cb85fe401c
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
146 lines
4.5 KiB
C++
146 lines
4.5 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_PLATFORM_H_
|
|
#define XENIA_BASE_PLATFORM_H_
|
|
|
|
// This file contains the main platform switches used by xenia as well as any
|
|
// fixups required to normalize the environment. Everything in here should be
|
|
// largely portable.
|
|
// Platform-specific headers, like platform_win.h, are used to house any
|
|
// super platform-specific stuff that implies code is not platform-agnostic.
|
|
//
|
|
// NOTE: ordering matters here as sometimes multiple flags are defined on
|
|
// certain platforms.
|
|
//
|
|
// Great resource on predefined macros:
|
|
// https://sourceforge.net/p/predef/wiki/OperatingSystems/
|
|
// Original link: https://predef.sourceforge.net/preos.html
|
|
|
|
#if defined(__APPLE__)
|
|
#include <TargetConditionals.h>
|
|
#endif
|
|
|
|
#if defined(TARGET_OS_MAC) && TARGET_OS_MAC
|
|
#define XE_PLATFORM_MAC 1
|
|
#elif defined(WIN32) || defined(_WIN32)
|
|
#define XE_PLATFORM_WIN32 1
|
|
#elif defined(__ANDROID__)
|
|
#define XE_PLATFORM_ANDROID 1
|
|
#define XE_PLATFORM_LINUX 1
|
|
#elif defined(__gnu_linux__)
|
|
#define XE_PLATFORM_GNU_LINUX 1
|
|
#define XE_PLATFORM_LINUX 1
|
|
#else
|
|
#error Unsupported target OS.
|
|
#endif
|
|
|
|
#if defined(__clang__) && !defined(_MSC_VER) // chrispy: support clang-cl
|
|
#define XE_COMPILER_CLANG 1
|
|
#define XE_COMPILER_HAS_CLANG_EXTENSIONS 1
|
|
#elif defined(__GNUC__)
|
|
#define XE_COMPILER_GNUC 1
|
|
#define XE_COMPILER_HAS_GNU_EXTENSIONS 1
|
|
#elif defined(_MSC_VER)
|
|
#define XE_COMPILER_MSVC 1
|
|
#define XE_COMPILER_HAS_MSVC_EXTENSIONS 1
|
|
#elif defined(__MINGW32)
|
|
#define XE_COMPILER_MINGW32 1
|
|
#define XE_COMPILER_HAS_GNU_EXTENSIONS 1
|
|
#elif defined(__INTEL_COMPILER)
|
|
#define XE_COMPILER_INTEL 1
|
|
#else
|
|
#define XE_COMPILER_UNKNOWN 1
|
|
#endif
|
|
// chrispy: had to place this here.
|
|
#if defined(__clang__) && defined(_MSC_VER)
|
|
#define XE_COMPILER_CLANG_CL 1
|
|
#define XE_COMPILER_HAS_CLANG_EXTENSIONS 1
|
|
#endif
|
|
|
|
// clang extensions == superset of gnu extensions
|
|
#if XE_COMPILER_HAS_CLANG_EXTENSIONS == 1
|
|
#define XE_COMPILER_HAS_GNU_EXTENSIONS 1
|
|
#endif
|
|
|
|
#if defined(_M_AMD64) || defined(__amd64__)
|
|
#define XE_ARCH_AMD64 1
|
|
#elif defined(_M_ARM64) || defined(__aarch64__)
|
|
#define XE_ARCH_ARM64 1
|
|
#elif defined(_M_IX86) || defined(__i386__) || defined(_M_ARM) || \
|
|
defined(__arm__)
|
|
#error Xenia is not supported on 32-bit platforms.
|
|
#elif defined(_M_PPC) || defined(__powerpc__)
|
|
#define XE_ARCH_PPC 1
|
|
#endif
|
|
|
|
#if XE_PLATFORM_WIN32
|
|
#define WIN32_LEAN_AND_MEAN
|
|
#define NOMINMAX // Don't want windows.h including min/max macros.
|
|
#endif // XE_PLATFORM_WIN32
|
|
|
|
#if XE_PLATFORM_WIN32
|
|
#include <intrin.h>
|
|
#elif XE_ARCH_AMD64
|
|
#include <x86intrin.h>
|
|
#endif // XE_PLATFORM_WIN32
|
|
|
|
#if XE_PLATFORM_MAC
|
|
#include <libkern/OSByteOrder.h>
|
|
#endif // XE_PLATFORM_MAC
|
|
|
|
#if XE_COMPILER_MSVC
|
|
#define _XEPACKEDSCOPE(body) __pragma(pack(push, 1)) body __pragma(pack(pop));
|
|
#else
|
|
#define _XEPACKEDSCOPE(body) \
|
|
_Pragma("pack(push, 1)") body; \
|
|
_Pragma("pack(pop)");
|
|
#endif // XE_PLATFORM_WIN32
|
|
|
|
#define XEPACKEDSTRUCT(name, value) _XEPACKEDSCOPE(struct name value)
|
|
#define XEPACKEDSTRUCTANONYMOUS(value) _XEPACKEDSCOPE(struct value)
|
|
#define XEPACKEDUNION(name, value) _XEPACKEDSCOPE(union name value)
|
|
|
|
#if XE_COMPILER_HAS_MSVC_EXTENSIONS == 1
|
|
#define XE_FORCEINLINE __forceinline
|
|
#define XE_NOINLINE __declspec(noinline)
|
|
// can't properly emulate "cold" in msvc, but can still segregate the function
|
|
// into its own seg
|
|
#define XE_COLD __declspec(code_seg(".cold"))
|
|
#define XE_LIKELY(...) (!!(__VA_ARGS__))
|
|
#define XE_UNLIKELY(...) (!!(__VA_ARGS__))
|
|
|
|
#elif XE_COMPILER_HAS_GNU_EXTENSIONS == 1
|
|
#define XE_FORCEINLINE __attribute__((always_inline))
|
|
#define XE_NOINLINE __attribute__((noinline))
|
|
#define XE_COLD __attribute__((cold))
|
|
#define XE_LIKELY(...) __builtin_expect(!!(__VA_ARGS__), true)
|
|
#define XE_UNLIKELY(...) __builtin_expect(!!(__VA_ARGS__), false)
|
|
#else
|
|
#define XE_FORCEINLINE inline
|
|
#define XE_NOINLINE
|
|
#define XE_COLD
|
|
#define XE_LIKELY(...) (!!(__VA_ARGS__))
|
|
#define XE_UNLIKELY(...) (!!(__VA_ARGS__))
|
|
#endif
|
|
|
|
namespace xe {
|
|
|
|
#if XE_PLATFORM_WIN32
|
|
const char kPathSeparator = '\\';
|
|
#else
|
|
const char kPathSeparator = '/';
|
|
#endif // XE_PLATFORM_WIN32
|
|
|
|
const char kGuestPathSeparator = '\\';
|
|
|
|
} // namespace xe
|
|
|
|
#endif // XENIA_BASE_PLATFORM_H_
|