Merge branch 'dev' into task/flushhull

This commit is contained in:
Valiantsin Dzerakh committed 2026-11-04 18:42:04 +03:00
commit be94fe0aa9
9 files changed
+100 -17

No files matched your search

+1 -1
View File
@@ -53,7 +53,7 @@ const GfxShader *gfx_shader_await(int stage, const uint8_t *control, const uint8
uint64_t gfx_shader_async_done(void); // translations finished by the background worker
void gfx_shader_counts(uint64_t *keys, uint64_t *translated); // distinct keys in memory, translations done (TOTK_TRACE=perf)
// Translator answers for this device (vk_caps.c): shaderFloat64, storage offset rounding, subgroup size per vs/fs/cs.
void gfx_shader_set_host(int float64, uint32_t sbuf_align, const uint32_t subgroup[3], uint32_t gather_bits);
void gfx_shader_set_host(int float64, uint32_t sbuf_align, const uint32_t subgroup[3], uint32_t gather_bits, int zero_locals);
const uint8_t *gfx_shader_key(const GfxShader *s); // the 32-byte cache key (stable while the translator is)
const uint8_t *gfx_shader_input_id(const GfxShader *s); // the 32-byte input id (stable across translators)
// By input id from memory or disk; xlate 1 also translates it from its stored inputs. NULL if absent.
+8 -6
View File
@@ -119,7 +119,7 @@ static struct { // translations in fl
static char cache_dir[PATH_CAP];
static char xlate_exe[PATH_CAP];
static uint8_t xlate_id[32]; // translator identity (see the keys at the top)
static int host_f64 = 1, host_set; // gfx_shader_set_host
static int host_f64 = 1, host_zero_locals, host_set; // gfx_shader_set_host
static uint32_t host_sbuf, host_sg[3] = {32, 32, 32}, host_gather;
static PlatOnce paths_once = PLAT_ONCE_INIT;
@@ -313,18 +313,19 @@ static void init_paths(void *param) {
static void paths(void) { plat_once(&paths_once, init_paths, NULL); }
// Host answers (vk_caps.c, at device creation, before any translation). Answers other than the defaults (Float64,
// exact storage offsets, 32 lanes, no gather bias) are mixed into the translator identity, so they get their own cache
// keys.
void gfx_shader_set_host(int float64, uint32_t sbuf_align, const uint32_t subgroup[3], uint32_t gather_bits) {
// exact storage offsets, 32 lanes, no gather bias, undefined locals) are mixed into the translator identity, so they
// get their own cache keys.
void gfx_shader_set_host(int float64, uint32_t sbuf_align, const uint32_t subgroup[3], uint32_t gather_bits, int zero_locals) {
paths();
if (host_set++) return;
host_f64 = float64, host_sbuf = sbuf_align, host_gather = gather_bits;
host_f64 = float64, host_sbuf = sbuf_align, host_gather = gather_bits, host_zero_locals = zero_locals;
memcpy(host_sg, subgroup, sizeof host_sg);
if (float64 && !sbuf_align && subgroup[0] == 32 && subgroup[1] == 32 && subgroup[2] == 32 && !gather_bits) return;
if (float64 && !sbuf_align && subgroup[0] == 32 && subgroup[1] == 32 && subgroup[2] == 32 && !gather_bits && !zero_locals) return;
uint8_t buf[32 + 96];
int n = snprintf((char *)buf + 32, 96, "TKHO f64=%d sbuf=%u sg=%u,%u,%u", float64, sbuf_align, subgroup[0], subgroup[1],
subgroup[2]);
if (gather_bits) n += snprintf((char *)buf + 32 + n, (size_t)(96 - n), " gather=%u", gather_bits);
if (zero_locals) n += snprintf((char *)buf + 32 + n, (size_t)(96 - n), " zero_locals");
memcpy(buf, xlate_id, 32);
rt_sha256(buf, 32 + (size_t)n, xlate_id);
rt_log("gfx_shader: host options %s: own shader cache keys", (char *)buf + 37);
@@ -1174,6 +1175,7 @@ static size_t build_request(char *o0, const char *hex, const char *stage, const
if (host_sbuf) o += sprintf(o, ",\"sbuf_align\":%u", host_sbuf);
if (host_sg[si] != 32) o += sprintf(o, ",\"subgroup\":%u", host_sg[si]);
if (host_gather) o += sprintf(o, ",\"gather_bias\":%u", host_gather);
if (host_zero_locals) o += sprintf(o, ",\"zero_locals\":true");
o += sprintf(o, "},\"out\":\"");
json_esc(&o, cache_dir);
o += sprintf(o, "\"}");
+2 -1
View File
@@ -57,9 +57,10 @@ typedef struct {
int gpl; // VK_EXT_graphics_pipeline_library enabled with fast linking (TOTK_GPL=0: off)
int amd; // an AMD GPU (vendor 0x1002), any driver
int amd_sc; // AMD's Windows driver branch for RDNA 1 and 2 ("AMD proprietary shader compiler")
int mesa; // a Mesa driver the game runs on: RADV, ANV or NVK
} VkCaps;
extern VkCaps vk_caps;
void vk_caps_driver(VkPhysicalDevice p); // first, before vkCreateDevice: vk_caps.amd, amd_sc
void vk_caps_driver(VkPhysicalDevice p); // first, before vkCreateDevice: vk_caps.amd, amd_sc, mesa
void vk_caps_features(VkPhysicalDeviceFeatures *f); // before vkCreateDevice (TOTK_VK_NO_FLOAT64 clears shaderFloat64)
// Before vkCreateDevice, with the driver's graphics pipeline library feature and properties: sets vk_caps.gpl,
// 1 = enable the extensions (VK_KHR_pipeline_library, VK_EXT_graphics_pipeline_library) and the feature.
+6 -1
View File
@@ -43,6 +43,8 @@ void vk_caps_driver(VkPhysicalDevice p) {
// AMD split RDNA 1 and 2 off into a driver branch of their own; its driverInfo reads
// "26.10.1 (AMD proprietary shader compiler)" where the RDNA 3 and 4 driver names LLPC.
vk_caps.amd_sc = drv.driverID == VK_DRIVER_ID_AMD_PROPRIETARY && strstr(drv.driverInfo, "shader compiler");
vk_caps.mesa = drv.driverID == VK_DRIVER_ID_MESA_RADV || drv.driverID == VK_DRIVER_ID_INTEL_OPEN_SOURCE_MESA ||
drv.driverID == VK_DRIVER_ID_MESA_NVK;
}
// TOTK_GPL=0 turns graphics pipeline libraries off; they are on wherever the driver has fast linking. AMD's RDNA 1/2
@@ -114,7 +116,10 @@ void vk_caps_init(VkCtx *c) {
// BotW and TotK on AMD). The translator biases gather coordinates by the host's sub-texel precision; NVIDIA rounds
// as Maxwell does. TOTK_GATHER_BIAS=<bits> forces it (0: off).
uint32_t gather = env_u32("TOTK_GATHER_BIAS", c->props.vendorID == 0x10de ? 0 : l->subTexelPrecisionBits);
gfx_shader_set_host(vk_caps.float64, vk_caps.sbuf_align, told, gather);
// A register read before any write is an undefined load in SPIR-V, and Mesa folds undefined values freely, so on
// Mesa function-local variables start at 0 (docs/maxwell.md 3.12). TOTK_ZERO_LOCALS=1 forces it, 0 turns it off.
uint32_t zero_locals = env_u32("TOTK_ZERO_LOCALS", (uint32_t)vk_caps.mesa);
gfx_shader_set_host(vk_caps.float64, vk_caps.sbuf_align, told, gather, zero_locals != 0);
if (gather) rt_log("vk caps: gather coordinates biased for %u sub-texel bits (TOTK_GATHER_BIAS)", gather);
char dv[32];
+5 -3
View File
@@ -1218,10 +1218,12 @@ void vk_dlaa_frame(void) {
// scaled picture into the output-sized target, in a pass without the depth attachment the in-place FXAA has: there it
// is always drawn, whatever fxaa says (skipping it would leave the 3D picture out), unless DLSS already wrote that
// target this frame.
// The stock translator's hash, the one with tools/xlate patch 0010 (PCSS, PR #89) applied, and the one with patches
// 0010 and 0011 (the shadow filter spread) applied. A scaling draw this list misses still scales DLSS's picture, not
// The stock translator's hash, the one with tools/xlate patch 0010 (PCSS, PR #89) applied, the one with patches 0010
// and 0011 (the shadow filter spread) applied, and that one with the zero_locals job flag (Mesa, vk_caps.c).
// A scaling draw this list misses still scales DLSS's picture, not
// the jittered scene: after DLSS ran, passes larger than the light target sample DLSS's output (vk_dlaa_swap_img).
static const uint64_t FXAA_FS[] = {0xf450003ebeb3dc52ull, 0x0a12f4bc2a9a4fbeull, 0x5c43ae18948d52cbull};
static const uint64_t FXAA_FS[] = {0xf450003ebeb3dc52ull, 0x0a12f4bc2a9a4fbeull, 0x5c43ae18948d52cbull,
0xaad42238801d31d8ull};
static uint64_t spirv_hash(const GfxShader *s) {
static struct { const GfxShader *s; uint64_t h; } tab[8192];