But for normal msvc builds i would put it at around 30-50% Added per-xexmodule caching of information per instruction, can be used to remember what code needs compiling at start up Record what guest addresses wrote mmio and backpropagate that to future runs, eliminating dependence on exception trapping. this makes many games like h3 actually tolerable to run under a debugger fixed a number of errors where temporaries were being passed by reference/pointer Can now be compiled with clang-cl 14.0.1, requires -Werror off though and some other solution/project changes. Added macros wrapping compiler extensions like noinline, forceinline, __expect, and cold. Removed the "global lock" in guest code completely. It does not properly emulate the behavior of mfmsrd/mtmsr and it seriously cripples amd cpus. Removing this yielded around a 3x speedup in Halo Reach for me. Disabled the microprofiler for now. The microprofiler has a huge performance cost associated with it. Developers can re-enable it in the base/profiling header if they really need it Disable the trace writer in release builds. despite just returning after checking if the file was open the trace functions were consuming about 0.60% cpu time total Add IsValidReg, GetRegisterInfo is a huge (about 45k) branching function and using that to check if a register was valid consumed a significant chunk of time Optimized RingBuffer::ReadAndSwap and RingBuffer::read_count. This gave us the largest overall boost in performance. The memcpies were unnecessary and one of them was always a no-op Added simplification rules for multiplicative patterns like (x+x), (x<<1)+x For the most frequently called win32 functions i added code to call their underlying NT implementations, which lets us skip a lot of MS code we don't care about/isnt relevant to our usecases ^this can be toggled off in the platform_win header handle indirect call true with constant function pointer, was occurring in h3 lookup host format swizzle in denser array by default, don't check if a gpu register is unknown, instead just check if its out of range. controlled by a cvar ^looking up whether its known or not took approx 0.3% cpu time Changed some things in /cpu to make the project UNITYBUILD friendly The timer thread was spinning way too much and consuming a ton of cpu, changed it to use a blocking wait instead tagged some conditions as XE_UNLIKELY/LIKELY based on profiler feedback (will only affect clang builds) Shifted around some code in CommandProcessor::WriteRegister based on how frequently it was executed added support for docdecaduple precision floating point so that we can represent our performance gains numerically tons of other stuff im probably forgetting
141 lines
3.7 KiB
C++
141 lines
3.7 KiB
C++
/**
|
|
******************************************************************************
|
|
* Xenia : Xbox 360 Emulator Research Project *
|
|
******************************************************************************
|
|
* Copyright 2020 Ben Vanik. All rights reserved. *
|
|
* Released under the BSD license - see LICENSE in the root for more details. *
|
|
******************************************************************************
|
|
*/
|
|
|
|
#ifndef XENIA_BASE_BYTE_ORDER_H_
|
|
#define XENIA_BASE_BYTE_ORDER_H_
|
|
|
|
#include <cstdint>
|
|
#if defined __has_include
|
|
#if __has_include(<version>)
|
|
#include <version>
|
|
#endif
|
|
#endif
|
|
#if __cpp_lib_endian
|
|
#include <bit>
|
|
#endif
|
|
|
|
#include "xenia/base/assert.h"
|
|
#include "xenia/base/platform.h"
|
|
|
|
#if !__cpp_lib_endian
|
|
// Polyfill
|
|
#ifdef __BYTE_ORDER__
|
|
namespace std {
|
|
enum class endian {
|
|
little = __ORDER_LITTLE_ENDIAN__,
|
|
big = __ORDER_BIG_ENDIAN__,
|
|
native = __BYTE_ORDER__
|
|
};
|
|
}
|
|
#else
|
|
// Hardcode to little endian for now
|
|
namespace std {
|
|
enum class endian { little = 0, big = 1, native = 0 };
|
|
}
|
|
#endif
|
|
#endif
|
|
// Check for mixed endian
|
|
static_assert((std::endian::native == std::endian::big) ||
|
|
(std::endian::native == std::endian::little));
|
|
|
|
namespace xe {
|
|
|
|
// chrispy: added workaround for clang, otherwise byteswap_ulong becomes calls
|
|
// to ucrtbase
|
|
#if XE_COMPILER_MSVC == 1 && !defined(__clang__)
|
|
#define XENIA_BASE_BYTE_SWAP_16 _byteswap_ushort
|
|
#define XENIA_BASE_BYTE_SWAP_32 _byteswap_ulong
|
|
#define XENIA_BASE_BYTE_SWAP_64 _byteswap_uint64
|
|
#else
|
|
#define XENIA_BASE_BYTE_SWAP_16 __builtin_bswap16
|
|
#define XENIA_BASE_BYTE_SWAP_32 __builtin_bswap32
|
|
#define XENIA_BASE_BYTE_SWAP_64 __builtin_bswap64
|
|
#endif // XE_PLATFORM_WIN32
|
|
|
|
template <class T>
|
|
inline T byte_swap(T value) {
|
|
static_assert(
|
|
sizeof(T) == 8 || sizeof(T) == 4 || sizeof(T) == 2 || sizeof(T) == 1,
|
|
"byte_swap(T value): Type T has illegal size");
|
|
if constexpr (sizeof(T) == 8) {
|
|
uint64_t temp =
|
|
XENIA_BASE_BYTE_SWAP_64(*reinterpret_cast<uint64_t*>(&value));
|
|
return *reinterpret_cast<T*>(&temp);
|
|
} else if constexpr (sizeof(T) == 4) {
|
|
uint32_t temp =
|
|
XENIA_BASE_BYTE_SWAP_32(*reinterpret_cast<uint32_t*>(&value));
|
|
return *reinterpret_cast<T*>(&temp);
|
|
} else if constexpr (sizeof(T) == 2) {
|
|
uint16_t temp =
|
|
XENIA_BASE_BYTE_SWAP_16(*reinterpret_cast<uint16_t*>(&value));
|
|
return *reinterpret_cast<T*>(&temp);
|
|
} else if constexpr (sizeof(T) == 1) {
|
|
return value;
|
|
}
|
|
}
|
|
|
|
template <typename T, std::endian E>
|
|
struct endian_store {
|
|
endian_store() = default;
|
|
endian_store(const T& src) { set(src); }
|
|
endian_store(const endian_store& other) { set(other); }
|
|
operator T() const { return get(); }
|
|
|
|
void set(const T& src) {
|
|
if constexpr (std::endian::native == E) {
|
|
value = src;
|
|
} else {
|
|
value = xe::byte_swap(src);
|
|
}
|
|
}
|
|
void set(const endian_store& other) { value = other.value; }
|
|
T get() const {
|
|
if constexpr (std::endian::native == E) {
|
|
return value;
|
|
}
|
|
return xe::byte_swap(value);
|
|
}
|
|
|
|
endian_store<T, E>& operator+=(int a) {
|
|
*this = *this + a;
|
|
return *this;
|
|
}
|
|
endian_store<T, E>& operator-=(int a) {
|
|
*this = *this - a;
|
|
return *this;
|
|
}
|
|
endian_store<T, E>& operator++() {
|
|
*this += 1;
|
|
return *this;
|
|
} // ++a
|
|
endian_store<T, E> operator++(int) {
|
|
*this += 1;
|
|
return (*this - 1);
|
|
} // a++
|
|
endian_store<T, E>& operator--() {
|
|
*this -= 1;
|
|
return *this;
|
|
} // --a
|
|
endian_store<T, E> operator--(int) {
|
|
*this -= 1;
|
|
return (*this + 1);
|
|
} // a--
|
|
|
|
T value;
|
|
};
|
|
|
|
template <typename T>
|
|
using be = endian_store<T, std::endian::big>;
|
|
template <typename T>
|
|
using le = endian_store<T, std::endian::little>;
|
|
|
|
} // namespace xe
|
|
|
|
#endif // XENIA_BASE_BYTE_ORDER_H_
|