mirror of
https://github.com/valentderah/totk-pc-recomp.git
synced 2026-11-11 01:41:02 +00:00
Encode decoded ASTC textures to BC3 on GPUs without ASTC (astc_bc)
A GPU that cannot sample ASTC gets the textures decoded to RGBA8, four times the video memory of the ASTC blocks. With astc_bc = 1 (default 0, GPU decoder only) a second compute pass, bc3_encode.comp, encodes the decoded texels to BC3 and the image is BC3_UNORM or BC3_SRGB: 8 bits per texel instead of 32. The encoder is the usual bounding-box method with the box diagonal turned to the sign of the colour covariance, and the eight-value alpha mode. A region of a WriteTexels that does not start on a 4x4 block corner is left as it was and logged. The setting is in totk.ini and the Advanced tab. The SPIR-V header was built with glslang 16.6 (build_shaders.py uses glslc) with the same source hash. On a GTX 1650 (4 GiB) in the Fire Temple the GPU time per frame went from 10-23 ms to 3-12 ms and the frame rate held at 59-60 fps. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
arthurhfcardosoandClaude Sonnet 5.5 authored and Valiantsin Dzerakh committed
1 parent
ff25b04cdb
commit
dd496bfd5d
12 files changed
+472
-18
No files matched your search
@@ -132,7 +132,7 @@ static int gpu_decode(VkCtx *c, const uint8_t *blk, size_t n0, size_t n1, uint32
|
||||
VkAstcRegion ar[2] = {{.src = 0, .w = w0, .h = h0, .slices = 1, .level = 0},
|
||||
{.src = n0 * 16, .w = w1, .h = h1, .slices = 1, .level = 1}};
|
||||
barrier(cb, ALL_RW, VK_PIPELINE_STAGE_2_COPY_BIT, VK_ACCESS_2_TRANSFER_WRITE_BIT);
|
||||
int ok = vk_astc_record(cb, sb, (n0 + n1) * 16, ar, 2, bw, bh, srgb, im.img, VK_IMAGE_ASPECT_COLOR_BIT, rb);
|
||||
int ok = vk_astc_record(cb, sb, (n0 + n1) * 16, ar, 2, bw, bh, srgb, 0, im.img, VK_IMAGE_ASPECT_COLOR_BIT, rb);
|
||||
barrier(cb, VK_PIPELINE_STAGE_2_COPY_BIT, VK_ACCESS_2_TRANSFER_WRITE_BIT, ALL_RW);
|
||||
VkBufferImageCopy cp[2] = {{.bufferOffset = 0, .imageSubresource = {VK_IMAGE_ASPECT_COLOR_BIT, 0, 0, 1}, .imageExtent = {w0, h0, 1}},
|
||||
{.bufferOffset = t0, .imageSubresource = {VK_IMAGE_ASPECT_COLOR_BIT, 1, 0, 1}, .imageExtent = {w1, h1, 1}}};
|
||||
|
||||
@@ -0,0 +1,263 @@
|
||||
// Generated by tools/build_shaders.py from runtime/shaders/bc3_encode.comp; do not edit.
|
||||
// source sha256 ac318d358136b39a113a18474a815f447223667657c90f9e0356a392639d8541
|
||||
#pragma once
|
||||
#include <stdint.h>
|
||||
static const uint32_t bc3_encode_spv[] = {
|
||||
0x07230203, 0x00010300, 0x0008000b, 0x00000325, 0x00000000, 0x00020011, 0x00000001, 0x0006000b,
|
||||
0x00000001, 0x4c534c47, 0x6474732e, 0x3035342e, 0x00000000, 0x0003000e, 0x00000000, 0x00000001,
|
||||
0x0006000f, 0x00000005, 0x00000004, 0x6e69616d, 0x00000000, 0x0000007f, 0x00060010, 0x00000004,
|
||||
0x00000011, 0x00000008, 0x00000008, 0x00000001, 0x00030003, 0x00000002, 0x000001c2, 0x00040005,
|
||||
0x00000004, 0x6e69616d, 0x00000000, 0x00040005, 0x0000001b, 0x61726150, 0x0000736d, 0x00050006,
|
||||
0x0000001b, 0x00000000, 0x625f6e69, 0x00657361, 0x00060006, 0x0000001b, 0x00000001, 0x5f74756f,
|
||||
0x65736162, 0x00000000, 0x00050006, 0x0000001b, 0x00000002, 0x74646977, 0x00000068, 0x00050006,
|
||||
0x0000001b, 0x00000003, 0x67696568, 0x00007468, 0x00040006, 0x0000001b, 0x00000004, 0x00007862,
|
||||
0x00050006, 0x0000001b, 0x00000005, 0x696c7362, 0x00006563, 0x00030005, 0x0000001d, 0x00006370,
|
||||
0x00040005, 0x0000002d, 0x65786554, 0x0000736c, 0x00040006, 0x0000002d, 0x00000000, 0x00007870,
|
||||
0x00030005, 0x0000002f, 0x00000000, 0x00080005, 0x0000007f, 0x475f6c67, 0x61626f6c, 0x766e496c,
|
||||
0x7461636f, 0x496e6f69, 0x00000044, 0x00030005, 0x000000ab, 0x00000074, 0x00040005, 0x000001ea,
|
||||
0x636f6c42, 0x0000736b, 0x00040006, 0x000001ea, 0x00000000, 0x006b6c62, 0x00030005, 0x000001ec,
|
||||
0x00000000, 0x00030047, 0x0000001b, 0x00000002, 0x00050048, 0x0000001b, 0x00000000, 0x00000023,
|
||||
0x00000000, 0x00050048, 0x0000001b, 0x00000001, 0x00000023, 0x00000004, 0x00050048, 0x0000001b,
|
||||
0x00000002, 0x00000023, 0x00000008, 0x00050048, 0x0000001b, 0x00000003, 0x00000023, 0x0000000c,
|
||||
0x00050048, 0x0000001b, 0x00000004, 0x00000023, 0x00000010, 0x00050048, 0x0000001b, 0x00000005,
|
||||
0x00000023, 0x00000014, 0x00040047, 0x0000002c, 0x00000006, 0x00000004, 0x00030047, 0x0000002d,
|
||||
0x00000002, 0x00040048, 0x0000002d, 0x00000000, 0x00000018, 0x00050048, 0x0000002d, 0x00000000,
|
||||
0x00000023, 0x00000000, 0x00030047, 0x0000002f, 0x00000018, 0x00040047, 0x0000002f, 0x00000021,
|
||||
0x00000000, 0x00040047, 0x0000002f, 0x00000022, 0x00000000, 0x00040047, 0x0000007f, 0x0000000b,
|
||||
0x0000001c, 0x00040047, 0x000001e9, 0x00000006, 0x00000010, 0x00030047, 0x000001ea, 0x00000002,
|
||||
0x00040048, 0x000001ea, 0x00000000, 0x00000019, 0x00050048, 0x000001ea, 0x00000000, 0x00000023,
|
||||
0x00000000, 0x00030047, 0x000001ec, 0x00000019, 0x00040047, 0x000001ec, 0x00000021, 0x00000001,
|
||||
0x00040047, 0x000001ec, 0x00000022, 0x00000000, 0x00040047, 0x0000020c, 0x0000000b, 0x00000019,
|
||||
0x00020013, 0x00000002, 0x00030021, 0x00000003, 0x00000002, 0x00040015, 0x00000006, 0x00000020,
|
||||
0x00000000, 0x00030016, 0x00000008, 0x00000020, 0x00040017, 0x00000009, 0x00000008, 0x00000004,
|
||||
0x00040017, 0x00000010, 0x00000008, 0x00000003, 0x0008001e, 0x0000001b, 0x00000006, 0x00000006,
|
||||
0x00000006, 0x00000006, 0x00000006, 0x00000006, 0x00040020, 0x0000001c, 0x00000009, 0x0000001b,
|
||||
0x0004003b, 0x0000001c, 0x0000001d, 0x00000009, 0x00040015, 0x0000001e, 0x00000020, 0x00000001,
|
||||
0x0004002b, 0x0000001e, 0x0000001f, 0x00000002, 0x00040020, 0x00000020, 0x00000009, 0x00000006,
|
||||
0x0004002b, 0x00000006, 0x00000023, 0x00000001, 0x0004002b, 0x0000001e, 0x00000027, 0x00000003,
|
||||
0x0003001d, 0x0000002c, 0x00000006, 0x0003001e, 0x0000002d, 0x0000002c, 0x00040020, 0x0000002e,
|
||||
0x0000000c, 0x0000002d, 0x0004003b, 0x0000002e, 0x0000002f, 0x0000000c, 0x0004002b, 0x0000001e,
|
||||
0x00000030, 0x00000000, 0x00040020, 0x0000003f, 0x0000000c, 0x00000006, 0x0004002b, 0x00000008,
|
||||
0x00000043, 0x437f0000, 0x00040017, 0x00000047, 0x00000006, 0x00000003, 0x0004002b, 0x00000008,
|
||||
0x0000004b, 0x00000000, 0x0004002b, 0x00000006, 0x00000057, 0x00000000, 0x0004002b, 0x0000001e,
|
||||
0x0000005a, 0x0000000b, 0x0004002b, 0x0000001e, 0x0000005e, 0x00000005, 0x0004002b, 0x00000006,
|
||||
0x00000061, 0x00000002, 0x0004002b, 0x00000006, 0x00000069, 0x0000001f, 0x0004002b, 0x00000006,
|
||||
0x00000070, 0x0000003f, 0x00040020, 0x0000007e, 0x00000001, 0x00000047, 0x0004003b, 0x0000007e,
|
||||
0x0000007f, 0x00000001, 0x0004002b, 0x00000006, 0x00000084, 0x00000003, 0x0004002b, 0x00000006,
|
||||
0x00000086, 0x00000004, 0x00020014, 0x00000088, 0x0004002b, 0x0000001e, 0x0000008b, 0x00000004,
|
||||
0x00040020, 0x0000009a, 0x00000007, 0x00000009, 0x0007002c, 0x00000009, 0x0000009c, 0x00000043,
|
||||
0x00000043, 0x00000043, 0x00000043, 0x0007002c, 0x00000009, 0x0000009e, 0x0000004b, 0x0000004b,
|
||||
0x0000004b, 0x0000004b, 0x0004002b, 0x00000006, 0x000000a7, 0x00000010, 0x0004001c, 0x000000a9,
|
||||
0x00000009, 0x000000a7, 0x00040020, 0x000000aa, 0x00000007, 0x000000a9, 0x0004002b, 0x0000001e,
|
||||
0x000000d0, 0x00000001, 0x00040020, 0x000000d7, 0x00000007, 0x00000008, 0x00040017, 0x000000df,
|
||||
0x00000006, 0x00000002, 0x0004002b, 0x0000001e, 0x000000e4, 0x00000008, 0x0004002b, 0x00000008,
|
||||
0x00000101, 0x40e00000, 0x0004002b, 0x00000006, 0x00000110, 0x00000007, 0x0004002b, 0x00000006,
|
||||
0x0000011f, 0x00000020, 0x0004002b, 0x00000008, 0x000001b5, 0x358637bd, 0x0004002b, 0x00000008,
|
||||
0x000001ca, 0x40400000, 0x00040017, 0x000001e8, 0x00000006, 0x00000004, 0x0003001d, 0x000001e9,
|
||||
0x000001e8, 0x0003001e, 0x000001ea, 0x000001e9, 0x00040020, 0x000001eb, 0x0000000c, 0x000001ea,
|
||||
0x0004003b, 0x000001eb, 0x000001ec, 0x0000000c, 0x0004002b, 0x0000001e, 0x00000204, 0x00000010,
|
||||
0x00040020, 0x00000209, 0x0000000c, 0x000001e8, 0x0004002b, 0x00000006, 0x0000020b, 0x00000008,
|
||||
0x0006002c, 0x00000047, 0x0000020c, 0x0000020b, 0x0000020b, 0x00000023, 0x0004002b, 0x00000006,
|
||||
0x000002c8, 0x00000013, 0x0006002c, 0x00000010, 0x000002ca, 0x0000004b, 0x0000004b, 0x0000004b,
|
||||
0x0006002c, 0x00000010, 0x000002cb, 0x00000043, 0x00000043, 0x00000043, 0x0004002b, 0x00000008,
|
||||
0x000002cc, 0x3d800000, 0x0007002c, 0x00000009, 0x000002cd, 0x000002cc, 0x000002cc, 0x000002cc,
|
||||
0x000002cc, 0x0006002c, 0x00000010, 0x000002ce, 0x000002cc, 0x000002cc, 0x000002cc, 0x0004002b,
|
||||
0x00000008, 0x000002d1, 0x3df8f8fa, 0x0004002b, 0x00000008, 0x000002d2, 0x3e7cfcfe, 0x0006002c,
|
||||
0x00000010, 0x000002d3, 0x000002d1, 0x000002d2, 0x000002d1, 0x0004002b, 0x00000008, 0x000002d5,
|
||||
0x41039ce7, 0x0004002b, 0x00000008, 0x000002d7, 0x40818619, 0x0004002b, 0x00000006, 0x000002d8,
|
||||
0xfffffff0, 0x00050036, 0x00000002, 0x00000004, 0x00000000, 0x00000003, 0x000200f8, 0x00000005,
|
||||
0x0004003b, 0x000000aa, 0x000000ab, 0x00000007, 0x000300f7, 0x0000020d, 0x00000000, 0x000300fb,
|
||||
0x00000057, 0x0000020e, 0x000200f8, 0x0000020e, 0x0004003d, 0x00000047, 0x00000080, 0x0000007f,
|
||||
0x00050041, 0x00000020, 0x00000082, 0x0000001d, 0x00000027, 0x0004003d, 0x00000006, 0x00000083,
|
||||
0x00000082, 0x00050080, 0x00000006, 0x00000085, 0x00000083, 0x00000084, 0x00050086, 0x00000006,
|
||||
0x00000087, 0x00000085, 0x00000086, 0x00050051, 0x00000006, 0x0000008a, 0x00000080, 0x00000000,
|
||||
0x00050041, 0x00000020, 0x0000008c, 0x0000001d, 0x0000008b, 0x0004003d, 0x00000006, 0x0000008d,
|
||||
0x0000008c, 0x000500ae, 0x00000088, 0x0000008e, 0x0000008a, 0x0000008d, 0x000400a8, 0x00000088,
|
||||
0x0000008f, 0x0000008e, 0x000300f7, 0x00000091, 0x00000000, 0x000400fa, 0x0000008f, 0x00000090,
|
||||
0x00000091, 0x000200f8, 0x00000090, 0x00050051, 0x00000006, 0x00000093, 0x00000080, 0x00000001,
|
||||
0x000500ae, 0x00000088, 0x00000095, 0x00000093, 0x00000087, 0x000200f9, 0x00000091, 0x000200f8,
|
||||
0x00000091, 0x000700f5, 0x00000088, 0x00000096, 0x0000008e, 0x0000020e, 0x00000095, 0x00000090,
|
||||
0x000300f7, 0x00000098, 0x00000000, 0x000400fa, 0x00000096, 0x00000097, 0x00000098, 0x000200f8,
|
||||
0x00000097, 0x000200f9, 0x0000020d, 0x000200f8, 0x00000098, 0x000200f9, 0x000000a1, 0x000200f8,
|
||||
0x000000a1, 0x000700f5, 0x00000009, 0x00000304, 0x0000009c, 0x00000098, 0x000000c4, 0x000000a2,
|
||||
0x000700f5, 0x00000009, 0x00000303, 0x0000009e, 0x00000098, 0x000000c9, 0x000000a2, 0x000700f5,
|
||||
0x00000009, 0x00000286, 0x0000009e, 0x00000098, 0x000000ce, 0x000000a2, 0x000700f5, 0x00000006,
|
||||
0x00000285, 0x00000057, 0x00000098, 0x000000d1, 0x000000a2, 0x000500b0, 0x00000088, 0x000000a8,
|
||||
0x00000285, 0x000000a7, 0x000400f6, 0x000000a3, 0x000000a2, 0x00000000, 0x000400fa, 0x000000a8,
|
||||
0x000000a2, 0x000000a3, 0x000200f8, 0x000000a2, 0x00050084, 0x00000006, 0x000000af, 0x0000008a,
|
||||
0x00000086, 0x000500c7, 0x00000006, 0x000000b1, 0x00000285, 0x00000084, 0x00050080, 0x00000006,
|
||||
0x000000b2, 0x000000af, 0x000000b1, 0x00050051, 0x00000006, 0x000000b4, 0x00000080, 0x00000001,
|
||||
0x00050084, 0x00000006, 0x000000b5, 0x000000b4, 0x00000086, 0x000500c2, 0x00000006, 0x000000b7,
|
||||
0x00000285, 0x0000001f, 0x00050080, 0x00000006, 0x000000b8, 0x000000b5, 0x000000b7, 0x00050051,
|
||||
0x00000006, 0x000000bd, 0x00000080, 0x00000002, 0x00050041, 0x00000020, 0x00000216, 0x0000001d,
|
||||
0x0000001f, 0x0004003d, 0x00000006, 0x00000217, 0x00000216, 0x00050082, 0x00000006, 0x00000218,
|
||||
0x00000217, 0x00000023, 0x0007000c, 0x00000006, 0x00000219, 0x00000001, 0x00000026, 0x000000b2,
|
||||
0x00000218, 0x00050082, 0x00000006, 0x0000021d, 0x00000083, 0x00000023, 0x0007000c, 0x00000006,
|
||||
0x0000021e, 0x00000001, 0x00000026, 0x000000b8, 0x0000021d, 0x00050041, 0x00000020, 0x0000021f,
|
||||
0x0000001d, 0x00000030, 0x0004003d, 0x00000006, 0x00000220, 0x0000021f, 0x00050084, 0x00000006,
|
||||
0x00000224, 0x000000bd, 0x00000083, 0x00050080, 0x00000006, 0x00000226, 0x00000224, 0x0000021e,
|
||||
0x00050084, 0x00000006, 0x00000229, 0x00000226, 0x00000217, 0x00050080, 0x00000006, 0x0000022a,
|
||||
0x00000220, 0x00000229, 0x00050080, 0x00000006, 0x0000022c, 0x0000022a, 0x00000219, 0x00060041,
|
||||
0x0000003f, 0x0000022d, 0x0000002f, 0x00000030, 0x0000022c, 0x0004003d, 0x00000006, 0x0000022e,
|
||||
0x0000022d, 0x0006000c, 0x00000009, 0x0000022f, 0x00000001, 0x00000040, 0x0000022e, 0x0005008e,
|
||||
0x00000009, 0x00000230, 0x0000022f, 0x00000043, 0x00050041, 0x0000009a, 0x000000bf, 0x000000ab,
|
||||
0x00000285, 0x0003003e, 0x000000bf, 0x00000230, 0x0004003d, 0x00000009, 0x000000c3, 0x000000bf,
|
||||
0x0007000c, 0x00000009, 0x000000c4, 0x00000001, 0x00000025, 0x00000304, 0x000000c3, 0x0004003d,
|
||||
0x00000009, 0x000000c8, 0x000000bf, 0x0007000c, 0x00000009, 0x000000c9, 0x00000001, 0x00000028,
|
||||
0x00000303, 0x000000c8, 0x0004003d, 0x00000009, 0x000000cc, 0x000000bf, 0x00050081, 0x00000009,
|
||||
0x000000ce, 0x00000286, 0x000000cc, 0x00050080, 0x00000006, 0x000000d1, 0x00000285, 0x000000d0,
|
||||
0x000200f9, 0x000000a1, 0x000200f8, 0x000000a3, 0x00050085, 0x00000009, 0x000000d5, 0x00000286,
|
||||
0x000002cd, 0x00050051, 0x00000008, 0x000000d9, 0x00000303, 0x00000003, 0x0004006d, 0x00000006,
|
||||
0x000000da, 0x000000d9, 0x00050051, 0x00000008, 0x000000dd, 0x00000304, 0x00000003, 0x0004006d,
|
||||
0x00000006, 0x000000de, 0x000000dd, 0x000500c4, 0x00000006, 0x000000e5, 0x000000de, 0x000000e4,
|
||||
0x000500c5, 0x00000006, 0x000000e6, 0x000000da, 0x000000e5, 0x00050050, 0x000000df, 0x000000e7,
|
||||
0x000000e6, 0x00000057, 0x000500ac, 0x00000088, 0x000000ea, 0x000000da, 0x000000de, 0x000300f7,
|
||||
0x000000ec, 0x00000000, 0x000400fa, 0x000000ea, 0x000000eb, 0x000000ec, 0x000200f8, 0x000000eb,
|
||||
0x00050082, 0x00000006, 0x000000f0, 0x000000da, 0x000000de, 0x00040070, 0x00000008, 0x000000f1,
|
||||
0x000000f0, 0x000200f9, 0x000000f3, 0x000200f8, 0x000000f3, 0x000700f5, 0x000000df, 0x00000314,
|
||||
0x000000e7, 0x000000eb, 0x00000324, 0x000000f6, 0x000700f5, 0x00000006, 0x00000287, 0x00000057,
|
||||
0x000000eb, 0x00000143, 0x000000f6, 0x000500b0, 0x00000088, 0x000000f9, 0x00000287, 0x000000a7,
|
||||
0x000400f6, 0x000000f5, 0x000000f6, 0x00000000, 0x000400fa, 0x000000f9, 0x000000f4, 0x000000f5,
|
||||
0x000200f8, 0x000000f4, 0x00040070, 0x00000008, 0x000000fc, 0x000000da, 0x00060041, 0x000000d7,
|
||||
0x000000fe, 0x000000ab, 0x00000287, 0x00000084, 0x0004003d, 0x00000008, 0x000000ff, 0x000000fe,
|
||||
0x00050083, 0x00000008, 0x00000100, 0x000000fc, 0x000000ff, 0x00050085, 0x00000008, 0x00000102,
|
||||
0x00000100, 0x00000101, 0x00050088, 0x00000008, 0x00000104, 0x00000102, 0x000000f1, 0x0006000c,
|
||||
0x00000008, 0x00000105, 0x00000001, 0x00000001, 0x00000104, 0x0008000c, 0x00000008, 0x00000106,
|
||||
0x00000001, 0x0000002b, 0x00000105, 0x0000004b, 0x00000101, 0x0004006d, 0x00000006, 0x00000107,
|
||||
0x00000106, 0x000500aa, 0x00000088, 0x0000010a, 0x00000107, 0x00000057, 0x000300f7, 0x0000010d,
|
||||
0x00000000, 0x000400fa, 0x0000010a, 0x0000010c, 0x0000010e, 0x000200f8, 0x0000010c, 0x000200f9,
|
||||
0x0000010d, 0x000200f8, 0x0000010e, 0x000500aa, 0x00000088, 0x00000111, 0x00000107, 0x00000110,
|
||||
0x000300f7, 0x00000114, 0x00000000, 0x000400fa, 0x00000111, 0x00000113, 0x00000115, 0x000200f8,
|
||||
0x00000113, 0x000200f9, 0x00000114, 0x000200f8, 0x00000115, 0x00050080, 0x00000006, 0x00000117,
|
||||
0x00000107, 0x00000023, 0x000200f9, 0x00000114, 0x000200f8, 0x00000114, 0x000700f5, 0x00000006,
|
||||
0x000002a4, 0x00000023, 0x00000113, 0x00000117, 0x00000115, 0x000200f9, 0x0000010d, 0x000200f8,
|
||||
0x0000010d, 0x000700f5, 0x00000006, 0x000002a5, 0x00000057, 0x0000010c, 0x000002a4, 0x00000114,
|
||||
0x00050084, 0x00000006, 0x0000011c, 0x00000084, 0x00000287, 0x00050080, 0x00000006, 0x0000011d,
|
||||
0x000000a7, 0x0000011c, 0x000500b0, 0x00000088, 0x00000120, 0x0000011d, 0x0000011f, 0x000300f7,
|
||||
0x00000122, 0x00000000, 0x000400fa, 0x00000120, 0x00000121, 0x00000122, 0x000200f8, 0x00000121,
|
||||
0x000500c4, 0x00000006, 0x00000125, 0x000002a5, 0x0000011d, 0x00050051, 0x00000006, 0x00000127,
|
||||
0x00000314, 0x00000000, 0x000500c5, 0x00000006, 0x00000128, 0x00000127, 0x00000125, 0x00060052,
|
||||
0x000000df, 0x000002e4, 0x00000128, 0x00000314, 0x00000000, 0x000200f9, 0x00000122, 0x000200f8,
|
||||
0x00000122, 0x000700f5, 0x000000df, 0x00000319, 0x00000314, 0x0000010d, 0x000002e4, 0x00000121,
|
||||
0x00050080, 0x00000006, 0x0000012b, 0x0000011c, 0x000002c8, 0x000500ac, 0x00000088, 0x0000012c,
|
||||
0x0000012b, 0x0000011f, 0x000300f7, 0x0000012e, 0x00000000, 0x000400fa, 0x0000012c, 0x0000012d,
|
||||
0x0000012e, 0x000200f8, 0x0000012d, 0x0007000c, 0x00000006, 0x00000131, 0x00000001, 0x00000026,
|
||||
0x0000011d, 0x0000011f, 0x00050082, 0x00000006, 0x00000132, 0x0000011f, 0x00000131, 0x000500c2,
|
||||
0x00000006, 0x00000133, 0x000002a5, 0x00000132, 0x000500ac, 0x00000088, 0x00000135, 0x0000011d,
|
||||
0x0000011f, 0x000300f7, 0x00000138, 0x00000000, 0x000400fa, 0x00000135, 0x00000137, 0x0000013b,
|
||||
0x000200f8, 0x00000137, 0x00050080, 0x00000006, 0x0000013a, 0x0000011c, 0x000002d8, 0x000200f9,
|
||||
0x00000138, 0x000200f8, 0x0000013b, 0x000200f9, 0x00000138, 0x000200f8, 0x00000138, 0x000700f5,
|
||||
0x00000006, 0x000002aa, 0x0000013a, 0x00000137, 0x00000057, 0x0000013b, 0x000500c4, 0x00000006,
|
||||
0x0000013d, 0x00000133, 0x000002aa, 0x00050051, 0x00000006, 0x0000013f, 0x00000319, 0x00000001,
|
||||
0x000500c5, 0x00000006, 0x00000140, 0x0000013f, 0x0000013d, 0x00060052, 0x000000df, 0x000002e7,
|
||||
0x00000140, 0x00000319, 0x00000001, 0x000200f9, 0x0000012e, 0x000200f8, 0x0000012e, 0x000700f5,
|
||||
0x000000df, 0x00000324, 0x00000319, 0x00000122, 0x000002e7, 0x00000138, 0x000200f9, 0x000000f6,
|
||||
0x000200f8, 0x000000f6, 0x00050080, 0x00000006, 0x00000143, 0x00000287, 0x000000d0, 0x000200f9,
|
||||
0x000000f3, 0x000200f8, 0x000000f5, 0x000200f9, 0x000000ec, 0x000200f8, 0x000000ec, 0x000700f5,
|
||||
0x000000df, 0x00000313, 0x000000e7, 0x000000a3, 0x00000314, 0x000000f5, 0x0008004f, 0x00000010,
|
||||
0x00000146, 0x00000304, 0x00000304, 0x00000000, 0x00000001, 0x00000002, 0x0008004f, 0x00000010,
|
||||
0x00000149, 0x00000303, 0x00000303, 0x00000000, 0x00000001, 0x00000002, 0x000200f9, 0x0000014d,
|
||||
0x000200f8, 0x0000014d, 0x000700f5, 0x00000008, 0x0000028b, 0x0000004b, 0x000000ec, 0x00000169,
|
||||
0x0000014e, 0x000700f5, 0x00000008, 0x00000289, 0x0000004b, 0x000000ec, 0x00000162, 0x0000014e,
|
||||
0x000700f5, 0x00000006, 0x00000288, 0x00000057, 0x000000ec, 0x0000016b, 0x0000014e, 0x000500b0,
|
||||
0x00000088, 0x00000153, 0x00000288, 0x000000a7, 0x000400f6, 0x0000014f, 0x0000014e, 0x00000000,
|
||||
0x000400fa, 0x00000153, 0x0000014e, 0x0000014f, 0x000200f8, 0x0000014e, 0x00050041, 0x0000009a,
|
||||
0x00000156, 0x000000ab, 0x00000288, 0x0004003d, 0x00000009, 0x00000157, 0x00000156, 0x0008004f,
|
||||
0x00000010, 0x00000158, 0x00000157, 0x00000157, 0x00000000, 0x00000001, 0x00000002, 0x0008004f,
|
||||
0x00000010, 0x0000015a, 0x000000d5, 0x000000d5, 0x00000000, 0x00000001, 0x00000002, 0x00050083,
|
||||
0x00000010, 0x0000015b, 0x00000158, 0x0000015a, 0x00050051, 0x00000008, 0x0000015d, 0x0000015b,
|
||||
0x00000000, 0x00050051, 0x00000008, 0x0000015f, 0x0000015b, 0x00000001, 0x00050085, 0x00000008,
|
||||
0x00000160, 0x0000015d, 0x0000015f, 0x00050081, 0x00000008, 0x00000162, 0x00000289, 0x00000160,
|
||||
0x00050051, 0x00000008, 0x00000164, 0x0000015b, 0x00000002, 0x00050085, 0x00000008, 0x00000167,
|
||||
0x00000164, 0x0000015f, 0x00050081, 0x00000008, 0x00000169, 0x0000028b, 0x00000167, 0x00050080,
|
||||
0x00000006, 0x0000016b, 0x00000288, 0x000000d0, 0x000200f9, 0x0000014d, 0x000200f8, 0x0000014f,
|
||||
0x000500b8, 0x00000088, 0x0000016d, 0x00000289, 0x0000004b, 0x000300f7, 0x0000016f, 0x00000000,
|
||||
0x000400fa, 0x0000016d, 0x0000016e, 0x0000016f, 0x000200f8, 0x0000016e, 0x00050051, 0x00000008,
|
||||
0x00000172, 0x00000304, 0x00000000, 0x00050051, 0x00000008, 0x00000174, 0x00000303, 0x00000000,
|
||||
0x00060052, 0x00000010, 0x000002ef, 0x00000174, 0x00000146, 0x00000000, 0x00060052, 0x00000010,
|
||||
0x000002f1, 0x00000172, 0x00000149, 0x00000000, 0x000200f9, 0x0000016f, 0x000200f8, 0x0000016f,
|
||||
0x000700f5, 0x00000010, 0x0000030c, 0x00000149, 0x0000014f, 0x000002f1, 0x0000016e, 0x000700f5,
|
||||
0x00000010, 0x0000030b, 0x00000146, 0x0000014f, 0x000002ef, 0x0000016e, 0x000500b8, 0x00000088,
|
||||
0x00000179, 0x0000028b, 0x0000004b, 0x000300f7, 0x0000017b, 0x00000000, 0x000400fa, 0x00000179,
|
||||
0x0000017a, 0x0000017b, 0x000200f8, 0x0000017a, 0x00050051, 0x00000008, 0x0000017e, 0x0000030b,
|
||||
0x00000002, 0x00050051, 0x00000008, 0x00000180, 0x0000030c, 0x00000002, 0x00060052, 0x00000010,
|
||||
0x000002f5, 0x00000180, 0x0000030b, 0x00000002, 0x00060052, 0x00000010, 0x000002f7, 0x0000017e,
|
||||
0x0000030c, 0x00000002, 0x000200f9, 0x0000017b, 0x000200f8, 0x0000017b, 0x000700f5, 0x00000010,
|
||||
0x0000030e, 0x0000030b, 0x0000016f, 0x000002f5, 0x0000017a, 0x000700f5, 0x00000010, 0x0000030d,
|
||||
0x0000030c, 0x0000016f, 0x000002f7, 0x0000017a, 0x00050083, 0x00000010, 0x00000187, 0x0000030d,
|
||||
0x0000030e, 0x00050085, 0x00000010, 0x00000189, 0x00000187, 0x000002ce, 0x00050083, 0x00000010,
|
||||
0x0000018d, 0x0000030d, 0x00000189, 0x0008000c, 0x00000010, 0x00000237, 0x00000001, 0x0000002b,
|
||||
0x0000018d, 0x000002ca, 0x000002cb, 0x00050085, 0x00000010, 0x0000023a, 0x00000237, 0x000002d3,
|
||||
0x0006000c, 0x00000010, 0x0000023b, 0x00000001, 0x00000001, 0x0000023a, 0x0004006d, 0x00000047,
|
||||
0x0000023c, 0x0000023b, 0x00050051, 0x00000006, 0x0000023e, 0x0000023c, 0x00000000, 0x000500c4,
|
||||
0x00000006, 0x0000023f, 0x0000023e, 0x0000005a, 0x00050051, 0x00000006, 0x00000241, 0x0000023c,
|
||||
0x00000001, 0x000500c4, 0x00000006, 0x00000242, 0x00000241, 0x0000005e, 0x000500c5, 0x00000006,
|
||||
0x00000243, 0x0000023f, 0x00000242, 0x00050051, 0x00000006, 0x00000245, 0x0000023c, 0x00000002,
|
||||
0x000500c5, 0x00000006, 0x00000246, 0x00000243, 0x00000245, 0x00050081, 0x00000010, 0x00000193,
|
||||
0x0000030e, 0x00000189, 0x0008000c, 0x00000010, 0x0000024d, 0x00000001, 0x0000002b, 0x00000193,
|
||||
0x000002ca, 0x000002cb, 0x00050085, 0x00000010, 0x00000250, 0x0000024d, 0x000002d3, 0x0006000c,
|
||||
0x00000010, 0x00000251, 0x00000001, 0x00000001, 0x00000250, 0x0004006d, 0x00000047, 0x00000252,
|
||||
0x00000251, 0x00050051, 0x00000006, 0x00000254, 0x00000252, 0x00000000, 0x000500c4, 0x00000006,
|
||||
0x00000255, 0x00000254, 0x0000005a, 0x00050051, 0x00000006, 0x00000257, 0x00000252, 0x00000001,
|
||||
0x000500c4, 0x00000006, 0x00000258, 0x00000257, 0x0000005e, 0x000500c5, 0x00000006, 0x00000259,
|
||||
0x00000255, 0x00000258, 0x00050051, 0x00000006, 0x0000025b, 0x00000252, 0x00000002, 0x000500c5,
|
||||
0x00000006, 0x0000025c, 0x00000259, 0x0000025b, 0x000500ab, 0x00000088, 0x00000199, 0x00000246,
|
||||
0x0000025c, 0x000300f7, 0x0000019b, 0x00000000, 0x000400fa, 0x00000199, 0x0000019a, 0x0000019b,
|
||||
0x000200f8, 0x0000019a, 0x000500b0, 0x00000088, 0x0000019e, 0x00000246, 0x0000025c, 0x000600a9,
|
||||
0x00000006, 0x000002d9, 0x0000019e, 0x00000246, 0x0000025c, 0x000600a9, 0x00000006, 0x000002da,
|
||||
0x0000019e, 0x0000025c, 0x00000246, 0x000500c2, 0x00000006, 0x00000260, 0x000002da, 0x0000005a,
|
||||
0x000500c7, 0x00000006, 0x00000261, 0x00000260, 0x00000069, 0x00040070, 0x00000008, 0x00000262,
|
||||
0x00000261, 0x00050085, 0x00000008, 0x00000264, 0x00000262, 0x000002d5, 0x000500c2, 0x00000006,
|
||||
0x00000266, 0x000002da, 0x0000005e, 0x000500c7, 0x00000006, 0x00000267, 0x00000266, 0x00000070,
|
||||
0x00040070, 0x00000008, 0x00000268, 0x00000267, 0x00050085, 0x00000008, 0x0000026a, 0x00000268,
|
||||
0x000002d7, 0x000500c7, 0x00000006, 0x0000026c, 0x000002da, 0x00000069, 0x00040070, 0x00000008,
|
||||
0x0000026d, 0x0000026c, 0x00050085, 0x00000008, 0x0000026f, 0x0000026d, 0x000002d5, 0x00060050,
|
||||
0x00000010, 0x00000270, 0x00000264, 0x0000026a, 0x0000026f, 0x000500c2, 0x00000006, 0x00000274,
|
||||
0x000002d9, 0x0000005a, 0x000500c7, 0x00000006, 0x00000275, 0x00000274, 0x00000069, 0x00040070,
|
||||
0x00000008, 0x00000276, 0x00000275, 0x00050085, 0x00000008, 0x00000278, 0x00000276, 0x000002d5,
|
||||
0x000500c2, 0x00000006, 0x0000027a, 0x000002d9, 0x0000005e, 0x000500c7, 0x00000006, 0x0000027b,
|
||||
0x0000027a, 0x00000070, 0x00040070, 0x00000008, 0x0000027c, 0x0000027b, 0x00050085, 0x00000008,
|
||||
0x0000027e, 0x0000027c, 0x000002d7, 0x000500c7, 0x00000006, 0x00000280, 0x000002d9, 0x00000069,
|
||||
0x00040070, 0x00000008, 0x00000281, 0x00000280, 0x00050085, 0x00000008, 0x00000283, 0x00000281,
|
||||
0x000002d5, 0x00060050, 0x00000010, 0x00000284, 0x00000278, 0x0000027e, 0x00000283, 0x00050083,
|
||||
0x00000010, 0x000001b0, 0x00000284, 0x00000270, 0x00050094, 0x00000008, 0x000001b4, 0x000001b0,
|
||||
0x000001b0, 0x0007000c, 0x00000008, 0x000001b6, 0x00000001, 0x00000028, 0x000001b4, 0x000001b5,
|
||||
0x000200f9, 0x000001b8, 0x000200f8, 0x000001b8, 0x000700f5, 0x00000006, 0x00000294, 0x00000057,
|
||||
0x0000019a, 0x000001e5, 0x000001bb, 0x000700f5, 0x00000006, 0x0000028e, 0x00000057, 0x0000019a,
|
||||
0x000001e7, 0x000001bb, 0x000500b0, 0x00000088, 0x000001be, 0x0000028e, 0x000000a7, 0x000400f6,
|
||||
0x000001ba, 0x000001bb, 0x00000000, 0x000400fa, 0x000001be, 0x000001b9, 0x000001ba, 0x000200f8,
|
||||
0x000001b9, 0x00050041, 0x0000009a, 0x000001c1, 0x000000ab, 0x0000028e, 0x0004003d, 0x00000009,
|
||||
0x000001c2, 0x000001c1, 0x0008004f, 0x00000010, 0x000001c3, 0x000001c2, 0x000001c2, 0x00000000,
|
||||
0x00000001, 0x00000002, 0x00050083, 0x00000010, 0x000001c5, 0x000001c3, 0x00000270, 0x00050094,
|
||||
0x00000008, 0x000001c7, 0x000001c5, 0x000001b0, 0x00050088, 0x00000008, 0x000001c9, 0x000001c7,
|
||||
0x000001b6, 0x00050085, 0x00000008, 0x000001cb, 0x000001c9, 0x000001ca, 0x0006000c, 0x00000008,
|
||||
0x000001cc, 0x00000001, 0x00000001, 0x000001cb, 0x0008000c, 0x00000008, 0x000001cd, 0x00000001,
|
||||
0x0000002b, 0x000001cc, 0x0000004b, 0x000001ca, 0x0004006d, 0x00000006, 0x000001ce, 0x000001cd,
|
||||
0x000500aa, 0x00000088, 0x000001d1, 0x000001ce, 0x00000057, 0x000300f7, 0x000001d4, 0x00000000,
|
||||
0x000400fa, 0x000001d1, 0x000001d3, 0x000001d5, 0x000200f8, 0x000001d3, 0x000200f9, 0x000001d4,
|
||||
0x000200f8, 0x000001d5, 0x000500aa, 0x00000088, 0x000001d7, 0x000001ce, 0x00000084, 0x000300f7,
|
||||
0x000001da, 0x00000000, 0x000400fa, 0x000001d7, 0x000001d9, 0x000001db, 0x000200f8, 0x000001d9,
|
||||
0x000200f9, 0x000001da, 0x000200f8, 0x000001db, 0x00050080, 0x00000006, 0x000001dd, 0x000001ce,
|
||||
0x00000023, 0x000200f9, 0x000001da, 0x000200f8, 0x000001da, 0x000700f5, 0x00000006, 0x00000299,
|
||||
0x00000023, 0x000001d9, 0x000001dd, 0x000001db, 0x000200f9, 0x000001d4, 0x000200f8, 0x000001d4,
|
||||
0x000700f5, 0x00000006, 0x0000029a, 0x00000057, 0x000001d3, 0x00000299, 0x000001da, 0x00050084,
|
||||
0x00000006, 0x000001e2, 0x00000061, 0x0000028e, 0x000500c4, 0x00000006, 0x000001e3, 0x0000029a,
|
||||
0x000001e2, 0x000500c5, 0x00000006, 0x000001e5, 0x00000294, 0x000001e3, 0x000200f9, 0x000001bb,
|
||||
0x000200f8, 0x000001bb, 0x00050080, 0x00000006, 0x000001e7, 0x0000028e, 0x000000d0, 0x000200f9,
|
||||
0x000001b8, 0x000200f8, 0x000001ba, 0x000200f9, 0x0000019b, 0x000200f8, 0x0000019b, 0x000700f5,
|
||||
0x00000006, 0x00000293, 0x00000057, 0x0000017b, 0x00000294, 0x000001ba, 0x000700f5, 0x00000006,
|
||||
0x00000291, 0x0000025c, 0x0000017b, 0x000002d9, 0x000001ba, 0x000700f5, 0x00000006, 0x0000028f,
|
||||
0x00000246, 0x0000017b, 0x000002da, 0x000001ba, 0x00050041, 0x00000020, 0x000001ed, 0x0000001d,
|
||||
0x000000d0, 0x0004003d, 0x00000006, 0x000001ee, 0x000001ed, 0x00050051, 0x00000006, 0x000001f0,
|
||||
0x00000080, 0x00000002, 0x00050041, 0x00000020, 0x000001f1, 0x0000001d, 0x0000005e, 0x0004003d,
|
||||
0x00000006, 0x000001f2, 0x000001f1, 0x00050084, 0x00000006, 0x000001f3, 0x000001f0, 0x000001f2,
|
||||
0x00050080, 0x00000006, 0x000001f4, 0x000001ee, 0x000001f3, 0x00050051, 0x00000006, 0x000001f6,
|
||||
0x00000080, 0x00000001, 0x00050084, 0x00000006, 0x000001f9, 0x000001f6, 0x0000008d, 0x00050080,
|
||||
0x00000006, 0x000001fa, 0x000001f4, 0x000001f9, 0x00050080, 0x00000006, 0x000001fd, 0x000001fa,
|
||||
0x0000008a, 0x00050051, 0x00000006, 0x000001ff, 0x00000313, 0x00000000, 0x00050051, 0x00000006,
|
||||
0x00000201, 0x00000313, 0x00000001, 0x000500c4, 0x00000006, 0x00000205, 0x00000291, 0x00000204,
|
||||
0x000500c5, 0x00000006, 0x00000206, 0x0000028f, 0x00000205, 0x00070050, 0x000001e8, 0x00000208,
|
||||
0x000001ff, 0x00000201, 0x00000206, 0x00000293, 0x00060041, 0x00000209, 0x0000020a, 0x000001ec,
|
||||
0x00000030, 0x000001fd, 0x0003003e, 0x0000020a, 0x00000208, 0x000200f9, 0x0000020d, 0x000200f8,
|
||||
0x0000020d, 0x000100fd, 0x00010038,
|
||||
};
|
||||
+3
-3
@@ -30,7 +30,7 @@ static int save_ok = 1; // the last cfg_save_to wrote (o
|
||||
// Every name the runtime reads (and the patch sets in generated/), without the prefix. A file key outside this list is
|
||||
// logged as unknown. A new variable goes here too, or its ini key logs a harmless "unknown key" line.
|
||||
static const char *const known[] = {
|
||||
"AB", "APP_POOL", "ASSUME_FOCUS", "ASTC", "ASTC_TIME", "ASYNC_PREEMPT", "AUDIO", "AUDIO_OFF", "AUDIO_PREFILL_MS",
|
||||
"AB", "APP_POOL", "ASSUME_FOCUS", "ASTC", "ASTC_BC", "ASTC_TIME", "ASYNC_PREEMPT", "AUDIO", "AUDIO_OFF", "AUDIO_PREFILL_MS",
|
||||
"BACKGROUND_WINDOW", "BIND_A", "BIND_B", "BIND_DOWN", "BIND_L", "BIND_LCLICK", "BIND_LEFT", "BIND_LSTICK_DOWN", "BIND_LSTICK_LEFT",
|
||||
"BIND_LSTICK_RIGHT", "BIND_LSTICK_UP", "BIND_MINUS",
|
||||
"BIND_PLUS", "BIND_R", "BIND_RCLICK", "BIND_RIGHT", "BIND_RSTICK_DOWN", "BIND_RSTICK_LEFT", "BIND_RSTICK_RIGHT", "BIND_RSTICK_UP",
|
||||
@@ -74,7 +74,7 @@ static const struct { const char *key, *section; } sections[] = {
|
||||
{"TIMER_1MS", "performance"}, {"PIPE_WAIT", "performance"}, {"PIPE_SKIP", "performance"},
|
||||
{"LIB_PREBUILD", "performance"}, {"LIB_PREBUILD_THREADS", "performance"}, {"PIPE_PREBUILD", "performance"},
|
||||
{"PREWARM_XLATE", "performance"}, {"GPL", "performance"}, {"ASTC", "performance"}, {"MEMORY", "performance"},
|
||||
{"TEX_ALIAS", "performance"}, {"TEX_VRAM_PRESSURE", "performance"}, {"LOD_GUARD", "performance"}, {"FIX_C0", "performance"}, {"FIX_ZERO", "performance"},
|
||||
{"TEX_ALIAS", "performance"}, {"TEX_VRAM_PRESSURE", "performance"}, {"ASTC_BC", "performance"}, {"LOD_GUARD", "performance"}, {"FIX_C0", "performance"}, {"FIX_ZERO", "performance"},
|
||||
{"BIND_SKIP", "performance"}, {"SHADER_MEMO", "performance"}, {"PIPE_MEMO", "performance"}, {"TEX_MEMO", "performance"}, {"DESC_TEMPLATE", "performance"},
|
||||
{"PUSH_SKIP", "performance"}, {"SPLIT_DRAWS", "performance"}, {"SPLIT_US", "performance"}, {"VK_VALIDATION", "performance"},
|
||||
{"VK_DYN_VERTEX", "performance"}, {"VK_SUBGROUP_PIN", "performance"},
|
||||
@@ -115,7 +115,7 @@ static const CfgMeta metas[] = {
|
||||
{"PIPE_PREBUILD", "1", "0|1", RESTART}, {"PREWARM_XLATE", "", "1..64", RESTART}, {"GPL", "", "0|1", RESTART},
|
||||
// textures and memory
|
||||
{"ASTC", "auto", "auto|gpu|native|cpu", RESTART}, {"MEMORY", "auto", "auto|import|mirror|verify", RESTART},
|
||||
{"TEX_ALIAS", "1", "0|1", RESTART}, {"TEX_VRAM_PRESSURE", "90", "0..100", RESTART}, {"ZSTD_NATIVE", "1", "0|1", RESTART}, {"ZSTD_CHECK", "0", "0|1", RESTART},
|
||||
{"TEX_ALIAS", "1", "0|1", RESTART}, {"TEX_VRAM_PRESSURE", "90", "0..100", RESTART}, {"ASTC_BC", "0", "0|1", RESTART}, {"ZSTD_NATIVE", "1", "0|1", RESTART}, {"ZSTD_CHECK", "0", "0|1", RESTART},
|
||||
// render fixes
|
||||
{"LOD_GUARD", "1", "0|1", RESTART}, {"FIX_C0", "1", "0|1", RESTART}, {"FIX_ZERO", "1", "0|1", RESTART},
|
||||
{"BIND_SKIP", "1", "0|1", RESTART}, {"SHADER_MEMO", "1", "0|1", RESTART}, {"PIPE_MEMO", "1", "0|1", RESTART}, {"TEX_MEMO", "1", "0|1", RESTART},
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
// RGBA8 texels to BC3 blocks on the GPU, one invocation per 4x4 block: the second pass of the ASTC decode when
|
||||
// TOTK_ASTC_BC is on (vk_astc.c), so a decoded ASTC texture takes 8 bits per texel in video memory instead of 32.
|
||||
// Texels past the right or bottom edge repeat the last column or row.
|
||||
//
|
||||
// Colour: the BC1 four-colour block of the box around the block's colours, its diagonal turned to the sign of the
|
||||
// colours' covariance and inset by 1/16 of the range (the bounding-box method of stb_dxt and of yuzu's BC1 recompression),
|
||||
// then each texel takes the nearest of the four palette entries along that axis. Alpha: the eight-value BC3 alpha
|
||||
// block between the block's smallest and largest alpha. The bytes are what the texels hold, so an sRGB image keeps
|
||||
// sRGB-encoded values, as BC3_SRGB expects.
|
||||
// Compiled to runtime/bc3_encode_spv.h by tools/build_shaders.py; vk_astc.c records the dispatch.
|
||||
#version 450
|
||||
|
||||
layout(local_size_x = 8, local_size_y = 8, local_size_z = 1) in;
|
||||
|
||||
layout(std430, set = 0, binding = 0) readonly buffer Texels { uint px[]; };
|
||||
layout(std430, set = 0, binding = 1) writeonly buffer Blocks { uvec4 blk[]; };
|
||||
|
||||
layout(push_constant) uniform Params {
|
||||
uint in_base; // first texel of slice 0 (index into px)
|
||||
uint out_base; // first block of slice 0 (uvec4 index into blk)
|
||||
uint width, height;
|
||||
uint bx; // blocks per row
|
||||
uint bslice; // blocks per slice
|
||||
} pc;
|
||||
|
||||
vec4 texel(uint x, uint y, uint z) {
|
||||
x = min(x, pc.width - 1u), y = min(y, pc.height - 1u);
|
||||
return unpackUnorm4x8(px[pc.in_base + (z * pc.height + y) * pc.width + x]) * 255.0;
|
||||
}
|
||||
|
||||
uint to565(vec3 c) {
|
||||
uvec3 q = uvec3(round(clamp(c, 0.0, 255.0) * vec3(31.0, 63.0, 31.0) / 255.0));
|
||||
return q.r << 11 | q.g << 5 | q.b;
|
||||
}
|
||||
|
||||
vec3 from565(uint v) {
|
||||
return vec3(float(v >> 11 & 31u) * 255.0 / 31.0, float(v >> 5 & 63u) * 255.0 / 63.0, float(v & 31u) * 255.0 / 31.0);
|
||||
}
|
||||
|
||||
void main() {
|
||||
uvec3 id = gl_GlobalInvocationID;
|
||||
uint by = (pc.height + 3u) / 4u;
|
||||
if (id.x >= pc.bx || id.y >= by) return;
|
||||
vec4 t[16];
|
||||
vec4 lo = vec4(255.0), hi = vec4(0.0), mean = vec4(0.0);
|
||||
for (uint i = 0u; i < 16u; i++) {
|
||||
t[i] = texel(id.x * 4u + (i & 3u), id.y * 4u + (i >> 2), id.z);
|
||||
lo = min(lo, t[i]), hi = max(hi, t[i]), mean += t[i];
|
||||
}
|
||||
mean /= 16.0;
|
||||
|
||||
// alpha: a0 > a1 selects the eight-value mode; index 0 is a0, 1 is a1, 2..7 the six steps from a0 to a1
|
||||
uint a0 = uint(hi.a), a1 = uint(lo.a);
|
||||
uvec2 ab = uvec2(a0 | a1 << 8, 0u);
|
||||
if (a0 > a1) {
|
||||
float range = float(a0 - a1);
|
||||
for (uint i = 0u; i < 16u; i++) {
|
||||
uint s = uint(clamp(round((float(a0) - t[i].a) * 7.0 / range), 0.0, 7.0)); // 0 = a0 .. 7 = a1
|
||||
uint code = s == 0u ? 0u : s == 7u ? 1u : s + 1u;
|
||||
uint bit = 16u + 3u * i;
|
||||
if (bit < 32u) ab.x |= code << bit;
|
||||
if (bit + 3u > 32u) ab.y |= code >> (32u - min(bit, 32u)) << (bit > 32u ? bit - 32u : 0u);
|
||||
}
|
||||
}
|
||||
|
||||
// colour: the box diagonal along the covariance of red and blue with green
|
||||
vec3 cmin = lo.rgb, cmax = hi.rgb;
|
||||
float crg = 0.0, cbg = 0.0;
|
||||
for (uint i = 0u; i < 16u; i++) {
|
||||
vec3 d = t[i].rgb - mean.rgb;
|
||||
crg += d.r * d.g, cbg += d.b * d.g;
|
||||
}
|
||||
if (crg < 0.0) { float s = cmin.r; cmin.r = cmax.r; cmax.r = s; }
|
||||
if (cbg < 0.0) { float s = cmin.b; cmin.b = cmax.b; cmax.b = s; }
|
||||
vec3 inset = (cmax - cmin) / 16.0;
|
||||
uint c0 = to565(cmax - inset), c1 = to565(cmin + inset);
|
||||
uint idx = 0u;
|
||||
if (c0 != c1) {
|
||||
if (c0 < c1) { uint s = c0; c0 = c1; c1 = s; } // c0 > c1: the four-colour mode
|
||||
vec3 e0 = from565(c0), e1 = from565(c1), axis = e1 - e0;
|
||||
float len2 = max(dot(axis, axis), 1e-6);
|
||||
for (uint i = 0u; i < 16u; i++) {
|
||||
uint s = uint(clamp(round(dot(t[i].rgb - e0, axis) / len2 * 3.0), 0.0, 3.0)); // 0 = e0 .. 3 = e1
|
||||
uint code = s == 0u ? 0u : s == 3u ? 1u : s + 1u; // palette order e0, e1, 2/3 e0 + 1/3 e1, 1/3 e0 + 2/3 e1
|
||||
idx |= code << (2u * i);
|
||||
}
|
||||
}
|
||||
blk[pc.out_base + id.z * pc.bslice + id.y * pc.bx + id.x] = uvec4(ab.x, ab.y, c0 | c1 << 16, idx);
|
||||
}
|
||||
@@ -54,6 +54,7 @@ typedef struct TexVkFormat {
|
||||
uint8_t astc_bw, astc_bh; // nonzero: ASTC decoded into vk (RGBA8, same colour space) by vk_astc.c or tex_astc.c;
|
||||
// zero for native ASTC (vk == ideal, raw blocks as for BC)
|
||||
uint8_t astc_srgb;
|
||||
uint8_t astc_bc; // ASTC decoded and then encoded to BC3 (vk BC3, TOTK_ASTC_BC; vk_astc.c)
|
||||
uint8_t depth, stencil; // aspect flags of depth / stencil formats
|
||||
const char *note; // why a fallback or an expansion was chosen; NULL when the mapping is direct
|
||||
const char *reason; // unmapped formats only: why there is no Vulkan format
|
||||
|
||||
@@ -671,6 +671,7 @@ static void tab_advanced(float scale) {
|
||||
opt_choice("TOTK_MEMORY", UI_MENU_MEMORY, mem, 4, UI_MENU_MEMORY_DESC);
|
||||
opt_toggle("TOTK_TEX_ALIAS", UI_MENU_TEX_ALIAS, UI_MENU_TEX_ALIAS_DESC);
|
||||
opt_slider("TOTK_TEX_VRAM_PRESSURE", UI_MENU_TEX_VRAM_PRESSURE, 0, 100, UI_MENU_TEX_VRAM_PRESSURE_DESC, 1, "%.0f%%");
|
||||
opt_toggle("TOTK_ASTC_BC", UI_MENU_ASTC_BC, UI_MENU_ASTC_BC_DESC);
|
||||
|
||||
opt_group(UI_MENU_GROUP_FIXES);
|
||||
opt_toggle("TOTK_LOD_GUARD", UI_MENU_LOD_GUARD, UI_MENU_LOD_GUARD_DESC);
|
||||
|
||||
@@ -187,6 +187,7 @@ static const char *const text_en[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_MEMORY_VERIFY] = "Verify",
|
||||
[UI_MENU_TEX_ALIAS] = "Texture aliasing", [UI_MENU_TEX_ALIAS_DESC] = "A new texture created over a live texture's memory starts with that content instead of empty.",
|
||||
[UI_MENU_TEX_VRAM_PRESSURE] = "Texture memory limit", [UI_MENU_TEX_VRAM_PRESSURE_DESC] = "Percent of video memory above which textures the game released are dropped (they come back from storage when used again). 0 keeps them.",
|
||||
[UI_MENU_ASTC_BC] = "Compress ASTC to BC3", [UI_MENU_ASTC_BC_DESC] = "With the GPU decoder: re-encodes decoded ASTC textures to BC3, a quarter of the video memory. For GPUs with 4 GB or less; textures look slightly blockier.",
|
||||
[UI_MENU_LOD_GUARD] = "LOD guard", [UI_MENU_LOD_GUARD_DESC] = "Prevents objects flashing in the wrong place or a flat far field for a frame, by waiting for the game to finish rewriting level-of-detail data before the GPU reads it.",
|
||||
[UI_MENU_FIX_C0] = "Constant buffer fix",
|
||||
[UI_MENU_FIX_C0_DESC] = "Fills the driver-reserved constant bank c0 (storage sizes, dispatch size, point size, base instance) instead of reading zeros.",
|
||||
@@ -411,6 +412,7 @@ static const char *const text_ru[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_MEMORY_VERIFY] = "Проверка",
|
||||
[UI_MENU_TEX_ALIAS] = "Наследование содержимого текстур", [UI_MENU_TEX_ALIAS_DESC] = "Новая текстура поверх памяти живой текстуры получает её содержимое, а не пустую.",
|
||||
[UI_MENU_TEX_VRAM_PRESSURE] = "Предел памяти текстур", [UI_MENU_TEX_VRAM_PRESSURE_DESC] = "Процент видеопамяти, выше которого освобождённые игрой текстуры удаляются (при повторном использовании загружаются снова). 0 — не удалять.",
|
||||
[UI_MENU_ASTC_BC] = "Сжатие ASTC в BC3", [UI_MENU_ASTC_BC_DESC] = "С декодером на GPU: декодированные текстуры ASTC пересжимаются в BC3 и занимают вчетверо меньше видеопамяти. Для видеокарт с 4 ГБ и меньше; текстуры чуть более блочные.",
|
||||
[UI_MENU_LOD_GUARD] = "Защита LOD", [UI_MENU_LOD_GUARD_DESC] = "Не даёт объектам мелькать не на своём месте, а дальнему плану — на кадр становиться плоским: ждёт, пока игра допишет данные уровней детализации, и только потом их читает GPU.",
|
||||
[UI_MENU_FIX_C0] = "Исправление константного буфера",
|
||||
[UI_MENU_FIX_C0_DESC] = "Заполняет зарезервированный драйвером банк констант c0 (размеры хранилищ, размер запуска, размер точки, базовый экземпляр) вместо чтения нулей.",
|
||||
|
||||
@@ -120,6 +120,7 @@ typedef enum {
|
||||
UI_MENU_MEMORY_VERIFY,
|
||||
UI_MENU_TEX_ALIAS, UI_MENU_TEX_ALIAS_DESC,
|
||||
UI_MENU_TEX_VRAM_PRESSURE, UI_MENU_TEX_VRAM_PRESSURE_DESC,
|
||||
UI_MENU_ASTC_BC, UI_MENU_ASTC_BC_DESC,
|
||||
UI_MENU_LOD_GUARD, UI_MENU_LOD_GUARD_DESC,
|
||||
UI_MENU_FIX_C0, UI_MENU_FIX_C0_DESC,
|
||||
UI_MENU_FIX_ZERO, UI_MENU_FIX_ZERO_DESC,
|
||||
|
||||
+3
-1
@@ -242,6 +242,7 @@ enum { VK_ASTC_CPU, VK_ASTC_GPU, VK_ASTC_NATIVE, VK_ASTC_CHECK };
|
||||
int vk_astc_mode(void); // decided once per device (logged); VK_ASTC_CPU before vk_init
|
||||
int vk_astc_native(VkFormat astc_fmt); // 1: images of this ASTC format are created as such and get the raw blocks
|
||||
int vk_astc_gpu(void); // 1: ASTC images decoded to RGBA8 by the compute decoder (vk_astc_record)
|
||||
int vk_astc_bc(void); // 1: those images are BC3 instead, encoded after the decode (TOTK_ASTC_BC=1)
|
||||
// One image region decoded from raw blocks: tight rows of 16-byte blocks at byte src of the source buffer (slices one
|
||||
// after the other), w x h texels and slices deep, written at offset of level / layer.
|
||||
typedef struct { VkDeviceSize src; uint32_t w, h, slices, level, layer; VkOffset3D offset; } VkAstcRegion;
|
||||
@@ -249,9 +250,10 @@ typedef struct { VkDeviceSize src; uint32_t w, h, slices, level, layer; VkOffset
|
||||
// bytes of blocks) goes to a device-local scratch buffer, a dispatch per region decodes it, and the texels are copied
|
||||
// into img (VK_IMAGE_LAYOUT_GENERAL). The caller records its usual barriers around an image copy before and after the
|
||||
// call. readback (optional, host-visible, TRANSFER_DST): also gets the decoded texels, the regions one after the other.
|
||||
// bc: img is BC3 (TexVkFormat.astc_bc); the texels are encoded to BC3 blocks before the copy, and readback is ignored.
|
||||
// 0 when the decoder is unavailable or the scratch buffer cannot be allocated (nothing recorded).
|
||||
int vk_astc_record(VkCommandBuffer cb, VkBuffer src, VkDeviceSize src_size, const VkAstcRegion *rg, int n, uint32_t bw,
|
||||
uint32_t bh, int srgb, VkImage img, VkImageAspectFlags aspect, VkBuffer readback);
|
||||
uint32_t bh, int srgb, int bc, VkImage img, VkImageAspectFlags aspect, VkBuffer readback);
|
||||
void vk_astc_stats(uint64_t *dispatches, uint64_t *texels); // since start
|
||||
// TOTK_ASTC_TIME=1: GPU timestamps around each vk_astc_record's dispatches (logged per footprint and the largest one)
|
||||
void vk_astc_time_enable(int on);
|
||||
|
||||
+100
-11
@@ -1,6 +1,10 @@
|
||||
// ASTC textures on the GPU: the TOTK_ASTC knob, a compute decoder that turns raw blocks into the RGBA8 image the CPU
|
||||
// decoder (tex_astc.c) would have written, and the native ASTC formats where the device samples them itself.
|
||||
//
|
||||
// TOTK_ASTC_BC = 1 (gpu mode only, default 0): a second pass (runtime/shaders/bc3_encode.comp) encodes the decoded
|
||||
// texels to BC3 and the image is BC3, 8 bits per texel instead of 32. For GPUs with little video memory, at the cost of
|
||||
// BC3's quality: textures look slightly blockier, and data textures (normal maps) lose some precision.
|
||||
//
|
||||
// TOTK_ASTC = auto (default): native when the device reports textureCompressionASTC_LDR and the format's features,
|
||||
// else gpu. gpu: compute decode into RGBA8 (runtime/shaders/astc_decode.comp). native: like auto, but logs when the
|
||||
// device cannot. cpu: astc_decode_ldr_mt on the uploading thread, as before. check: gpu, and every upload is also
|
||||
@@ -17,6 +21,7 @@
|
||||
#include <windows.h>
|
||||
|
||||
#include "astc_decode_spv.h"
|
||||
#include "bc3_encode_spv.h"
|
||||
#include "cfg.h"
|
||||
#include "host.h"
|
||||
#include "tex.h"
|
||||
@@ -99,6 +104,8 @@ static struct {
|
||||
VkDescriptorSetLayout dsl;
|
||||
VkPipelineLayout layout;
|
||||
VkPipeline pipe;
|
||||
VkPipeline bc_pipe; // the BC3 encoder (TOTK_ASTC_BC): the decoder's layout, bindings 0 and 1
|
||||
int bc; // 1: ASTC images are BC3 (vk_astc_bc)
|
||||
PFN_vkCmdPushDescriptorSetKHR push;
|
||||
VkBuffer tab; // device-local copy of the tables
|
||||
VmaAllocation tab_alloc;
|
||||
@@ -293,6 +300,36 @@ static int create_pipeline(VkCtx *c) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
// TOTK_ASTC_BC=1: the BC3 encoder, when the device samples BC3 (every desktop GPU does); 0 leaves ASTC as RGBA8.
|
||||
static int create_bc_pipeline(VkCtx *c) {
|
||||
const char *e = cfg_get("TOTK_ASTC_BC");
|
||||
if (!e || !*e || *e == '0') return 0;
|
||||
VkFormatProperties p;
|
||||
vkGetPhysicalDeviceFormatProperties(c->phys, VK_FORMAT_BC3_SRGB_BLOCK, &p);
|
||||
VkFormatFeatureFlags need = VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT | VK_FORMAT_FEATURE_TRANSFER_DST_BIT;
|
||||
if ((p.optimalTilingFeatures & need) != need) {
|
||||
rt_log("vk: TOTK_ASTC_BC: the device does not sample BC3; ASTC stays RGBA8");
|
||||
return 0;
|
||||
}
|
||||
VkShaderModuleCreateInfo mi = {.sType = VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO, .codeSize = sizeof bc3_encode_spv,
|
||||
.pCode = bc3_encode_spv};
|
||||
VkShaderModule m = VK_NULL_HANDLE;
|
||||
if (vkCreateShaderModule(c->device, &mi, NULL, &m) != VK_SUCCESS) return 0;
|
||||
VkComputePipelineCreateInfo ci = {.sType = VK_STRUCTURE_TYPE_COMPUTE_PIPELINE_CREATE_INFO,
|
||||
.stage = {.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO,
|
||||
.stage = VK_SHADER_STAGE_COMPUTE_BIT, .module = m, .pName = "main"},
|
||||
.layout = G.layout};
|
||||
VkResult r = vkCreateComputePipelines(c->device, VK_NULL_HANDLE, 1, &ci, NULL, &G.bc_pipe);
|
||||
vkDestroyShaderModule(c->device, m, NULL);
|
||||
if (r != VK_SUCCESS) {
|
||||
G.bc_pipe = VK_NULL_HANDLE;
|
||||
rt_log("vk: TOTK_ASTC_BC: the BC3 encoder pipeline failed (%d); ASTC stays RGBA8", (int)r);
|
||||
return 0;
|
||||
}
|
||||
rt_log("vk: ASTC textures are encoded to BC3 after the decode (TOTK_ASTC_BC)");
|
||||
return 1;
|
||||
}
|
||||
|
||||
static int native_device(VkCtx *c) { return c->has_astc_ldr; }
|
||||
|
||||
static const char *mode_name(int m) {
|
||||
@@ -324,6 +361,7 @@ int vk_astc_mode(void) {
|
||||
rt_log("vk: ASTC compute decoder unavailable on %s: ASTC decodes on the CPU", c->props.deviceName);
|
||||
}
|
||||
if (G.failed && m != VK_ASTC_NATIVE) m = VK_ASTC_CPU;
|
||||
G.bc = m == VK_ASTC_GPU && G.pipe && create_bc_pipeline(c);
|
||||
G.mode = m;
|
||||
rt_log("vk: ASTC textures: %s (textureCompressionASTC_LDR %d)", mode_name(m), native_device(c));
|
||||
}
|
||||
@@ -352,6 +390,15 @@ int vk_astc_gpu(void) {
|
||||
return ok;
|
||||
}
|
||||
|
||||
int vk_astc_bc(void) {
|
||||
VkCtx *c = vk_ctx();
|
||||
if (!c || vk_astc_mode() != VK_ASTC_GPU) return 0;
|
||||
AcquireSRWLockShared(&g_lock);
|
||||
int on = G.dev == c->device && G.bc;
|
||||
ReleaseSRWLockShared(&g_lock);
|
||||
return on;
|
||||
}
|
||||
|
||||
static void mem_barrier(VkCommandBuffer cb, VkPipelineStageFlags2 src, VkAccessFlags2 sa, VkPipelineStageFlags2 dst,
|
||||
VkAccessFlags2 da) {
|
||||
VkMemoryBarrier2 mb = {.sType = VK_STRUCTURE_TYPE_MEMORY_BARRIER_2, .srcStageMask = src, .srcAccessMask = sa,
|
||||
@@ -368,30 +415,47 @@ static VkDeviceSize region_out(const VkAstcRegion *r) { return (VkDeviceSize)r->
|
||||
static VkDeviceSize region_in(const VkAstcRegion *r, uint32_t bw, uint32_t bh) {
|
||||
return (VkDeviceSize)((r->w + bw - 1) / bw) * ((r->h + bh - 1) / bh) * r->slices * 16;
|
||||
}
|
||||
static VkDeviceSize region_bc(const VkAstcRegion *r) { return region_in(r, 4, 4); } // BC3: 16 bytes per 4x4 block
|
||||
|
||||
typedef struct { uint32_t in_base, out_base, width, height, bx, bslice; } BcPush; // bc3_encode.comp Params
|
||||
|
||||
int vk_astc_record(VkCommandBuffer cb, VkBuffer src, VkDeviceSize src_size, const VkAstcRegion *rg, int n, uint32_t bw,
|
||||
uint32_t bh, int srgb, VkImage img, VkImageAspectFlags aspect, VkBuffer readback) {
|
||||
static volatile long n_fail;
|
||||
uint32_t bh, int srgb, int bc, VkImage img, VkImageAspectFlags aspect, VkBuffer readback) {
|
||||
static volatile long n_fail, n_unaligned;
|
||||
(void)src_size;
|
||||
VkCtx *c = vk_ctx();
|
||||
if (!c || !vk_astc_gpu() || bw < 4 || bh < 4 || bw > 12 || bh > 12) return 0;
|
||||
AcquireSRWLockShared(&g_lock);
|
||||
VkPipeline pipe = G.dev == c->device ? G.pipe : VK_NULL_HANDLE;
|
||||
VkPipeline pipe = G.dev == c->device ? G.pipe : VK_NULL_HANDLE, bc_pipe = G.dev == c->device ? G.bc_pipe : VK_NULL_HANDLE;
|
||||
ReleaseSRWLockShared(&g_lock);
|
||||
if (!pipe) return 0;
|
||||
// chunks of consecutive regions; scratch = the largest chunk's blocks, then its texels
|
||||
VkDeviceSize out_total = 0, cap_in = 0, cap_out = 0, ci = 0, co = 0;
|
||||
if (!pipe || (bc && !bc_pipe)) return 0;
|
||||
if (bc) {
|
||||
readback = VK_NULL_HANDLE;
|
||||
for (int i = 0; i < n; i++) // a BC copy starts on a block corner; a WriteTexels region of a 5x5 or 6x6 footprint may not
|
||||
if ((rg[i].offset.x & 3) || (rg[i].offset.y & 3)) {
|
||||
if (InterlockedIncrement(&n_unaligned) <= 16)
|
||||
rt_log("vk: ASTC to BC3: region at %d,%d is not on a 4x4 block corner: texture left as it was",
|
||||
rg[i].offset.x, rg[i].offset.y);
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
// chunks of consecutive regions; scratch = the largest chunk's blocks, then its texels, then (bc) its BC3 blocks
|
||||
VkDeviceSize out_total = 0, cap_in = 0, cap_out = 0, cap_bc = 0, ci = 0, co = 0, cb3 = 0;
|
||||
for (int i = 0; i < n; i++) {
|
||||
VkDeviceSize o = region_out(&rg[i]), b = region_in(&rg[i], bw, bh);
|
||||
if (co && co + o > CHUNK_OUT) ci = co = 0;
|
||||
ci += b, co += o, out_total += o;
|
||||
if (co && co + o > CHUNK_OUT) ci = co = cb3 = 0;
|
||||
ci += b, co += o, cb3 += region_bc(&rg[i]), out_total += o;
|
||||
if (ci > cap_in) cap_in = ci;
|
||||
if (co > cap_out) cap_out = co;
|
||||
if (cb3 > cap_bc) cap_bc = cb3;
|
||||
}
|
||||
if (!out_total) return 1;
|
||||
VkDeviceSize al = c->props.limits.minStorageBufferOffsetAlignment; // the texels bind at cap_in
|
||||
if (al > 1) cap_in = (cap_in + al - 1) / al * al;
|
||||
VkBufferCreateInfo bi = {.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .size = cap_in + cap_out,
|
||||
VkDeviceSize al = c->props.limits.minStorageBufferOffsetAlignment; // the texels bind at cap_in, the BC3 blocks after them
|
||||
if (al < 16) al = 16;
|
||||
cap_in = (cap_in + al - 1) / al * al;
|
||||
cap_out = (cap_out + al - 1) / al * al;
|
||||
if (!bc) cap_bc = 0;
|
||||
VkBufferCreateInfo bi = {.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .size = cap_in + cap_out + cap_bc,
|
||||
.usage = VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_SRC_BIT |
|
||||
VK_BUFFER_USAGE_TRANSFER_DST_BIT};
|
||||
VmaAllocationCreateInfo aci = {.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE};
|
||||
@@ -485,6 +549,30 @@ int vk_astc_record(VkCommandBuffer cb, VkBuffer src, VkDeviceSize src_size, cons
|
||||
}
|
||||
if (slot >= 0)
|
||||
vkCmdWriteTimestamp2(cb, VK_PIPELINE_STAGE_2_ALL_COMMANDS_BIT, tpool, 2 * (uint32_t)slot + 1);
|
||||
if (bc) { // the chunk's texels to BC3 blocks behind them; the image copy then takes the blocks
|
||||
mem_barrier(cb, VK_PIPELINE_STAGE_2_COMPUTE_SHADER_BIT, VK_ACCESS_2_SHADER_STORAGE_WRITE_BIT,
|
||||
VK_PIPELINE_STAGE_2_COMPUTE_SHADER_BIT, VK_ACCESS_2_SHADER_STORAGE_READ_BIT);
|
||||
VkDescriptorBufferInfo bdi[2] = {{sb, cap_in, cap_out}, {sb, cap_in + cap_out, cap_bc}};
|
||||
VkWriteDescriptorSet bw2[2];
|
||||
for (int k = 0; k < 2; k++)
|
||||
bw2[k] = (VkWriteDescriptorSet){.sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET, .dstBinding = (uint32_t)k,
|
||||
.descriptorCount = 1, .descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
|
||||
.pBufferInfo = &bdi[k]};
|
||||
vkCmdBindPipeline(cb, VK_PIPELINE_BIND_POINT_COMPUTE, bc_pipe);
|
||||
rec_push(G.push, cb, VK_PIPELINE_BIND_POINT_COMPUTE, G.layout, 0, 2, bw2);
|
||||
VkDeviceSize to = 0, bo = 0;
|
||||
for (int i = i0; i < i1; i++) {
|
||||
const VkAstcRegion *r = &rg[i];
|
||||
uint32_t bx4 = (r->w + 3) / 4, by4 = (r->h + 3) / 4;
|
||||
BcPush pc = {.in_base = (uint32_t)(to / 4), .out_base = (uint32_t)(bo / 16), .width = r->w, .height = r->h,
|
||||
.bx = bx4, .bslice = bx4 * by4};
|
||||
vkCmdPushConstants(cb, G.layout, VK_SHADER_STAGE_COMPUTE_BIT, 0, sizeof pc, &pc);
|
||||
vkCmdDispatch(cb, (bx4 + 7) / 8, (by4 + 7) / 8, r->slices);
|
||||
VkBufferImageCopy *cp = &copies[i - i0];
|
||||
cp->bufferOffset = cap_in + cap_out + bo, cp->bufferRowLength = bx4 * 4, cp->bufferImageHeight = by4 * 4;
|
||||
to += region_out(r), bo += region_bc(r);
|
||||
}
|
||||
}
|
||||
mem_barrier(cb, VK_PIPELINE_STAGE_2_COMPUTE_SHADER_BIT, VK_ACCESS_2_SHADER_STORAGE_WRITE_BIT,
|
||||
VK_PIPELINE_STAGE_2_COPY_BIT, VK_ACCESS_2_TRANSFER_READ_BIT);
|
||||
vkCmdCopyBufferToImage(cb, sb, img, VK_IMAGE_LAYOUT_GENERAL, (uint32_t)(i1 - i0), copies);
|
||||
@@ -525,6 +613,7 @@ void vk_astc_release(void) {
|
||||
AcquireSRWLockExclusive(&g_lock);
|
||||
if (c && G.dev == c->device) {
|
||||
if (G.pipe) vkDestroyPipeline(c->device, G.pipe, NULL);
|
||||
if (G.bc_pipe) vkDestroyPipeline(c->device, G.bc_pipe, NULL);
|
||||
if (G.layout) vkDestroyPipelineLayout(c->device, G.layout, NULL);
|
||||
if (G.dsl) vkDestroyDescriptorSetLayout(c->device, G.dsl, NULL);
|
||||
if (G.tab) vmaDestroyBuffer(c->vma, G.tab, G.tab_alloc);
|
||||
|
||||
@@ -126,6 +126,11 @@ int tex_vk_format(int nvn_format, TexVkFormat *o) {
|
||||
o->astc_bh = astc[i].bh;
|
||||
o->astc_srgb = (uint8_t)srgb;
|
||||
o->note = "no native ASTC: decoded to RGBA8 (vk_astc.c compute decoder, or tex_astc.c with TOTK_ASTC=cpu)";
|
||||
if (vk_astc_bc()) {
|
||||
o->vk = srgb ? VK_FORMAT_BC3_SRGB_BLOCK : VK_FORMAT_BC3_UNORM_BLOCK;
|
||||
o->astc_bc = 1;
|
||||
o->note = "no native ASTC: decoded and encoded to BC3 on the GPU (vk_astc.c, TOTK_ASTC_BC)";
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
if ((f >= 0x51 && f <= 0x68) || f == 0x6B || f == 0x6C) {
|
||||
|
||||
@@ -657,7 +657,7 @@ static void upload(Tex *e) {
|
||||
int checked = 0;
|
||||
if (agpu) {
|
||||
uint64_t a0 = perf_begin();
|
||||
checked = vk_astc_record(cb, sb, total, ar, (int)n, e->f.astc_bw, e->f.astc_bh, e->f.astc_srgb, e->pub.image,
|
||||
checked = vk_astc_record(cb, sb, total, ar, (int)n, e->f.astc_bw, e->f.astc_bh, e->f.astc_srgb, e->f.astc_bc, e->pub.image,
|
||||
e->pub.aspect, rbuf);
|
||||
perf_end(PERF_ASTC, a0);
|
||||
if (!checked)
|
||||
@@ -741,6 +741,7 @@ static void make_fresh_snap(Tex *e) {
|
||||
// Bytes per block and block size of the image's VkFormat (ASTC decodes to RGBA8, RGB expands to RGBA); 0 when the
|
||||
// VkFormat substitutes another one of unknown size.
|
||||
static int img_block(const Tex *e, int *bw, int *bh) {
|
||||
if (e->f.astc_bc) { *bw = *bh = 4; return 16; }
|
||||
if (e->f.astc_bw) { *bw = *bh = 1; return 4; }
|
||||
int b = nvn_fmt_bpb(e->t.d.format, bw, bh);
|
||||
if (e->f.expand_rgb) { *bw = *bh = 1; return b / 3 * 4; }
|
||||
@@ -1221,7 +1222,7 @@ static int image_texels(Tex *e, const Region *g, const NVNcopyRegion *r, uint8_t
|
||||
ar[z] = (VkAstcRegion){.src = slice * (size_t)z, .w = w, .h = h, .slices = 1, .level = rg[z].imageSubresource.mipLevel,
|
||||
.layer = rg[z].imageSubresource.baseArrayLayer, .offset = rg[z].imageOffset};
|
||||
uint64_t a0 = perf_begin();
|
||||
done = vk_astc_record(cb, sb, slice * (size_t)g->nz, ar, g->nz, e->f.astc_bw, e->f.astc_bh, e->f.astc_srgb,
|
||||
done = vk_astc_record(cb, sb, slice * (size_t)g->nz, ar, g->nz, e->f.astc_bw, e->f.astc_bh, e->f.astc_srgb, e->f.astc_bc,
|
||||
e->pub.image, aspect, VK_NULL_HANDLE);
|
||||
perf_end(PERF_ASTC, a0);
|
||||
free(ar);
|
||||
|
||||
Reference in new issue
Block a user