Compare commits
2 Commits
| Author | SHA1 | Date |
|---|---|---|
 Inga 🏳🌈
|
8ce1001d45 | 8 years ago |
|
Inga 🏳🌈
|
5d2c16668b | 8 years ago |
@ -1,38 +0,0 @@ |
|||||||
#include "stdafx.h" |
|
||||||
|
|
||||||
using namespace System; |
|
||||||
using namespace System::Reflection; |
|
||||||
using namespace System::Runtime::CompilerServices; |
|
||||||
using namespace System::Runtime::InteropServices; |
|
||||||
using namespace System::Security::Permissions; |
|
||||||
|
|
||||||
//
|
|
||||||
// General Information about an assembly is controlled through the following
|
|
||||||
// set of attributes. Change these attribute values to modify the information
|
|
||||||
// associated with an assembly.
|
|
||||||
//
|
|
||||||
[assembly:AssemblyTitleAttribute(L"WhiteRabbitUnmanagedBridge")]; |
|
||||||
[assembly:AssemblyDescriptionAttribute(L"")]; |
|
||||||
[assembly:AssemblyConfigurationAttribute(L"")]; |
|
||||||
[assembly:AssemblyCompanyAttribute(L"")]; |
|
||||||
[assembly:AssemblyProductAttribute(L"WhiteRabbitUnmanagedBridge")]; |
|
||||||
[assembly:AssemblyCopyrightAttribute(L"Copyright (c) 2017")]; |
|
||||||
[assembly:AssemblyTrademarkAttribute(L"")]; |
|
||||||
[assembly:AssemblyCultureAttribute(L"")]; |
|
||||||
|
|
||||||
//
|
|
||||||
// Version information for an assembly consists of the following four values:
|
|
||||||
//
|
|
||||||
// Major Version
|
|
||||||
// Minor Version
|
|
||||||
// Build Number
|
|
||||||
// Revision
|
|
||||||
//
|
|
||||||
// You can specify all the value or you can default the Revision and Build Numbers
|
|
||||||
// by using the '*' as shown below:
|
|
||||||
|
|
||||||
[assembly:AssemblyVersionAttribute("1.0.*")]; |
|
||||||
|
|
||||||
[assembly:ComVisible(false)]; |
|
||||||
|
|
||||||
[assembly:CLSCompliantAttribute(true)]; |
|
||||||
@ -1,5 +0,0 @@ |
|||||||
// stdafx.cpp : source file that includes just the standard includes
|
|
||||||
// WhiteRabbit.Unmanaged.pch will be the pre-compiled header
|
|
||||||
// stdafx.obj will contain the pre-compiled type information
|
|
||||||
|
|
||||||
#include "stdafx.h" |
|
||||||
@ -1,7 +0,0 @@ |
|||||||
// stdafx.h : include file for standard system include files,
|
|
||||||
// or project specific include files that are used frequently,
|
|
||||||
// but are changed infrequently
|
|
||||||
|
|
||||||
#pragma once |
|
||||||
|
|
||||||
|
|
||||||
@ -1,32 +0,0 @@ |
|||||||
// This is the main DLL file.
|
|
||||||
|
|
||||||
#include "stdafx.h" |
|
||||||
|
|
||||||
#include "WhiteRabbit.UnmanagedBridge.h" |
|
||||||
#include "md5.h" |
|
||||||
#include "phraseset.h" |
|
||||||
|
|
||||||
void WhiteRabbitUnmanagedBridge::MD5Unmanaged::ComputeMD5(unsigned __int32 * input, unsigned __int32 * expected) |
|
||||||
{ |
|
||||||
#if AVX2 |
|
||||||
md5(input + 0 * 8 * 8, expected); |
|
||||||
#elif SIMD |
|
||||||
md5(input + 0 * 8 * 4); |
|
||||||
md5(input + 1 * 8 * 4); |
|
||||||
if (input[2 * 8 * 4] != 0) |
|
||||||
{ |
|
||||||
md5(input + 2 * 8 * 4); |
|
||||||
md5(input + 3 * 8 * 4); |
|
||||||
} |
|
||||||
#else |
|
||||||
for (int i = 0; i < 16; i++) |
|
||||||
{ |
|
||||||
md5(input + i * 8); |
|
||||||
} |
|
||||||
#endif |
|
||||||
} |
|
||||||
|
|
||||||
void WhiteRabbitUnmanagedBridge::MD5Unmanaged::FillPhraseSet(unsigned __int64* initialBufferPointer, unsigned __int64* bufferPointer, unsigned __int64* allWordsPointer, __int32* wordIndexes, unsigned __int64* permutationsPointer, int numberOfWords) |
|
||||||
{ |
|
||||||
fillPhraseSet(initialBufferPointer, bufferPointer, allWordsPointer, wordIndexes, permutationsPointer, numberOfWords); |
|
||||||
} |
|
||||||
@ -1,18 +0,0 @@ |
|||||||
// WhiteRabbit.Unmanaged.h
|
|
||||||
|
|
||||||
#pragma once |
|
||||||
|
|
||||||
#include "constants.h" |
|
||||||
|
|
||||||
using namespace System; |
|
||||||
|
|
||||||
namespace WhiteRabbitUnmanagedBridge { |
|
||||||
|
|
||||||
public ref class MD5Unmanaged |
|
||||||
{ |
|
||||||
public: |
|
||||||
literal int PhrasesPerSet = PHRASES_PER_SET; |
|
||||||
static void ComputeMD5(unsigned int* input, unsigned __int32 * expected); |
|
||||||
static void FillPhraseSet(unsigned __int64* initialBufferPointer, unsigned __int64* bufferPointer, unsigned __int64* allWordsPointer, __int32* wordIndexes, unsigned __int64* permutationsPointer, int numberOfWords); |
|
||||||
}; |
|
||||||
} |
|
||||||
@ -1,3 +0,0 @@ |
|||||||
#pragma once |
|
||||||
|
|
||||||
#define PHRASES_PER_SET 16 |
|
||||||
@ -1,236 +0,0 @@ |
|||||||
#include "stdafx.h" |
|
||||||
#include "md5.h" |
|
||||||
|
|
||||||
#include "intrin.h" |
|
||||||
|
|
||||||
#pragma unmanaged |
|
||||||
|
|
||||||
struct MD5Vector |
|
||||||
{ |
|
||||||
__m256i m_V0; |
|
||||||
__m256i m_V1; |
|
||||||
__forceinline MD5Vector() {} |
|
||||||
__forceinline MD5Vector(__m256i C0, __m256i C1) :m_V0(C0), m_V1(C1) {} |
|
||||||
|
|
||||||
__forceinline MD5Vector MXor(MD5Vector R) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_xor_si256(m_V0, R.m_V0), _mm256_xor_si256(m_V1, R.m_V1)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline MD5Vector MAnd(MD5Vector R) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_and_si256(m_V0, R.m_V0), _mm256_and_si256(m_V1, R.m_V1)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline MD5Vector MAndNot(MD5Vector R) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_andnot_si256(m_V0, R.m_V0), _mm256_andnot_si256(m_V1, R.m_V1)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline const MD5Vector MOr(const MD5Vector R) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_or_si256(m_V0, R.m_V0), _mm256_or_si256(m_V1, R.m_V1)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline const MD5Vector MAdd(const MD5Vector R) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_add_epi32(m_V0, R.m_V0), _mm256_add_epi32(m_V1, R.m_V1)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline const MD5Vector MShiftLeft(const int shift) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_slli_epi32(m_V0, shift), _mm256_slli_epi32(m_V1, shift)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline const MD5Vector MShiftRight(const int shift) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_srli_epi32(m_V0, shift), _mm256_srli_epi32(m_V1, shift)); |
|
||||||
} |
|
||||||
|
|
||||||
template<int imm8> |
|
||||||
__forceinline const MD5Vector Permute() const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_permute4x64_epi64(m_V0, imm8), _mm256_permute4x64_epi64(m_V1, imm8)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline const MD5Vector CompareEquality32(const __m256i other) const |
|
||||||
{ |
|
||||||
return MD5Vector(_mm256_cmpeq_epi32(m_V0, other), _mm256_cmpeq_epi32(m_V1, other)); |
|
||||||
} |
|
||||||
|
|
||||||
__forceinline void WriteMoveMask8(__int32 * output) const |
|
||||||
{ |
|
||||||
output[0] = _mm256_movemask_epi8(m_V0); |
|
||||||
output[1] = _mm256_movemask_epi8(m_V1); |
|
||||||
} |
|
||||||
}; |
|
||||||
|
|
||||||
__forceinline const MD5Vector OP_XOR(const MD5Vector a, const MD5Vector b) { return a.MXor(b); } |
|
||||||
__forceinline const MD5Vector OP_AND(const MD5Vector a, const MD5Vector b) { return a.MAnd(b); } |
|
||||||
__forceinline const MD5Vector OP_ANDNOT(const MD5Vector a, const MD5Vector b) { return a.MAndNot(b); } |
|
||||||
__forceinline const MD5Vector OP_OR(const MD5Vector a, const MD5Vector b) { return a.MOr(b); } |
|
||||||
__forceinline const MD5Vector OP_ADD(const MD5Vector a, const MD5Vector b) { return a.MAdd(b); } |
|
||||||
template<int r> |
|
||||||
__forceinline const MD5Vector OP_ROT(const MD5Vector a) { return OP_OR(a.MShiftLeft(r), a.MShiftRight(32 - (r))); } |
|
||||||
__forceinline const MD5Vector OP_BLEND(const MD5Vector a, const MD5Vector b, const MD5Vector x) { return OP_OR(OP_AND(x, b), OP_ANDNOT(x, a)); } |
|
||||||
|
|
||||||
__forceinline const MD5Vector CREATE_VECTOR(const int a) { return MD5Vector(_mm256_set1_epi32(a), _mm256_set1_epi32(a)); } |
|
||||||
__forceinline const MD5Vector CREATE_VECTOR_FROM_INPUT(const unsigned __int32* input, const size_t offset) |
|
||||||
{ |
|
||||||
return MD5Vector( |
|
||||||
_mm256_i32gather_epi32((int*)(input + offset), _mm256_set_epi32(7 * 8, 6 * 8, 5 * 8, 4 * 8, 3 * 8, 2 * 8, 1 * 8, 0 * 8), 4), |
|
||||||
_mm256_i32gather_epi32((int*)(input + offset), _mm256_set_epi32(15 * 8, 14 * 8, 13 * 8, 12 * 8, 11 * 8, 10 * 8, 9 * 8, 8 * 8), 4)); |
|
||||||
} |
|
||||||
|
|
||||||
#define WRITE_TO_OUTPUT(a, output, expected) \ |
|
||||||
a.Permute<0 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output); \
|
|
||||||
a.Permute<1 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output + 2); \
|
|
||||||
a.Permute<2 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output + 4); \
|
|
||||||
a.Permute<3 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output + 6); \
|
|
||||||
output[8] = _mm256_movemask_epi8(_mm256_cmpeq_epi8(*((__m256i*)output), _mm256_setzero_si256())); |
|
||||||
|
|
||||||
__forceinline void WriteToOutput(const MD5Vector a, __int32 * output, __m256i * expected) |
|
||||||
{ |
|
||||||
a.Permute<0 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output); |
|
||||||
a.Permute<1 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output); |
|
||||||
a.Permute<2 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output); |
|
||||||
a.Permute<3 * 0x55>().CompareEquality32(*expected).WriteMoveMask8(output); |
|
||||||
output[8] = _mm256_movemask_epi8(_mm256_cmpeq_epi8(*((__m256i*)output), _mm256_setzero_si256())); |
|
||||||
} |
|
||||||
|
|
||||||
const MD5Vector Ones = CREATE_VECTOR(0xffffffff); |
|
||||||
__forceinline const MD5Vector OP_NEG(const MD5Vector a) { return OP_ANDNOT(a, Ones); } |
|
||||||
|
|
||||||
__forceinline const MD5Vector Blend(const MD5Vector a, const MD5Vector b, const MD5Vector x) { return OP_BLEND(a, b, x); } |
|
||||||
__forceinline const MD5Vector Xor(const MD5Vector a, const MD5Vector b, const MD5Vector c) { return OP_XOR(a, OP_XOR(b, c)); } |
|
||||||
__forceinline const MD5Vector I(const MD5Vector a, const MD5Vector b, const MD5Vector c) { return OP_XOR(a, OP_OR(b, OP_NEG(c))); } |
|
||||||
|
|
||||||
template<int r> |
|
||||||
__forceinline const MD5Vector StepOuter(const MD5Vector a, const MD5Vector b, const MD5Vector x) { return OP_ADD(b, OP_ROT<r>(x)); } |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step1(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d, const MD5Vector w) { |
|
||||||
return StepOuter<r>(a, b, OP_ADD(Blend(d, c, b), OP_ADD(CREATE_VECTOR(k), OP_ADD(a, w)))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step1(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d) { |
|
||||||
return StepOuter<r>(a, b, OP_ADD(Blend(d, c, b), OP_ADD(CREATE_VECTOR(k), a))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step2(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d, const MD5Vector w) { |
|
||||||
return StepOuter<r>(a, c, OP_ADD(Blend(d, c, b), OP_ADD(CREATE_VECTOR(k), OP_ADD(a, w)))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step2(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d) { |
|
||||||
return StepOuter<r>(a, c, OP_ADD(Blend(d, c, b), OP_ADD(CREATE_VECTOR(k), a))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step3(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d, const MD5Vector w) { |
|
||||||
return StepOuter<r>(a, b, OP_ADD(Xor(b, c, d), OP_ADD(CREATE_VECTOR(k), OP_ADD(a, w)))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step3(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d) { |
|
||||||
return StepOuter<r>(a, b, OP_ADD(Xor(b, c, d), OP_ADD(CREATE_VECTOR(k), a))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step4(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d, const MD5Vector w) { |
|
||||||
return StepOuter<r>(a, b, OP_ADD(I(c, b, d), OP_ADD(CREATE_VECTOR(k), OP_ADD(a, w)))); |
|
||||||
} |
|
||||||
|
|
||||||
template<int r, unsigned __int32 k> |
|
||||||
__forceinline const MD5Vector Step4(const MD5Vector a, const MD5Vector b, const MD5Vector c, const MD5Vector d) { |
|
||||||
return StepOuter<r>(a, b, OP_ADD(I(c, b, d), OP_ADD(CREATE_VECTOR(k), a))); |
|
||||||
} |
|
||||||
|
|
||||||
void md5(unsigned __int32 * input, unsigned __int32 * expected) |
|
||||||
{ |
|
||||||
MD5Vector a = CREATE_VECTOR(0x67452301); |
|
||||||
MD5Vector b = CREATE_VECTOR(0xefcdab89); |
|
||||||
MD5Vector c = CREATE_VECTOR(0x98badcfe); |
|
||||||
MD5Vector d = CREATE_VECTOR(0x10325476); |
|
||||||
|
|
||||||
MD5Vector inputVector0 = CREATE_VECTOR_FROM_INPUT(input, 0); |
|
||||||
MD5Vector inputVector1 = CREATE_VECTOR_FROM_INPUT(input, 1); |
|
||||||
MD5Vector inputVector2 = CREATE_VECTOR_FROM_INPUT(input, 2); |
|
||||||
MD5Vector inputVector3 = CREATE_VECTOR_FROM_INPUT(input, 3); |
|
||||||
MD5Vector inputVector4 = CREATE_VECTOR_FROM_INPUT(input, 4); |
|
||||||
MD5Vector inputVector5 = CREATE_VECTOR_FROM_INPUT(input, 5); |
|
||||||
MD5Vector inputVector6 = CREATE_VECTOR_FROM_INPUT(input, 6); |
|
||||||
MD5Vector inputVector7 = CREATE_VECTOR_FROM_INPUT(input, 7); |
|
||||||
|
|
||||||
a = Step1< 7, 0xd76aa478>(a, b, c, d, inputVector0); |
|
||||||
d = Step1<12, 0xe8c7b756>(d, a, b, c, inputVector1); |
|
||||||
c = Step1<17, 0x242070db>(c, d, a, b, inputVector2); |
|
||||||
b = Step1<22, 0xc1bdceee>(b, c, d, a, inputVector3); |
|
||||||
a = Step1< 7, 0xf57c0faf>(a, b, c, d, inputVector4); |
|
||||||
d = Step1<12, 0x4787c62a>(d, a, b, c, inputVector5); |
|
||||||
c = Step1<17, 0xa8304613>(c, d, a, b, inputVector6); |
|
||||||
b = Step1<22, 0xfd469501>(b, c, d, a); |
|
||||||
a = Step1< 7, 0x698098d8>(a, b, c, d); |
|
||||||
d = Step1<12, 0x8b44f7af>(d, a, b, c); |
|
||||||
c = Step1<17, 0xffff5bb1>(c, d, a, b); |
|
||||||
b = Step1<22, 0x895cd7be>(b, c, d, a); |
|
||||||
a = Step1< 7, 0x6b901122>(a, b, c, d); |
|
||||||
d = Step1<12, 0xfd987193>(d, a, b, c); |
|
||||||
c = Step1<17, 0xa679438e>(c, d, a, b, inputVector7); |
|
||||||
b = Step1<22, 0x49b40821>(b, c, d, a); |
|
||||||
|
|
||||||
a = Step2< 5, 0xf61e2562>(a, d, b, c, inputVector1); |
|
||||||
d = Step2< 9, 0xc040b340>(d, c, a, b, inputVector6); |
|
||||||
c = Step2<14, 0x265e5a51>(c, b, d, a); |
|
||||||
b = Step2<20, 0xe9b6c7aa>(b, a, c, d, inputVector0); |
|
||||||
a = Step2< 5, 0xd62f105d>(a, d, b, c, inputVector5); |
|
||||||
d = Step2< 9, 0x02441453>(d, c, a, b); |
|
||||||
c = Step2<14, 0xd8a1e681>(c, b, d, a); |
|
||||||
b = Step2<20, 0xe7d3fbc8>(b, a, c, d, inputVector4); |
|
||||||
a = Step2< 5, 0x21e1cde6>(a, d, b, c); |
|
||||||
d = Step2< 9, 0xc33707d6>(d, c, a, b, inputVector7); |
|
||||||
c = Step2<14, 0xf4d50d87>(c, b, d, a, inputVector3); |
|
||||||
b = Step2<20, 0x455a14ed>(b, a, c, d); |
|
||||||
a = Step2< 5, 0xa9e3e905>(a, d, b, c); |
|
||||||
d = Step2< 9, 0xfcefa3f8>(d, c, a, b, inputVector2); |
|
||||||
c = Step2<14, 0x676f02d9>(c, b, d, a); |
|
||||||
b = Step2<20, 0x8d2a4c8a>(b, a, c, d); |
|
||||||
|
|
||||||
a = Step3< 4, 0xfffa3942>(a, b, c, d, inputVector5); |
|
||||||
d = Step3<11, 0x8771f681>(d, a, b, c); |
|
||||||
c = Step3<16, 0x6d9d6122>(c, d, a, b); |
|
||||||
b = Step3<23, 0xfde5380c>(b, c, d, a, inputVector7); |
|
||||||
a = Step3< 4, 0xa4beea44>(a, b, c, d, inputVector1); |
|
||||||
d = Step3<11, 0x4bdecfa9>(d, a, b, c, inputVector4); |
|
||||||
c = Step3<16, 0xf6bb4b60>(c, d, a, b); |
|
||||||
b = Step3<23, 0xbebfbc70>(b, c, d, a); |
|
||||||
a = Step3< 4, 0x289b7ec6>(a, b, c, d); |
|
||||||
d = Step3<11, 0xeaa127fa>(d, a, b, c, inputVector0); |
|
||||||
c = Step3<16, 0xd4ef3085>(c, d, a, b, inputVector3); |
|
||||||
b = Step3<23, 0x04881d05>(b, c, d, a, inputVector6); |
|
||||||
a = Step3< 4, 0xd9d4d039>(a, b, c, d); |
|
||||||
d = Step3<11, 0xe6db99e5>(d, a, b, c); |
|
||||||
c = Step3<16, 0x1fa27cf8>(c, d, a, b); |
|
||||||
b = Step3<23, 0xc4ac5665>(b, c, d, a, inputVector2); |
|
||||||
|
|
||||||
a = Step4< 6, 0xf4292244>(a, b, c, d, inputVector0); |
|
||||||
d = Step4<10, 0x432aff97>(d, a, b, c); |
|
||||||
c = Step4<15, 0xab9423a7>(c, d, a, b, inputVector7); |
|
||||||
b = Step4<21, 0xfc93a039>(b, c, d, a, inputVector5); |
|
||||||
a = Step4< 6, 0x655b59c3>(a, b, c, d); |
|
||||||
d = Step4<10, 0x8f0ccc92>(d, a, b, c, inputVector3); |
|
||||||
c = Step4<15, 0xffeff47d>(c, d, a, b); |
|
||||||
b = Step4<21, 0x85845dd1>(b, c, d, a, inputVector1); |
|
||||||
a = Step4< 6, 0x6fa87e4f>(a, b, c, d); |
|
||||||
d = Step4<10, 0xfe2ce6e0>(d, a, b, c); |
|
||||||
c = Step4<15, 0xa3014314>(c, d, a, b, inputVector6); |
|
||||||
b = Step4<21, 0x4e0811a1>(b, c, d, a); |
|
||||||
a = Step4< 6, 0xf7537e82>(a, b, c, d, inputVector4); |
|
||||||
|
|
||||||
a = OP_ADD(CREATE_VECTOR(0x67452301), a); |
|
||||||
|
|
||||||
WRITE_TO_OUTPUT(a, ((__int32*)input), ((__m256i*)expected)); |
|
||||||
} |
|
||||||
#pragma managed |
|
||||||
@ -1,3 +0,0 @@ |
|||||||
#pragma once |
|
||||||
|
|
||||||
void md5(unsigned int* input, unsigned __int32 * expected); |
|
||||||
@ -1,86 +0,0 @@ |
|||||||
#include "stdafx.h" |
|
||||||
#include "phraseset.h" |
|
||||||
#include "constants.h" |
|
||||||
|
|
||||||
#include "intrin.h" |
|
||||||
|
|
||||||
#pragma unmanaged |
|
||||||
|
|
||||||
template<int numberOfWords> |
|
||||||
class Processor |
|
||||||
{ |
|
||||||
public: |
|
||||||
template<int wordNumber> |
|
||||||
static __forceinline const __m256i ProcessWord(const __m256i phrase, const unsigned __int64 cumulativeWordOffset, const unsigned __int64 permutation, unsigned __int64* allWordsPointer, __int32* wordIndexes) |
|
||||||
{ |
|
||||||
auto currentWord = allWordsPointer + wordIndexes[_bextr_u64(permutation, 4 * wordNumber, 4)] * 128; |
|
||||||
|
|
||||||
return ProcessWord<wordNumber + 1>( |
|
||||||
_mm256_xor_si256(phrase, *(__m256i*)(currentWord + cumulativeWordOffset)), |
|
||||||
cumulativeWordOffset + currentWord[127], |
|
||||||
permutation, |
|
||||||
allWordsPointer, |
|
||||||
wordIndexes); |
|
||||||
} |
|
||||||
|
|
||||||
template<> |
|
||||||
static __forceinline const __m256i ProcessWord<numberOfWords>(const __m256i phrase, const unsigned __int64 cumulativeWordOffset, const unsigned __int64 permutation, unsigned __int64* allWordsPointer, __int32* wordIndexes) |
|
||||||
{ |
|
||||||
return phrase; |
|
||||||
} |
|
||||||
|
|
||||||
template<int phraseNumber> |
|
||||||
static __forceinline void ProcessWordsForPhrase(__m256i* avx2initialBuffer, __m256i* avx2buffer, unsigned __int64* allWordsPointer, __int32* wordIndexes, unsigned __int64* permutationsPointer) |
|
||||||
{ |
|
||||||
avx2buffer[phraseNumber] = ProcessWord<0>(*avx2initialBuffer, 0, permutationsPointer[phraseNumber], allWordsPointer, wordIndexes); |
|
||||||
ProcessWordsForPhrase<phraseNumber + 1>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
} |
|
||||||
|
|
||||||
template<> |
|
||||||
static __forceinline void ProcessWordsForPhrase<PHRASES_PER_SET>(__m256i* avx2initialBuffer, __m256i* avx2buffer, unsigned __int64* allWordsPointer, __int32* wordIndexes, unsigned __int64* permutationsPointer) |
|
||||||
{ |
|
||||||
return; |
|
||||||
} |
|
||||||
}; |
|
||||||
|
|
||||||
void fillPhraseSet(unsigned __int64* initialBufferPointer, unsigned __int64* bufferPointer, unsigned __int64* allWordsPointer, __int32* wordIndexes, unsigned __int64* permutationsPointer, int numberOfWords) |
|
||||||
{ |
|
||||||
auto avx2initialBuffer = (__m256i*)initialBufferPointer; |
|
||||||
auto avx2buffer = (__m256i*)bufferPointer; |
|
||||||
|
|
||||||
switch (numberOfWords) |
|
||||||
{ |
|
||||||
case 1: |
|
||||||
Processor<1>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 2: |
|
||||||
Processor<2>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 3: |
|
||||||
Processor<3>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 4: |
|
||||||
Processor<4>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 5: |
|
||||||
Processor<5>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 6: |
|
||||||
Processor<6>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 7: |
|
||||||
Processor<7>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 8: |
|
||||||
Processor<8>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 9: |
|
||||||
Processor<9>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
case 10: |
|
||||||
Processor<10>::ProcessWordsForPhrase<0>(avx2initialBuffer, avx2buffer, allWordsPointer, wordIndexes, permutationsPointer); |
|
||||||
break; |
|
||||||
} |
|
||||||
} |
|
||||||
|
|
||||||
#pragma managed |
|
||||||
@ -1,3 +0,0 @@ |
|||||||
#pragma once |
|
||||||
|
|
||||||
void fillPhraseSet(unsigned __int64* initialBufferPointer, unsigned __int64* bufferPointer, unsigned __int64* allWordsPointer, __int32* wordIndexes, unsigned __int64* permutationsPointer, int numberOfWords); |
|
||||||
@ -1,3 +0,0 @@ |
|||||||
//{{NO_DEPENDENCIES}}
|
|
||||||
// Microsoft Visual C++ generated include file.
|
|
||||||
// Used by app.rc
|
|
||||||
Loading…
Reference in new issue