SHA-1 padding (fips180-2 5.1.1)
|
2016-04-01 12:30:16 +08:00
|
|
|
|
|
|
|
// Pad with 0x80 followed by 0x00 until the end of the block
|
|
|
|
addUncounted(0x80);
|
|
|
|
while (InternalState.BufferOffset != 56)
|
|
|
|
addUncounted(0x00);
|
|
|
|
|
|
|
|
// Append length in the last 8 bytes
|
|
|
|
addUncounted(0); // We're only using 32 bit lengths
|
|
|
|
addUncounted(0); // But SHA-1 supports 64 bit lengths
|
|
|
|
addUncounted(0); // So zero pad the top bits
|
|
|
|
addUncounted(InternalState.ByteCount >> 29); // Shifting to multiply by 8
|
|
|
|
addUncounted(InternalState.ByteCount >>
|
|
|
|
21); // as SHA-1 supports bitstreams as well as
|
|
|
|
addUncounted(InternalState.ByteCount >> 13); // byte.
|
|
|
|
addUncounted(InternalState.ByteCount >> 5);
|
|
|
|
addUncounted(InternalState.ByteCount << 3);
|
|
|
|
}
|
|
|
|
|
|
|
|
StringRef SHA1::final() {
|
|
|
|
// Pad to complete the last block
|
|
|
|
pad();
|
|
|
|
|
|
|
|
#ifdef SHA_BIG_ENDIAN
|
|
|
|
// Just copy the current state
|
|
|
|
for (int i = 0; i < 5; i++) {
|
|
|
|
HashResult[i] = InternalState.State[i];
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
// Swap byte order back
|
|
|
|
for (int i = 0; i < 5; i++) {
|
|
|
|
HashResult[i] = (((InternalState.State[i]) << 24) & 0xff000000) |
|
|
|
|
(((InternalState.State[i]) << 8) & 0x00ff0000) |
|
|
|
|
(((InternalState.State[i]) >> 8) & 0x0000ff00) |
|
|
|
|
(((InternalState.State[i]) >> 24) & 0x000000ff);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
// Return pointer to hash (20 characters)
|
|
|
|
return StringRef((char *)HashResult, HASH_LENGTH);
|
|
|
|
}
|
|
|
|
|
|
|
|
StringRef SHA1::result() {
|
|
|
|
auto StateToRestore = InternalState;
|
|
|
|
|
|
|
|
auto Hash = final();
|
|
|
|
|
|
|
|
// Restore the state
|
|
|
|
InternalState = StateToRestore;
|
|
|
|
|
|
|
|
// Return pointer to hash (20 characters)
|
|
|
|
return Hash;
|
|
|
|
}
|
2016-11-23 08:46:09 +08:00
|
|
|
|
|
|
|
std::array<uint8_t, 20> SHA1::hash(ArrayRef<uint8_t> Data) {
|
|
|
|
SHA1 Hash;
|
|
|
|
Hash.update(Data);
|
2016-11-23 11:58:12 +08:00
|
|
|
StringRef S = Hash.final();
|
2016-11-23 08:46:09 +08:00
|
|
|
|
|
|
|
std::array<uint8_t, 20> Arr;
|
|
|
|
memcpy(Arr.data(), S.data(), S.size());
|
|
|
|
return Arr;
|
|
|
|
}
|