core/d3d12: wire the textured Nearest batch FS pre-bake into the PSO path
Activates the 72 pre-baked DXBC blobs from9e4c33d("core/d3d12: pre-bake the textured Nearest batch FS slice"). The data + recipe landed there; this commit makes the runtime actually consume them, eliminating D3DCompile from the textured-Nearest slice of GPU_HW_D3D12::GetBatchPipeline. What changes: src/common/d3d12/embedded_shaders.h 144 new extern declarations covering the 72 batch_textured_nearest_ps_* blobs (uint8_t array + size_t pair per blob). Section comment documents the variant axes + the runtime-selection mapping that the call site in gpu_hw_d3d12.cpp performs. src/common/d3d12/embedded_shaders.cpp 72 new #include lines pulling in the .inc files inside the namespace block. Same convention as the existing batch untextured + non-batch helper blobs. src/core/gpu_hw_d3d12.cpp 1. New file-local helper PickBatchTexturedNearestFSBytecode in the anonymous namespace right after PickBatchUntexturedFSBytecode. Takes 5 inputs (lookup_mode + 4 session-level flags), returns the matching D3D12_SHADER_BYTECODE from a static 4-D table [6][2][3][2] indexed by texture_mode / dual_source / interp / nopersp. Statically initialised; no runtime cost after .so load. lookup_mode -> tm_idx mapping (Reserved_* already deduped by the caller via the lookup_mode parameter that has been in the codebase since before the pre-bake arc): actual_mode = lookup_mode & 0x3 raw = (lookup_mode & 0x4) != 0 tm_idx: 0: p0r0 (Direct16Bit, actual=2, raw=0) 1: p0r1 (RawDirect16Bit, actual=2, raw=1) 2: p4r0 (Palette4Bit, actual=0, raw=0) 3: p4r1 (RawPalette4Bit, actual=0, raw=1) 4: p8r0 (Palette8Bit, actual=1, raw=0) 5: p8r1 (RawPalette8Bit, actual=1, raw=1) The interp / persp axes mirror PickBatchUntexturedFSBytecode (same shadergen formulae). use_dual_source comes from the caller pre-computed - same bit the PSO blend state needs, computed once at the call site. 2. GetBatchPipeline restructured: the textured branch now forks on filter. m_texture_filter == Nearest takes the pre-baked path via PickBatchTexturedNearestFSBytecode; other filter values still call GetBatchFragmentShader. The use_dual_source bool is now hoisted to the top of the FS-pickup block so both pre-baked pickers (textured Nearest + untextured) and the eventual textured non- Nearest paths consume the same value. 3. precompile_sync's FS cache-warm loop generalises its pre-baked skip: pre_baked = (texture_mode == Disabled) || (cur_filter == Nearest). The textured Nearest cells join untextured in skipping GetBatchFragmentShader; the progress.Increment still ticks for each so the user- facing progress bar reads the same count. Pre-existing PSO-build inner loop is untouched. It calls GetBatchPipeline, which now picks the pre-baked blob inside on the Nearest+textured path - PSO builds happen (they need to; the FS bytecode source changed), but the D3DCompile cost is gone. What does NOT change in this commit: - m_batch_fragment_shader_blobs's slots for the textured- Nearest cells (filter dim index 0, texture_mode dims 0-6 minus the Reserved_* dedup slots, render_mode 0-3) now go unused on this path. They stay null - the matrix shape remains <9, 4, 7> = 252 slots because the other 3 textured filter templates still consume them. A future cleanup can shrink the [filter] dim from 7 to 3 (Bilinear / JINC2 / xBR only) once those templates are pre-baked too. - The 3 remaining textured filter templates (Bilinear / JINC2 / xBR, each with a *BinAlpha variant baked via the BINALPHA -D axis) still go through D3DCompile via GetBatchFragmentShader. They land in subsequent commits. The pre-bake-vs-D3DCompile branch in GetBatchPipeline is the integration point for them. - m_pgxp_depth_buffer still triggers PSO rebuild on the textured Nearest path - that's the PSO depth-comp swap (LESS_EQUAL vs GREATER_EQUAL) at PSO build time, not a shader source dependency. The FS bytecode is invariant under m_pgxp_depth_buffer post-routing-arc, so the same pre-baked blob serves both PGXP values; only the PSO rebuilds. Behavioural change for users: - First batch of textured Nearest drawcalls in a session no longer triggers D3DCompile. With Disabled shader-precompile mode this saves O(20-50ms) per slot on first draw of each new (render_mode, texture_mode) combination. With Lazy mode the background warm-up finishes O(N Nearest+textured slots * 20ms) faster; with Enabled mode the upfront precompile_sync finishes that much sooner. PSX content overwhelmingly uses Palette4Bit textures (UI, sprites, most 3D meshes), so the Palette4Bit Nearest cells are the hot ones in stock content. - Cold-launch shader-disk-cache misses for textured-Nearest variants: zero, post-this-commit. No on-disk shader cache entries are produced for them anymore (the picker bypasses m_shader_cache.GetPixelShader entirely). Existing cache entries from previous versions still hit on the Bilinear / JINC2 / xBR slots (the cache hash is per-source-string). - DXBC output of fxc /T ps_5_0 /E main /O3 should be bit- identical to what D3DCompile would have produced from the shadergen-emitted HLSL (fxc and D3DCompile share the underlying compiler). Visual diff: zero. Pixel diff: zero. Test: - g++ -std=c++17 -c on src/common/d3d12/embedded_shaders.cpp standalone (with -Isrc) compiles cleanly. The 72 new blobs link in correctly; .o size grows by ~400 KiB to ~1.5 MiB to match the per-variant .inc sizes from9e4c33d. - g++ -std=c++17 syntax check on both pickers (PickBatchUntexturedFSBytecode + PickBatchTexturedNearestFSBytecode) against a shim D3D12_SHADER_BYTECODE / GPU_HW::BatchRenderMode / GPUTextureFilter compiles cleanly. - Boot any PSX title on D3D12 default settings (filter= Nearest, no PGXP, no MSAA): the textured Nearest slice is cold; first time it draws, the PSO builds without D3DCompile; the FS DXBC comes from k_batch_textured_nearest_ps_p4r0_d0_none_n0 (Palette4Bit, non-trans, dual=0, no interp qual, no nopersp) for typical Palette4Bit + TransparencyDisabled UI / sprite draws. Visual output identical to pre-commit. - Boot with MSAA 4x: interp_idx=1 (centroid). Picks k_batch_textured_nearest_ps_*_*_centroid_*. - Transparent textured geometry: u_render_mode != 0 routes through the runtime branch inside the pre-baked DXBC. The semitransparent texel test is u_render_mode-invariant; the OnlyOpaque (==2u) / OnlyTransparent (==3u) discards fire on the matching two-pass DrawIndexed re-upload from c532a34's FlushRender path. - 16-bit raw textures (RawDirect16Bit / 0x6): picks p0r1_* variants. Render-to-texture effects (MGS, Vagrant Story) take this path. Cumulative pre-bake variant count progress for D3D12 batch FS: Pre-arc: 75 264 (every axis a -D) Post-cbuffer-routing of: DITHERING/INTERLACING/UV_LIMITS/PGXP_DEPTH 4 704 Post-c532a34 (TRANSPARENCY -> u_render_mode) 1 176 Post-c01f8ae (untextured re-baked, live) 12 baked + live Post-9e4c33d (Nearest .inc on disk) 72 baked Post-this-commit (Nearest live): Untextured slice: 12 live Textured Nearest slice: 72 live Total runtime-D3DCompile-free batch FS: 84 Remaining filters (Bilinear / JINC2 / xBR): 3 templates x ~144 variants (the BINALPHA `-D` axis adds one more dimension for those) = ~432 variants for the full bake. Next: - Pre-bake the Bilinear filter slice. The Bilinear template is simpler than JINC2 / xBR - 2x2 texel blend with the BinAlpha variant gated on a BINALPHA `-D` macro. ~144 variants per template (6 tex_mode x 2 dual x 3 interp x 2 persp x 2 BinAlpha). Each filter slice gets a foundation commit (HLSL + regen + .inc) and an activation commit (extern decls + picker + GetBatchPipeline wiring), mirroring the untextured / Nearest arcs.
This commit is contained in:
parent
9e4c33d53c
commit
a7f5717ff8
3 changed files with 603 additions and 23 deletions
|
|
@ -107,4 +107,77 @@ namespace D3D12::EmbeddedShaders {
|
|||
#include "embedded_dxbc/batch_untextured_ps_d1_sample_p0.inc"
|
||||
#include "embedded_dxbc/batch_untextured_ps_d1_sample_p1.inc"
|
||||
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d0_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d0_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d0_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d0_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d0_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d0_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d1_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d1_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d1_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d1_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d1_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r0_d1_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d0_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d0_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d0_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d0_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d0_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d0_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d1_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d1_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d1_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d1_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d1_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p0r1_d1_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d0_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d0_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d0_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d0_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d0_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d0_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d1_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d1_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d1_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d1_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d1_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r0_d1_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d0_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d0_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d0_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d0_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d0_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d0_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d1_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d1_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d1_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d1_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d1_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p4r1_d1_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d0_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d0_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d0_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d0_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d0_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d0_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d1_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d1_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d1_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d1_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d1_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r0_d1_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d0_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d0_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d0_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d0_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d0_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d0_sample_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d1_centroid_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d1_centroid_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d1_none_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d1_none_n1.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d1_sample_n0.inc"
|
||||
#include "embedded_dxbc/batch_textured_nearest_ps_p8r1_d1_sample_n1.inc"
|
||||
|
||||
} // namespace D3D12::EmbeddedShaders
|
||||
|
|
|
|||
|
|
@ -381,4 +381,189 @@ extern const size_t k_batch_untextured_ps_d1_sample_p0_size_bytes;
|
|||
extern const uint8_t k_batch_untextured_ps_d1_sample_p1[];
|
||||
extern const size_t k_batch_untextured_ps_d1_sample_p1_size_bytes;
|
||||
|
||||
// Batch fragment shader, textured + Nearest-filter slice. Equivalent
|
||||
// to GPU_HW_ShaderGen::GenerateBatchFragmentShader invoked with
|
||||
// texture_mode != GPUTextureMode::Disabled AND m_texture_filter ==
|
||||
// GPUTextureFilter::Nearest. Used by GPU_HW_D3D12::GetBatchPipeline's
|
||||
// textured-Nearest branch in place of the runtime shadergen +
|
||||
// D3DCompile path for the same slice. Second batch FS template
|
||||
// pre-baked, after batch_untextured. The remaining three textured
|
||||
// filter templates (Bilinear / JINC2 / xBR) land in subsequent
|
||||
// commits.
|
||||
//
|
||||
// Variant axes (4 dimensions, 6+2+3+2 = 72 blobs):
|
||||
//
|
||||
// * Texture mode (6 combos via PALETTE_4_BIT / PALETTE_8_BIT /
|
||||
// RAW_TEXTURE -D macros). Palette4Bit / Palette8Bit are mutually
|
||||
// exclusive in the shadergen #elif chain - no variant has both
|
||||
// set. Reserved_Direct16Bit / Reserved_RawDirect16Bit dedup to
|
||||
// Direct16Bit / RawDirect16Bit at the C++ picker level.
|
||||
// * USE_DUAL_SOURCE (0/1)
|
||||
// * INTERP_CENTROID / INTERP_SAMPLE (mutually exclusive tri-state)
|
||||
// * NOPERSP (0/1)
|
||||
//
|
||||
// 6 (tex_mode) x 2 (dual) x 3 (interp) x 2 (persp) = 72 blobs.
|
||||
// MSAA cardinality does not multiply this slice - the batch FS reads
|
||||
// from the single-sample shadow VRAM regardless of m_multisamples.
|
||||
//
|
||||
// Runtime selection at the GetBatchPipeline call site:
|
||||
// tm_idx = derived from lookup_mode (Reserved_* deduped):
|
||||
// 0: p0r0 (Direct16Bit)
|
||||
// 1: p0r1 (RawDirect16Bit)
|
||||
// 2: p4r0 (Palette4Bit)
|
||||
// 3: p4r1 (RawPalette4Bit)
|
||||
// 4: p8r0 (Palette8Bit)
|
||||
// 5: p8r1 (RawPalette8Bit)
|
||||
// dual_idx = use_dual_source ? 1 : 0
|
||||
// interp_idx = m_per_sample_shading ? 2 :
|
||||
// (m_multisamples > 1 ? 1 : 0)
|
||||
// persp_idx = m_disable_color_perspective ? 1 : 0
|
||||
//
|
||||
// Source: data/shaders/d3d12/batch_textured_nearest.ps.hlsl
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d0_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d0_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d0_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d0_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d0_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d0_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d0_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d0_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d0_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d0_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d0_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d0_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d1_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d1_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d1_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d1_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d1_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d1_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d1_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d1_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d1_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d1_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r0_d1_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r0_d1_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d0_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d0_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d0_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d0_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d0_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d0_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d0_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d0_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d0_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d0_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d0_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d0_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d1_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d1_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d1_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d1_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d1_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d1_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d1_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d1_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d1_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d1_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p0r1_d1_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p0r1_d1_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d0_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d0_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d0_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d0_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d0_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d0_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d0_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d0_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d0_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d0_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d0_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d0_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d1_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d1_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d1_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d1_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d1_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d1_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d1_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d1_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d1_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d1_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r0_d1_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r0_d1_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d0_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d0_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d0_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d0_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d0_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d0_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d0_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d0_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d0_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d0_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d0_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d0_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d1_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d1_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d1_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d1_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d1_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d1_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d1_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d1_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d1_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d1_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p4r1_d1_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p4r1_d1_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d0_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d0_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d0_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d0_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d0_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d0_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d0_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d0_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d0_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d0_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d0_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d0_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d1_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d1_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d1_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d1_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d1_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d1_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d1_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d1_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d1_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d1_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r0_d1_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r0_d1_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d0_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d0_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d0_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d0_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d0_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d0_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d0_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d0_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d0_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d0_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d0_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d0_sample_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d1_centroid_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d1_centroid_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d1_centroid_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d1_centroid_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d1_none_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d1_none_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d1_none_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d1_none_n1_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d1_sample_n0[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d1_sample_n0_size_bytes;
|
||||
extern const uint8_t k_batch_textured_nearest_ps_p8r1_d1_sample_n1[];
|
||||
extern const size_t k_batch_textured_nearest_ps_p8r1_d1_sample_n1_size_bytes;
|
||||
|
||||
|
||||
} // namespace D3D12::EmbeddedShaders
|
||||
|
|
|
|||
|
|
@ -894,13 +894,18 @@ bool GPU_HW_D3D12::CompilePipelines()
|
|||
|
||||
// Pre-baked variants skip the GetBatchFragmentShader cache-
|
||||
// warm step - the bytecode is statically linked, no
|
||||
// D3DCompile to run. Currently the untextured slice is the
|
||||
// only pre-baked template (commits 9e6f933 + this one); the
|
||||
// four textured filter templates are still runtime-compiled
|
||||
// and land in subsequent commits. The progress.Increment
|
||||
// below still ticks for visual continuity so the
|
||||
// user-facing progress bar reads the same as pre-pre-bake.
|
||||
if (static_cast<GPUTextureMode>(texture_mode) != GPUTextureMode::Disabled)
|
||||
// D3DCompile to run. Pre-baked templates so far:
|
||||
// - Untextured (texture_mode == Disabled): commits
|
||||
// 9e6f933 / b6d1903 / c01f8ae (re-bake).
|
||||
// - Textured + Nearest: commits 9e4c33d + this one.
|
||||
// The three remaining textured filter templates (Bilinear /
|
||||
// JINC2 / xBR) are still runtime-compiled and land in
|
||||
// subsequent commits. progress.Increment ticks regardless so
|
||||
// the user-facing progress bar reads the same count.
|
||||
const bool pre_baked =
|
||||
(static_cast<GPUTextureMode>(texture_mode) == GPUTextureMode::Disabled) ||
|
||||
(cur_filter == GPUTextureFilter::Nearest);
|
||||
if (!pre_baked)
|
||||
{
|
||||
ComPtr<ID3DBlob> blob = GetBatchFragmentShader(cur_filter, render_mode, texture_mode);
|
||||
if (!blob)
|
||||
|
|
@ -1238,6 +1243,304 @@ static D3D12_SHADER_BYTECODE PickBatchUntexturedFSBytecode(
|
|||
return k_blobs[use_dual_source ? 1 : 0][interp_idx][persp_idx];
|
||||
}
|
||||
|
||||
|
||||
// Textured + Nearest-filter batch FS pre-baked variant picker.
|
||||
// Returns the matching DXBC blob from the 72-entry table at
|
||||
// src/common/d3d12/embedded_dxbc/batch_textured_nearest_ps_*.inc,
|
||||
// indexed by the 4 axes the regen tool bakes:
|
||||
//
|
||||
// texture_mode 6 combos (Palette4Bit / Palette8Bit /
|
||||
// Direct16Bit each in non-raw / raw form). The
|
||||
// Reserved_Direct16Bit / Reserved_RawDirect16Bit
|
||||
// enum values are deduped to their non-Reserved
|
||||
// counterparts at the GPU_HW_D3D12 caller via
|
||||
// the `lookup_mode` parameter.
|
||||
// use_dual_source driven by the same call-site formula as the
|
||||
// untextured picker - the caller computes once
|
||||
// and hands the bit to both this picker AND the
|
||||
// PSO blend-state setup that references SRC1_*.
|
||||
// interp (per_sample_shading > MSAA > none; mirror of
|
||||
// ShaderGen::GetInterpolationQualifier)
|
||||
// noperspective (m_disable_color_perspective)
|
||||
//
|
||||
// As with the untextured slice (c01f8ae), the former TRANSPARENCY
|
||||
// axis (4 BatchRenderMode enum values) is now read from
|
||||
// u_render_mode in the cbuffer - the DXBC is invariant across
|
||||
// render_mode post-c532a34, so a single set of 72 variants covers
|
||||
// all 4 render_modes.
|
||||
static D3D12_SHADER_BYTECODE PickBatchTexturedNearestFSBytecode(
|
||||
uint8_t lookup_mode, bool use_dual_source, uint32_t multisamples,
|
||||
bool per_sample_shading, bool disable_color_perspective)
|
||||
{
|
||||
// texture_mode dim: derived from lookup_mode (Reserved_* already
|
||||
// deduped by the caller). lookup_mode is a 3-bit value with
|
||||
// bits 0..1 = actual_mode (0 = Palette4Bit, 1 = Palette8Bit,
|
||||
// 2 = Direct16Bit; 3 is Reserved_Direct16Bit but
|
||||
// the caller maps it to 2 before invoking us)
|
||||
// bit 2 = RawTextureBit
|
||||
// The 6 reachable combos map to a 6-slot 1-D table:
|
||||
// 0: p0r0 Direct16Bit (actual=2, raw=0)
|
||||
// 1: p0r1 RawDirect16Bit (actual=2, raw=1)
|
||||
// 2: p4r0 Palette4Bit (actual=0, raw=0)
|
||||
// 3: p4r1 RawPalette4Bit (actual=0, raw=1)
|
||||
// 4: p8r0 Palette8Bit (actual=1, raw=0)
|
||||
// 5: p8r1 RawPalette8Bit (actual=1, raw=1)
|
||||
const uint8_t actual_mode = lookup_mode & 0x3u;
|
||||
const bool raw = (lookup_mode & 0x4u) != 0;
|
||||
unsigned tm_idx;
|
||||
if (actual_mode == 2u) // Direct16Bit family
|
||||
tm_idx = raw ? 1u : 0u;
|
||||
else if (actual_mode == 0u) // Palette4Bit family
|
||||
tm_idx = raw ? 3u : 2u;
|
||||
else // actual_mode == 1u (Palette8Bit family)
|
||||
tm_idx = raw ? 5u : 4u;
|
||||
|
||||
// 0 = none, 1 = centroid, 2 = sample. Same shape as the untextured
|
||||
// picker - mirror of ShaderGen::GetInterpolationQualifier.
|
||||
const unsigned interp_idx =
|
||||
per_sample_shading ? 2u : ((multisamples > 1u) ? 1u : 0u);
|
||||
const unsigned persp_idx = disable_color_perspective ? 1u : 0u;
|
||||
|
||||
static const D3D12_SHADER_BYTECODE k_blobs[6][2][3][2] = {
|
||||
// tm = p0r0 (Direct16Bit)
|
||||
{
|
||||
// no dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d0_sample_n1_size_bytes}},
|
||||
},
|
||||
// dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r0_d1_sample_n1_size_bytes}},
|
||||
},
|
||||
},
|
||||
// tm = p0r1 (RawDirect16Bit)
|
||||
{
|
||||
// no dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d0_sample_n1_size_bytes}},
|
||||
},
|
||||
// dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p0r1_d1_sample_n1_size_bytes}},
|
||||
},
|
||||
},
|
||||
// tm = p4r0 (Palette4Bit)
|
||||
{
|
||||
// no dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d0_sample_n1_size_bytes}},
|
||||
},
|
||||
// dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r0_d1_sample_n1_size_bytes}},
|
||||
},
|
||||
},
|
||||
// tm = p4r1 (RawPalette4Bit)
|
||||
{
|
||||
// no dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d0_sample_n1_size_bytes}},
|
||||
},
|
||||
// dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p4r1_d1_sample_n1_size_bytes}},
|
||||
},
|
||||
},
|
||||
// tm = p8r0 (Palette8Bit)
|
||||
{
|
||||
// no dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d0_sample_n1_size_bytes}},
|
||||
},
|
||||
// dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r0_d1_sample_n1_size_bytes}},
|
||||
},
|
||||
},
|
||||
// tm = p8r1 (RawPalette8Bit)
|
||||
{
|
||||
// no dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d0_sample_n1_size_bytes}},
|
||||
},
|
||||
// dual
|
||||
{
|
||||
// interp = none
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_none_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_none_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_none_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_none_n1_size_bytes}},
|
||||
// interp = centroid
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_centroid_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_centroid_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_centroid_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_centroid_n1_size_bytes}},
|
||||
// interp = sample
|
||||
{{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_sample_n0,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_sample_n0_size_bytes},
|
||||
{D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_sample_n1,
|
||||
D3D12::EmbeddedShaders::k_batch_textured_nearest_ps_p8r1_d1_sample_n1_size_bytes}},
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
return k_blobs[tm_idx][use_dual_source ? 1 : 0][interp_idx][persp_idx];
|
||||
}
|
||||
|
||||
} // anonymous namespace
|
||||
|
||||
GPU_HW_D3D12::ComPtr<ID3DBlob> GPU_HW_D3D12::GetBatchFragmentShader(GPUTextureFilter filter, uint8_t render_mode, uint8_t texture_mode)
|
||||
|
|
@ -1395,29 +1698,48 @@ GPU_HW_D3D12::ComPtr<ID3D12PipelineState> GPU_HW_D3D12::GetBatchPipeline(GPUText
|
|||
// branch shrinks until every batch FS variant is pre-baked.
|
||||
const bool textured = (static_cast<GPUTextureMode>(lookup_mode) != GPUTextureMode::Disabled);
|
||||
|
||||
// Mirror of the shadergen formula in
|
||||
// GPU_HW_ShaderGen::GenerateBatchFragmentShader. The bit drives
|
||||
// both the FS variant choice (via PickBatch*FSBytecode below)
|
||||
// AND the PSO blend state (via SetBlendState below for SRC1_*-
|
||||
// using cells), so it must come from the same input set for
|
||||
// both consumers. Identical for textured / untextured slices;
|
||||
// pre-baked pickers and the shadergen GetBatchFragmentShader
|
||||
// path all consume the same bit.
|
||||
const bool use_dual_source =
|
||||
m_supports_dual_source_blend &&
|
||||
((render_mode != static_cast<uint8_t>(GPU_HW::BatchRenderMode::TransparencyDisabled) &&
|
||||
render_mode != static_cast<uint8_t>(GPU_HW::BatchRenderMode::OnlyOpaque)) ||
|
||||
filter != GPUTextureFilter::Nearest);
|
||||
|
||||
D3D12_SHADER_BYTECODE fs_bc;
|
||||
ComPtr<ID3DBlob> fs_blob; // null on the pre-baked path; held for ref-life otherwise
|
||||
if (textured)
|
||||
{
|
||||
fs_blob = GetBatchFragmentShader(filter, render_mode, lookup_mode);
|
||||
if (!fs_blob)
|
||||
return {};
|
||||
fs_bc.pShaderBytecode = fs_blob->GetBufferPointer();
|
||||
fs_bc.BytecodeLength = fs_blob->GetBufferSize();
|
||||
if (filter == GPUTextureFilter::Nearest)
|
||||
{
|
||||
// Second pre-baked batch FS slice (9e4c33d + this commit).
|
||||
// Picker selects from 72 .inc blobs at
|
||||
// src/common/d3d12/embedded_dxbc/batch_textured_nearest_ps_*.inc;
|
||||
// no D3DCompile, no shader-cache lookup.
|
||||
fs_bc = PickBatchTexturedNearestFSBytecode(lookup_mode, use_dual_source,
|
||||
m_multisamples, m_per_sample_shading,
|
||||
m_disable_color_perspective);
|
||||
}
|
||||
else
|
||||
{
|
||||
// Bilinear / JINC2 / xBR (and their *BinAlpha variants) still
|
||||
// go through shadergen + D3DCompile. Pre-bake commits for the
|
||||
// 3 remaining filter templates land subsequently.
|
||||
fs_blob = GetBatchFragmentShader(filter, render_mode, lookup_mode);
|
||||
if (!fs_blob)
|
||||
return {};
|
||||
fs_bc.pShaderBytecode = fs_blob->GetBufferPointer();
|
||||
fs_bc.BytecodeLength = fs_blob->GetBufferSize();
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
// Mirror of the shadergen formula in
|
||||
// GPU_HW_ShaderGen::GenerateBatchFragmentShader. The bit drives
|
||||
// both the FS variant choice (via PickBatchUntexturedFSBytecode
|
||||
// below) AND the PSO blend state (via SetBlendState below for
|
||||
// SRC1_*-using cells), so it must come from the same input set
|
||||
// for both consumers.
|
||||
const bool use_dual_source =
|
||||
m_supports_dual_source_blend &&
|
||||
((render_mode != static_cast<uint8_t>(GPU_HW::BatchRenderMode::TransparencyDisabled) &&
|
||||
render_mode != static_cast<uint8_t>(GPU_HW::BatchRenderMode::OnlyOpaque)) ||
|
||||
filter != GPUTextureFilter::Nearest);
|
||||
fs_bc = PickBatchUntexturedFSBytecode(use_dual_source, m_multisamples,
|
||||
m_per_sample_shading,
|
||||
m_disable_color_perspective);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue