The .inc consumers and the C++ host namespace moved to d3d_common in24bacbf, but the HLSL sources and the regen tool kept their d3d12 tags for "historical / churn-avoidance reasons" - the commit message there explicitly flagged it as deferred cleanup ("data/shaders/d3d12 -> data/shaders/d3d_common + tool rename. Currently kept as d3d12 for historical/churn-avoidance reasons"). With the downsample foundation landed at251e457also putting its HLSL under data/shaders/d3d12/ (despite being consumed only by D3D11 today, with D3D12 consumption arriving in a later phase), the naming inconsistency is now actively confusing. This commit completes the rename. What changes (mechanically, via git mv + sweep): data/shaders/d3d12/ -> data/shaders/d3d_common/ Whole directory renames via git mv. 16 files move: README.md + 10 .hlsl source templates (5 batch + display + copy + vram_{copy,fill,read,update_depth,write} + fullscreen_quad + 4 downsample). Each .hlsl content is unchanged except where a comment string referenced the old path (3 files: box_sample_downsample.ps.hlsl, adaptive_downsample_composite.ps.hlsl, vram_fill.ps.hlsl). tools/regen_d3d12_dxbc.py -> tools/regen_d3d_common_dxbc.py Renamed via git mv. The HLSL_DIR constant repointed to the new HLSL directory; the .inc preamble template updated to emit the new paths; the top-of-file comment updated to drop the "kept as d3d12 for historical reasons" note now that it doesn't apply. Behaviour unchanged: same HLSL -> fxc /T ps_5_0 /E main /O3 -> same .inc bytes. src/common/d3d_common/embedded_dxbc/*.inc (182 files) Preamble line 1 updated: // Autogenerated from data/shaders/d3d12/<name>.hlsl. -> // Autogenerated from data/shaders/d3d_common/<name>.hlsl. Preamble line 2 updated: // DO NOT EDIT. Regenerate with tools/regen_d3d12_dxbc.py. -> // DO NOT EDIT. Regenerate with tools/regen_d3d_common_dxbc.py. The byte arrays themselves are bit-identical pre/post-commit (fxc emits identical DXBC from the same HLSL source). Only the two comment lines of each .inc change. src/common/d3d_common/embedded_shaders.h 14 doc comments updated: "// Source: data/shaders/d3d12/<name>.hlsl" -> "// Source: data/shaders/d3d_common/<name>.hlsl" Plus the top-of-file rationale block updated to drop the d3d12-tagged path reference. src/core/gpu_hw_d3d12.cpp Two comment lines referencing the old data/shaders/d3d12/ path and the old regen tool name. The pre-bake call sites themselves were already namespace-qualified (D3DCommon:: EmbeddedShaders::*) and need no change. data/shaders/d3d_common/README.md 8 doc references to the old paths updated. What doesn't change in this commit: - DXBC byte content. fxc is deterministic on identical source + flags; the post-rename HLSL is byte-identical to the pre-rename HLSL except for comment text, and comments don't survive into the compiled bytecode. Re-running tools/regen_d3d_common_dxbc.py produces .inc files that match this commit's preamble lines + the pre-existing byte arrays. - C++ namespaces. Already D3DCommon::EmbeddedShaders since24bacbf. Not touched here. - Header / library / TU layout. embedded_shaders.{h,cpp} already live at src/common/d3d_common/ since24bacbf; embedded_dxbc/ already lives at src/common/d3d_common/embedded_dxbc/. This commit completes the symmetric rename on the data-side and tools-side. - Build system files (CMakeLists.txt, Makefile.libretro): none of them references the data/shaders directory tree or the regen tool - the data is consumed at HLSL-source-edit time only, not at build time. Untouched. - Runtime behaviour: zero diff across D3D11 + D3D12. Same blobs, same pickers, same PSOs. Test: - git status post-rename shows 16 renames + 184 minor edits (preamble-only diffs in the .inc files + comment-only diffs in the regen tool + embedded_shaders.h + gpu_hw_d3d12.cpp). No moved file's content changed structurally. - Hand-compile of a representative variant (box_sample_downsample at RESOLUTION_SCALE=4) post-rename: 1044 bytes DXBC, identical to pre-rename. - String search across the tree: zero remaining references to "data/shaders/d3d12" or "regen_d3d12_dxbc" outside of .git history. Next: - Activation commit for the downsample pre-bake: add 22 extern pairs + 22 #include lines to embedded_shaders.{h,cpp}, add 4 picker functions, rewrite the 5 shadergen calls in GPU_HW_D3D11::CompileShaders. The d3d_common naming is now coherent across HLSL sources, regen tool, .inc files, host TU, and host namespace - new pre-bake additions don't have to thread the old d3d12 naming. - Phase 2 (separate effort): port the D3D11 downsample machinery to D3D12 - PSOs, explicit resource barriers, texture / mip-view creation - and set m_supports_adaptive_downsampling = true on the D3D12 caps path. The pre-baked blobs are already in place by then.
67 lines
2.7 KiB
HLSL
67 lines
2.7 KiB
HLSL
// Pre-baked HLSL for
|
|
// GPU_HW_ShaderGen::GenerateBoxSampleDownsampleFragmentShader().
|
|
//
|
|
// Backport of data/shaders/vulkan/box_sample_downsample.frag.glsl
|
|
// to HLSL for the D3D backends. Used when m_downsample_mode = Box:
|
|
// averages a RESOLUTION_SCALE x RESOLUTION_SCALE block of upscaled
|
|
// texels back down to a single PSX-native-resolution pixel.
|
|
//
|
|
// Variant axis (1 dimension, 15 blobs):
|
|
// RESOLUTION_SCALE (-D macro, integer literal). Drives:
|
|
// - base_coords block-origin scaling
|
|
// - the two inner loop bounds (so fxc can unroll at compile
|
|
// time)
|
|
// - the final averaging divisor (RESOLUTION_SCALE^2)
|
|
//
|
|
// The Vulkan template uses spec constant id=0 here; on HLSL we
|
|
// use -D RESOLUTION_SCALE=N at fxc time so the inner loops become
|
|
// fixed-trip-count and fxc fully unrolls them in the DXBC.
|
|
// Reachable values for the Box downsample mode are [2,
|
|
// m_max_resolution_scale]. With D3D11_REQ_TEXTURE2D_U_OR_V_DIMENSION
|
|
// = 16384 and VRAM_WIDTH = 1024 the cap is 16, so the reachable
|
|
// set is {2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}
|
|
// -> 15 variants. RESOLUTION_SCALE=1 disables downsampling entirely
|
|
// (see GPU_HW::GetDownsampleMode in gpu_hw.cpp:399) so we don't
|
|
// bake a variant for it.
|
|
//
|
|
// Note on loop unrolling: at scale=16 the inner body runs 256
|
|
// times. fxc unrolls fully when RESOLUTION_SCALE is a literal at
|
|
// /D-time, which is fine for this pass - the downsample runs once
|
|
// per frame, not per drawcall, and the post-c532a34 throughput
|
|
// budget at PSX framerates handles 256 LOAD_TEXTURE ops per
|
|
// downsampled pixel comfortably even at 4K + 16x.
|
|
//
|
|
// Suffix: s{2..16}.
|
|
//
|
|
// Bindings:
|
|
// Texture2D samp0 at register(t0) : high-res render target
|
|
// SamplerState samp0_ss at register(s0)
|
|
//
|
|
// The Box mode does not bind the SmoothingUBOData cbuffer (it's
|
|
// only used by the Adaptive mip / blur / composite passes), so
|
|
// no cbuffer is declared here.
|
|
//
|
|
// Box composite reads v_pos.xy (SV_Position), matching the shader
|
|
// gen output's #if at the entry point.
|
|
|
|
#ifndef RESOLUTION_SCALE
|
|
# error "Compile with /D RESOLUTION_SCALE=<N>. See TEMPLATE_VARIANTS in tools/regen_d3d_common_dxbc.py."
|
|
#endif
|
|
|
|
Texture2D samp0 : register(t0);
|
|
SamplerState samp0_ss : register(s0);
|
|
|
|
void main(
|
|
in float4 v_pos : SV_Position,
|
|
out float4 o_col0 : SV_Target0)
|
|
{
|
|
float3 color = float3(0.0, 0.0, 0.0);
|
|
uint2 base_coords = uint2(v_pos.xy) * uint2(RESOLUTION_SCALE, RESOLUTION_SCALE);
|
|
for (uint offset_x = 0u; offset_x < RESOLUTION_SCALE; offset_x++)
|
|
{
|
|
for (uint offset_y = 0u; offset_y < RESOLUTION_SCALE; offset_y++)
|
|
color += samp0.Load(int3(int2(base_coords + uint2(offset_x, offset_y)), 0)).rgb;
|
|
}
|
|
color /= float(RESOLUTION_SCALE * RESOLUTION_SCALE);
|
|
o_col0 = float4(color, 1.0);
|
|
}
|