diff --git a/core/libs/prx/libSceAgcDriver/CMakeLists.txt b/core/libs/prx/libSceAgcDriver/CMakeLists.txt index 66a438c1fb..79e28aa9b6 100644 --- a/core/libs/prx/libSceAgcDriver/CMakeLists.txt +++ b/core/libs/prx/libSceAgcDriver/CMakeLists.txt @@ -1954,6 +1954,8 @@ target_link_libraries(agc_driver_job_manager_compute_tests PRIVATE libSceJobMana target_include_directories(agc_driver_packed_unorm_color_target_tests PRIVATE $) +target_include_directories(agc_driver_packed_unorm4444_color_target_tests PRIVATE $) + target_include_directories(agc_driver_color1555_target_tests PRIVATE $) target_include_directories(agc_driver_color565_target_tests PRIVATE $) diff --git a/core/libs/prx/libSceAgcDriver/tests/execution/PackedUnorm4444ColorTarget.cpp b/core/libs/prx/libSceAgcDriver/tests/execution/PackedUnorm4444ColorTarget.cpp new file mode 100644 index 0000000000..85326136cf --- /dev/null +++ b/core/libs/prx/libSceAgcDriver/tests/execution/PackedUnorm4444ColorTarget.cpp @@ -0,0 +1,330 @@ +#include "prx/libSceAgcDriver/Execution/include/GuestMemory.hpp" +#include "prx/libSceAgcDriver/Execution/include/VulkanDevice.hpp" +#include "prx/libSceAgcDriver/Execution/include/Driver/Shaders/ShaderRegistry.hpp" +#include "prx/libSceAgcDriver/Graphics/include/ColorTargetLayout.hpp" +#include "prx/libSceAgcDriver/Graphics/include/Draw.hpp" +#include "prx/libSceAgcDriver/Graphics/include/ShaderInputState.hpp" +#include "prx/libSceAgcDriver/Graphics/include/State.hpp" +#include "prx/libSceAgcDriver/Graphics/include/Texture.hpp" +#include "prx/libc/include/GuestAllocations.hpp" +#include "prx/libc/include/GuestArena.hpp" +#include "prx/libc/include/GuestWriteWatch.hpp" +#include "Recompiler.hpp" +#include "Optimization/ResourceProgram.hpp" +#include "VulkanTestDevice.hpp" +#ifdef _WIN32 +#ifndef NOMINMAX +#define NOMINMAX +#endif +#include +#else +#include +#endif +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace { + +using AgcDriver::Graphics::ColorTargetLayout; +using AgcDriver::Graphics::ColorTileMode; +using AgcDriver::Graphics::Require; +using ShaderRecompiler::ShaderStage; + +constexpr std::uint32_t Width = 256; +constexpr std::uint32_t Height = 128; +constexpr std::uint32_t ScissorWidth = 128; +constexpr std::size_t BlockBytes = 65536; +constexpr std::uint32_t Unorm4_4_4_4Info = 0x8000u | (19u << 2u) | (2u << 11u); +constexpr std::uint32_t LinearAttrib3 = 0x09000000u; +constexpr std::uint32_t Float32Export = 9; +constexpr std::uint32_t Float16Export = 4; + +alignas(256) constexpr std::array VertexCode{ + 0xe0382000, 0x80000005, 0xbf8c3f70, 0xf80008cf, 0x03020100, 0xbf810000, +}; + +constexpr std::array, 3> Triangle{{ + {-1.0f, -1.0f, 0.5f, 1.0f}, {3.0f, -1.0f, 0.5f, 1.0f}, {-1.0f, 3.0f, 0.5f, 1.0f} +}}; + +alignas(256) std::array, 32> Programs{}; +std::size_t programCount = 0; + +struct Golden { + std::array rgba; + std::uint16_t word; +}; + +std::uint32_t Half(float value) { + Require(value == 0.0f || (value >= 0.0625f && value <= 1.0f), "the test's half values are normal and at most 1"); + if (value == 0.0f) return 0; + const auto bits = std::bit_cast(value); + Require((bits & 0x1fffu) == 0, "the test's half values are exact"); + return ((((bits >> 23u) & 0xffu) - 112u) << 10u) | ((bits >> 13u) & 0x3ffu); +} + +std::span Program(const std::array& vgprs, bool compressed) { + Require(programCount < Programs.size(), "too many test programs"); + auto& code = Programs[programCount++]; + std::size_t at = 0; + for (std::uint32_t vgpr = 0; vgpr < (compressed ? 2u : 4u); ++vgpr) { + code[at++] = 0x7e0002ffu | ((4u + vgpr) << 17u); + code[at++] = vgprs[vgpr]; + } + code[at++] = compressed ? 0xf8001c0fu : 0xf800180fu; + code[at++] = compressed ? 0x00000504u : 0x07060504u; + code[at++] = 0xbf810000u; + return std::span(code.data(), at); +} + +std::span Float32Program(std::array rgba) { + return Program({std::bit_cast(rgba[0]), std::bit_cast(rgba[1]), std::bit_cast(rgba[2]), std::bit_cast(rgba[3])}, false); +} + +std::span Float16Program(std::array rgba) { + return Program({Half(rgba[0]) | (Half(rgba[1]) << 16u), Half(rgba[2]) | (Half(rgba[3]) << 16u), 0, 0}, true); +} + +struct Block { + explicit Block(std::size_t bytes) : bytes(bytes), watched(AgcDriver::GuestMemory::WriteWatched()) { +#ifdef _WIN32 + if (watched) { + data = static_cast(GuestArena::GuestArenaAllocate_nid_postfix(bytes, BlockBytes)); + GuestArena::GuestArenaCommit_nid_postfix(data, bytes, PAGE_READWRITE, bytes); + } else { + data = static_cast(VirtualAlloc(nullptr, bytes, MEM_RESERVE | MEM_COMMIT, PAGE_READWRITE)); + } +#else + if (watched) { + void* raw = mmap(nullptr, bytes + BlockBytes, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + Require(raw != MAP_FAILED, "cannot map the color target"); + const auto begin = reinterpret_cast(raw); + const auto aligned = (begin + BlockBytes - 1) & ~(static_cast(BlockBytes) - 1); + if (aligned != begin) munmap(raw, aligned - begin); + if (aligned + bytes != begin + bytes + BlockBytes) munmap(reinterpret_cast(aligned + bytes), begin + BlockBytes - aligned); + data = reinterpret_cast(aligned); + GuestWriteWatch::GuestWriteWatchRegister_nid_postfix(data, bytes); + } else { + data = static_cast(std::aligned_alloc(BlockBytes, bytes)); + } +#endif + Require(data != nullptr, "cannot allocate the color target"); + Require(!watched || AgcDriver::GuestMemory::Watched(Address(), bytes), "the color target is not write-watched"); + GuestAllocations::Mutation mutation; + mutation.Add(data, bytes, true, true, true); + } + ~Block() { + AgcDriver::Graphics::StorageTexture::FlushPending(Address(), bytes, nullptr, "test release"); + { + GuestAllocations::Mutation mutation; + mutation.Remove(data); + } +#ifdef _WIN32 + if (watched) { + GuestArena::GuestArenaReset_nid_postfix(data, bytes); + GuestArena::GuestArenaRelease_nid_postfix(data, bytes); + } else { + VirtualFree(data, 0, MEM_RELEASE); + } +#else + if (watched) { + munmap(data, bytes); + GuestWriteWatch::GuestWriteWatchUnregister_nid_postfix(data, bytes); + } else { + std::free(data); + } +#endif + } + Block(const Block&) = delete; + Block& operator=(const Block&) = delete; + std::uint64_t Address() const { return reinterpret_cast(data); } + std::size_t bytes; + bool watched; + std::uint8_t* data = nullptr; +}; + +AgcDriver::Graphics::ColorTarget DecodeTarget(const Block& block, std::uint32_t attrib3) { + AgcDriver::Registers cx; + cx[0x318] = static_cast(block.Address() >> 8u); + cx[0x31b] = 0; + cx[0x31c] = Unorm4_4_4_4Info; + cx[0x31d] = 0; + cx[0x3b0] = ((Width - 1u) << 14u) | (Height - 1u); + cx[0x3b8] = attrib3; + cx[0x390] = static_cast(block.Address() >> 40u); + auto color = AgcDriver::Graphics::DecodeColorBuffer(cx, 0); + Require(color.format == VK_FORMAT_R16_UINT && color.elementBytes == 2 && color.componentMapping == 0x1bu && color.packing == ShaderRecompiler::ColorExportPacking::Unorm4_4_4_4 && color.bytes == block.bytes, "the 4_4_4_4 unorm target did not decode as a packed R16_UINT target"); + return color; +} + +void Draw(AgcDriver::VulkanDevice& device, const AgcDriver::Graphics::ColorTarget& color, std::uint32_t exportFormat, std::span pixelCode) { + const auto target = device.Target(); + constexpr std::uint32_t waveSize = 64; + std::vector vertexUserData(4, 0u); + const auto address = reinterpret_cast(Triangle.data()); + const std::array vertexBuffer{static_cast(address), static_cast((address >> 32u) & 0xffffu) | (16u << 16u), static_cast(Triangle.size()), 0x01016facu}; + std::copy(vertexBuffer.begin(), vertexBuffer.end(), vertexUserData.begin()); + const std::array vertexMemory{{{reinterpret_cast(VertexCode.data()), std::as_bytes(std::span(VertexCode))}}}; + ShaderRecompiler::RecompileRequest vertex{ + {ShaderStage::Vertex, reinterpret_cast(VertexCode.data()), VertexCode, 0, {}}, + {waveSize, 0, vertexUserData, std::nullopt, std::nullopt, ShaderRecompiler::ShaderVertexStageInfo{}, vertexMemory}, + target, + {0, 0, 0, 64} + }; + vertex.useCache = false; + const auto vertexResult = ShaderRecompiler::Recompile(vertex); + const auto vertexPush = static_cast(vertexResult.pushConstants.size()); + + AgcDriver::Graphics::State state{}; + state.stages = {AgcDriver::Graphics::ShaderPath::Vertex, 0u, waveSize, waveSize, std::nullopt, std::nullopt}; + state.colors = {color}; + state.color = color; + state.hasColorTarget = true; + state.renderExtent = {Width, Height}; + state.topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST; + state.viewport = {0, static_cast(Height), static_cast(Width), -static_cast(Height), 0, 1}; + state.negativeOneToOne = false; + state.scissor = {{0, 0}, {ScissorWidth, Height}}; + state.cullMode = VK_CULL_MODE_NONE; + state.frontFace = VK_FRONT_FACE_COUNTER_CLOCKWISE; + VkPipelineColorBlendAttachmentState blend{}; + blend.colorWriteMask = VK_COLOR_COMPONENT_R_BIT | VK_COLOR_COMPONENT_G_BIT | VK_COLOR_COMPONENT_B_BIT | VK_COLOR_COMPONENT_A_BIT; + state.blends = {blend}; + state.blend = blend; + state.blendConstants = {}; + + const auto codeAddress = reinterpret_cast(pixelCode.data()); + const AgcDriver::Registers context{{0x1b6, 0x8000}, {0x1b3, 0}, {0x1b4, 0}, {0x203, 0}, {0x1c5, exportFormat}}; + const std::array pixelMemory{{{codeAddress, std::as_bytes(pixelCode)}}}; + ShaderRecompiler::RecompileRequest fragment{ + {ShaderStage::Fragment, codeAddress, pixelCode, 0, {}}, + {waveSize, 0, {}, std::nullopt, AgcDriver::Graphics::DecodePixelStageInfo(context, {}), std::nullopt, pixelMemory}, + target, + PixelPushLayout(vertexPush, target) + }; + const auto handle = ShaderRecompiler::PrepareShader(fragment); + AgcDriver::DriverDetail::ShaderSnapshot snapshot{codeAddress, 0, 1, {pixelCode.begin(), pixelCode.end()}, {}}; + snapshot.prepared->entries.push_back({0, handle}); + fragment.shader.code = snapshot.code; + fragment.context.pixel = AgcDriver::Graphics::DecodePixelStageInfo(context, AgcDriver::Graphics::ExportMappings(state)); + fragment.context.pixel->targetExportPacking = AgcDriver::Graphics::ExportPackings(state); + const ShaderRecompiler::SrtRuntime runtime{}; + const auto materialize = [&](const ShaderRecompiler::RecompileRequest& request) { + const auto invocation = AgcDriver::DriverDetail::InvocationFor(snapshot, 0, request); + return invocation.Materialize(*invocation.Capture(runtime)); + }; + const auto pixelResult = materialize(fragment); + auto unpacked = fragment; + unpacked.context.pixel->targetExportPacking.fill(ShaderRecompiler::ColorExportPacking::None); + const auto plain = materialize(unpacked); + Require(pixelResult->variantId == ShaderRecompiler::GetPreparedArtifact(*handle).variantId && plain->variantId == pixelResult->variantId, "the draw did not use the registered pixel shader"); + Require(plain->PipelineVariantId() != pixelResult->PipelineVariantId() && materialize(fragment)->PipelineVariantId() == pixelResult->PipelineVariantId(), "the 4_4_4_4 unorm packing did not key its own specialization"); + const std::array shaders{{ + {ShaderStage::Vertex, &vertexResult, 0}, + {ShaderStage::Fragment, pixelResult.get(), PixelPushOffset(vertexPush, target)} + }}; + const AgcDriver::Pm4::DrawParameters draw{0, static_cast(Triangle.size()), 0, 1, 0, false}; + device.Draw(state, draw, shaders); +} + +std::vector ReadBack(AgcDriver::VulkanDevice& device, const Block& block) { + AgcDriver::Graphics::StorageTexture::FlushPending(block.Address(), block.bytes, nullptr, "test read-back"); + device.WaitIdle(); + std::vector stored(block.bytes / 2u); + AgcDriver::GuestMemory::Read(block.Address(), std::as_writable_bytes(std::span(stored)), 1); + return stored; +} + +void ExpectSurface(AgcDriver::VulkanDevice& device, const Block& block, const ColorTargetLayout& layout, const std::vector& before, std::uint32_t word, const std::string& what) { + const auto stored = ReadBack(device, block); + for (std::uint32_t y = 0; y < Height; ++y) { + for (std::uint32_t x = 0; x < Width; ++x) { + const auto index = layout.Offset(x, y) / 2u; + const bool inside = x < ScissorWidth; + const std::uint32_t expected = inside ? word : before[index]; + if (stored[index] == expected) continue; + char detail[160]; + std::snprintf(detail, sizeof(detail), ": pixel (%u, %u) %s the scissor holds 0x%04x, expected 0x%04x", x, y, inside ? "inside" : "outside", stored[index], expected); + throw std::runtime_error(what + detail); + } + } +} + +std::vector Fill(Block& block) { + std::vector words(block.bytes / 2u); + for (std::size_t index = 0; index < words.size(); ++index) words[index] = static_cast((index * 0x9e3779b9u) >> 11u); + std::memcpy(block.data, words.data(), block.bytes); + return words; +} + +std::string Describe(std::array rgba) { + char text[112]; + std::snprintf(text, sizeof(text), "(%.9g, %.9g, %.9g, %.9g)", rgba[0], rgba[1], rgba[2], rgba[3]); + return text; +} + +void TargetTests(AgcDriver::VulkanDevice& device, Block& block, std::uint32_t attrib3, ColorTileMode mode, const char* kind) { + const ColorTargetLayout layout(Width, Height, mode, 2); + Require(layout.Bytes() == block.bytes, "the test surface size disagrees with its layout"); + const auto color = DecodeTarget(block, attrib3); + auto before = Fill(block); + const float nan = std::numeric_limits::quiet_NaN(); + const float infinity = std::numeric_limits::infinity(); + const std::array float32Cases{{ + {{1.0f, 0.0f, 0.0f, 0.0f}, 0xf000u}, + {{0.0f, 1.0f, 0.0f, 0.0f}, 0x0f00u}, + {{0.0f, 0.0f, 1.0f, 0.0f}, 0x00f0u}, + {{0.0f, 0.0f, 0.0f, 1.0f}, 0x000fu}, + {{1.0f, 1.0f, 1.0f, 1.0f}, 0xffffu}, + {{1.0f, 0.5f, 0.0f, 0.25f}, 0xf804u}, + {{0.0f, 1.0f, 0.5f, 0.25f}, 0x0f84u}, + {{nan, -1.0f, 2.0f, infinity}, 0x00ffu}, + {{1.0f / 15.0f, 2.0f / 15.0f, 7.0f / 15.0f, 14.0f / 15.0f}, 0x127eu}, + {{0.1f, 0.7f, 0.9f, 0.3f}, 0x2ad5u}, + {{-infinity, std::numeric_limits::min(), 0.999999940f, std::numeric_limits::denorm_min()}, 0x00f0u}, + }}; + for (const auto& golden : float32Cases) { + Draw(device, color, Float32Export, Float32Program(golden.rgba)); + ExpectSurface(device, block, layout, before, golden.word, std::string("a 32_ABGR export of ") + Describe(golden.rgba) + " into a " + kind + " 4_4_4_4 unorm target"); + before = ReadBack(device, block); + } + const std::array float16Cases{{ + {{1.0f, 0.0f, 0.0f, 0.0f}, 0xf000u}, + {{0.0f, 1.0f, 0.0f, 0.0f}, 0x0f00u}, + {{0.0f, 0.0f, 1.0f, 0.0f}, 0x00f0u}, + {{0.0f, 0.0f, 0.0f, 1.0f}, 0x000fu}, + {{1.0f, 1.0f, 1.0f, 1.0f}, 0xffffu}, + {{1.0f, 0.5f, 0.0f, 0.25f}, 0xf804u}, + {{0.5f, 0.75f, 0.125f, 0.25f}, 0x8b24u}, + }}; + for (const auto& golden : float16Cases) { + Draw(device, color, Float16Export, Float16Program(golden.rgba)); + ExpectSurface(device, block, layout, before, golden.word, std::string("an FP16_ABGR export of ") + Describe(golden.rgba) + " into a " + kind + " 4_4_4_4 unorm target"); + before = ReadBack(device, block); + } +} + +} + +int main() { + try { + const auto device = OpenVulkanTestDevice(); + if (!device) return VulkanTestSkipped; + Block linear(ColorTargetLayout(Width, Height, ColorTileMode::Linear, 2).Bytes()); + TargetTests(*device, linear, LinearAttrib3, ColorTileMode::Linear, "linear"); + std::puts("4_4_4_4 unorm color target tests passed"); + return 0; + } catch (const std::exception& error) { + std::cerr << error.what() << '\n'; + return 1; + } +}