mirror of
https://github.com/xmrig/xmrig.git
synced 2025-12-09 00:33:33 -05:00
Compare commits
19 Commits
v6.22.1
...
0a54c642d3
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0a54c642d3 | ||
|
|
16ecb8f085 | ||
|
|
0229c65232 | ||
|
|
4a13a8a75c | ||
|
|
cd2fd9d7a6 | ||
|
|
064cd3ef20 | ||
|
|
e8bbd134f9 | ||
|
|
cf86a1e05c | ||
|
|
f9e990d0f0 | ||
|
|
200f23bba7 | ||
|
|
4234b20e21 | ||
|
|
c5d8b8265b | ||
|
|
77c14c8362 | ||
|
|
8b03750806 | ||
|
|
40949f2767 | ||
|
|
56c447e02a | ||
|
|
21c206f05d | ||
|
|
862280f28c | ||
|
|
814e1de2a6 |
@@ -1,3 +1,7 @@
|
||||
# v6.22.2
|
||||
- [#3569](https://github.com/xmrig/xmrig/pull/3569) Fixed corrupted API output in some rare conditions.
|
||||
- [#3571](https://github.com/xmrig/xmrig/pull/3571) Fixed number of threads on the new Intel Core Ultra CPUs.
|
||||
|
||||
# v6.22.1
|
||||
- [#3531](https://github.com/xmrig/xmrig/pull/3531) Always reset nonce on RandomX dataset change.
|
||||
- [#3534](https://github.com/xmrig/xmrig/pull/3534) Fixed threads auto-config on Zen5.
|
||||
|
||||
@@ -30,10 +30,10 @@
|
||||
#include "base/tools/Handle.h"
|
||||
|
||||
|
||||
inline static const char *format(double h, char *buf, size_t size)
|
||||
inline static const char *format(std::pair<bool, double> h, char *buf, size_t size)
|
||||
{
|
||||
if (std::isnormal(h)) {
|
||||
snprintf(buf, size, (h < 100.0) ? "%04.2f" : "%03.1f", h);
|
||||
if (h.first) {
|
||||
snprintf(buf, size, (h.second < 100.0) ? "%04.2f" : "%03.1f", h.second);
|
||||
return buf;
|
||||
}
|
||||
|
||||
@@ -80,15 +80,16 @@ double xmrig::Hashrate::average() const
|
||||
}
|
||||
|
||||
|
||||
const char *xmrig::Hashrate::format(double h, char *buf, size_t size)
|
||||
const char *xmrig::Hashrate::format(std::pair<bool, double> h, char *buf, size_t size)
|
||||
{
|
||||
return ::format(h, buf, size);
|
||||
}
|
||||
|
||||
|
||||
rapidjson::Value xmrig::Hashrate::normalize(double d)
|
||||
rapidjson::Value xmrig::Hashrate::normalize(std::pair<bool, double> d)
|
||||
{
|
||||
return Json::normalize(d, false);
|
||||
using namespace rapidjson;
|
||||
return d.first ? Value(floor(d.second * 100.0) / 100.0) : Value(kNullType);
|
||||
}
|
||||
|
||||
|
||||
@@ -122,11 +123,11 @@ rapidjson::Value xmrig::Hashrate::toJSON(size_t threadId, rapidjson::Document &d
|
||||
#endif
|
||||
|
||||
|
||||
double xmrig::Hashrate::hashrate(size_t index, size_t ms) const
|
||||
std::pair<bool, double> xmrig::Hashrate::hashrate(size_t index, size_t ms) const
|
||||
{
|
||||
assert(index < m_threads);
|
||||
if (index >= m_threads) {
|
||||
return nan("");
|
||||
return { false, 0.0 };
|
||||
}
|
||||
|
||||
uint64_t earliestHashCount = 0;
|
||||
@@ -157,17 +158,27 @@ double xmrig::Hashrate::hashrate(size_t index, size_t ms) const
|
||||
} while (idx != idx_start);
|
||||
|
||||
if (!haveFullSet || earliestStamp == 0 || lastestStamp == 0) {
|
||||
return nan("");
|
||||
return { false, 0.0 };
|
||||
}
|
||||
|
||||
if (lastestStamp - earliestStamp == 0) {
|
||||
return nan("");
|
||||
if (lastestHashCnt == earliestHashCount) {
|
||||
return { true, 0.0 };
|
||||
}
|
||||
|
||||
if (lastestStamp == earliestStamp) {
|
||||
return { false, 0.0 };
|
||||
}
|
||||
|
||||
const auto hashes = static_cast<double>(lastestHashCnt - earliestHashCount);
|
||||
const auto time = static_cast<double>(lastestStamp - earliestStamp) / 1000.0;
|
||||
const auto time = static_cast<double>(lastestStamp - earliestStamp);
|
||||
|
||||
return hashes / time;
|
||||
const auto hr = hashes * 1000.0 / time;
|
||||
|
||||
if (!std::isnormal(hr)) {
|
||||
return { false, 0.0 };
|
||||
}
|
||||
|
||||
return { true, hr };
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -47,16 +47,16 @@ public:
|
||||
Hashrate(size_t threads);
|
||||
~Hashrate();
|
||||
|
||||
inline double calc(size_t ms) const { const double data = hashrate(0U, ms); return std::isnormal(data) ? data : 0.0; }
|
||||
inline double calc(size_t threadId, size_t ms) const { return hashrate(threadId + 1, ms); }
|
||||
inline std::pair<bool, double> calc(size_t ms) const { return hashrate(0U, ms); }
|
||||
inline std::pair<bool, double> calc(size_t threadId, size_t ms) const { return hashrate(threadId + 1, ms); }
|
||||
inline size_t threads() const { return m_threads > 0U ? m_threads - 1U : 0U; }
|
||||
inline void add(size_t threadId, uint64_t count, uint64_t timestamp) { addData(threadId + 1U, count, timestamp); }
|
||||
inline void add(uint64_t count, uint64_t timestamp) { addData(0U, count, timestamp); }
|
||||
|
||||
double average() const;
|
||||
|
||||
static const char *format(double h, char *buf, size_t size);
|
||||
static rapidjson::Value normalize(double d);
|
||||
static const char *format(std::pair<bool, double> h, char *buf, size_t size);
|
||||
static rapidjson::Value normalize(std::pair<bool, double> d);
|
||||
|
||||
# ifdef XMRIG_FEATURE_API
|
||||
rapidjson::Value toJSON(rapidjson::Document &doc) const;
|
||||
@@ -64,7 +64,7 @@ public:
|
||||
# endif
|
||||
|
||||
private:
|
||||
double hashrate(size_t index, size_t ms) const;
|
||||
std::pair<bool, double> hashrate(size_t index, size_t ms) const;
|
||||
void addData(size_t index, uint64_t count, uint64_t timestamp);
|
||||
|
||||
constexpr static size_t kBucketSize = 2 << 11;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -19,10 +19,8 @@
|
||||
#ifndef XMRIG_PCITOPOLOGY_H
|
||||
#define XMRIG_PCITOPOLOGY_H
|
||||
|
||||
|
||||
#include <cstdio>
|
||||
|
||||
|
||||
#include "base/tools/String.h"
|
||||
|
||||
|
||||
@@ -33,7 +31,14 @@ class PciTopology
|
||||
{
|
||||
public:
|
||||
PciTopology() = default;
|
||||
PciTopology(uint32_t bus, uint32_t device, uint32_t function) : m_valid(true), m_bus(bus), m_device(device), m_function(function) {}
|
||||
|
||||
template<typename T>
|
||||
inline PciTopology(T bus, T device, T function)
|
||||
: m_valid(true),
|
||||
m_bus(static_cast<uint8_t>(bus)),
|
||||
m_device(static_cast<uint8_t>(device)),
|
||||
m_function(static_cast<uint8_t>(function))
|
||||
{}
|
||||
|
||||
inline bool isEqual(const PciTopology &other) const { return m_valid == other.m_valid && toUint32() == other.toUint32(); }
|
||||
inline bool isValid() const { return m_valid; }
|
||||
@@ -70,4 +75,4 @@ private:
|
||||
} // namespace xmrig
|
||||
|
||||
|
||||
#endif /* XMRIG_PCITOPOLOGY_H */
|
||||
#endif // XMRIG_PCITOPOLOGY_H
|
||||
|
||||
@@ -342,7 +342,7 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
|
||||
}
|
||||
|
||||
# ifdef XMRIG_ALGO_RANDOMX
|
||||
if ((algorithm.family() == Algorithm::RANDOM_X) && L3_exclusive && (PUs > cores.size()) && (PUs < cores.size() * 2)) {
|
||||
if ((vendor() == VENDOR_INTEL) && (algorithm.family() == Algorithm::RANDOM_X) && L3_exclusive && (PUs < cores.size() * 2)) {
|
||||
// Use all L3+L2 on latest Intel CPUs with P-cores, E-cores and exclusive L3 cache
|
||||
cacheHashes = (L3 + L2) / scratchpad;
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -227,7 +227,7 @@ public:
|
||||
# endif
|
||||
|
||||
Log::print("|" CYAN_BOLD("%3zu") " |" CYAN_BOLD("%4u") " |" YELLOW(" %7s") " |" CYAN_BOLD("%10d") " |" CYAN_BOLD("%8d") " |"
|
||||
CYAN_BOLD("%7d") " |" CYAN_BOLD("%3d") " |" CYAN_BOLD("%4d") " |" CYAN("%7zu") " | " GREEN("%s"),
|
||||
CYAN_BOLD("%7d") " |" CYAN_BOLD("%3d") " |" CYAN_BOLD("%4d") " |" CYAN("%7zu") " | " GREEN_BOLD("%s"),
|
||||
i,
|
||||
data.thread.index(),
|
||||
data.device.topology().toString().data(),
|
||||
@@ -372,15 +372,20 @@ void xmrig::CudaBackend::printHashrate(bool details)
|
||||
|
||||
char num[16 * 3] = { 0 };
|
||||
|
||||
const double hashrate_short = hashrate()->calc(Hashrate::ShortInterval);
|
||||
const double hashrate_medium = hashrate()->calc(Hashrate::MediumInterval);
|
||||
const double hashrate_large = hashrate()->calc(Hashrate::LargeInterval);
|
||||
auto hashrate_short = hashrate()->calc(Hashrate::ShortInterval);
|
||||
auto hashrate_medium = hashrate()->calc(Hashrate::MediumInterval);
|
||||
auto hashrate_large = hashrate()->calc(Hashrate::LargeInterval);
|
||||
|
||||
double scale = 1.0;
|
||||
const char* h = " H/s";
|
||||
|
||||
if ((hashrate_short >= 1e6) || (hashrate_medium >= 1e6) || (hashrate_large >= 1e6)) {
|
||||
if ((hashrate_short.second >= 1e6) || (hashrate_medium.second >= 1e6) || (hashrate_large.second >= 1e6)) {
|
||||
scale = 1e-6;
|
||||
|
||||
hashrate_short.second *= scale;
|
||||
hashrate_medium.second *= scale;
|
||||
hashrate_large.second *= scale;
|
||||
|
||||
h = "MH/s";
|
||||
}
|
||||
|
||||
@@ -388,12 +393,20 @@ void xmrig::CudaBackend::printHashrate(bool details)
|
||||
|
||||
size_t i = 0;
|
||||
for (const auto& data : d_ptr->threads) {
|
||||
Log::print("| %8zu | %8" PRId64 " | %8s | %8s | %8s |" CYAN_BOLD(" #%u") YELLOW(" %s") GREEN(" %s"),
|
||||
auto h0 = hashrate()->calc(i, Hashrate::ShortInterval);
|
||||
auto h1 = hashrate()->calc(i, Hashrate::MediumInterval);
|
||||
auto h2 = hashrate()->calc(i, Hashrate::LargeInterval);
|
||||
|
||||
h0.second *= scale;
|
||||
h1.second *= scale;
|
||||
h2.second *= scale;
|
||||
|
||||
Log::print("| %8zu | %8" PRId64 " | %8s | %8s | %8s |" CYAN_BOLD(" #%u") YELLOW(" %s") GREEN(" %s"),
|
||||
i,
|
||||
data.thread.affinity(),
|
||||
Hashrate::format(hashrate()->calc(i, Hashrate::ShortInterval) * scale, num, sizeof num / 3),
|
||||
Hashrate::format(hashrate()->calc(i, Hashrate::MediumInterval) * scale, num + 16, sizeof num / 3),
|
||||
Hashrate::format(hashrate()->calc(i, Hashrate::LargeInterval) * scale, num + 16 * 2, sizeof num / 3),
|
||||
Hashrate::format(h0, num, sizeof num / 3),
|
||||
Hashrate::format(h1, num + 16, sizeof num / 3),
|
||||
Hashrate::format(h2, num + 16 * 2, sizeof num / 3),
|
||||
data.device.index(),
|
||||
data.device.topology().toString().data(),
|
||||
data.device.name().data()
|
||||
@@ -403,9 +416,9 @@ void xmrig::CudaBackend::printHashrate(bool details)
|
||||
}
|
||||
|
||||
Log::print(WHITE_BOLD_S "| - | - | %8s | %8s | %8s |",
|
||||
Hashrate::format(hashrate_short * scale, num, sizeof num / 3),
|
||||
Hashrate::format(hashrate_medium * scale, num + 16, sizeof num / 3),
|
||||
Hashrate::format(hashrate_large * scale, num + 16 * 2, sizeof num / 3)
|
||||
Hashrate::format(hashrate_short , num, sizeof num / 3),
|
||||
Hashrate::format(hashrate_medium, num + 16, sizeof num / 3),
|
||||
Hashrate::format(hashrate_large , num + 16 * 2, sizeof num / 3)
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
* Copyright 2014-2016 Wolf9466 <https://github.com/OhGodAPet>
|
||||
* Copyright 2016 Jay D Dee <jayddee246@gmail.com>
|
||||
* Copyright 2017-2018 XMR-Stak <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
|
||||
* Copyright 2018-2019 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright 2016-2019 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -22,7 +22,6 @@
|
||||
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
*/
|
||||
|
||||
|
||||
#include "backend/cuda/runners/CudaRxRunner.h"
|
||||
#include "backend/cuda/CudaLaunchData.h"
|
||||
#include "backend/cuda/wrappers/CudaLib.h"
|
||||
@@ -55,12 +54,21 @@ bool xmrig::CudaRxRunner::run(uint32_t startNonce, uint32_t *rescount, uint32_t
|
||||
|
||||
bool xmrig::CudaRxRunner::set(const Job &job, uint8_t *blob)
|
||||
{
|
||||
if (!m_datasetHost && (m_seed != job.seed())) {
|
||||
m_seed = job.seed();
|
||||
|
||||
if (m_ready) {
|
||||
const auto *dataset = Rx::dataset(job, 0);
|
||||
callWrapper(CudaLib::rxUpdateDataset(m_ctx, dataset->raw(), dataset->size(false)));
|
||||
}
|
||||
}
|
||||
|
||||
const bool rc = CudaBaseRunner::set(job, blob);
|
||||
if (!rc || m_ready) {
|
||||
return rc;
|
||||
}
|
||||
|
||||
auto dataset = Rx::dataset(job, 0);
|
||||
const auto *dataset = Rx::dataset(job, 0);
|
||||
m_ready = callWrapper(CudaLib::rxPrepare(m_ctx, dataset->raw(), dataset->size(false), m_datasetHost, m_intensity));
|
||||
|
||||
return m_ready;
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
* Copyright 2014-2016 Wolf9466 <https://github.com/OhGodAPet>
|
||||
* Copyright 2016 Jay D Dee <jayddee246@gmail.com>
|
||||
* Copyright 2017-2018 XMR-Stak <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
|
||||
* Copyright 2018-2019 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright 2016-2019 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -27,6 +27,7 @@
|
||||
|
||||
|
||||
#include "backend/cuda/runners/CudaBaseRunner.h"
|
||||
#include "base/tools/Buffer.h"
|
||||
|
||||
|
||||
namespace xmrig {
|
||||
@@ -46,6 +47,7 @@ protected:
|
||||
private:
|
||||
bool m_ready = false;
|
||||
const bool m_datasetHost = false;
|
||||
Buffer m_seed;
|
||||
size_t m_intensity = 0;
|
||||
};
|
||||
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
* Copyright 2014-2016 Wolf9466 <https://github.com/OhGodAPet>
|
||||
* Copyright 2016 Jay D Dee <jayddee246@gmail.com>
|
||||
* Copyright 2017-2018 XMR-Stak <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
|
||||
* Copyright 2018-2020 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright 2016-2020 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -22,7 +22,6 @@
|
||||
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
*/
|
||||
|
||||
|
||||
#include "backend/cuda/wrappers/CudaDevice.h"
|
||||
#include "3rdparty/rapidjson/document.h"
|
||||
#include "backend/cuda/CudaThreads.h"
|
||||
@@ -41,7 +40,7 @@
|
||||
xmrig::CudaDevice::CudaDevice(uint32_t index, int32_t bfactor, int32_t bsleep) :
|
||||
m_index(index)
|
||||
{
|
||||
auto ctx = CudaLib::alloc(index, bfactor, bsleep);
|
||||
auto *ctx = CudaLib::alloc(index, bfactor, bsleep);
|
||||
if (!CudaLib::deviceInfo(ctx, 0, 0, Algorithm::INVALID)) {
|
||||
CudaLib::release(ctx);
|
||||
|
||||
@@ -50,7 +49,7 @@ xmrig::CudaDevice::CudaDevice(uint32_t index, int32_t bfactor, int32_t bsleep) :
|
||||
|
||||
m_ctx = ctx;
|
||||
m_name = CudaLib::deviceName(ctx);
|
||||
m_topology = PciTopology(CudaLib::deviceUint(ctx, CudaLib::DevicePciBusID), CudaLib::deviceUint(ctx, CudaLib::DevicePciDeviceID), 0);
|
||||
m_topology = { CudaLib::deviceUint(ctx, CudaLib::DevicePciBusID), CudaLib::deviceUint(ctx, CudaLib::DevicePciDeviceID), 0U };
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -19,10 +19,10 @@
|
||||
#include <stdexcept>
|
||||
#include <uv.h>
|
||||
|
||||
|
||||
#include "backend/cuda/wrappers/CudaLib.h"
|
||||
#include "base/io/Env.h"
|
||||
#include "base/io/log/Log.h"
|
||||
#include "base/io/log/Tags.h"
|
||||
#include "base/kernel/Process.h"
|
||||
#include "crypto/rx/RxAlgo.h"
|
||||
|
||||
@@ -68,6 +68,7 @@ static const char *kPluginVersion = "pluginVersion";
|
||||
static const char *kRelease = "release";
|
||||
static const char *kRxHash = "rxHash";
|
||||
static const char *kRxPrepare = "rxPrepare";
|
||||
static const char *kRxUpdateDataset = "rxUpdateDataset";
|
||||
static const char *kSetJob = "setJob";
|
||||
static const char *kSetJob_v2 = "setJob_v2";
|
||||
static const char *kVersion = "version";
|
||||
@@ -92,6 +93,7 @@ using pluginVersion_t = const char * (*)();
|
||||
using release_t = void (*)(nvid_ctx *);
|
||||
using rxHash_t = bool (*)(nvid_ctx *, uint32_t, uint64_t, uint32_t *, uint32_t *);
|
||||
using rxPrepare_t = bool (*)(nvid_ctx *, const void *, size_t, bool, uint32_t);
|
||||
using rxUpdateDataset_t = bool (*)(nvid_ctx *, const void *, size_t);
|
||||
using setJob_t = bool (*)(nvid_ctx *, const void *, size_t, uint32_t);
|
||||
using setJob_v2_t = bool (*)(nvid_ctx *, const void *, size_t, const char *);
|
||||
using version_t = uint32_t (*)(Version);
|
||||
@@ -116,6 +118,7 @@ static pluginVersion_t pPluginVersion = nullptr;
|
||||
static release_t pRelease = nullptr;
|
||||
static rxHash_t pRxHash = nullptr;
|
||||
static rxPrepare_t pRxPrepare = nullptr;
|
||||
static rxUpdateDataset_t pRxUpdateDataset = nullptr;
|
||||
static setJob_t pSetJob = nullptr;
|
||||
static setJob_v2_t pSetJob_v2 = nullptr;
|
||||
static version_t pVersion = nullptr;
|
||||
@@ -202,10 +205,26 @@ bool xmrig::CudaLib::rxHash(nvid_ctx *ctx, uint32_t startNonce, uint64_t target,
|
||||
|
||||
bool xmrig::CudaLib::rxPrepare(nvid_ctx *ctx, const void *dataset, size_t datasetSize, bool dataset_host, uint32_t batchSize) noexcept
|
||||
{
|
||||
# ifdef XMRIG_ALGO_RANDOMX
|
||||
if (!pRxUpdateDataset) {
|
||||
LOG_WARN("%s" YELLOW_BOLD("CUDA plugin is outdated. Please update to the latest version"), Tags::randomx());
|
||||
}
|
||||
# endif
|
||||
|
||||
return pRxPrepare(ctx, dataset, datasetSize, dataset_host, batchSize);
|
||||
}
|
||||
|
||||
|
||||
bool xmrig::CudaLib::rxUpdateDataset(nvid_ctx *ctx, const void *dataset, size_t datasetSize) noexcept
|
||||
{
|
||||
if (pRxUpdateDataset) {
|
||||
return pRxUpdateDataset(ctx, dataset, datasetSize);
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
bool xmrig::CudaLib::kawPowHash(nvid_ctx *ctx, uint8_t* job_blob, uint64_t target, uint32_t *rescount, uint32_t *resnonce, uint32_t *skipped_hashes) noexcept
|
||||
{
|
||||
return pKawPowHash(ctx, job_blob, target, rescount, resnonce, skipped_hashes);
|
||||
@@ -401,5 +420,7 @@ void xmrig::CudaLib::load()
|
||||
DLSYM(SetJob_v2);
|
||||
}
|
||||
|
||||
uv_dlsym(&cudaLib, kRxUpdateDataset, reinterpret_cast<void**>(&pRxUpdateDataset));
|
||||
|
||||
pInit();
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -71,6 +71,7 @@ public:
|
||||
static bool deviceInit(nvid_ctx *ctx) noexcept;
|
||||
static bool rxHash(nvid_ctx *ctx, uint32_t startNonce, uint64_t target, uint32_t *rescount, uint32_t *resnonce) noexcept;
|
||||
static bool rxPrepare(nvid_ctx *ctx, const void *dataset, size_t datasetSize, bool dataset_host, uint32_t batchSize) noexcept;
|
||||
static bool rxUpdateDataset(nvid_ctx *ctx, const void *dataset, size_t datasetSize) noexcept;
|
||||
static bool kawPowHash(nvid_ctx *ctx, uint8_t* job_blob, uint64_t target, uint32_t *rescount, uint32_t *resnonce, uint32_t *skipped_hashes) noexcept;
|
||||
static bool kawPowPrepare(nvid_ctx *ctx, const void* cache, size_t cache_size, const void* dag_precalc, size_t dag_size, uint32_t height, const uint64_t* dag_sizes) noexcept;
|
||||
static bool kawPowStopHash(nvid_ctx *ctx) noexcept;
|
||||
|
||||
@@ -352,15 +352,20 @@ void xmrig::OclBackend::printHashrate(bool details)
|
||||
|
||||
char num[16 * 3] = { 0 };
|
||||
|
||||
const double hashrate_short = hashrate()->calc(Hashrate::ShortInterval);
|
||||
const double hashrate_medium = hashrate()->calc(Hashrate::MediumInterval);
|
||||
const double hashrate_large = hashrate()->calc(Hashrate::LargeInterval);
|
||||
auto hashrate_short = hashrate()->calc(Hashrate::ShortInterval);
|
||||
auto hashrate_medium = hashrate()->calc(Hashrate::MediumInterval);
|
||||
auto hashrate_large = hashrate()->calc(Hashrate::LargeInterval);
|
||||
|
||||
double scale = 1.0;
|
||||
const char* h = " H/s";
|
||||
|
||||
if ((hashrate_short >= 1e6) || (hashrate_medium >= 1e6) || (hashrate_large >= 1e6)) {
|
||||
if ((hashrate_short.second >= 1e6) || (hashrate_medium.second >= 1e6) || (hashrate_large.second >= 1e6)) {
|
||||
scale = 1e-6;
|
||||
|
||||
hashrate_short.second *= scale;
|
||||
hashrate_medium.second *= scale;
|
||||
hashrate_large.second *= scale;
|
||||
|
||||
h = "MH/s";
|
||||
}
|
||||
|
||||
@@ -368,12 +373,16 @@ void xmrig::OclBackend::printHashrate(bool details)
|
||||
|
||||
size_t i = 0;
|
||||
for (const auto& data : d_ptr->threads) {
|
||||
Log::print("| %8zu | %8" PRId64 " | %8s | %8s | %8s |" CYAN_BOLD(" #%u") YELLOW(" %s") " %s",
|
||||
auto h0 = hashrate()->calc(i, Hashrate::ShortInterval);
|
||||
auto h1 = hashrate()->calc(i, Hashrate::MediumInterval);
|
||||
auto h2 = hashrate()->calc(i, Hashrate::LargeInterval);
|
||||
|
||||
Log::print("| %8zu | %8" PRId64 " | %8s | %8s | %8s |" CYAN_BOLD(" #%u") YELLOW(" %s") " %s",
|
||||
i,
|
||||
data.affinity,
|
||||
Hashrate::format(hashrate()->calc(i, Hashrate::ShortInterval) * scale, num, sizeof num / 3),
|
||||
Hashrate::format(hashrate()->calc(i, Hashrate::MediumInterval) * scale, num + 16, sizeof num / 3),
|
||||
Hashrate::format(hashrate()->calc(i, Hashrate::LargeInterval) * scale, num + 16 * 2, sizeof num / 3),
|
||||
Hashrate::format(h0, num, sizeof num / 3),
|
||||
Hashrate::format(h1, num + 16, sizeof num / 3),
|
||||
Hashrate::format(h2, num + 16 * 2, sizeof num / 3),
|
||||
data.device.index(),
|
||||
data.device.topology().toString().data(),
|
||||
data.device.printableName().data()
|
||||
@@ -383,9 +392,9 @@ void xmrig::OclBackend::printHashrate(bool details)
|
||||
}
|
||||
|
||||
Log::print(WHITE_BOLD_S "| - | - | %8s | %8s | %8s |",
|
||||
Hashrate::format(hashrate_short * scale, num, sizeof num / 3),
|
||||
Hashrate::format(hashrate_medium * scale, num + 16, sizeof num / 3),
|
||||
Hashrate::format(hashrate_large * scale, num + 16 * 2, sizeof num / 3)
|
||||
Hashrate::format(hashrate_short , num, sizeof num / 3),
|
||||
Hashrate::format(hashrate_medium, num + 16, sizeof num / 3),
|
||||
Hashrate::format(hashrate_large , num + 16 * 2, sizeof num / 3)
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -5,13 +5,7 @@ if (BUILD_STATIC AND XMRIG_OS_UNIX AND WITH_OPENCL)
|
||||
endif()
|
||||
|
||||
if (WITH_OPENCL)
|
||||
add_definitions(/DXMRIG_FEATURE_OPENCL)
|
||||
add_definitions(/DCL_USE_DEPRECATED_OPENCL_1_2_APIS)
|
||||
if (XMRIG_OS_APPLE)
|
||||
add_definitions(/DCL_TARGET_OPENCL_VERSION=120)
|
||||
elseif (WITH_OPENCL_VERSION)
|
||||
add_definitions(/DCL_TARGET_OPENCL_VERSION=${WITH_OPENCL_VERSION})
|
||||
endif()
|
||||
add_definitions(/DXMRIG_FEATURE_OPENCL /DCL_USE_DEPRECATED_OPENCL_1_2_APIS)
|
||||
|
||||
set(HEADERS_BACKEND_OPENCL
|
||||
src/backend/opencl/cl/OclSource.h
|
||||
@@ -71,6 +65,13 @@ if (WITH_OPENCL)
|
||||
src/backend/opencl/wrappers/OclPlatform.cpp
|
||||
)
|
||||
|
||||
if (XMRIG_OS_APPLE)
|
||||
add_definitions(/DCL_TARGET_OPENCL_VERSION=120)
|
||||
list(APPEND SOURCES_BACKEND_OPENCL src/backend/opencl/wrappers/OclDevice_mac.cpp)
|
||||
elseif (WITH_OPENCL_VERSION)
|
||||
add_definitions(/DCL_TARGET_OPENCL_VERSION=${WITH_OPENCL_VERSION})
|
||||
endif()
|
||||
|
||||
if (WIN32)
|
||||
list(APPEND SOURCES_BACKEND_OPENCL src/backend/opencl/OclCache_win.cpp)
|
||||
else()
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright (c) 2021 Spudz76 <https://github.com/Spudz76>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -17,6 +18,7 @@
|
||||
*/
|
||||
|
||||
#include "backend/opencl/wrappers/OclDevice.h"
|
||||
#include "3rdparty/fmt/core.h"
|
||||
#include "3rdparty/rapidjson/document.h"
|
||||
#include "backend/opencl/OclGenerator.h"
|
||||
#include "backend/opencl/OclThreads.h"
|
||||
@@ -30,19 +32,21 @@
|
||||
|
||||
|
||||
#include <algorithm>
|
||||
|
||||
|
||||
// NOLINTNEXTLINE(modernize-use-using)
|
||||
typedef union
|
||||
{
|
||||
struct { cl_uint type; cl_uint data[5]; } raw;
|
||||
struct { cl_uint type; cl_char unused[17]; cl_char bus; cl_char device; cl_char function; } pcie;
|
||||
} topology_amd;
|
||||
#include <map>
|
||||
|
||||
|
||||
namespace xmrig {
|
||||
|
||||
|
||||
struct topology_amd {
|
||||
cl_uint type;
|
||||
cl_char unused[17];
|
||||
cl_char bus;
|
||||
cl_char device;
|
||||
cl_char function;
|
||||
};
|
||||
|
||||
|
||||
#ifdef XMRIG_ALGO_RANDOMX
|
||||
extern bool ocl_generic_rx_generator(const OclDevice &device, const Algorithm &algorithm, OclThreads &threads);
|
||||
#endif
|
||||
@@ -81,9 +85,11 @@ static OclVendor getPlatformVendorId(const String &vendor, const String &extensi
|
||||
return OCL_VENDOR_INTEL;
|
||||
}
|
||||
|
||||
# ifdef XMRIG_OS_APPLE
|
||||
if (extensions.contains("cl_APPLE_") || vendor.contains("Apple")) {
|
||||
return OCL_VENDOR_APPLE;
|
||||
}
|
||||
# endif
|
||||
|
||||
return OCL_VENDOR_UNKNOWN;
|
||||
}
|
||||
@@ -103,117 +109,16 @@ static OclVendor getVendorId(const String &vendor)
|
||||
return OCL_VENDOR_INTEL;
|
||||
}
|
||||
|
||||
# ifdef XMRIG_OS_APPLE
|
||||
if (vendor.contains("Apple")) {
|
||||
return OCL_VENDOR_APPLE;
|
||||
}
|
||||
# endif
|
||||
|
||||
return OCL_VENDOR_UNKNOWN;
|
||||
}
|
||||
|
||||
|
||||
static OclDevice::Type getType(const String &name, const OclVendor platformVendorId)
|
||||
{
|
||||
if (platformVendorId == OCL_VENDOR_APPLE) {
|
||||
// Apple Platform: uses product names, not gfx# or codenames
|
||||
if (name.contains("AMD Radeon")) {
|
||||
if (name.contains(" 450 ") ||
|
||||
name.contains(" 455 ") ||
|
||||
name.contains(" 460 ")) {
|
||||
return OclDevice::Baffin;
|
||||
}
|
||||
|
||||
if (name.contains(" 555 ") || name.contains(" 555X ") ||
|
||||
name.contains(" 560 ") || name.contains(" 560X ") ||
|
||||
name.contains(" 570 ") || name.contains(" 570X ") ||
|
||||
name.contains(" 575 ") || name.contains(" 575X ")) {
|
||||
return OclDevice::Polaris;
|
||||
}
|
||||
|
||||
if (name.contains(" 580 ") || name.contains(" 580X ")) {
|
||||
return OclDevice::Ellesmere;
|
||||
}
|
||||
|
||||
if (name.contains(" Vega ")) {
|
||||
if (name.contains(" 48 ") ||
|
||||
name.contains(" 56 ") ||
|
||||
name.contains(" 64 ") ||
|
||||
name.contains(" 64X ")) {
|
||||
return OclDevice::Vega_10;
|
||||
}
|
||||
if (name.contains(" 16 ") ||
|
||||
name.contains(" 20 ") ||
|
||||
name.contains(" II ")) {
|
||||
return OclDevice::Vega_20;
|
||||
}
|
||||
}
|
||||
|
||||
if (name.contains(" 5700 ") || name.contains(" W5700X ")) {
|
||||
return OclDevice::Navi_10;
|
||||
}
|
||||
|
||||
if (name.contains(" 5600 ") || name.contains(" 5600M ")) {
|
||||
return OclDevice::Navi_12;
|
||||
}
|
||||
|
||||
if (name.contains(" 5300 ") || name.contains(" 5300M ") ||
|
||||
name.contains(" 5500 ") || name.contains(" 5500M ")) {
|
||||
return OclDevice::Navi_14;
|
||||
}
|
||||
|
||||
if (name.contains(" W6800 ") || name.contains(" W6900X ")) {
|
||||
return OclDevice::Navi_21;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (name == "gfx900" || name == "gfx901") {
|
||||
return OclDevice::Vega_10;
|
||||
}
|
||||
|
||||
if (name == "gfx902" || name == "gfx903") {
|
||||
return OclDevice::Raven;
|
||||
}
|
||||
|
||||
if (name == "gfx906" || name == "gfx907") {
|
||||
return OclDevice::Vega_20;
|
||||
}
|
||||
|
||||
if (name == "gfx1010") {
|
||||
return OclDevice::Navi_10;
|
||||
}
|
||||
|
||||
if (name == "gfx1011") {
|
||||
return OclDevice::Navi_12;
|
||||
}
|
||||
|
||||
if (name == "gfx1012") {
|
||||
return OclDevice::Navi_14;
|
||||
}
|
||||
|
||||
if (name == "gfx1030") {
|
||||
return OclDevice::Navi_21;
|
||||
}
|
||||
|
||||
if (name == "gfx804") {
|
||||
return OclDevice::Lexa;
|
||||
}
|
||||
|
||||
if (name == "Baffin") {
|
||||
return OclDevice::Baffin;
|
||||
}
|
||||
|
||||
if (name.contains("Ellesmere")) {
|
||||
return OclDevice::Ellesmere;
|
||||
}
|
||||
|
||||
if (name == "gfx803" || name.contains("polaris")) {
|
||||
return OclDevice::Polaris;
|
||||
}
|
||||
|
||||
return OclDevice::Unknown;
|
||||
}
|
||||
|
||||
|
||||
} // namespace xmrig
|
||||
|
||||
|
||||
@@ -231,21 +136,21 @@ xmrig::OclDevice::OclDevice(uint32_t index, cl_device_id id, cl_platform_id plat
|
||||
{
|
||||
m_vendorId = getVendorId(m_vendor);
|
||||
m_platformVendorId = getPlatformVendorId(m_platformVendor, m_extensions);
|
||||
m_type = getType(m_name, m_platformVendorId);
|
||||
m_type = getType(m_name);
|
||||
|
||||
if (m_extensions.contains("cl_amd_device_attribute_query")) {
|
||||
topology_amd topology;
|
||||
|
||||
if (OclLib::getDeviceInfo(id, CL_DEVICE_TOPOLOGY_AMD, sizeof(topology), &topology, nullptr) == CL_SUCCESS && topology.raw.type == CL_DEVICE_TOPOLOGY_TYPE_PCIE_AMD) {
|
||||
m_topology = PciTopology(static_cast<uint32_t>(topology.pcie.bus), static_cast<uint32_t>(topology.pcie.device), static_cast<uint32_t>(topology.pcie.function));
|
||||
topology_amd topology{};
|
||||
if (OclLib::getDeviceInfo(id, CL_DEVICE_TOPOLOGY_AMD, sizeof(topology), &topology) == CL_SUCCESS && topology.type == CL_DEVICE_TOPOLOGY_TYPE_PCIE_AMD) {
|
||||
m_topology = { topology.bus, topology.device, topology.function };
|
||||
}
|
||||
|
||||
m_board = OclLib::getString(id, CL_DEVICE_BOARD_NAME_AMD);
|
||||
}
|
||||
else if (m_extensions.contains("cl_nv_device_attribute_query")) {
|
||||
cl_uint bus = 0;
|
||||
if (OclLib::getDeviceInfo(id, CL_DEVICE_PCI_BUS_ID_NV, sizeof (bus), &bus, nullptr) == CL_SUCCESS) {
|
||||
if (OclLib::getDeviceInfo(id, CL_DEVICE_PCI_BUS_ID_NV, sizeof(bus), &bus) == CL_SUCCESS) {
|
||||
cl_uint slot = OclLib::getUint(id, CL_DEVICE_PCI_SLOT_ID_NV);
|
||||
m_topology = PciTopology(bus, (slot >> 3) & 0xff, slot & 7);
|
||||
m_topology = { bus, (slot >> 3) & 0xff, slot & 7 };
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -253,17 +158,11 @@ xmrig::OclDevice::OclDevice(uint32_t index, cl_device_id id, cl_platform_id plat
|
||||
|
||||
xmrig::String xmrig::OclDevice::printableName() const
|
||||
{
|
||||
const size_t size = m_board.size() + m_name.size() + 64;
|
||||
char *buf = new char[size]();
|
||||
|
||||
if (m_board.isNull()) {
|
||||
snprintf(buf, size, GREEN_BOLD("%s"), m_name.data());
|
||||
}
|
||||
else {
|
||||
snprintf(buf, size, GREEN_BOLD("%s") " (" CYAN_BOLD("%s") ")", m_board.data(), m_name.data());
|
||||
return fmt::format(GREEN_BOLD("{}"), m_name).c_str();
|
||||
}
|
||||
|
||||
return buf;
|
||||
return fmt::format(GREEN_BOLD("{}") " (" CYAN_BOLD("{}") ")", m_board, m_name).c_str();
|
||||
}
|
||||
|
||||
|
||||
@@ -311,3 +210,35 @@ void xmrig::OclDevice::toJSON(rapidjson::Value &out, rapidjson::Document &doc) c
|
||||
# endif
|
||||
}
|
||||
#endif
|
||||
|
||||
|
||||
#ifndef XMRIG_OS_APPLE
|
||||
xmrig::OclDevice::Type xmrig::OclDevice::getType(const String &name)
|
||||
{
|
||||
static std::map<const char *, OclDevice::Type> types = {
|
||||
{ "gfx900", Vega_10 },
|
||||
{ "gfx901", Vega_10 },
|
||||
{ "gfx902", Raven },
|
||||
{ "gfx903", Raven },
|
||||
{ "gfx906", Vega_20 },
|
||||
{ "gfx907", Vega_20 },
|
||||
{ "gfx1010", Navi_10 },
|
||||
{ "gfx1011", Navi_12 },
|
||||
{ "gfx1012", Navi_14 },
|
||||
{ "gfx1030", Navi_21 },
|
||||
{ "gfx804", Lexa },
|
||||
{ "Baffin", Baffin },
|
||||
{ "Ellesmere", Ellesmere },
|
||||
{ "gfx803", Polaris },
|
||||
{ "polaris", Polaris },
|
||||
};
|
||||
|
||||
for (auto &kv : types) {
|
||||
if (name.contains(kv.first)) {
|
||||
return kv.second;
|
||||
}
|
||||
}
|
||||
|
||||
return OclDevice::Unknown;
|
||||
}
|
||||
#endif
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -86,6 +86,8 @@ public:
|
||||
# endif
|
||||
|
||||
private:
|
||||
static OclDevice::Type getType(const String &name);
|
||||
|
||||
cl_device_id m_id = nullptr;
|
||||
cl_platform_id m_platform = nullptr;
|
||||
const String m_platformVendor;
|
||||
|
||||
77
src/backend/opencl/wrappers/OclDevice_mac.cpp
Normal file
77
src/backend/opencl/wrappers/OclDevice_mac.cpp
Normal file
@@ -0,0 +1,77 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2021 Spudz76 <https://github.com/Spudz76>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License
|
||||
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
*/
|
||||
|
||||
#include "backend/opencl/wrappers/OclDevice.h"
|
||||
|
||||
|
||||
xmrig::OclDevice::Type xmrig::OclDevice::getType(const String &name)
|
||||
{
|
||||
// Apple Platform: uses product names, not gfx# or codenames
|
||||
if (name.contains("AMD Radeon")) {
|
||||
if (name.contains(" 450 ") ||
|
||||
name.contains(" 455 ") ||
|
||||
name.contains(" 460 ")) {
|
||||
return Baffin;
|
||||
}
|
||||
|
||||
if (name.contains(" 555 ") || name.contains(" 555X ") ||
|
||||
name.contains(" 560 ") || name.contains(" 560X ") ||
|
||||
name.contains(" 570 ") || name.contains(" 570X ") ||
|
||||
name.contains(" 575 ") || name.contains(" 575X ")) {
|
||||
return Polaris;
|
||||
}
|
||||
|
||||
if (name.contains(" 580 ") || name.contains(" 580X ")) {
|
||||
return Ellesmere;
|
||||
}
|
||||
|
||||
if (name.contains(" Vega ")) {
|
||||
if (name.contains(" 48 ") ||
|
||||
name.contains(" 56 ") ||
|
||||
name.contains(" 64 ") ||
|
||||
name.contains(" 64X ")) {
|
||||
return Vega_10;
|
||||
}
|
||||
if (name.contains(" 16 ") ||
|
||||
name.contains(" 20 ") ||
|
||||
name.contains(" II ")) {
|
||||
return Vega_20;
|
||||
}
|
||||
}
|
||||
|
||||
if (name.contains(" 5700 ") || name.contains(" W5700X ")) {
|
||||
return Navi_10;
|
||||
}
|
||||
|
||||
if (name.contains(" 5600 ") || name.contains(" 5600M ")) {
|
||||
return Navi_12;
|
||||
}
|
||||
|
||||
if (name.contains(" 5300 ") || name.contains(" 5300M ") ||
|
||||
name.contains(" 5500 ") || name.contains(" 5500M ")) {
|
||||
return Navi_14;
|
||||
}
|
||||
|
||||
if (name.contains(" W6800 ") || name.contains(" W6900X ")) {
|
||||
return Navi_21;
|
||||
}
|
||||
}
|
||||
|
||||
return OclDevice::Unknown;
|
||||
}
|
||||
@@ -173,7 +173,7 @@ public:
|
||||
Value total(kArrayType);
|
||||
Value threads(kArrayType);
|
||||
|
||||
double t[3] = { 0.0 };
|
||||
std::pair<bool, double> t[3] = { { true, 0.0 }, { true, 0.0 }, { true, 0.0 } };
|
||||
|
||||
for (IBackend *backend : backends) {
|
||||
const Hashrate *hr = backend->hashrate();
|
||||
@@ -181,9 +181,13 @@ public:
|
||||
continue;
|
||||
}
|
||||
|
||||
t[0] += hr->calc(Hashrate::ShortInterval);
|
||||
t[1] += hr->calc(Hashrate::MediumInterval);
|
||||
t[2] += hr->calc(Hashrate::LargeInterval);
|
||||
const auto h0 = hr->calc(Hashrate::ShortInterval);
|
||||
const auto h1 = hr->calc(Hashrate::MediumInterval);
|
||||
const auto h2 = hr->calc(Hashrate::LargeInterval);
|
||||
|
||||
if (h0.first) { t[0].second += h0.second; } else { t[0].first = false; }
|
||||
if (h1.first) { t[1].second += h1.second; } else { t[1].first = false; }
|
||||
if (h2.first) { t[2].second += h2.second; } else { t[2].first = false; }
|
||||
|
||||
if (version > 1) {
|
||||
continue;
|
||||
@@ -204,7 +208,7 @@ public:
|
||||
total.PushBack(Hashrate::normalize(t[2]), allocator);
|
||||
|
||||
hashrate.AddMember("total", total, allocator);
|
||||
hashrate.AddMember("highest", Hashrate::normalize(maxHashrate[algorithm]), allocator);
|
||||
hashrate.AddMember("highest", Hashrate::normalize({ maxHashrate[algorithm] > 0.0, maxHashrate[algorithm] }), allocator);
|
||||
|
||||
if (version == 1) {
|
||||
hashrate.AddMember("threads", threads, allocator);
|
||||
@@ -283,7 +287,7 @@ public:
|
||||
void printHashrate(bool details)
|
||||
{
|
||||
char num[16 * 5] = { 0 };
|
||||
double speed[3] = { 0.0 };
|
||||
std::pair<bool, double> speed[3] = { { true, 0.0 }, { true, 0.0 }, { true, 0.0 } };
|
||||
uint32_t count = 0;
|
||||
|
||||
double avg_hashrate = 0.0;
|
||||
@@ -293,9 +297,13 @@ public:
|
||||
if (hashrate) {
|
||||
++count;
|
||||
|
||||
speed[0] += hashrate->calc(Hashrate::ShortInterval);
|
||||
speed[1] += hashrate->calc(Hashrate::MediumInterval);
|
||||
speed[2] += hashrate->calc(Hashrate::LargeInterval);
|
||||
const auto h0 = hashrate->calc(Hashrate::ShortInterval);
|
||||
const auto h1 = hashrate->calc(Hashrate::MediumInterval);
|
||||
const auto h2 = hashrate->calc(Hashrate::LargeInterval);
|
||||
|
||||
if (h0.first) { speed[0].second += h0.second; } else { speed[0].first = false; }
|
||||
if (h1.first) { speed[1].second += h1.second; } else { speed[1].first = false; }
|
||||
if (h2.first) { speed[2].second += h2.second; } else { speed[2].first = false; }
|
||||
|
||||
avg_hashrate += hashrate->average();
|
||||
}
|
||||
@@ -312,8 +320,13 @@ public:
|
||||
double scale = 1.0;
|
||||
const char* h = "H/s";
|
||||
|
||||
if ((speed[0] >= 1e6) || (speed[1] >= 1e6) || (speed[2] >= 1e6) || (maxHashrate[algorithm] >= 1e6)) {
|
||||
if ((speed[0].second >= 1e6) || (speed[1].second >= 1e6) || (speed[2].second >= 1e6) || (maxHashrate[algorithm] >= 1e6)) {
|
||||
scale = 1e-6;
|
||||
|
||||
speed[0].second *= scale;
|
||||
speed[1].second *= scale;
|
||||
speed[2].second *= scale;
|
||||
|
||||
h = "MH/s";
|
||||
}
|
||||
|
||||
@@ -322,16 +335,16 @@ public:
|
||||
|
||||
# ifdef XMRIG_ALGO_GHOSTRIDER
|
||||
if (algorithm.family() == Algorithm::GHOSTRIDER) {
|
||||
snprintf(avg_hashrate_buf, sizeof(avg_hashrate_buf), " avg " CYAN_BOLD("%s %s"), Hashrate::format(avg_hashrate * scale, num + 16 * 4, 16), h);
|
||||
snprintf(avg_hashrate_buf, sizeof(avg_hashrate_buf), " avg " CYAN_BOLD("%s %s"), Hashrate::format({ true, avg_hashrate * scale }, num + 16 * 4, 16), h);
|
||||
}
|
||||
# endif
|
||||
|
||||
LOG_INFO("%s " WHITE_BOLD("speed") " 10s/60s/15m " CYAN_BOLD("%s") CYAN(" %s %s ") CYAN_BOLD("%s") " max " CYAN_BOLD("%s %s") "%s",
|
||||
Tags::miner(),
|
||||
Hashrate::format(speed[0] * scale, num, 16),
|
||||
Hashrate::format(speed[1] * scale, num + 16, 16),
|
||||
Hashrate::format(speed[2] * scale, num + 16 * 2, 16), h,
|
||||
Hashrate::format(maxHashrate[algorithm] * scale, num + 16 * 3, 16), h,
|
||||
Hashrate::format(speed[0], num, 16),
|
||||
Hashrate::format(speed[1], num + 16, 16),
|
||||
Hashrate::format(speed[2], num + 16 * 2, 16), h,
|
||||
Hashrate::format({ maxHashrate[algorithm] > 0.0, maxHashrate[algorithm] * scale }, num + 16 * 3, 16), h,
|
||||
avg_hashrate_buf
|
||||
);
|
||||
|
||||
@@ -646,7 +659,10 @@ void xmrig::Miner::onTimer(const Timer *)
|
||||
}
|
||||
|
||||
if (backend->hashrate()) {
|
||||
maxHashrate += backend->hashrate()->calc(Hashrate::ShortInterval);
|
||||
const auto h = backend->hashrate()->calc(Hashrate::ShortInterval);
|
||||
if (h.first) {
|
||||
maxHashrate += h.second;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -37,14 +37,36 @@ class CnAlgo
|
||||
public:
|
||||
constexpr CnAlgo() {};
|
||||
|
||||
constexpr inline Algorithm::Id base() const { static_assert(Algorithm::isCN(ALGO), "invalid CRYPTONIGHT algorithm"); return Algorithm::base(ALGO); }
|
||||
constexpr inline bool isHeavy() const { return Algorithm::family(ALGO) == Algorithm::CN_HEAVY; }
|
||||
constexpr inline bool isR() const { return ALGO == Algorithm::CN_R; }
|
||||
constexpr inline size_t memory() const { static_assert(Algorithm::isCN(ALGO), "invalid CRYPTONIGHT algorithm"); return Algorithm::l3(ALGO); }
|
||||
constexpr inline uint32_t iterations() const { static_assert(Algorithm::isCN(ALGO), "invalid CRYPTONIGHT algorithm"); return CN_ITER; }
|
||||
# define ASSERT_CN static_assert(Algorithm::isCN(ALGO), "invalid CRYPTONIGHT algorithm")
|
||||
constexpr inline Algorithm::Id base() const { ASSERT_CN; return Algorithm::base(ALGO); }
|
||||
constexpr inline size_t memory() const { ASSERT_CN; return Algorithm::l3(ALGO); }
|
||||
constexpr inline uint32_t iterations() const { ASSERT_CN; return CN_ITER; }
|
||||
constexpr inline uint32_t mask() const { return static_cast<uint32_t>(((memory() - 1) / 16) * 16); }
|
||||
constexpr inline uint32_t half_mem() const { return mask() < memory() / 2; }
|
||||
|
||||
constexpr inline bool isBase1() const { ASSERT_CN; return Algorithm::base(ALGO) == Algorithm::CN_1; }
|
||||
constexpr inline bool isBase2() const { ASSERT_CN; return Algorithm::base(ALGO) == Algorithm::CN_2; }
|
||||
constexpr inline bool is2() const { return ALGO == Algorithm::CN_2; }
|
||||
constexpr inline bool isR() const { return ALGO == Algorithm::CN_R; }
|
||||
constexpr inline bool isHalf() const { return ALGO == Algorithm::CN_HALF; }
|
||||
constexpr inline bool isRTO() const { return ALGO == Algorithm::CN_RTO; }
|
||||
constexpr inline bool isRWZ() const { return ALGO == Algorithm::CN_RWZ; }
|
||||
constexpr inline bool isZLS() const { return ALGO == Algorithm::CN_ZLS; }
|
||||
constexpr inline bool isDouble() const { return ALGO == Algorithm::CN_DOUBLE; }
|
||||
constexpr inline bool isCCX() const { return ALGO == Algorithm::CN_CCX; }
|
||||
constexpr inline bool isHeavy() const { ASSERT_CN; return Algorithm::family(ALGO) == Algorithm::CN_HEAVY; }
|
||||
constexpr inline bool isHeavyTube() const { return ALGO == Algorithm::CN_HEAVY_TUBE; }
|
||||
constexpr inline bool isHeavyXHV() const { return ALGO == Algorithm::CN_HEAVY_XHV; }
|
||||
constexpr inline bool isPico0() const { return ALGO == Algorithm::CN_PICO_0; }
|
||||
constexpr inline bool isPicoTLO() const { return ALGO == Algorithm::CN_PICO_TLO; }
|
||||
constexpr inline bool isUPX2() const { return ALGO == Algorithm::CN_UPX2; }
|
||||
constexpr inline bool isGR0() const { return ALGO == Algorithm::CN_GR_0; }
|
||||
constexpr inline bool isGR1() const { return ALGO == Algorithm::CN_GR_1; }
|
||||
constexpr inline bool isGR2() const { return ALGO == Algorithm::CN_GR_2; }
|
||||
constexpr inline bool isGR3() const { return ALGO == Algorithm::CN_GR_3; }
|
||||
constexpr inline bool isGR4() const { return ALGO == Algorithm::CN_GR_4; }
|
||||
constexpr inline bool isGR5() const { return ALGO == Algorithm::CN_GR_5; }
|
||||
|
||||
inline static uint32_t iterations(Algorithm::Id algo)
|
||||
{
|
||||
switch (algo) {
|
||||
|
||||
@@ -603,7 +603,7 @@ static inline void cryptonight_monero_tweak(uint64_t *mem_out, const uint8_t *l,
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
|
||||
if (props.base() == Algorithm::CN_2) {
|
||||
VARIANT2_SHUFFLE(l, idx, ax0, bx0, bx1, cx, (((ALGO == Algorithm::CN_RWZ) || (ALGO == Algorithm::CN_UPX2)) ? 1 : 0));
|
||||
VARIANT2_SHUFFLE(l, idx, ax0, bx0, bx1, cx, ((props.isRWZ() || props.isUPX2()) ? 1 : 0));
|
||||
_mm_store_si128(reinterpret_cast<__m128i *>(mem_out), _mm_xor_si128(bx0, cx));
|
||||
} else {
|
||||
__m128i tmp = _mm_xor_si128(bx0, cx);
|
||||
@@ -665,15 +665,8 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr size_t MASK = props.mask();
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
# ifdef XMRIG_ALGO_CN_HEAVY
|
||||
constexpr bool IS_CN_HEAVY_TUBE = ALGO == Algorithm::CN_HEAVY_TUBE;
|
||||
# else
|
||||
constexpr bool IS_CN_HEAVY_TUBE = false;
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 32);
|
||||
return;
|
||||
}
|
||||
@@ -694,10 +687,7 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
V4_Instruction code[256];
|
||||
const int code_size = v4_random_math_init<ALGO>(code, height);
|
||||
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
v4_soft_aes_compile_code(code, code_size, reinterpret_cast<void*>(ctx[0]->generated_code), Assembly::NONE);
|
||||
}
|
||||
|
||||
v4_soft_aes_compile_code(code, code_size, reinterpret_cast<void*>(ctx[0]->generated_code), Assembly::NONE);
|
||||
ctx[0]->generated_code_data = { ALGO, height };
|
||||
}
|
||||
|
||||
@@ -718,26 +708,26 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
__m128i bx1 = _mm_set_epi64x(static_cast<int64_t>(h0[9] ^ h0[11]), static_cast<int64_t>(h0[8] ^ h0[10]));
|
||||
|
||||
__m128 conc_var;
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
conc_var = _mm_setzero_ps();
|
||||
RESTORE_ROUNDING_MODE();
|
||||
}
|
||||
|
||||
for (size_t i = 0; i < props.iterations(); i++) {
|
||||
__m128i cx;
|
||||
if (IS_CN_HEAVY_TUBE || !SOFT_AES) {
|
||||
if (props.isHeavyTube() || !SOFT_AES) {
|
||||
cx = _mm_load_si128(reinterpret_cast<const __m128i *>(&l0[interleaved_index<interleave>(idx0 & MASK)]));
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
cryptonight_conceal_tweak(cx, conc_var);
|
||||
}
|
||||
}
|
||||
|
||||
const __m128i ax0 = _mm_set_epi64x(static_cast<int64_t>(ah0), static_cast<int64_t>(al0));
|
||||
if (IS_CN_HEAVY_TUBE) {
|
||||
if (props.isHeavyTube()) {
|
||||
cx = aes_round_tweak_div(cx, ax0);
|
||||
}
|
||||
else if (SOFT_AES) {
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
cx = _mm_load_si128(reinterpret_cast<const __m128i*>(&l0[interleaved_index<interleave>(idx0 & MASK)]));
|
||||
cryptonight_conceal_tweak(cx, conc_var);
|
||||
cx = soft_aesenc(&cx, ax0, reinterpret_cast<const uint32_t*>(saes_table));
|
||||
@@ -750,7 +740,7 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
cx = _mm_aesenc_si128(cx, ax0);
|
||||
}
|
||||
|
||||
if (BASE == Algorithm::CN_1 || BASE == Algorithm::CN_2) {
|
||||
if (props.isBase1() || props.isBase2()) {
|
||||
cryptonight_monero_tweak<ALGO>(reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)]), l0, idx0 & MASK, ax0, bx0, bx1, cx);
|
||||
} else {
|
||||
_mm_store_si128(reinterpret_cast<__m128i *>(&l0[interleaved_index<interleave>(idx0 & MASK)]), _mm_xor_si128(bx0, cx));
|
||||
@@ -762,13 +752,11 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
cl = (reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)]))[0];
|
||||
ch = (reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)]))[1];
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (props.isBase2()) {
|
||||
if (props.isR()) {
|
||||
VARIANT4_RANDOM_MATH(0, al0, ah0, cl, bx0, bx1);
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
al0 ^= r0[2] | (static_cast<uint64_t>(r0[3]) << 32);
|
||||
ah0 ^= r0[0] | (static_cast<uint64_t>(r0[1]) << 32);
|
||||
}
|
||||
al0 ^= r0[2] | (static_cast<uint64_t>(r0[3]) << 32);
|
||||
ah0 ^= r0[0] | (static_cast<uint64_t>(r0[1]) << 32);
|
||||
} else {
|
||||
VARIANT2_INTEGER_MATH(0, cl, cx);
|
||||
}
|
||||
@@ -776,11 +764,11 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
lo = __umul128(idx0, cl, &hi);
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
if (props.isBase2()) {
|
||||
if (props.isR()) {
|
||||
VARIANT2_SHUFFLE(l0, idx0 & MASK, ax0, bx0, bx1, cx, 0);
|
||||
} else {
|
||||
VARIANT2_SHUFFLE2(l0, idx0 & MASK, ax0, bx0, bx1, hi, lo, (((ALGO == Algorithm::CN_RWZ) || (ALGO == Algorithm::CN_UPX2)) ? 1 : 0));
|
||||
VARIANT2_SHUFFLE2(l0, idx0 & MASK, ax0, bx0, bx1, hi, lo, ((props.isRWZ() || props.isUPX2()) ? 1 : 0));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -789,9 +777,9 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)])[0] = al0;
|
||||
|
||||
if (IS_CN_HEAVY_TUBE || ALGO == Algorithm::CN_RTO) {
|
||||
if (props.isHeavyTube() || props.isRTO()) {
|
||||
reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)])[1] = ah0 ^ tweak1_2_0 ^ al0;
|
||||
} else if (BASE == Algorithm::CN_1) {
|
||||
} else if (props.isBase1()) {
|
||||
reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)])[1] = ah0 ^ tweak1_2_0;
|
||||
} else {
|
||||
reinterpret_cast<uint64_t*>(&l0[interleaved_index<interleave>(idx0 & MASK)])[1] = ah0;
|
||||
@@ -819,7 +807,7 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
((int64_t*)&l0[interleaved_index<interleave>(idx0 & MASK)])[0] = n ^ q;
|
||||
|
||||
if (ALGO == Algorithm::CN_HEAVY_XHV) {
|
||||
if (props.isHeavyXHV()) {
|
||||
d = ~d;
|
||||
}
|
||||
|
||||
@@ -827,7 +815,7 @@ inline void cryptonight_single_hash(const uint8_t *__restrict__ input, size_t si
|
||||
}
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (props.isBase2()) {
|
||||
bx1 = bx0;
|
||||
}
|
||||
|
||||
@@ -960,7 +948,7 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
}
|
||||
cn_explode_scratchpad<ALGO, false, 0>(ctx[0]);
|
||||
|
||||
if (ALGO == Algorithm::CN_2) {
|
||||
if (props.is2()) {
|
||||
if (ASM == Assembly::INTEL) {
|
||||
cnv2_mainloop_ivybridge_asm(ctx);
|
||||
}
|
||||
@@ -971,7 +959,7 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
cnv2_mainloop_bulldozer_asm(ctx);
|
||||
}
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_HALF) {
|
||||
else if (props.isHalf()) {
|
||||
if (ASM == Assembly::INTEL) {
|
||||
cn_half_mainloop_ivybridge_asm(ctx);
|
||||
}
|
||||
@@ -983,7 +971,7 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
}
|
||||
}
|
||||
# ifdef XMRIG_ALGO_CN_PICO
|
||||
else if (ALGO == Algorithm::CN_PICO_0) {
|
||||
else if (props.isPico0()) {
|
||||
if (ASM == Assembly::INTEL) {
|
||||
cn_trtl_mainloop_ivybridge_asm(ctx);
|
||||
}
|
||||
@@ -994,7 +982,7 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
cn_trtl_mainloop_bulldozer_asm(ctx);
|
||||
}
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_PICO_TLO) {
|
||||
else if (props.isPicoTLO()) {
|
||||
if (ASM == Assembly::INTEL) {
|
||||
cn_tlo_mainloop_ivybridge_asm(ctx);
|
||||
}
|
||||
@@ -1006,10 +994,10 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
}
|
||||
}
|
||||
# endif
|
||||
else if (ALGO == Algorithm::CN_RWZ) {
|
||||
else if (props.isRWZ()) {
|
||||
cnv2_rwz_mainloop_asm(ctx);
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_ZLS) {
|
||||
else if (props.isZLS()) {
|
||||
if (ASM == Assembly::INTEL) {
|
||||
cn_zls_mainloop_ivybridge_asm(ctx);
|
||||
}
|
||||
@@ -1020,7 +1008,7 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
cn_zls_mainloop_bulldozer_asm(ctx);
|
||||
}
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_DOUBLE) {
|
||||
else if (props.isDouble()) {
|
||||
if (ASM == Assembly::INTEL) {
|
||||
cn_double_mainloop_ivybridge_asm(ctx);
|
||||
}
|
||||
@@ -1032,7 +1020,7 @@ inline void cryptonight_single_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
}
|
||||
}
|
||||
# ifdef XMRIG_ALGO_CN_FEMTO
|
||||
else if (ALGO == Algorithm::CN_UPX2) {
|
||||
else if (props.isUPX2()) {
|
||||
cn_upx2_mainloop_asm(ctx);
|
||||
}
|
||||
# endif
|
||||
@@ -1078,22 +1066,22 @@ inline void cryptonight_double_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
cn_explode_scratchpad<ALGO, false, 0>(ctx[1]);
|
||||
}
|
||||
|
||||
if (ALGO == Algorithm::CN_2) {
|
||||
if (props.is2()) {
|
||||
cnv2_double_mainloop_sandybridge_asm(ctx);
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_HALF) {
|
||||
else if (props.isHalf()){
|
||||
cn_half_double_mainloop_sandybridge_asm(ctx);
|
||||
}
|
||||
# ifdef XMRIG_ALGO_CN_PICO
|
||||
else if (ALGO == Algorithm::CN_PICO_0) {
|
||||
else if (props.isPico0()) {
|
||||
cn_trtl_double_mainloop_sandybridge_asm(ctx);
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_PICO_TLO) {
|
||||
else if (props.isPicoTLO()) {
|
||||
cn_tlo_double_mainloop_sandybridge_asm(ctx);
|
||||
}
|
||||
# endif
|
||||
# ifdef XMRIG_ALGO_CN_FEMTO
|
||||
else if (ALGO == Algorithm::CN_UPX2) {
|
||||
else if (props.isUPX2()) {
|
||||
if (Cpu::info()->arch() == ICpuInfo::ARCH_ZEN3) {
|
||||
cnv2_upx_double_mainloop_zen3_asm(ctx);
|
||||
}
|
||||
@@ -1102,13 +1090,13 @@ inline void cryptonight_double_hash_asm(const uint8_t *__restrict__ input, size_
|
||||
}
|
||||
}
|
||||
# endif
|
||||
else if (ALGO == Algorithm::CN_RWZ) {
|
||||
else if (props.isRWZ()) {
|
||||
cnv2_rwz_double_mainloop_asm(ctx);
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_ZLS) {
|
||||
else if (props.isZLS()) {
|
||||
cn_zls_double_mainloop_sandybridge_asm(ctx);
|
||||
}
|
||||
else if (ALGO == Algorithm::CN_DOUBLE) {
|
||||
else if (props.isDouble()) {
|
||||
cn_double_double_mainloop_sandybridge_asm(ctx);
|
||||
}
|
||||
else if (props.isR()) {
|
||||
@@ -1146,9 +1134,8 @@ template<Algorithm::Id ALGO>
|
||||
static NOINLINE void cryptonight_single_hash_gr_sse41(const uint8_t* __restrict__ input, size_t size, uint8_t* __restrict__ output, cryptonight_ctx** __restrict__ ctx, uint64_t height)
|
||||
{
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 32);
|
||||
return;
|
||||
}
|
||||
@@ -1163,12 +1150,12 @@ static NOINLINE void cryptonight_single_hash_gr_sse41(const uint8_t* __restrict_
|
||||
VARIANT1_INIT(0);
|
||||
ctx[0]->tweak1_2 = tweak1_2_0;
|
||||
ctx[0]->tweak1_table = tweak1_table;
|
||||
if (ALGO == Algorithm::CN_GR_0) cn_gr0_single_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_1) cn_gr1_single_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_2) cn_gr2_single_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_3) cn_gr3_single_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_4) cn_gr4_single_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_5) cn_gr5_single_mainloop_asm(ctx);
|
||||
if (props.isGR0()) cn_gr0_single_mainloop_asm(ctx);
|
||||
if (props.isGR1()) cn_gr1_single_mainloop_asm(ctx);
|
||||
if (props.isGR2()) cn_gr2_single_mainloop_asm(ctx);
|
||||
if (props.isGR3()) cn_gr3_single_mainloop_asm(ctx);
|
||||
if (props.isGR4()) cn_gr4_single_mainloop_asm(ctx);
|
||||
if (props.isGR5()) cn_gr5_single_mainloop_asm(ctx);
|
||||
|
||||
cn_implode_scratchpad<ALGO, false, 0>(ctx[0]);
|
||||
keccakf(reinterpret_cast<uint64_t*>(ctx[0]->state), 24);
|
||||
@@ -1180,9 +1167,8 @@ template<Algorithm::Id ALGO>
|
||||
static NOINLINE void cryptonight_double_hash_gr_sse41(const uint8_t *__restrict__ input, size_t size, uint8_t *__restrict__ output, cryptonight_ctx **__restrict__ ctx, uint64_t height)
|
||||
{
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 64);
|
||||
return;
|
||||
}
|
||||
@@ -1196,7 +1182,7 @@ static NOINLINE void cryptonight_double_hash_gr_sse41(const uint8_t *__restrict_
|
||||
}
|
||||
|
||||
# ifdef XMRIG_VAES
|
||||
if (!props.isHeavy() && cn_vaes_enabled) {
|
||||
if (cn_vaes_enabled) {
|
||||
cn_explode_scratchpad_vaes_double(ctx[0], ctx[1], props.memory(), props.half_mem());
|
||||
}
|
||||
else
|
||||
@@ -1214,15 +1200,15 @@ static NOINLINE void cryptonight_double_hash_gr_sse41(const uint8_t *__restrict_
|
||||
|
||||
ctx[0]->tweak1_table = tweak1_table;
|
||||
|
||||
if (ALGO == Algorithm::CN_GR_0) cn_gr0_double_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_1) cn_gr1_double_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_2) cn_gr2_double_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_3) cn_gr3_double_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_4) cn_gr4_double_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_5) cn_gr5_double_mainloop_asm(ctx);
|
||||
if (props.isGR0()) cn_gr0_double_mainloop_asm(ctx);
|
||||
if (props.isGR1()) cn_gr1_double_mainloop_asm(ctx);
|
||||
if (props.isGR2()) cn_gr2_double_mainloop_asm(ctx);
|
||||
if (props.isGR3()) cn_gr3_double_mainloop_asm(ctx);
|
||||
if (props.isGR4()) cn_gr4_double_mainloop_asm(ctx);
|
||||
if (props.isGR5()) cn_gr5_double_mainloop_asm(ctx);
|
||||
|
||||
# ifdef XMRIG_VAES
|
||||
if (!props.isHeavy() && cn_vaes_enabled) {
|
||||
if (cn_vaes_enabled) {
|
||||
cn_implode_scratchpad_vaes_double(ctx[0], ctx[1], props.memory(), props.half_mem());
|
||||
}
|
||||
else
|
||||
@@ -1267,15 +1253,8 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr size_t MASK = props.mask();
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
# ifdef XMRIG_ALGO_CN_HEAVY
|
||||
constexpr bool IS_CN_HEAVY_TUBE = ALGO == Algorithm::CN_HEAVY_TUBE;
|
||||
# else
|
||||
constexpr bool IS_CN_HEAVY_TUBE = false;
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 64);
|
||||
return;
|
||||
}
|
||||
@@ -1323,7 +1302,7 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
__m128i bx11 = _mm_set_epi64x(h1[9] ^ h1[11], h1[8] ^ h1[10]);
|
||||
|
||||
__m128 conc_var0, conc_var1;
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
conc_var0 = _mm_setzero_ps();
|
||||
conc_var1 = _mm_setzero_ps();
|
||||
RESTORE_ROUNDING_MODE();
|
||||
@@ -1334,10 +1313,10 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
for (size_t i = 0; i < props.iterations(); i++) {
|
||||
__m128i cx0, cx1;
|
||||
if (IS_CN_HEAVY_TUBE || !SOFT_AES) {
|
||||
if (props.isHeavyTube() || !SOFT_AES) {
|
||||
cx0 = _mm_load_si128(reinterpret_cast<const __m128i *>(&l0[idx0 & MASK]));
|
||||
cx1 = _mm_load_si128(reinterpret_cast<const __m128i *>(&l1[idx1 & MASK]));
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
cryptonight_conceal_tweak(cx0, conc_var0);
|
||||
cryptonight_conceal_tweak(cx1, conc_var1);
|
||||
}
|
||||
@@ -1345,12 +1324,12 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
const __m128i ax0 = _mm_set_epi64x(ah0, al0);
|
||||
const __m128i ax1 = _mm_set_epi64x(ah1, al1);
|
||||
if (IS_CN_HEAVY_TUBE) {
|
||||
if (props.isHeavyTube()) {
|
||||
cx0 = aes_round_tweak_div(cx0, ax0);
|
||||
cx1 = aes_round_tweak_div(cx1, ax1);
|
||||
}
|
||||
else if (SOFT_AES) {
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
cx0 = _mm_load_si128(reinterpret_cast<const __m128i*>(&l0[idx0 & MASK]));
|
||||
cx1 = _mm_load_si128(reinterpret_cast<const __m128i*>(&l1[idx1 & MASK]));
|
||||
cryptonight_conceal_tweak(cx0, conc_var0);
|
||||
@@ -1368,7 +1347,7 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
cx1 = _mm_aesenc_si128(cx1, ax1);
|
||||
}
|
||||
|
||||
if (BASE == Algorithm::CN_1 || BASE == Algorithm::CN_2) {
|
||||
if (props.isBase1() || props.isBase2()) {
|
||||
cryptonight_monero_tweak<ALGO>((uint64_t*)&l0[idx0 & MASK], l0, idx0 & MASK, ax0, bx00, bx01, cx0);
|
||||
cryptonight_monero_tweak<ALGO>((uint64_t*)&l1[idx1 & MASK], l1, idx1 & MASK, ax1, bx10, bx11, cx1);
|
||||
} else {
|
||||
@@ -1383,13 +1362,11 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
cl = ((uint64_t*) &l0[idx0 & MASK])[0];
|
||||
ch = ((uint64_t*) &l0[idx0 & MASK])[1];
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (props.isBase2()) {
|
||||
if (props.isR()) {
|
||||
VARIANT4_RANDOM_MATH(0, al0, ah0, cl, bx00, bx01);
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
al0 ^= r0[2] | ((uint64_t)(r0[3]) << 32);
|
||||
ah0 ^= r0[0] | ((uint64_t)(r0[1]) << 32);
|
||||
}
|
||||
al0 ^= r0[2] | ((uint64_t)(r0[3]) << 32);
|
||||
ah0 ^= r0[0] | ((uint64_t)(r0[1]) << 32);
|
||||
} else {
|
||||
VARIANT2_INTEGER_MATH(0, cl, cx0);
|
||||
}
|
||||
@@ -1397,11 +1374,11 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
lo = __umul128(idx0, cl, &hi);
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
if (props.isBase2()) {
|
||||
if (props.isR()) {
|
||||
VARIANT2_SHUFFLE(l0, idx0 & MASK, ax0, bx00, bx01, cx0, 0);
|
||||
} else {
|
||||
VARIANT2_SHUFFLE2(l0, idx0 & MASK, ax0, bx00, bx01, hi, lo, (((ALGO == Algorithm::CN_RWZ) || (ALGO == Algorithm::CN_UPX2)) ? 1 : 0));
|
||||
VARIANT2_SHUFFLE2(l0, idx0 & MASK, ax0, bx00, bx01, hi, lo, ((props.isRWZ() || props.isUPX2()) ? 1 : 0));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1410,9 +1387,9 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
((uint64_t*)&l0[idx0 & MASK])[0] = al0;
|
||||
|
||||
if (IS_CN_HEAVY_TUBE || ALGO == Algorithm::CN_RTO) {
|
||||
if (props.isHeavyTube() || props.isRTO()) {
|
||||
((uint64_t*) &l0[idx0 & MASK])[1] = ah0 ^ tweak1_2_0 ^ al0;
|
||||
} else if (BASE == Algorithm::CN_1) {
|
||||
} else if (props.isBase1()) {
|
||||
((uint64_t*) &l0[idx0 & MASK])[1] = ah0 ^ tweak1_2_0;
|
||||
} else {
|
||||
((uint64_t*) &l0[idx0 & MASK])[1] = ah0;
|
||||
@@ -1430,7 +1407,7 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
((int64_t*)&l0[idx0 & MASK])[0] = n ^ q;
|
||||
|
||||
if (ALGO == Algorithm::CN_HEAVY_XHV) {
|
||||
if (props.isHeavyXHV()) {
|
||||
d = ~d;
|
||||
}
|
||||
|
||||
@@ -1441,13 +1418,11 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
cl = ((uint64_t*) &l1[idx1 & MASK])[0];
|
||||
ch = ((uint64_t*) &l1[idx1 & MASK])[1];
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (props.isBase2()) {
|
||||
if (props.isR()) {
|
||||
VARIANT4_RANDOM_MATH(1, al1, ah1, cl, bx10, bx11);
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
al1 ^= r1[2] | ((uint64_t)(r1[3]) << 32);
|
||||
ah1 ^= r1[0] | ((uint64_t)(r1[1]) << 32);
|
||||
}
|
||||
al1 ^= r1[2] | ((uint64_t)(r1[3]) << 32);
|
||||
ah1 ^= r1[0] | ((uint64_t)(r1[1]) << 32);
|
||||
} else {
|
||||
VARIANT2_INTEGER_MATH(1, cl, cx1);
|
||||
}
|
||||
@@ -1455,11 +1430,11 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
lo = __umul128(idx1, cl, &hi);
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (ALGO == Algorithm::CN_R) {
|
||||
if (props.isBase2()) {
|
||||
if (props.isR()) {
|
||||
VARIANT2_SHUFFLE(l1, idx1 & MASK, ax1, bx10, bx11, cx1, 0);
|
||||
} else {
|
||||
VARIANT2_SHUFFLE2(l1, idx1 & MASK, ax1, bx10, bx11, hi, lo, (((ALGO == Algorithm::CN_RWZ) || (ALGO == Algorithm::CN_UPX2)) ? 1 : 0));
|
||||
VARIANT2_SHUFFLE2(l1, idx1 & MASK, ax1, bx10, bx11, hi, lo, ((props.isRWZ() || props.isUPX2()) ? 1 : 0));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1468,9 +1443,9 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
((uint64_t*)&l1[idx1 & MASK])[0] = al1;
|
||||
|
||||
if (IS_CN_HEAVY_TUBE || ALGO == Algorithm::CN_RTO) {
|
||||
if (props.isHeavyTube() || props.isRTO()) {
|
||||
((uint64_t*)&l1[idx1 & MASK])[1] = ah1 ^ tweak1_2_1 ^ al1;
|
||||
} else if (BASE == Algorithm::CN_1) {
|
||||
} else if (props.isBase1()) {
|
||||
((uint64_t*)&l1[idx1 & MASK])[1] = ah1 ^ tweak1_2_1;
|
||||
} else {
|
||||
((uint64_t*)&l1[idx1 & MASK])[1] = ah1;
|
||||
@@ -1488,7 +1463,7 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
|
||||
((int64_t*)&l1[idx1 & MASK])[0] = n ^ q;
|
||||
|
||||
if (ALGO == Algorithm::CN_HEAVY_XHV) {
|
||||
if (props.isHeavyXHV()) {
|
||||
d = ~d;
|
||||
}
|
||||
|
||||
@@ -1496,7 +1471,7 @@ inline void cryptonight_double_hash(const uint8_t *__restrict__ input, size_t si
|
||||
}
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_2) {
|
||||
if (props.isBase2()) {
|
||||
bx01 = bx00;
|
||||
bx11 = bx10;
|
||||
}
|
||||
@@ -1529,9 +1504,8 @@ template<Algorithm::Id ALGO>
|
||||
static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__ input, size_t size, uint8_t* __restrict__ output, cryptonight_ctx** __restrict__ ctx, uint64_t height)
|
||||
{
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 32 * 4);
|
||||
return;
|
||||
}
|
||||
@@ -1549,7 +1523,7 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
}
|
||||
|
||||
# ifdef XMRIG_VAES
|
||||
if (!props.isHeavy() && cn_vaes_enabled) {
|
||||
if (cn_vaes_enabled) {
|
||||
cn_explode_scratchpad_vaes_double(ctx[0], ctx[1], props.memory(), props.half_mem());
|
||||
cn_explode_scratchpad_vaes_double(ctx[2], ctx[3], props.memory(), props.half_mem());
|
||||
}
|
||||
@@ -1569,15 +1543,15 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
|
||||
ctx[0]->tweak1_table = tweak1_table;
|
||||
|
||||
if (ALGO == Algorithm::CN_GR_0) cn_gr0_quad_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_1) cn_gr1_quad_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_2) cn_gr2_quad_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_3) cn_gr3_quad_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_4) cn_gr4_quad_mainloop_asm(ctx);
|
||||
if (ALGO == Algorithm::CN_GR_5) cn_gr5_quad_mainloop_asm(ctx);
|
||||
if (props.isGR0()) cn_gr0_quad_mainloop_asm(ctx);
|
||||
if (props.isGR1()) cn_gr1_quad_mainloop_asm(ctx);
|
||||
if (props.isGR2()) cn_gr2_quad_mainloop_asm(ctx);
|
||||
if (props.isGR3()) cn_gr3_quad_mainloop_asm(ctx);
|
||||
if (props.isGR4()) cn_gr4_quad_mainloop_asm(ctx);
|
||||
if (props.isGR5()) cn_gr5_quad_mainloop_asm(ctx);
|
||||
|
||||
# ifdef XMRIG_VAES
|
||||
if (!props.isHeavy() && cn_vaes_enabled) {
|
||||
if (cn_vaes_enabled) {
|
||||
cn_implode_scratchpad_vaes_double(ctx[0], ctx[1], props.memory(), props.half_mem());
|
||||
cn_implode_scratchpad_vaes_double(ctx[2], ctx[3], props.memory(), props.half_mem());
|
||||
}
|
||||
@@ -1606,14 +1580,14 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
#define CN_STEP1(a, b0, b1, c, l, ptr, idx, conc_var) \
|
||||
ptr = reinterpret_cast<__m128i*>(&l[idx & MASK]); \
|
||||
c = _mm_load_si128(ptr); \
|
||||
if (ALGO == Algorithm::CN_CCX) { \
|
||||
if (props.isCCX()) { \
|
||||
cryptonight_conceal_tweak(c, conc_var); \
|
||||
}
|
||||
|
||||
|
||||
|
||||
#define CN_STEP2(a, b0, b1, c, l, ptr, idx) \
|
||||
if (IS_CN_HEAVY_TUBE) { \
|
||||
if (props.isHeavyTube()) { \
|
||||
c = aes_round_tweak_div(c, a); \
|
||||
} \
|
||||
else if (SOFT_AES) { \
|
||||
@@ -1622,7 +1596,7 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
c = _mm_aesenc_si128(c, a); \
|
||||
} \
|
||||
\
|
||||
if (BASE == Algorithm::CN_1 || BASE == Algorithm::CN_2) { \
|
||||
if (props.isBase1() || props.isBase2()) { \
|
||||
cryptonight_monero_tweak<ALGO>((uint64_t*)ptr, l, idx & MASK, a, b0, b1, c); \
|
||||
} else { \
|
||||
_mm_store_si128(ptr, _mm_xor_si128(b0, c)); \
|
||||
@@ -1638,36 +1612,34 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
|
||||
#define CN_STEP4(part, a, b0, b1, c, l, mc, ptr, idx) \
|
||||
uint64_t al##part, ah##part; \
|
||||
if (BASE == Algorithm::CN_2) { \
|
||||
if (props.isBase2()) { \
|
||||
if (props.isR()) { \
|
||||
al##part = _mm_cvtsi128_si64(a); \
|
||||
ah##part = _mm_cvtsi128_si64(_mm_srli_si128(a, 8)); \
|
||||
VARIANT4_RANDOM_MATH(part, al##part, ah##part, cl##part, b0, b1); \
|
||||
if (ALGO == Algorithm::CN_R) { \
|
||||
al##part ^= r##part[2] | ((uint64_t)(r##part[3]) << 32); \
|
||||
ah##part ^= r##part[0] | ((uint64_t)(r##part[1]) << 32); \
|
||||
} \
|
||||
al##part ^= r##part[2] | ((uint64_t)(r##part[3]) << 32); \
|
||||
ah##part ^= r##part[0] | ((uint64_t)(r##part[1]) << 32); \
|
||||
} else { \
|
||||
VARIANT2_INTEGER_MATH(part, cl##part, c); \
|
||||
} \
|
||||
} \
|
||||
lo = __umul128(idx, cl##part, &hi); \
|
||||
if (BASE == Algorithm::CN_2) { \
|
||||
if (ALGO == Algorithm::CN_R) { \
|
||||
if (props.isBase2()) { \
|
||||
if (props.isR()) { \
|
||||
VARIANT2_SHUFFLE(l, idx & MASK, a, b0, b1, c, 0); \
|
||||
} else { \
|
||||
VARIANT2_SHUFFLE2(l, idx & MASK, a, b0, b1, hi, lo, (((ALGO == Algorithm::CN_RWZ) || (ALGO == Algorithm::CN_UPX2)) ? 1 : 0)); \
|
||||
VARIANT2_SHUFFLE2(l, idx & MASK, a, b0, b1, hi, lo, ((props.isRWZ() || props.isUPX2()) ? 1 : 0)); \
|
||||
} \
|
||||
} \
|
||||
if (ALGO == Algorithm::CN_R) { \
|
||||
if (props.isR()) { \
|
||||
a = _mm_set_epi64x(ah##part, al##part); \
|
||||
} \
|
||||
a = _mm_add_epi64(a, _mm_set_epi64x(lo, hi)); \
|
||||
\
|
||||
if (BASE == Algorithm::CN_1) { \
|
||||
if (props.isBase1()) { \
|
||||
_mm_store_si128(ptr, _mm_xor_si128(a, mc)); \
|
||||
\
|
||||
if (IS_CN_HEAVY_TUBE || ALGO == Algorithm::CN_RTO) { \
|
||||
if (props.isHeavyTube() || props.isRTO()) { \
|
||||
((uint64_t*)ptr)[1] ^= ((uint64_t*)ptr)[0]; \
|
||||
} \
|
||||
} else { \
|
||||
@@ -1681,13 +1653,13 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
int32_t d = ((int32_t*)&l[idx & MASK])[2]; \
|
||||
int64_t q = n / (d | 0x5); \
|
||||
((int64_t*)&l[idx & MASK])[0] = n ^ q; \
|
||||
if (IS_CN_HEAVY_XHV) { \
|
||||
if (props.isHeavyXHV()) { \
|
||||
d = ~d; \
|
||||
} \
|
||||
\
|
||||
idx = d ^ q; \
|
||||
} \
|
||||
if (BASE == Algorithm::CN_2) { \
|
||||
if (props.isBase2()) { \
|
||||
b1 = b0; \
|
||||
} \
|
||||
b0 = c;
|
||||
@@ -1697,11 +1669,11 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
__m128i mc##n; \
|
||||
__m128i division_result_xmm_##n; \
|
||||
__m128i sqrt_result_xmm_##n; \
|
||||
if (BASE == Algorithm::CN_1) { \
|
||||
if (props.isBase1()) { \
|
||||
mc##n = _mm_set_epi64x(*reinterpret_cast<const uint64_t*>(input + n * size + 35) ^ \
|
||||
*(reinterpret_cast<const uint64_t*>((ctx)->state) + 24), 0); \
|
||||
} \
|
||||
if (BASE == Algorithm::CN_2) { \
|
||||
if (props.isBase2()) { \
|
||||
division_result_xmm_##n = _mm_cvtsi64_si128(h##n[12]); \
|
||||
sqrt_result_xmm_##n = _mm_cvtsi64_si128(h##n[13]); \
|
||||
} \
|
||||
@@ -1710,7 +1682,7 @@ static NOINLINE void cryptonight_quad_hash_gr_sse41(const uint8_t* __restrict__
|
||||
__m128i bx##n##1 = _mm_set_epi64x(h##n[9] ^ h##n[11], h##n[8] ^ h##n[10]); \
|
||||
__m128i cx##n = _mm_setzero_si128(); \
|
||||
__m128 conc_var##n; \
|
||||
if (ALGO == Algorithm::CN_CCX) { \
|
||||
if (props.isCCX()) { \
|
||||
conc_var##n = _mm_setzero_ps(); \
|
||||
} \
|
||||
VARIANT4_RANDOM_MATH_INIT(n);
|
||||
@@ -1721,17 +1693,8 @@ inline void cryptonight_triple_hash(const uint8_t *__restrict__ input, size_t si
|
||||
{
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr size_t MASK = props.mask();
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
# ifdef XMRIG_ALGO_CN_HEAVY
|
||||
constexpr bool IS_CN_HEAVY_TUBE = ALGO == Algorithm::CN_HEAVY_TUBE;
|
||||
constexpr bool IS_CN_HEAVY_XHV = ALGO == Algorithm::CN_HEAVY_XHV;
|
||||
# else
|
||||
constexpr bool IS_CN_HEAVY_TUBE = false;
|
||||
constexpr bool IS_CN_HEAVY_XHV = false;
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 32 * 3);
|
||||
return;
|
||||
}
|
||||
@@ -1755,7 +1718,7 @@ inline void cryptonight_triple_hash(const uint8_t *__restrict__ input, size_t si
|
||||
CONST_INIT(ctx[1], 1);
|
||||
CONST_INIT(ctx[2], 2);
|
||||
VARIANT2_SET_ROUNDING_MODE();
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
RESTORE_ROUNDING_MODE();
|
||||
}
|
||||
|
||||
@@ -1819,17 +1782,8 @@ inline void cryptonight_quad_hash(const uint8_t *__restrict__ input, size_t size
|
||||
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr size_t MASK = props.mask();
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
# ifdef XMRIG_ALGO_CN_HEAVY
|
||||
constexpr bool IS_CN_HEAVY_TUBE = ALGO == Algorithm::CN_HEAVY_TUBE;
|
||||
constexpr bool IS_CN_HEAVY_XHV = ALGO == Algorithm::CN_HEAVY_XHV;
|
||||
# else
|
||||
constexpr bool IS_CN_HEAVY_TUBE = false;
|
||||
constexpr bool IS_CN_HEAVY_XHV = false;
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 32 * 4);
|
||||
return;
|
||||
}
|
||||
@@ -1869,7 +1823,7 @@ inline void cryptonight_quad_hash(const uint8_t *__restrict__ input, size_t size
|
||||
CONST_INIT(ctx[2], 2);
|
||||
CONST_INIT(ctx[3], 3);
|
||||
VARIANT2_SET_ROUNDING_MODE();
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
RESTORE_ROUNDING_MODE();
|
||||
}
|
||||
|
||||
@@ -1930,17 +1884,8 @@ inline void cryptonight_penta_hash(const uint8_t *__restrict__ input, size_t siz
|
||||
{
|
||||
constexpr CnAlgo<ALGO> props;
|
||||
constexpr size_t MASK = props.mask();
|
||||
constexpr Algorithm::Id BASE = props.base();
|
||||
|
||||
# ifdef XMRIG_ALGO_CN_HEAVY
|
||||
constexpr bool IS_CN_HEAVY_TUBE = ALGO == Algorithm::CN_HEAVY_TUBE;
|
||||
constexpr bool IS_CN_HEAVY_XHV = ALGO == Algorithm::CN_HEAVY_XHV;
|
||||
# else
|
||||
constexpr bool IS_CN_HEAVY_TUBE = false;
|
||||
constexpr bool IS_CN_HEAVY_XHV = false;
|
||||
# endif
|
||||
|
||||
if (BASE == Algorithm::CN_1 && size < 43) {
|
||||
if (props.isBase1() && size < 43) {
|
||||
memset(output, 0, 32 * 5);
|
||||
return;
|
||||
}
|
||||
@@ -1970,7 +1915,7 @@ inline void cryptonight_penta_hash(const uint8_t *__restrict__ input, size_t siz
|
||||
CONST_INIT(ctx[3], 3);
|
||||
CONST_INIT(ctx[4], 4);
|
||||
VARIANT2_SET_ROUNDING_MODE();
|
||||
if (ALGO == Algorithm::CN_CCX) {
|
||||
if (props.isCCX()) {
|
||||
RESTORE_ROUNDING_MODE();
|
||||
}
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* XMRig
|
||||
* Copyright (c) 2018-2019 tevador <tevador@gmail.com>
|
||||
* Copyright (c) 2018-2020 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2020 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
* Copyright (c) 2018-2024 SChernykh <https://github.com/SChernykh>
|
||||
* Copyright (c) 2016-2024 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
@@ -17,9 +17,7 @@
|
||||
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
*/
|
||||
|
||||
|
||||
#include "crypto/rx/RxBasicStorage.h"
|
||||
#include "backend/common/Tags.h"
|
||||
#include "base/io/log/Log.h"
|
||||
#include "base/io/log/Tags.h"
|
||||
#include "base/tools/Chrono.h"
|
||||
|
||||
@@ -22,7 +22,7 @@
|
||||
#define APP_ID "xmrig"
|
||||
#define APP_NAME "XMRig"
|
||||
#define APP_DESC "XMRig miner"
|
||||
#define APP_VERSION "6.22.1"
|
||||
#define APP_VERSION "6.22.3-dev"
|
||||
#define APP_DOMAIN "xmrig.com"
|
||||
#define APP_SITE "www.xmrig.com"
|
||||
#define APP_COPYRIGHT "Copyright (C) 2016-2024 xmrig.com"
|
||||
@@ -30,7 +30,7 @@
|
||||
|
||||
#define APP_VER_MAJOR 6
|
||||
#define APP_VER_MINOR 22
|
||||
#define APP_VER_PATCH 1
|
||||
#define APP_VER_PATCH 3
|
||||
|
||||
#ifdef _MSC_VER
|
||||
# if (_MSC_VER >= 1930)
|
||||
|
||||
Reference in New Issue
Block a user