Integrated RandomX, added RandomXL (Loki)
This commit is contained in:
parent
0aaf2d38d4
commit
6eb9d0963b
78 changed files with 9870 additions and 36 deletions
125
src/crypto/randomx/vm_interpreted.cpp
Normal file
125
src/crypto/randomx/vm_interpreted.cpp
Normal file
|
@ -0,0 +1,125 @@
|
|||
/*
|
||||
Copyright (c) 2018-2019, tevador <tevador@gmail.com>
|
||||
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
* Neither the name of the copyright holder nor the
|
||||
names of its contributors may be used to endorse or promote products
|
||||
derived from this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
||||
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
||||
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
|
||||
#include "vm_interpreted.hpp"
|
||||
#include "dataset.hpp"
|
||||
#include "intrin_portable.h"
|
||||
#include "reciprocal.h"
|
||||
|
||||
namespace randomx {
|
||||
|
||||
template<class Allocator, bool softAes>
|
||||
void InterpretedVm<Allocator, softAes>::setDataset(randomx_dataset* dataset) {
|
||||
datasetPtr = dataset;
|
||||
mem.memory = dataset->memory;
|
||||
}
|
||||
|
||||
template<class Allocator, bool softAes>
|
||||
void InterpretedVm<Allocator, softAes>::run(void* seed) {
|
||||
VmBase<Allocator, softAes>::generateProgram(seed);
|
||||
randomx_vm::initialize();
|
||||
execute();
|
||||
}
|
||||
|
||||
template<class Allocator, bool softAes>
|
||||
void InterpretedVm<Allocator, softAes>::execute() {
|
||||
|
||||
NativeRegisterFile nreg;
|
||||
|
||||
for(unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
nreg.a[i] = rx_load_vec_f128(®.a[i].lo);
|
||||
|
||||
compileProgram(program, bytecode, nreg);
|
||||
|
||||
uint32_t spAddr0 = mem.mx;
|
||||
uint32_t spAddr1 = mem.ma;
|
||||
|
||||
for(unsigned ic = 0; ic < RandomX_CurrentConfig.ProgramIterations; ++ic) {
|
||||
uint64_t spMix = nreg.r[config.readReg0] ^ nreg.r[config.readReg1];
|
||||
spAddr0 ^= spMix;
|
||||
spAddr0 &= ScratchpadL3Mask64;
|
||||
spAddr1 ^= spMix >> 32;
|
||||
spAddr1 &= ScratchpadL3Mask64;
|
||||
|
||||
for (unsigned i = 0; i < RegistersCount; ++i)
|
||||
nreg.r[i] ^= load64(scratchpad + spAddr0 + 8 * i);
|
||||
|
||||
for (unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
nreg.f[i] = rx_cvt_packed_int_vec_f128(scratchpad + spAddr1 + 8 * i);
|
||||
|
||||
for (unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
nreg.e[i] = maskRegisterExponentMantissa(config, rx_cvt_packed_int_vec_f128(scratchpad + spAddr1 + 8 * (RegisterCountFlt + i)));
|
||||
|
||||
executeBytecode(bytecode, scratchpad, config);
|
||||
|
||||
mem.mx ^= nreg.r[config.readReg2] ^ nreg.r[config.readReg3];
|
||||
mem.mx &= CacheLineAlignMask;
|
||||
datasetPrefetch(datasetOffset + mem.mx);
|
||||
datasetRead(datasetOffset + mem.ma, nreg.r);
|
||||
std::swap(mem.mx, mem.ma);
|
||||
|
||||
for (unsigned i = 0; i < RegistersCount; ++i)
|
||||
store64(scratchpad + spAddr1 + 8 * i, nreg.r[i]);
|
||||
|
||||
for (unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
nreg.f[i] = rx_xor_vec_f128(nreg.f[i], nreg.e[i]);
|
||||
|
||||
for (unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
rx_store_vec_f128((double*)(scratchpad + spAddr0 + 16 * i), nreg.f[i]);
|
||||
|
||||
spAddr0 = 0;
|
||||
spAddr1 = 0;
|
||||
}
|
||||
|
||||
for (unsigned i = 0; i < RegistersCount; ++i)
|
||||
store64(®.r[i], nreg.r[i]);
|
||||
|
||||
for (unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
rx_store_vec_f128(®.f[i].lo, nreg.f[i]);
|
||||
|
||||
for (unsigned i = 0; i < RegisterCountFlt; ++i)
|
||||
rx_store_vec_f128(®.e[i].lo, nreg.e[i]);
|
||||
}
|
||||
|
||||
template<class Allocator, bool softAes>
|
||||
void InterpretedVm<Allocator, softAes>::datasetRead(uint64_t address, int_reg_t(&r)[RegistersCount]) {
|
||||
uint64_t* datasetLine = (uint64_t*)(mem.memory + address);
|
||||
for (int i = 0; i < RegistersCount; ++i)
|
||||
r[i] ^= datasetLine[i];
|
||||
}
|
||||
|
||||
template<class Allocator, bool softAes>
|
||||
void InterpretedVm<Allocator, softAes>::datasetPrefetch(uint64_t address) {
|
||||
rx_prefetch_nta(mem.memory + address);
|
||||
}
|
||||
|
||||
template class InterpretedVm<AlignedAllocator<CacheLineSize>, false>;
|
||||
template class InterpretedVm<AlignedAllocator<CacheLineSize>, true>;
|
||||
template class InterpretedVm<LargePageAllocator, false>;
|
||||
template class InterpretedVm<LargePageAllocator, true>;
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue