coalesced cpu caps + wall clokc timer

This commit is contained in:
lizzie 2026-05-24 01:26:46 +00:00
parent c5c581d5f3
commit d0445f1d4d
15 changed files with 362 additions and 380 deletions

View file

@ -141,12 +141,12 @@ add_library(
vector_math.h vector_math.h
virtual_buffer.cpp virtual_buffer.cpp
virtual_buffer.h virtual_buffer.h
wall_clock.cpp
wall_clock.h
zstd_compression.cpp zstd_compression.cpp
zstd_compression.h zstd_compression.h
fs/ryujinx_compat.h fs/ryujinx_compat.cpp fs/ryujinx_compat.h fs/ryujinx_compat.cpp
fs/symlink.h fs/symlink.cpp fs/symlink.h fs/symlink.cpp
cpu_features.cpp
cpu_features.h
httplib.h httplib.h
net/net.h net/net.cpp) net/net.h net/net.cpp)
@ -180,8 +180,7 @@ endif()
if(ARCHITECTURE_x86_64) if(ARCHITECTURE_x86_64)
target_sources( target_sources(
common common
PRIVATE x64/cpu_detect.cpp PRIVATE
x64/cpu_detect.h
x64/rdtsc.cpp x64/rdtsc.cpp
x64/rdtsc.h x64/rdtsc.h
x64/xbyak.h) x64/xbyak.h)

View file

@ -13,33 +13,42 @@
#include <string_view> #include <string_view>
#include <thread> #include <thread>
#include <vector> #include <vector>
#include "common/bit_util.h"
#include "common/common_types.h"
#include "common/logging.h"
#ifdef ARCHITECTURE_x86_64
#include "common/x64/cpu_detect.h"
#include "common/x64/rdtsc.h"
#endif
#ifdef _WIN32 #ifdef _WIN32
#include <windows.h> #include <windows.h>
#endif #endif
#if defined(__DragonFly__) || defined(__FreeBSD__)
#include <sys/types.h>
#include <machine/cpufunc.h>
#endif
#include "common/steady_clock.h"
#include "common/uint128.h"
#include "common/bit_util.h"
#include "common/common_types.h"
#include "common/cpu_detect.h"
#ifdef ARCHITECTURE_x86_64
#include "common/x64/rdtsc.h"
#ifdef _MSC_VER #ifdef _MSC_VER
#include <intrin.h> #include <intrin.h>
static inline u64 xgetbv(u32 index) { static inline u64 xgetbv(u32 index) {
return _xgetbv(index); return _xgetbv(index);
} }
#else #else
#if defined(__DragonFly__) || defined(__FreeBSD__)
// clang-format off
#include <sys/types.h>
#include <machine/cpufunc.h>
// clang-format on
#endif #endif
#ifdef __ANDROID__
#include <sys/system_properties.h>
#endif
#ifdef ARCHITECTURE_x86_64
#include "common/x64/rdtsc.h"
#endif
namespace Common {
#ifdef ARCHITECTURE_x86_64
namespace {
static inline void __cpuidex(int info[4], u32 function_id, u32 subfunction_id) { static inline void __cpuidex(int info[4], u32 function_id, u32 subfunction_id) {
#if defined(__DragonFly__) || defined(__FreeBSD__) #if defined(__DragonFly__) || defined(__FreeBSD__)
// Despite the name, this is just do_cpuid() with ECX as second input. // Despite the name, this is just do_cpuid() with ECX as second input.
@ -64,8 +73,7 @@ static inline u64 xgetbv(u32 index) {
return ((u64)edx << 32) | eax; return ((u64)edx << 32) | eax;
} }
#endif // _MSC_VER #endif // _MSC_VER
}
namespace Common {
CPUCaps::Manufacturer CPUCaps::ParseManufacturer(std::string_view brand_string) { CPUCaps::Manufacturer CPUCaps::ParseManufacturer(std::string_view brand_string) {
if (brand_string == "GenuineIntel") { if (brand_string == "GenuineIntel") {
@ -78,6 +86,47 @@ CPUCaps::Manufacturer CPUCaps::ParseManufacturer(std::string_view brand_string)
return Manufacturer::Unknown; return Manufacturer::Unknown;
} }
std::optional<int> GetProcessorCount() {
#if defined(_WIN32)
// Get the buffer length.
DWORD length = 0;
GetLogicalProcessorInformation(nullptr, &length);
if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
LOG_ERROR(Frontend, "Failed to query core count.");
return std::nullopt;
}
std::vector<SYSTEM_LOGICAL_PROCESSOR_INFORMATION> buffer(
length / sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION));
// Now query the core count.
if (!GetLogicalProcessorInformation(buffer.data(), &length)) {
LOG_ERROR(Frontend, "Failed to query core count.");
return std::nullopt;
}
return static_cast<int>(
std::count_if(buffer.cbegin(), buffer.cend(), [](const auto& proc_info) {
return proc_info.Relationship == RelationProcessorCore;
}));
#elif defined(__unix__)
const int thread_count = std::thread::hardware_concurrency();
std::ifstream smt("/sys/devices/system/cpu/smt/active");
char state = '0';
if (smt) {
smt.read(&state, sizeof(state));
}
switch (state) {
case '0':
return thread_count;
case '1':
return thread_count / 2;
default:
return std::nullopt;
}
#else
// Shame on you
return std::nullopt;
#endif
}
/// @brief Detects the various CPU features /// @brief Detects the various CPU features
const CPUCaps g_cpu_caps = [] { const CPUCaps g_cpu_caps = [] {
CPUCaps caps = {}; CPUCaps caps = {};
@ -184,12 +233,14 @@ const CPUCaps g_cpu_caps = [] {
// https://github.com/torvalds/linux/blob/master/tools/power/x86/turbostat/turbostat.c#L5569 // https://github.com/torvalds/linux/blob/master/tools/power/x86/turbostat/turbostat.c#L5569
// but it's easier to just estimate the TSC tick rate for these cases. // but it's easier to just estimate the TSC tick rate for these cases.
if (caps.tsc_crystal_ratio_denominator) { if (caps.tsc_crystal_ratio_denominator) {
caps.tsc_frequency = static_cast<u64>(caps.crystal_frequency) * caps.tsc_frequency = u64(caps.crystal_frequency)
caps.tsc_crystal_ratio_numerator / * caps.tsc_crystal_ratio_numerator / caps.tsc_crystal_ratio_denominator;
caps.tsc_crystal_ratio_denominator;
} else { } else {
caps.tsc_frequency = X64::EstimateRDTSCFrequency(); caps.tsc_frequency = X64::EstimateRDTSCFrequency();
} }
caps.tsc_to_ns_ratio = GetFixedPoint64Factor(NsRatio::den, caps.tsc_frequency);
} else {
caps.tsc_to_ns_ratio = 1;
} }
if (max_std_fn >= 0x16) { if (max_std_fn >= 0x16) {
@ -201,45 +252,184 @@ const CPUCaps g_cpu_caps = [] {
return caps; return caps;
}(); }();
std::optional<int> GetProcessorCount() {
#if defined(_WIN32)
// Get the buffer length.
DWORD length = 0;
GetLogicalProcessorInformation(nullptr, &length);
if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
LOG_ERROR(Frontend, "Failed to query core count.");
return std::nullopt;
}
std::vector<SYSTEM_LOGICAL_PROCESSOR_INFORMATION> buffer(
length / sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION));
// Now query the core count.
if (!GetLogicalProcessorInformation(buffer.data(), &length)) {
LOG_ERROR(Frontend, "Failed to query core count.");
return std::nullopt;
}
return static_cast<int>(
std::count_if(buffer.cbegin(), buffer.cend(), [](const auto& proc_info) {
return proc_info.Relationship == RelationProcessorCore;
}));
#elif defined(__unix__)
const int thread_count = std::thread::hardware_concurrency();
std::ifstream smt("/sys/devices/system/cpu/smt/active");
char state = '0';
if (smt) {
smt.read(&state, sizeof(state));
}
switch (state) {
case '0':
return thread_count;
case '1':
return thread_count / 2;
default:
return std::nullopt;
}
#else #else
// Shame on you
return std::nullopt; #endif
#if defined(ARCHITECTURE_x86_64)
WallClock::WallClock(bool invariant_, u64 rdtsc_frequency_) noexcept
: rdtsc_frequency{rdtsc_frequency_}
, ns_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(NsRatio::den, rdtsc_frequency_) : 0}
, us_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(UsRatio::den, rdtsc_frequency_) : 0}
, ms_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(MsRatio::den, rdtsc_frequency_) : 0}
, cntpct_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(CNTFRQ, rdtsc_frequency_) : 0}
, gputick_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(GPUTickFreq, rdtsc_frequency_) : 0}
, invariant{invariant_}
{}
std::chrono::nanoseconds WallClock::GetTimeNS() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::system_clock::now().time_since_epoch());
return std::chrono::nanoseconds{MultiplyHigh(GetUptime(), ns_rdtsc_factor)};
}
std::chrono::microseconds WallClock::GetTimeUS() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::system_clock::now().time_since_epoch());
return std::chrono::microseconds{MultiplyHigh(GetUptime(), us_rdtsc_factor)};
}
std::chrono::milliseconds WallClock::GetTimeMS() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch());
return std::chrono::milliseconds{MultiplyHigh(GetUptime(), ms_rdtsc_factor)};
}
s64 WallClock::GetCNTPCT() const {
if (!invariant)
return GetUptime() * NsToCNTPCTRatio::num / NsToCNTPCTRatio::den;
return MultiplyHigh(GetUptime(), cntpct_rdtsc_factor);
}
s64 WallClock::GetGPUTick() const {
if (!invariant)
return GetUptime() * NsToGPUTickRatio::num / NsToGPUTickRatio::den;
return MultiplyHigh(GetUptime(), gputick_rdtsc_factor);
}
s64 WallClock::GetUptime() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::steady_clock::now().time_since_epoch()).count();
return s64(Common::X64::FencedRDTSC());
}
bool WallClock::IsNative() const {
return invariant;
}
#elif defined(HAS_NCE)
namespace {
[[nodiscard]] WallClock::FactorType GetFixedPointFactor(u64 num, u64 den) noexcept {
return (WallClock::FactorType(num) << 64) / den;
}
[[nodiscard]] u64 MultiplyHigh(u64 m, WallClock::FactorType factor) noexcept {
return static_cast<u64>((m * factor) >> 64);
}
[[nodiscard]] s64 GetHostCNTFRQ() noexcept {
u64 cntfrq_el0 = 0;
#ifdef ANDROID
std::string_view board{""};
char buffer[PROP_VALUE_MAX];
int len{__system_property_get("ro.product.board", buffer)};
board = std::string_view(buffer, static_cast<size_t>(len));
if (board == "s5e9925") { // Exynos 2200
cntfrq_el0 = 25600000;
} else if (board == "exynos2100") { // Exynos 2100
cntfrq_el0 = 26000000;
} else if (board == "exynos9810") { // Exynos 9810
cntfrq_el0 = 26000000;
} else if (board == "s5e8825") { // Exynos 1280
cntfrq_el0 = 26000000;
} else {
asm volatile("mrs %[cntfrq_el0], cntfrq_el0" : [cntfrq_el0] "=r"(cntfrq_el0));
}
return cntfrq_el0;
#else
asm volatile("mrs %[cntfrq_el0], cntfrq_el0" : [cntfrq_el0] "=r"(cntfrq_el0));
return cntfrq_el0;
#endif #endif
} }
} // namespace
WallClock::WallClock(bool invariant_, u64 rdtsc_frequency_) noexcept {
const u64 host_cntfrq = std::max<u64>(GetHostCNTFRQ(), 1);
ns_cntfrq_factor = GetFixedPointFactor(NsRatio::den, host_cntfrq);
us_cntfrq_factor = GetFixedPointFactor(UsRatio::den, host_cntfrq);
ms_cntfrq_factor = GetFixedPointFactor(MsRatio::den, host_cntfrq);
guest_cntfrq_factor = GetFixedPointFactor(CNTFRQ, host_cntfrq);
gputick_cntfrq_factor = GetFixedPointFactor(GPUTickFreq, host_cntfrq);
}
std::chrono::nanoseconds WallClock::GetTimeNS() const {
return std::chrono::nanoseconds{MultiplyHigh(GetUptime(), ns_cntfrq_factor)};
}
std::chrono::microseconds WallClock::GetTimeUS() const {
return std::chrono::microseconds{MultiplyHigh(GetUptime(), us_cntfrq_factor)};
}
std::chrono::milliseconds WallClock::GetTimeMS() const {
return std::chrono::milliseconds{MultiplyHigh(GetUptime(), ms_cntfrq_factor)};
}
s64 WallClock::GetCNTPCT() const {
return MultiplyHigh(GetUptime(), guest_cntfrq_factor);
}
s64 WallClock::GetGPUTick() const {
return MultiplyHigh(GetUptime(), gputick_cntfrq_factor);
}
s64 WallClock::GetUptime() const {
s64 cntvct_el0 = 0;
asm volatile(
"dsb ish\n\t"
"mrs %[cntvct_el0], cntvct_el0\n\t"
"dsb ish\n\t"
: [cntvct_el0] "=r"(cntvct_el0)
);
return cntvct_el0;
}
bool WallClock::IsNative() const {
return true;
}
#else
WallClock::WallClock(bool invariant_, u64 rdtsc_frequency_) noexcept {}
std::chrono::nanoseconds WallClock::GetTimeNS() const {
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::system_clock::now().time_since_epoch());
}
std::chrono::microseconds WallClock::GetTimeUS() const {
return std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::system_clock::now().time_since_epoch());
}
std::chrono::milliseconds WallClock::GetTimeMS() const {
return std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch());
}
s64 WallClock::GetCNTPCT() const {
return GetUptime() * NsToCNTPCTRatio::num / NsToCNTPCTRatio::den;
}
s64 WallClock::GetGPUTick() const {
return GetUptime() * NsToGPUTickRatio::num / NsToGPUTickRatio::den;
}
s64 WallClock::GetUptime() const {
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::steady_clock::now().time_since_epoch()).count();
}
bool WallClock::IsNative() const {
return false;
}
#endif
// Wall clock MUST be initialized AFTER g_cpu_caps
// C++ only guarantees ctor init in the order they appear in TU
const WallClock g_wall_clock = [] {
#if defined(ARCHITECTURE_x86_64)
auto const& caps = Common::g_cpu_caps;
return WallClock(caps.invariant_tsc && caps.tsc_frequency >= std::nano::den, caps.tsc_frequency);
#elif defined(HAS_NCE)
return WallClock(false, 1);
#else
return WallClock(true, 1);
#endif
}();
} // namespace Common } // namespace Common

View file

@ -1,11 +1,14 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project // SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later // SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
// SPDX-FileCopyrightText: Copyright 2013 Dolphin Emulator Project / 2015 Citra Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later // SPDX-License-Identifier: GPL-2.0-or-later
#pragma once #pragma once
#include <optional>
#include <string_view>
#include <chrono> #include <chrono>
#include <memory> #include <memory>
#include <ratio> #include <ratio>
@ -107,11 +110,78 @@ protected:
FactorType ms_cntfrq_factor; FactorType ms_cntfrq_factor;
FactorType guest_cntfrq_factor; FactorType guest_cntfrq_factor;
FactorType gputick_cntfrq_factor; FactorType gputick_cntfrq_factor;
#else
#endif #endif
}; };
[[nodiscard]] WallClock CreateOptimalClock() noexcept; #ifdef ARCHITECTURE_x86_64
/// x86/x64 CPU capabilities that may be detected by this module
struct CPUCaps {
enum class Manufacturer : u8 {
Unknown = 0,
Intel = 1,
AMD = 2,
Hygon = 3,
};
static Manufacturer ParseManufacturer(std::string_view brand_string);
Manufacturer manufacturer;
char brand_string[13];
char cpu_string[48];
u32 base_frequency;
u32 max_frequency;
u32 bus_frequency;
u32 tsc_crystal_ratio_denominator;
u32 tsc_crystal_ratio_numerator;
u32 crystal_frequency;
u64 tsc_frequency; // Derived from the above three values
u64 tsc_to_ns_ratio; // Derived
bool sse3 : 1;
bool ssse3 : 1;
bool sse4_1 : 1;
bool sse4_2 : 1;
bool avx : 1;
bool avx2 : 1;
bool avx512f : 1;
bool avx512dq : 1;
bool avx512cd : 1;
bool avx512bw : 1;
bool avx512vl : 1;
bool avx512vbmi : 1;
bool avx512bitalg : 1;
bool aes : 1;
bool bmi1 : 1;
bool bmi2 : 1;
bool f16c : 1;
bool fma : 1;
bool gfni : 1;
bool invariant_tsc : 1;
bool lzcnt : 1;
bool monitorx : 1;
bool movbe : 1;
bool pclmulqdq : 1;
bool popcnt : 1;
bool sha : 1;
bool waitpkg : 1;
};
#else
struct CPUCaps {
bool padding;
};
#endif
/// Detects CPU core count
std::optional<int> GetProcessorCount();
/// @brief Global cpu caps
extern const CPUCaps g_cpu_caps;
/// @brief Global wall clock
extern const WallClock g_wall_clock;
} // namespace Common } // namespace Common

View file

@ -38,13 +38,13 @@
#include <unistd.h> #include <unistd.h>
#endif #endif
#include "common/cpu_features.h"
#ifdef ARCHITECTURE_x86_64 #ifdef ARCHITECTURE_x86_64
#ifdef _MSC_VER #ifdef _MSC_VER
#include <intrin.h> #include <intrin.h>
#else #else
#include <x86intrin.h> #include <x86intrin.h>
#endif #endif
#include "common/x64/cpu_detect.h"
#include "common/x64/rdtsc.h" #include "common/x64/rdtsc.h"
#endif #endif
#include "core/core_timing.h" #include "core/core_timing.h"
@ -174,8 +174,7 @@ __attribute__((target("waitpkg,mwaitx")))
bool Event::WaitFor(const std::chrono::nanoseconds time) { bool Event::WaitFor(const std::chrono::nanoseconds time) {
auto const start = Common::X64::FencedRDTSC(); auto const start = Common::X64::FencedRDTSC();
auto const& caps = Common::g_cpu_caps; auto const& caps = Common::g_cpu_caps;
auto const ns_ratio = std::max<u64>(1, caps.tsc_frequency / 1'000); [[maybe_unused]] auto const end = start + time.count() * caps.tsc_to_ns_ratio;
[[maybe_unused]] auto const end = start + time.count() * ns_ratio;
if (caps.monitorx) { if (caps.monitorx) {
while (true) { while (true) {
// Armed monitor, as per manual, MWAITX must be conditional if the condition isn't satisfied // Armed monitor, as per manual, MWAITX must be conditional if the condition isn't satisfied
@ -232,11 +231,22 @@ bool Event::WaitFor(const std::chrono::nanoseconds time) {
} }
#else #else
bool Event::WaitFor(const std::chrono::nanoseconds time) { bool Event::WaitFor(const std::chrono::nanoseconds time) {
#ifdef _WIN32
s64 rem = s64(time.count()); //98 years
while (!is_set.load() && rem > 0) {
Common::Windows::SleepForOneTick();
rem = s64(Common::g_wall_clock.GetGlobalTimeNs().count()) - s64(time.count());
}
if (is_set.load())
Reset();
return true;
#else
std::unique_lock lk{mutex}; std::unique_lock lk{mutex};
if (!condvar.wait_for(lk, time, [this] { return is_set.load(); })) if (!condvar.wait_for(lk, time, [this] { return is_set.load(); }))
return false; return false;
is_set = false; is_set = false;
return true; return true;
#endif
} }
#endif #endif

View file

@ -1,195 +0,0 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#include "common/steady_clock.h"
#include "common/uint128.h"
#include "common/wall_clock.h"
#ifdef __ANDROID__
#include <sys/system_properties.h>
#endif
#ifdef ARCHITECTURE_x86_64
#include "common/x64/cpu_detect.h"
#include "common/x64/rdtsc.h"
#endif
namespace Common {
#if defined(ARCHITECTURE_x86_64)
WallClock::WallClock(bool invariant_, u64 rdtsc_frequency_) noexcept
: rdtsc_frequency{rdtsc_frequency_}
, ns_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(NsRatio::den, rdtsc_frequency_) : 0}
, us_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(UsRatio::den, rdtsc_frequency_) : 0}
, ms_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(MsRatio::den, rdtsc_frequency_) : 0}
, cntpct_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(CNTFRQ, rdtsc_frequency_) : 0}
, gputick_rdtsc_factor{invariant_ ? GetFixedPoint64Factor(GPUTickFreq, rdtsc_frequency_) : 0}
, invariant{invariant_}
{}
std::chrono::nanoseconds WallClock::GetTimeNS() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::system_clock::now().time_since_epoch());
return std::chrono::nanoseconds{MultiplyHigh(GetUptime(), ns_rdtsc_factor)};
}
std::chrono::microseconds WallClock::GetTimeUS() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::system_clock::now().time_since_epoch());
return std::chrono::microseconds{MultiplyHigh(GetUptime(), us_rdtsc_factor)};
}
std::chrono::milliseconds WallClock::GetTimeMS() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch());
return std::chrono::milliseconds{MultiplyHigh(GetUptime(), ms_rdtsc_factor)};
}
s64 WallClock::GetCNTPCT() const {
if (!invariant)
return GetUptime() * NsToCNTPCTRatio::num / NsToCNTPCTRatio::den;
return MultiplyHigh(GetUptime(), cntpct_rdtsc_factor);
}
s64 WallClock::GetGPUTick() const {
if (!invariant)
return GetUptime() * NsToGPUTickRatio::num / NsToGPUTickRatio::den;
return MultiplyHigh(GetUptime(), gputick_rdtsc_factor);
}
s64 WallClock::GetUptime() const {
if (!invariant)
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::steady_clock::now().time_since_epoch()).count();
return s64(Common::X64::FencedRDTSC());
}
bool WallClock::IsNative() const {
return invariant;
}
#elif defined(HAS_NCE)
namespace {
[[nodiscard]] WallClock::FactorType GetFixedPointFactor(u64 num, u64 den) noexcept {
return (WallClock::FactorType(num) << 64) / den;
}
[[nodiscard]] u64 MultiplyHigh(u64 m, WallClock::FactorType factor) noexcept {
return static_cast<u64>((m * factor) >> 64);
}
[[nodiscard]] s64 GetHostCNTFRQ() noexcept {
u64 cntfrq_el0 = 0;
#ifdef ANDROID
std::string_view board{""};
char buffer[PROP_VALUE_MAX];
int len{__system_property_get("ro.product.board", buffer)};
board = std::string_view(buffer, static_cast<size_t>(len));
if (board == "s5e9925") { // Exynos 2200
cntfrq_el0 = 25600000;
} else if (board == "exynos2100") { // Exynos 2100
cntfrq_el0 = 26000000;
} else if (board == "exynos9810") { // Exynos 9810
cntfrq_el0 = 26000000;
} else if (board == "s5e8825") { // Exynos 1280
cntfrq_el0 = 26000000;
} else {
asm volatile("mrs %[cntfrq_el0], cntfrq_el0" : [cntfrq_el0] "=r"(cntfrq_el0));
}
return cntfrq_el0;
#else
asm volatile("mrs %[cntfrq_el0], cntfrq_el0" : [cntfrq_el0] "=r"(cntfrq_el0));
return cntfrq_el0;
#endif
}
} // namespace
WallClock::WallClock(bool invariant_, u64 rdtsc_frequency_) noexcept {
const u64 host_cntfrq = std::max<u64>(GetHostCNTFRQ(), 1);
ns_cntfrq_factor = GetFixedPointFactor(NsRatio::den, host_cntfrq);
us_cntfrq_factor = GetFixedPointFactor(UsRatio::den, host_cntfrq);
ms_cntfrq_factor = GetFixedPointFactor(MsRatio::den, host_cntfrq);
guest_cntfrq_factor = GetFixedPointFactor(CNTFRQ, host_cntfrq);
gputick_cntfrq_factor = GetFixedPointFactor(GPUTickFreq, host_cntfrq);
}
std::chrono::nanoseconds WallClock::GetTimeNS() const {
return std::chrono::nanoseconds{MultiplyHigh(GetUptime(), ns_cntfrq_factor)};
}
std::chrono::microseconds WallClock::GetTimeUS() const {
return std::chrono::microseconds{MultiplyHigh(GetUptime(), us_cntfrq_factor)};
}
std::chrono::milliseconds WallClock::GetTimeMS() const {
return std::chrono::milliseconds{MultiplyHigh(GetUptime(), ms_cntfrq_factor)};
}
s64 WallClock::GetCNTPCT() const {
return MultiplyHigh(GetUptime(), guest_cntfrq_factor);
}
s64 WallClock::GetGPUTick() const {
return MultiplyHigh(GetUptime(), gputick_cntfrq_factor);
}
s64 WallClock::GetUptime() const {
s64 cntvct_el0 = 0;
asm volatile(
"dsb ish\n\t"
"mrs %[cntvct_el0], cntvct_el0\n\t"
"dsb ish\n\t"
: [cntvct_el0] "=r"(cntvct_el0)
);
return cntvct_el0;
}
bool WallClock::IsNative() const {
return true;
}
#else
WallClock::WallClock(bool invariant_, u64 rdtsc_frequency_) noexcept {}
std::chrono::nanoseconds WallClock::GetTimeNS() const {
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::system_clock::now().time_since_epoch());
}
std::chrono::microseconds WallClock::GetTimeUS() const {
return std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::system_clock::now().time_since_epoch());
}
std::chrono::milliseconds WallClock::GetTimeMS() const {
return std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch());
}
s64 WallClock::GetCNTPCT() const {
return GetUptime() * NsToCNTPCTRatio::num / NsToCNTPCTRatio::den;
}
s64 WallClock::GetGPUTick() const {
return GetUptime() * NsToGPUTickRatio::num / NsToGPUTickRatio::den;
}
s64 WallClock::GetUptime() const {
return std::chrono::duration_cast<std::chrono::nanoseconds>(std::chrono::steady_clock::now().time_since_epoch()).count();
}
bool WallClock::IsNative() const {
return false;
}
#endif
WallClock CreateOptimalClock() noexcept {
#if defined(ARCHITECTURE_x86_64)
auto const& caps = Common::g_cpu_caps;
return WallClock(caps.invariant_tsc && caps.tsc_frequency >= std::nano::den, caps.tsc_frequency);
#elif defined(HAS_NCE)
return WallClock(false, 1);
#else
return WallClock(true, 1);
#endif
}
} // namespace Common

View file

@ -1,79 +0,0 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2022 yuzu Emulator Project
// SPDX-FileCopyrightText: Copyright 2013 Dolphin Emulator Project / 2015 Citra Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#pragma once
#include <optional>
#include <string_view>
#include "common/common_types.h"
namespace Common {
/// x86/x64 CPU capabilities that may be detected by this module
struct CPUCaps {
enum class Manufacturer : u8 {
Unknown = 0,
Intel = 1,
AMD = 2,
Hygon = 3,
};
static Manufacturer ParseManufacturer(std::string_view brand_string);
Manufacturer manufacturer;
char brand_string[13];
char cpu_string[48];
u32 base_frequency;
u32 max_frequency;
u32 bus_frequency;
u32 tsc_crystal_ratio_denominator;
u32 tsc_crystal_ratio_numerator;
u32 crystal_frequency;
u64 tsc_frequency; // Derived from the above three values
bool sse3 : 1;
bool ssse3 : 1;
bool sse4_1 : 1;
bool sse4_2 : 1;
bool avx : 1;
bool avx2 : 1;
bool avx512f : 1;
bool avx512dq : 1;
bool avx512cd : 1;
bool avx512bw : 1;
bool avx512vl : 1;
bool avx512vbmi : 1;
bool avx512bitalg : 1;
bool aes : 1;
bool bmi1 : 1;
bool bmi2 : 1;
bool f16c : 1;
bool fma : 1;
bool gfni : 1;
bool invariant_tsc : 1;
bool lzcnt : 1;
bool monitorx : 1;
bool movbe : 1;
bool pclmulqdq : 1;
bool popcnt : 1;
bool sha : 1;
bool waitpkg : 1;
};
/// @brief Global cpu caps
extern const CPUCaps g_cpu_caps;
/// Detects CPU core count
std::optional<int> GetProcessorCount();
} // namespace Common

View file

@ -3,7 +3,7 @@
#include <numeric> #include <numeric>
#include <bit> #include <bit>
#include "common/wall_clock.h" #include "common/cpu_features.h"
#include "common/alignment.h" #include "common/alignment.h"
#include "common/literals.h" #include "common/literals.h"
#include "core/arm/nce/arm_nce.h" #include "core/arm/nce/arm_nce.h"

View file

@ -8,7 +8,8 @@
#include <mutex> #include <mutex>
#include <string> #include <string>
#include <tuple> #include <tuple>
#include "common/x64/cpu_detect.h" #include "common/cpu_features.h"
#include "common/cpu_features.h"
#ifdef _WIN32 #ifdef _WIN32
#include "common/windows/timer_resolution.h" #include "common/windows/timer_resolution.h"
@ -44,8 +45,7 @@ struct CoreTiming::Event {
} }
}; };
CoreTiming::CoreTiming() : clock{Common::CreateOptimalClock()} {} CoreTiming::CoreTiming() = default;
CoreTiming::~CoreTiming() { CoreTiming::~CoreTiming() {
Reset(); Reset();
} }
@ -208,7 +208,7 @@ void CoreTiming::ResetTicks() {
} }
u64 CoreTiming::GetClockTicks() const { u64 CoreTiming::GetClockTicks() const {
u64 fres = is_multicore ? clock.GetCNTPCT() : Common::WallClock::CPUTickToCNTPCT(cpu_ticks); u64 fres = is_multicore ? Common::g_wall_clock.GetCNTPCT() : Common::WallClock::CPUTickToCNTPCT(cpu_ticks);
if (auto const overclock = Settings::values.fast_cpu_time.GetValue(); overclock != Settings::CpuClock::Off) { if (auto const overclock = Settings::values.fast_cpu_time.GetValue(); overclock != Settings::CpuClock::Off) {
fres = u64(f64(fres) * (1.7 + 0.3 * u32(overclock))); fres = u64(f64(fres) * (1.7 + 0.3 * u32(overclock)));
} }
@ -222,7 +222,7 @@ u64 CoreTiming::GetClockTicks() const {
u64 CoreTiming::GetGPUTicks() const { u64 CoreTiming::GetGPUTicks() const {
return is_multicore return is_multicore
? clock.GetGPUTick() ? Common::g_wall_clock.GetGPUTick()
: Common::WallClock::CPUTickToGPUTick(cpu_ticks); : Common::WallClock::CPUTickToGPUTick(cpu_ticks);
} }
@ -299,14 +299,14 @@ void CoreTiming::Reset() {
/// @brief Returns current time in nanoseconds. /// @brief Returns current time in nanoseconds.
std::chrono::nanoseconds CoreTiming::GetGlobalTimeNs() const noexcept { std::chrono::nanoseconds CoreTiming::GetGlobalTimeNs() const noexcept {
return is_multicore return is_multicore
? clock.GetTimeNS() ? Common::g_wall_clock.GetTimeNS()
: std::chrono::nanoseconds{Common::WallClock::CPUTickToNS(cpu_ticks)}; : std::chrono::nanoseconds{Common::WallClock::CPUTickToNS(cpu_ticks)};
} }
/// @brief Returns current time in microseconds. /// @brief Returns current time in microseconds.
std::chrono::microseconds CoreTiming::GetGlobalTimeUs() const noexcept { std::chrono::microseconds CoreTiming::GetGlobalTimeUs() const noexcept {
return is_multicore return is_multicore
? clock.GetTimeUS() ? Common::g_wall_clock.GetTimeUS()
: std::chrono::microseconds{Common::WallClock::CPUTickToUS(cpu_ticks)}; : std::chrono::microseconds{Common::WallClock::CPUTickToUS(cpu_ticks)};
} }

View file

@ -19,7 +19,7 @@
#include "common/common_types.h" #include "common/common_types.h"
#include "common/thread.h" #include "common/thread.h"
#include "common/wall_clock.h" #include "common/cpu_features.h"
namespace Core::Timing { namespace Core::Timing {
@ -142,37 +142,28 @@ public:
void Reset(); void Reset();
Common::WallClock clock; using heap_t = boost::heap::fibonacci_heap<CoreTiming::Event, boost::heap::compare<std::greater<>>>;
heap_t event_queue;
s64 global_timer = 0; s64 global_timer = 0;
#ifdef _WIN32 #ifdef _WIN32
s64 timer_resolution_ns; s64 timer_resolution_ns;
#endif #endif
using heap_t =
boost::heap::fibonacci_heap<CoreTiming::Event, boost::heap::compare<std::greater<>>>;
heap_t event_queue;
u64 event_fifo_id = 0; u64 event_fifo_id = 0;
s64 pause_end_time{};
/// Cycle timing
u64 cpu_ticks{};
s64 downcount{};
Common::Event event{}; Common::Event event{};
Common::Event pause_event{}; Common::Event pause_event{};
std::function<void()> on_thread_init{};
std::jthread timer_thread;
mutable std::mutex basic_lock; mutable std::mutex basic_lock;
std::mutex advance_lock; std::mutex advance_lock;
std::jthread timer_thread;
std::atomic<bool> paused{}; std::atomic<bool> paused{};
std::atomic<bool> paused_set{}; std::atomic<bool> paused_set{};
std::atomic<bool> wait_set{}; std::atomic<bool> wait_set{};
std::atomic<bool> has_started{}; std::atomic<bool> has_started{};
std::function<void()> on_thread_init{};
bool is_multicore{}; bool is_multicore{};
s64 pause_end_time{};
/// Cycle timing
u64 cpu_ticks{};
s64 downcount{};
}; };
/// Creates a core timing event with the given name and callback. /// Creates a core timing event with the given name and callback.

View file

@ -10,6 +10,7 @@
#include "common/assert.h" #include "common/assert.h"
#include "common/logging.h" #include "common/logging.h"
#include "common/settings.h" #include "common/settings.h"
#include "common/cpu_features.h"
#include "core/hle/kernel/k_event.h" #include "core/hle/kernel/k_event.h"
#include "core/hle/kernel/k_readable_event.h" #include "core/hle/kernel/k_readable_event.h"
#include "core/hle/kernel/kernel.h" #include "core/hle/kernel/kernel.h"
@ -28,7 +29,6 @@ BufferQueueProducer::BufferQueueProducer(Service::KernelHelpers::ServiceContext&
Service::Nvidia::NvCore::NvMap& nvmap_) Service::Nvidia::NvCore::NvMap& nvmap_)
: service_context{service_context_}, core{std::move(buffer_queue_core_)} : service_context{service_context_}, core{std::move(buffer_queue_core_)}
, slots(core->slots) , slots(core->slots)
, clock{Common::CreateOptimalClock()}
, nvmap(nvmap_) , nvmap(nvmap_)
{ {
buffer_wait_event = service_context.CreateEvent("BufferQueue:WaitEvent"); buffer_wait_event = service_context.CreateEvent("BufferQueue:WaitEvent");
@ -488,7 +488,7 @@ Status BufferQueueProducer::QueueBuffer(s32 slot, const QueueBufferInput& input,
slots[slot].buffer_state = BufferState::Queued; slots[slot].buffer_state = BufferState::Queued;
slots[slot].frame_number = core->frame_counter; slots[slot].frame_number = core->frame_counter;
slots[slot].queue_time = timestamp; slots[slot].queue_time = timestamp;
slots[slot].presentation_time = clock.GetTimeNS().count(); slots[slot].presentation_time = Common::g_wall_clock.GetTimeNS().count();
slots[slot].fence = fence; slots[slot].fence = fence;
item.slot = slot; item.slot = slot;

View file

@ -14,7 +14,7 @@
#include <mutex> #include <mutex>
#include "common/common_funcs.h" #include "common/common_funcs.h"
#include "common/wall_clock.h" #include "common/cpu_features.h"
#include "core/hle/service/nvdrv/nvdata.h" #include "core/hle/service/nvdrv/nvdata.h"
#include "core/hle/service/nvnflinger/binder.h" #include "core/hle/service/nvnflinger/binder.h"
#include "core/hle/service/nvnflinger/buffer_queue_defs.h" #include "core/hle/service/nvnflinger/buffer_queue_defs.h"
@ -89,7 +89,6 @@ private:
s32 next_callback_ticket{}; s32 next_callback_ticket{};
s32 current_callback_ticket{}; s32 current_callback_ticket{};
std::condition_variable_any callback_condition; std::condition_variable_any callback_condition;
Common::WallClock clock;
Service::Nvidia::NvCore::NvMap& nvmap; Service::Nvidia::NvCore::NvMap& nvmap;
}; };

View file

@ -1,4 +1,4 @@
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project // SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later // SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project // SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
@ -13,7 +13,7 @@
#include "common/common_types.h" #include "common/common_types.h"
#include "common/intrusive_list.h" #include "common/intrusive_list.h"
#include "common/uuid.h" #include "common/uuid.h"
#include "common/wall_clock.h" #include "common/cpu_features.h"
#include "core/hle/kernel/k_event.h" #include "core/hle/kernel/k_event.h"
#include "core/hle/service/kernel_helpers.h" #include "core/hle/service/kernel_helpers.h"
#include "core/hle/service/psc/time/errors.h" #include "core/hle/service/psc/time/errors.h"

View file

@ -13,12 +13,9 @@
#include "common/fs/path_util.h" #include "common/fs/path_util.h"
#include "common/logging.h" #include "common/logging.h"
#include "common/scm_rev.h" #include "common/scm_rev.h"
#include "common/cpu_features.h"
#include "core/memory.h" #include "core/memory.h"
#ifdef ARCHITECTURE_x86_64
#include "common/x64/cpu_detect.h"
#endif
#include <QGuiApplication> #include <QGuiApplication>
#include <QStringLiteral> #include <QStringLiteral>
#include "core/frontend/emu_window.h" #include "core/frontend/emu_window.h"

View file

@ -39,7 +39,7 @@ extern "C" {
#include "video_core/textures/decoders.h" #include "video_core/textures/decoders.h"
#if defined(ARCHITECTURE_x86_64) #if defined(ARCHITECTURE_x86_64)
#include "common/x64/cpu_detect.h" #include "common/cpu_features.h"
#endif #endif
#if defined(ARCHITECTURE_x86_64) \ #if defined(ARCHITECTURE_x86_64) \

View file

@ -124,7 +124,7 @@ static FileSys::VirtualFile VfsDirectoryCreateFileWrapper(const FileSys::Virtual
#include "common/string_util.h" #include "common/string_util.h"
#ifdef ARCHITECTURE_x86_64 #ifdef ARCHITECTURE_x86_64
#include "common/x64/cpu_detect.h" #include "common/cpu_features.h"
#endif #endif
// Core // // Core //