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
4.7 KiB
C++
146 lines
4.7 KiB
C++
/**
|
|
******************************************************************************
|
|
* Xenia : Xbox 360 Emulator Research Project *
|
|
******************************************************************************
|
|
* Copyright 2022 Ben Vanik. All rights reserved. *
|
|
* Released under the BSD license - see LICENSE in the root for more details. *
|
|
******************************************************************************
|
|
*/
|
|
|
|
#ifndef XENIA_GPU_TRACE_VIEWER_H_
|
|
#define XENIA_GPU_TRACE_VIEWER_H_
|
|
|
|
#include <string_view>
|
|
|
|
#include "xenia/base/cvar.h"
|
|
#include "xenia/emulator.h"
|
|
#include "xenia/gpu/shader.h"
|
|
#include "xenia/gpu/trace_player.h"
|
|
#include "xenia/gpu/trace_protocol.h"
|
|
#include "xenia/gpu/xenos.h"
|
|
#include "xenia/memory.h"
|
|
#include "xenia/ui/imgui_dialog.h"
|
|
#include "xenia/ui/imgui_drawer.h"
|
|
#include "xenia/ui/immediate_drawer.h"
|
|
#include "xenia/ui/window.h"
|
|
#include "xenia/ui/window_listener.h"
|
|
#include "xenia/ui/windowed_app.h"
|
|
DECLARE_path(target_trace_file);
|
|
namespace xe {
|
|
namespace gpu {
|
|
|
|
struct SamplerInfo;
|
|
struct TextureInfo;
|
|
|
|
class TraceViewer : public xe::ui::WindowedApp {
|
|
public:
|
|
virtual ~TraceViewer();
|
|
|
|
bool OnInitialize() override;
|
|
|
|
protected:
|
|
explicit TraceViewer(xe::ui::WindowedAppContext& app_context,
|
|
const std::string_view name);
|
|
|
|
virtual std::unique_ptr<gpu::GraphicsSystem> CreateGraphicsSystem() = 0;
|
|
GraphicsSystem* graphics_system() const { return graphics_system_; }
|
|
|
|
void DrawMultilineString(const std::string_view str);
|
|
|
|
virtual uintptr_t GetColorRenderTarget(
|
|
uint32_t pitch, xenos::MsaaSamples samples, uint32_t base,
|
|
xenos::ColorRenderTargetFormat format) = 0;
|
|
virtual uintptr_t GetDepthRenderTarget(
|
|
uint32_t pitch, xenos::MsaaSamples samples, uint32_t base,
|
|
xenos::DepthRenderTargetFormat format) = 0;
|
|
virtual uintptr_t GetTextureEntry(const TextureInfo& texture_info,
|
|
const SamplerInfo& sampler_info) = 0;
|
|
|
|
virtual size_t QueryVSOutputSize() { return 0; }
|
|
virtual size_t QueryVSOutputElementSize() { return 0; }
|
|
virtual bool QueryVSOutput(void* buffer, size_t size) { return false; }
|
|
|
|
virtual bool Setup();
|
|
|
|
private:
|
|
class TraceViewerWindowListener final : public xe::ui::WindowListener,
|
|
public xe::ui::WindowInputListener {
|
|
public:
|
|
explicit TraceViewerWindowListener(TraceViewer& trace_viewer)
|
|
: trace_viewer_(trace_viewer) {}
|
|
|
|
void OnClosing(xe::ui::UIEvent& e) override;
|
|
|
|
void OnKeyDown(xe::ui::KeyEvent& e) override;
|
|
|
|
private:
|
|
TraceViewer& trace_viewer_;
|
|
};
|
|
|
|
class TraceViewerDialog final : public ui::ImGuiDialog {
|
|
public:
|
|
explicit TraceViewerDialog(xe::ui::ImGuiDrawer* imgui_drawer,
|
|
TraceViewer& trace_viewer)
|
|
: xe::ui::ImGuiDialog(imgui_drawer), trace_viewer_(trace_viewer) {}
|
|
|
|
protected:
|
|
void OnDraw(ImGuiIO& io) override;
|
|
|
|
private:
|
|
TraceViewer& trace_viewer_;
|
|
};
|
|
|
|
enum class ShaderDisplayType : int {
|
|
kUcode,
|
|
kTranslated,
|
|
kHostDisasm,
|
|
};
|
|
|
|
// Same as for Dear ImGui tooltips. Windows are translucent as the controls
|
|
// may take a pretty large fraction of the screen, especially on small
|
|
// screens, so the image from the guest can be seen through them.
|
|
static constexpr float kWindowBgAlpha = 0.6f;
|
|
|
|
bool Load(const std::string_view trace_file_path);
|
|
|
|
void DrawUI();
|
|
void DrawControllerUI();
|
|
void DrawPacketDisassemblerUI();
|
|
int RecursiveDrawCommandBufferUI(const TraceReader::Frame* frame,
|
|
TraceReader::CommandBuffer* buffer);
|
|
void DrawCommandListUI();
|
|
void DrawStateUI();
|
|
|
|
ShaderDisplayType DrawShaderTypeUI();
|
|
void DrawShaderUI(Shader* shader, ShaderDisplayType display_type);
|
|
|
|
void DrawBlendMode(uint32_t src_blend, uint32_t dest_blend,
|
|
uint32_t blend_op);
|
|
|
|
void DrawTextureInfo(const Shader::TextureBinding& texture_binding);
|
|
void DrawFailedTextureInfo(const Shader::TextureBinding& texture_binding,
|
|
const char* message);
|
|
|
|
void DrawVertexFetcher(Shader* shader,
|
|
const Shader::VertexBinding& vertex_binding,
|
|
const xenos::xe_gpu_vertex_fetch_t* fetch);
|
|
|
|
TraceViewerWindowListener window_listener_;
|
|
|
|
std::unique_ptr<xe::ui::Window> window_;
|
|
|
|
std::unique_ptr<Emulator> emulator_;
|
|
Memory* memory_ = nullptr;
|
|
GraphicsSystem* graphics_system_ = nullptr;
|
|
std::unique_ptr<TracePlayer> player_;
|
|
|
|
std::unique_ptr<xe::ui::ImmediateDrawer> immediate_drawer_;
|
|
std::unique_ptr<xe::ui::ImGuiDrawer> imgui_drawer_;
|
|
std::unique_ptr<TraceViewerDialog> trace_viewer_dialog_;
|
|
};
|
|
|
|
} // namespace gpu
|
|
} // namespace xe
|
|
|
|
#endif // XENIA_GPU_TRACE_VIEWER_H_
|