perf(agc): pipelined draws and exact draw write ranges on by default

Queue 0 now pipelines draw commits unless APS5_PIPELINED_DRAWS=0, and draw write ranges use the exact
color, DCC, CMASK, depth and stencil sizes unless APS5_EXACT_DRAW_WRITES=0. The base tests now run the
pipeline; agc_driver_pm4_failure_inline and agc_driver_draw_cache_reuse_inline keep the inline path
covered.

Co-Authored-By: Claude <noreply@anthropic.com>

core/libs/prx/libSceAgcDriver/CMakeLists.txt

@@ -1639,14 +1639,14 @@ if(BUILD_TESTING)
             "PATH=path_list_prepend:$<TARGET_FILE_DIR:libc>")
     endif()
     add_test(NAME agc_driver_pm4_failure COMMAND agc_driver_pm4_tests failure)
-    set_tests_properties(agc_driver_pm4_failure PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1" SKIP_RETURN_CODE 77)
+    set_tests_properties(agc_driver_pm4_failure PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1" SKIP_RETURN_CODE 77 TIMEOUT 30)
     add_test(NAME agc_descriptor_pool_reset_failure COMMAND agc_driver_graphics_tests --descriptor-pool-reset-failure)
     add_test(NAME agc_driver_address_space_teardown COMMAND agc_driver_graphics_tests --address-space-teardown)
     set_tests_properties(agc_driver_address_space_teardown PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1" WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}")
-    add_test(NAME agc_driver_pm4_failure_pipelined COMMAND agc_driver_pm4_tests failure)
-    set_tests_properties(agc_driver_pm4_failure_pipelined PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1;APS5_PIPELINED_DRAWS=1" SKIP_RETURN_CODE 77 TIMEOUT 30)
+    add_test(NAME agc_driver_pm4_failure_inline COMMAND agc_driver_pm4_tests failure)
+    set_tests_properties(agc_driver_pm4_failure_inline PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1;APS5_PIPELINED_DRAWS=0" SKIP_RETURN_CODE 77)
     if(WIN32)
-        set_tests_properties(agc_driver_pm4_failure agc_driver_pm4_failure_pipelined agc_descriptor_pool_reset_failure agc_driver_address_space_teardown PROPERTIES ENVIRONMENT_MODIFICATION
+        set_tests_properties(agc_driver_pm4_failure agc_driver_pm4_failure_inline agc_descriptor_pool_reset_failure agc_driver_address_space_teardown PROPERTIES ENVIRONMENT_MODIFICATION
             "PATH=path_list_prepend:$<TARGET_FILE_DIR:libc>")
     endif()
     if(NOT WIN32)
@@ -1667,12 +1667,12 @@ if(BUILD_TESTING)
     set_tests_properties(agc_driver_draw_cache_reuse_off PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1;APS5_NO_GPL=1" SKIP_RETURN_CODE 77)
     add_test(NAME agc_driver_draw_cache_reuse_verify COMMAND agc_driver_draw_cache_reuse_tests)
     set_tests_properties(agc_driver_draw_cache_reuse_verify PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1;APS5_VERIFY_DRAW_DATA_HITS=1" SKIP_RETURN_CODE 77)
-    add_test(NAME agc_driver_draw_cache_reuse_pipelined COMMAND agc_driver_draw_cache_reuse_tests)
-    set_tests_properties(agc_driver_draw_cache_reuse_pipelined PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1;APS5_PIPELINED_DRAWS=1;APS5_VERIFY_DRAW_RECIPE=1;APS5_VERIFY_REGISTER_KEYS=1" SKIP_RETURN_CODE 77)
-    set_tests_properties(agc_driver_draw_cache_reuse agc_driver_draw_cache_reuse_off agc_driver_draw_cache_reuse_verify agc_driver_draw_cache_reuse_pipelined PROPERTIES FAIL_REGULAR_EXPRESSION "FATAL:")
+    add_test(NAME agc_driver_draw_cache_reuse_inline COMMAND agc_driver_draw_cache_reuse_tests)
+    set_tests_properties(agc_driver_draw_cache_reuse_inline PROPERTIES ENVIRONMENT "ANYPS5_NO_SHADER_CACHE=1;APS5_PIPELINED_DRAWS=0;APS5_VERIFY_DRAW_RECIPE=1;APS5_VERIFY_REGISTER_KEYS=1" SKIP_RETURN_CODE 77)
+    set_tests_properties(agc_driver_draw_cache_reuse agc_driver_draw_cache_reuse_off agc_driver_draw_cache_reuse_verify agc_driver_draw_cache_reuse_inline PROPERTIES FAIL_REGULAR_EXPRESSION "FATAL:")
     set_property(TEST agc_driver_draw_cache_reuse agc_driver_draw_cache_reuse_off APPEND PROPERTY ENVIRONMENT "APS5_VERIFY_DRAW_RECIPE=1" "APS5_VERIFY_REGISTER_KEYS=1")
     if(WIN32)
-        set_tests_properties(agc_driver_draw_cache_reuse_off agc_driver_draw_cache_reuse_verify agc_driver_draw_cache_reuse_pipelined PROPERTIES ENVIRONMENT_MODIFICATION
+        set_tests_properties(agc_driver_draw_cache_reuse_off agc_driver_draw_cache_reuse_verify agc_driver_draw_cache_reuse_inline PROPERTIES ENVIRONMENT_MODIFICATION
             "PATH=path_list_prepend:$<TARGET_FILE_DIR:libc>")
     endif()
 

core/libs/prx/libSceAgcDriver/Execution/src/Driver/Draw/DrawPipeline.cpp

@@ -28,7 +28,8 @@ DrawPipeline& DrawPipeline::Queue0() {
 std::size_t DrawPipeline::Depth() {
     static const std::size_t depth = [] {
         const char* text = std::getenv("APS5_PIPELINED_DRAWS");
-        if (text == nullptr || std::getenv("APS5_LOCKED_DRAW_PREPARE") != nullptr || std::getenv("APS5_DRAW_DRAIN") != nullptr || std::getenv("APS5_DRAIN_ALL") != nullptr || std::getenv("APS5_NO_WORDWISE_CAPTURE") != nullptr) return std::size_t{0};
+        if (std::getenv("APS5_LOCKED_DRAW_PREPARE") != nullptr || std::getenv("APS5_DRAW_DRAIN") != nullptr || std::getenv("APS5_DRAIN_ALL") != nullptr || std::getenv("APS5_NO_WORDWISE_CAPTURE") != nullptr) return std::size_t{0};
+        if (text == nullptr) return std::size_t{8};
         const auto value = std::strtoull(text, nullptr, 10);
         return value == 0 ? std::size_t{0} : value == 1 ? std::size_t{8} : static_cast<std::size_t>(std::min<unsigned long long>(value, 256));
     }();

core/libs/prx/libSceAgcDriver/Execution/src/Driver/Memory/WrittenBuffers.cpp

@@ -7,6 +7,7 @@
 #include "Optimization/ShaderStageInputInfo.hpp"
 #include <algorithm>
 #include <cstdlib>
+#include <cstring>
 
 namespace AgcDriver::DriverDetail {
 
@@ -63,7 +64,7 @@ void Driver::noteDrawWriters(std::span<const Graphics::CompiledShader> stages, s
 }
 
 bool ExactDrawWrites() {
-    static const bool exact = std::getenv("APS5_EXACT_DRAW_WRITES") != nullptr;
+    static const bool exact = [] { const char* text = std::getenv("APS5_EXACT_DRAW_WRITES"); return text == nullptr || std::strcmp(text, "0") != 0; }();
     return exact;
 }
 

docs/dev/ARCHITECTURE.md

@@ -97,7 +97,7 @@ flowchart LR
 - `ShaderRecompiler::Recompile` keeps compiled variants in memory, and `ShaderDiskCache` stores them on disk so later runs reuse them. Before the writable cache, a miss is also looked up in read-only prebuilt packs and loose entry folders under `shader_cache/prebuilt`; pack entries are ordinary encoded cache entries behind a sorted key-hash index, validated by magic, compiler source version and index checksum when mapped, and a miss or rejected entry falls through to the writable cache and the compiler. Cache format 35 also stores the finite stencil-reference set, its replay-safety proof and reserved push-data word in the artifact and binding layouts. Entries from formats 31 to 34 are rejected.
 - A compute shader whose LDS plus its lock dword exceeds the host's `maxComputeSharedMemorySize` is not given a `Workgroup` array. `Recompile` sets `ShaderInfo::sharedMemoryBytes` for it and the SPIR-V backend addresses the LDS in a coherent storage buffer at descriptor set 1 (`WorkgroupMemoryDescriptorSet`), with a slice of `RecompileResult::workgroupMemoryDwords` per workgroup, indexed by `WorkgroupID` and `NumWorkGroups`. `VulkanDevice` keeps one such buffer, sized from the dispatch dimensions, and binds it after the resource set; programs that fit keep using shared memory.
 - `Driver::RegisterShader` splits shader preparation in two. `PlanRegistered` runs on the registering guest thread: it validates the registers and entry point, decodes the code and builds the recompile request, so invalid registrations still fail there. The RDNA to IR translation and resource plan (`PrepareShader`) run on a background pool of `hardware_concurrency() / 2` detached threads (at least 2, 64 MiB stacks).
-- With `APS5_PIPELINED_DRAWS=1`, queue 0's packet worker decodes, captures and prepares a draw and hands its recording (`Graphics::Draw` under the GPU lock) to a committer thread in [`DrawPipeline.cpp`](../../core/libs/prx/libSceAgcDriver/Execution/src/Driver/Draw/DrawPipeline.cpp), so the next packet is decoded while the previous draw is recorded. Each queued item carries the guest ranges it will write (`DrawWriteRanges`: written buffers and storage images, color targets with their DCC and CMASK, depth and stencil). A later packet that reads or writes one of those ranges, or that the pipeline can't order, drains it first; labels, submission ends, buffer fills and (with `APS5_PIPELINE_DMA=1`) DMA packets are queued as items instead. An exception thrown by a commit is rethrown on the worker at its next enqueue or drain, as an inline draw error would be. Off by default.
+- Queue 0's packet worker decodes, captures and prepares a draw and hands its recording (`Graphics::Draw` under the GPU lock) to a committer thread in [`DrawPipeline.cpp`](../../core/libs/prx/libSceAgcDriver/Execution/src/Driver/Draw/DrawPipeline.cpp), so the next packet is decoded while the previous draw is recorded. Each queued item carries the guest ranges it will write (`DrawWriteRanges`: written buffers and storage images, color targets with their DCC and CMASK, depth and stencil). A later packet that reads or writes one of those ranges, or that the pipeline can't order, drains it first; labels, submission ends, buffer fills and (with `APS5_PIPELINE_DMA=1`) DMA packets are queued as items instead. An exception thrown by a commit is rethrown on the worker at its next enqueue or drain, as an inline draw error would be. On by default; `APS5_PIPELINED_DRAWS=0` records every draw inline, and `APS5_EXACT_DRAW_WRITES=0` widens the color and depth ranges to estimates.
 - The shader registry maps a code address to every header registered for that code, in registration order. Static, graphics and rectangle ABI resolution pick the header at the bound address (or one equal to it, `SameHeader`, which also takes a hull header fused by `sceAgcFuseShaderHalves` (type 3) as the registered back half (type 7) it copies, the fused registers aside; graphics ABI resolution then uses the fused header's shader registers); draws and dispatches pick the program by the stage's binary type (`RegisteredProgram`), and a front entry matching both type 2 and type 4 throws. Within a type the last registration wins; re-registering an identical earlier header makes its snapshot current again without preparing it again, and changed code drops the older headers.
 - The snapshot is published as pending. `SourceHandleFor`, `InvocationFor` and `ShaderPreparationTransaction::Edit` / `Read` wait for the pending job before reading `PreparedShaders`, and rethrow its failure. `APS5_SYNC_SHADER_PREPARE=1` prepares on the registering thread instead.
 - On devices with graphics pipeline libraries (`SpirvTarget::registrationModules`), a vertex or pixel artifact is emitted in registration form: the buffer V# words, image modes, swizzles and mip ranges, depth-compare state, export mappings and vertex component selectors it used to specialize on per draw are read at run time (image `ResourceMetadata` and a few state dwords in the shader data), descriptor heaps keep every element in place (an unused one gets a null or placeholder descriptor), and the pixel stage's bindings live in descriptor set 1 so each stage's library depends only on its own set layout (`INDEPENDENT_SETS`). An artifact above `registrationWordLimit` SPIR-V words is re-emitted specialized, and `CompiledShaderArtifact::registrationModule` records which form it has. For artifacts in registration form, `RegistrationResult` materializes the module once, and `PrebuildStageLibrary` builds its pre-rasterization or fragment-shader library on a separate one-thread pool (`APS5_PREBUILD_THREADS`) with a fixed default state, pairing it with a stub stage. A later draw with that state finds both libraries in the store and only links.