mirror of
https://github.com/wheremyfoodat/Panda3DS.git
synced 2025-04-06 06:05:40 +12:00
49a94a13c5
* Renderer: Add prepareForDraw callback * Add fmt submodule and port shader decompiler instructions to it * Add shader acceleration setting * Hook up vertex shaders to shader cache * Shader decompiler: Fix redundant compilations * Shader Decompiler: Fix vertex attribute upload * Shader compiler: Simplify generated code for reading and faster compilation * Further simplify shader decompiler output * Shader decompiler: More smallen-ing * Shader decompiler: Get PICA uniforms uploaded to the GPU * Shader decompiler: Readd clipping * Shader decompiler: Actually `break` on control flow instructions * Shader decompiler: More control flow handling * Shader decompiler: Fix desitnation mask * Shader Decomp: Remove pair member capture in lambda (unsupported on NDK) * Disgusting changes to handle the fact that hw shader shaders are 2x as big * Shader decompiler: Implement proper output semantic mapping * Moar instructions * Shader decompiler: Add FLR/SLT/SLTI/SGE/SGEI * Shader decompiler: Add register indexing * Shader decompiler: Optimize mova with both x and y masked * Shader decompiler: Add DPH/DPHI * Fix shader caching being broken * PICA decompiler: Cache VS uniforms * Simply vertex cache code * Simplify vertex cache code * Shader decompiler: Add loops * Shader decompiler: Implement safe multiplication * Shader decompiler: Implement LG2/EX2 * Shader decompiler: More control flow * Shader decompiler: Fix JMPU condition * Shader decompiler: Convert main function to void * PICA: Start implementing GPU vertex fetch * More hw VAO work * More hw VAO work * More GPU vertex fetch code * Add GL Stream Buffer from Duckstation * GL: Actually upload data to stream buffers * GPU: Cleanup immediate mode handling * Get first renders working with accelerated draws * Shader decompiler: Fix control flow analysis bugs * HW shaders: Accelerate indexed draws * Shader decompiler: Add support for compilation errors * GLSL decompiler: Fall back for LITP * Add Renderdoc scope classes * Fix control flow analysis bug * HW shaders: Fix attribute fetch * Rewriting hw vertex fetch * Stream buffer: Fix copy-paste mistake * HW shaders: Fix indexed rendering * HW shaders: Add padding attributes * HW shaders: Avoid redundant glVertexAttrib4f calls * HW shaders: Fix loops * HW shaders: Make generated shaders slightly smaller * Fix libretro build * HW shaders: Fix android * Remove redundant ubershader checks * Set accelerate shader default to true * Shader decompiler: Don't declare VS input attributes as an array * Change ubuntu-latest to Ubuntu 24.04 because Microsoft screwed up their CI again * fix merge conflict bug
57 lines
No EOL
1.8 KiB
C++
57 lines
No EOL
1.8 KiB
C++
#pragma once
|
|
#include <array>
|
|
#include <cassert>
|
|
#include <cstring>
|
|
#include <type_traits>
|
|
#include <unordered_map>
|
|
|
|
#include "PICA/pica_hash.hpp"
|
|
#include "PICA/regs.hpp"
|
|
#include "PICA/shader.hpp"
|
|
#include "bitfield.hpp"
|
|
#include "helpers.hpp"
|
|
|
|
namespace PICA {
|
|
// Configuration struct used
|
|
struct VertConfig {
|
|
PICAHash::HashType shaderHash;
|
|
PICAHash::HashType opdescHash;
|
|
u32 entrypoint;
|
|
|
|
// PICA registers for configuring shader output->fragment semantic mapping
|
|
std::array<u32, 7> outmaps{};
|
|
u16 outputMask;
|
|
u8 outputCount;
|
|
bool usingUbershader;
|
|
|
|
// Pad to 56 bytes so that the compiler won't insert unnecessary padding, which in turn will affect our unordered_map lookup
|
|
// As the padding will get hashed and memcmp'd...
|
|
u32 pad{};
|
|
|
|
bool operator==(const VertConfig& config) const {
|
|
// Hash function and equality operator required by std::unordered_map
|
|
return std::memcmp(this, &config, sizeof(VertConfig)) == 0;
|
|
}
|
|
|
|
VertConfig(PICAShader& shader, const std::array<u32, 0x300>& regs, bool usingUbershader) : usingUbershader(usingUbershader) {
|
|
shaderHash = shader.getCodeHash();
|
|
opdescHash = shader.getOpdescHash();
|
|
entrypoint = shader.entrypoint;
|
|
|
|
outputCount = regs[PICA::InternalRegs::ShaderOutputCount] & 7;
|
|
outputMask = regs[PICA::InternalRegs::VertexShaderOutputMask];
|
|
for (int i = 0; i < outputCount; i++) {
|
|
// Mask out unused bits
|
|
outmaps[i] = regs[PICA::InternalRegs::ShaderOutmap0 + i] & 0x1F1F1F1F;
|
|
}
|
|
}
|
|
};
|
|
} // namespace PICA
|
|
|
|
static_assert(sizeof(PICA::VertConfig) == 56);
|
|
|
|
// Override std::hash for our vertex config class
|
|
template <>
|
|
struct std::hash<PICA::VertConfig> {
|
|
std::size_t operator()(const PICA::VertConfig& config) const noexcept { return PICAHash::computeHash((const char*)&config, sizeof(config)); }
|
|
}; |