mirror of
https://github.com/valentderah/totk-pc-recomp.git
synced 2026-11-20 12:45:57 +00:00
Read the gradients of a TXD per coordinate so terrain picks the right mip level
TotK's terrain shaders fill the gradient registers of a texture-with-derivatives instruction per coordinate (du/dx, du/dy, dv/dx, dv/dy), while the translator takes the first two registers as dPdx and the last two as dPdy. The mip level then came from the wrong derivatives and was too sharp on terrain faces turned across the screen, so patches that followed the faces crawled when the camera moved. After a shader loads, every two-dimensional gradient pair has its inner components swapped by two new composite constructs, so the shader cache is untouched. TOTK_TXD_TRANSPOSE=0 turns it off. The finding is row 2.13 of docs/maxwell.md.
This commit is contained in:
1 parent
6c2595275d
commit
984c9bc7c3
3 files changed
+64
-1
No files matched your search
@@ -68,6 +68,7 @@ Source shorthands:
|
||||
| 2.9 | **LOD**: TSC min/max LOD clamp, LOD bias, `TWO_D_NO_MIPMAP` texture type, a min filter without mips stays on the base level; TIC carries its own max anisotropy and aniso quality fields. | `minLod`/`maxLod`, `mipLodBias` limited by `maxSamplerLodBias`. | yuzu: anisotropy heuristics for mods forcing trilinear (YZ-2306, PR 10744). Ours: non-mip filter → `maxLod = minLod + 0.25`, bias clamped (`vk_texture.c` `make_sampler`). | G80TEX |
|
||||
| 2.10 | **Texture gather rounding**: Maxwell sub-texel precision differs from AMD/Intel; edge texels picked by TLD4 differ by one. | Implementation-defined `subTexelPrecisionBits`. | yuzu adds a sub-pixel offset to gathers on non-NVIDIA hosts: fixed BotW shadow artifacts at object edges ("shader_recompiler: Add subpixel offset for correct rounding at ImageGather", <https://git.openpunk.com/OpenPunk/yuzu/src/commit/780240e6979b198e7bd10feaad5399b8b4b63762>, title only). Ours: the translator biases gather coordinates by the host's `subTexelPrecisionBits` on every non-NVIDIA GPU (`vk_caps.c` → job `gather_bias` → Ryujinx `TexturePass.InsertCoordGatherBias`); TotK on RADV drew dashed dark lines along wall and floor edges in the prologue caves without it. `TOTK_GATHER_BIAS=0` turns it off. | — |
|
||||
| 2.11 | **Gather offsets**: `TLD4.PTP` takes four per-texel offsets, possibly from registers. | `ConstOffsets` must be constant. | Ours: `QueryHostSupportsNonConstantTextureOffset() => false` makes Ryujinx emulate register offsets (`tools/xlate/Program.cs`). | RYU-SH `Translation/Optimizations` (TexturePass) |
|
||||
| 2.13 | **TXD gradient register order**: TotK's terrain shaders fill the gradient registers of a `TXD` per coordinate (du/dx, du/dy, dv/dx, dv/dy). | Vulkan's `Grad` takes dPdx (du/dx, dv/dx) and dPdy (du/dy, dv/dy). | Ryujinx's `EmitTxd` takes the first two registers as dPdx and the last two as dPdy, so the mip level came from the wrong derivatives and was too sharp on terrain faces turned across the screen: patches that followed the faces crawled when the camera moved (1.4.3, the Depths; found by the user from their F9 frame, a gradient sample's coordinate and gradients traced back to `DPdx` and `DPdy` of the interpolants). Ours: `gfx_shader.c` `patch_txd_transpose` swaps the two inner components of every two-component gradient pair in the loaded SPIR-V (the shader cache is untouched). `TOTK_TXD_TRANSPOSE=0` turns it off. Only 2D gradients are handled; 3D and cube ones are left as translated. | — |
|
||||
| 2.12 | **Depth compare** (`TSC` depth compare + `TIC_4_DEPTH_TEXTURE`), min/max reduction filtering. | `compareEnable`; reduction mode needs `samplerFilterMinmax` and is not allowed with compare. | Ours: reduction dropped when compare is on (`vk_texture.c` `make_sampler`). | G80TEX |
|
||||
| 2.13 | **ASTC / BC**: native ASTC; zero ASTC block = error colour on hosts. | AMD and NVIDIA desktop GPUs lack ASTC: decode to RGBA8. yuzu offered ASTC recompression to BC1/BC3 for low VRAM (YZ-2305, PR 10398). | Ours: native upload where the device samples ASTC, else a compute-shader decode (`vk_astc.c`, `TOTK_ASTC`), CPU decode (`tex_astc.c`) as the fallback. | `runtime/vk_astc.c` |
|
||||
| 2.14 | **Linear CPU-written textures** (`FLAGS_LINEAR`, small ramps, glyph caches): CPU writes visible to the GPU directly. | Must re-upload or use linear images over host memory. | NXN Mario: sky black without its 64×1 RGBA16F ramps. | NXN |
|
||||
|
||||
+1
-1
@@ -53,7 +53,7 @@ static const char *const known[] = {
|
||||
"SHADER_MEMO", "SHADOW_RANGE", "SHADOW_RES", "SHADOW_SCALE", "SHARED_FONTS", "SHARPNESS", "SHOTS", "SHOTS_DIR",
|
||||
"SHOTS_FULL", "SPEED_PROBE", "SPIN", "SPIN_HANDOFF_US", "SPLIT_DRAWS", "SPLIT_US", "STICK_DEADZONE", "STICK_SENS",
|
||||
"SWKBD_ANSWER",
|
||||
"SWKBD_TEST", "TEST_PAD", "TEST_PREPARE_SHADERS", "TEX_ALIAS", "TEX_MEMO", "TEX_VRAM_PRESSURE", "TIMER_1MS", "TRACE", "UBO_SNAPSHOT", "UPSCALER", "VK_DYN_A2C", "VK_DYN_VERTEX", "VK_NO_FLOAT64",
|
||||
"SWKBD_TEST", "TEST_PAD", "TEST_PREPARE_SHADERS", "TEX_ALIAS", "TEX_MEMO", "TEX_VRAM_PRESSURE", "TIMER_1MS", "TRACE", "TXD_TRANSPOSE", "UBO_SNAPSHOT", "UPSCALER", "VK_DYN_A2C", "VK_DYN_VERTEX", "VK_NO_FLOAT64",
|
||||
"VK_PRESENT", "VK_RECORDER", "VK_SSBO_ALIGN", "VK_SUBGROUP", "VK_SUBGROUP_PIN", "VK_VALIDATION", "VOLUME", "VRAM_HEADROOM", "VS_OUTS",
|
||||
"WALK_KEY", "WALK_SCALE", "WB_EXACT", "WB_FENCE_LIMIT", "WINDOW_SIZE", "XLATE", "XLATE_ID", "XLATE_PROCS",
|
||||
"ZSTD_CHECK", "ZSTD_NATIVE",
|
||||
|
||||
@@ -759,6 +759,67 @@ out:
|
||||
free(loc), free(packed), free(ttype), free(tcomps), free(pointee);
|
||||
}
|
||||
|
||||
// Every gradient sample (OpImageSampleExplicitLod with Grad) whose two gradients are each built from two components gets
|
||||
// them transposed, dx = (a, c) and dy = (b, d) from dx = (a, b) and dy = (c, d), by two new OpCompositeConstruct before
|
||||
// it. TotK's shaders fill a TXD's gradient registers per coordinate (du/dx, du/dy, dv/dx, dv/dy), and the translator
|
||||
// (Ryujinx, InstEmitTexture EmitTxd) builds dx = (first two registers), dy = (last two) = (du/dx, du/dy) and
|
||||
// (dv/dx, dv/dy): a mip level chosen from the wrong derivatives, too sharp on terrain faces turned across the screen,
|
||||
// which crawled in patches that followed the faces (1.4.3, the Depths). TOTK_TXD_TRANSPOSE=0 turns it off.
|
||||
// Applied to the SPIR-V after it is loaded, so the shader cache is untouched.
|
||||
enum { OP_COMPOSITE_CONSTRUCT = 80, OP_SAMPLE_EXPLICIT = 88, IO_GRAD = 4 };
|
||||
|
||||
static void patch_txd_transpose(GfxShader *s) {
|
||||
static int on = -1;
|
||||
static volatile int32_t n_logged;
|
||||
if (on < 0) {
|
||||
const char *e = cfg_get("TOTK_TXD_TRANSPOSE");
|
||||
on = !(e && *e == '0');
|
||||
}
|
||||
uint32_t *w = s->spirv;
|
||||
uint64_t n = s->words;
|
||||
if (!on || n < 5) return;
|
||||
uint32_t bound = w[3] < (1u << 20) ? w[3] : (1u << 20);
|
||||
uint64_t *cc = calloc(bound, sizeof *cc); // word index of a 2-constituent OpCompositeConstruct defining the id
|
||||
int found = 0;
|
||||
if (!cc) return;
|
||||
for (uint64_t i = 5; i < n;) {
|
||||
uint32_t op = w[i] & 0xffff, len = w[i] >> 16;
|
||||
if (!len || i + len > n) goto out;
|
||||
if (op == OP_COMPOSITE_CONSTRUCT && len == 5 && w[i + 2] < bound) cc[w[i + 2]] = i;
|
||||
if (op == OP_SAMPLE_EXPLICIT && len >= 8 && w[i + 5] == IO_GRAD && w[i + 6] < bound && w[i + 7] < bound &&
|
||||
cc[w[i + 6]] && cc[w[i + 7]] && w[cc[w[i + 6]] + 1] == w[cc[w[i + 7]] + 1])
|
||||
found++;
|
||||
i += len;
|
||||
}
|
||||
if (!found) goto out;
|
||||
uint32_t *o = malloc((n + (uint64_t)found * 10) * sizeof *o);
|
||||
if (!o) goto out;
|
||||
uint64_t k = 0;
|
||||
uint32_t next = w[3];
|
||||
for (uint64_t i = 0; i < 5; i++) o[k++] = w[i];
|
||||
for (uint64_t i = 5; i < n;) {
|
||||
uint32_t op = w[i] & 0xffff, len = w[i] >> 16;
|
||||
if (op == OP_SAMPLE_EXPLICIT && len >= 8 && w[i + 5] == IO_GRAD && w[i + 6] < bound && w[i + 7] < bound &&
|
||||
cc[w[i + 6]] && cc[w[i + 7]] && w[cc[w[i + 6]] + 1] == w[cc[w[i + 7]] + 1]) {
|
||||
const uint32_t *dx = w + cc[w[i + 6]], *dy = w + cc[w[i + 7]]; // [hdr, type, id, a, b], [hdr, type, id, c, d]
|
||||
uint32_t ndx = next++, ndy = next++;
|
||||
o[k++] = 5u << 16 | OP_COMPOSITE_CONSTRUCT, o[k++] = dx[1], o[k++] = ndx, o[k++] = dx[3], o[k++] = dy[3];
|
||||
o[k++] = 5u << 16 | OP_COMPOSITE_CONSTRUCT, o[k++] = dx[1], o[k++] = ndy, o[k++] = dx[4], o[k++] = dy[4];
|
||||
for (uint32_t j = 0; j < len; j++) o[k++] = w[i + j];
|
||||
o[k - len + 6] = ndx, o[k - len + 7] = ndy;
|
||||
} else {
|
||||
for (uint32_t j = 0; j < len; j++) o[k++] = w[i + j];
|
||||
}
|
||||
i += len;
|
||||
}
|
||||
o[3] = next;
|
||||
free(s->spirv);
|
||||
s->spirv = o, s->words = k;
|
||||
if (plat_inc32(&n_logged) <= 4) rt_log("gfx_shader: %d gradient samples now read their derivatives per coordinate", found);
|
||||
out:
|
||||
free(cc);
|
||||
}
|
||||
|
||||
static void reflect(GfxShader *s) {
|
||||
static const char *const kinds[GFX_RES_KINDS] = {"cbufs", "sbufs", "textures", "images"};
|
||||
const char *js = s->reflection;
|
||||
@@ -771,6 +832,7 @@ static void reflect(GfxShader *s) {
|
||||
json_objects(js, kinds[k], add_res, s, k);
|
||||
}
|
||||
reflect_spirv(s);
|
||||
patch_txd_transpose(s);
|
||||
}
|
||||
|
||||
// ---- use masks (see the cache key at the top)
|
||||
|
||||
Reference in new issue
Block a user