Merge Tobim6's work for older graphics cards: mesh shaders emulated with compute, video memory kept within the heaps' budgets, staged mirror uploads and the submit wait that goes with them.

Conflicts: the settings key lists take both sides; frame generation keeps the camera-cut handling and logs its counters every 600 frames with the cuts among them; the pass-time mark moves into draw_viewport; mo_desc keeps the pose depth and notes the reader.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-12 12:14:58 -05:00
43 changed files with 4748 additions and 266 deletions

View File

@@ -860,6 +860,7 @@ void vk_exec_pass_begin(VkExec *ex) {
m->step = ex->mark_passes++;
m->w = ex->pass_w, m->h = ex->pass_h, m->d = ex->pass_layers;
m->layer = ex->depth.image ? ex->depth.base_layer : 0;
m->vw = m->vh = 0;
m->ncolor = (uint8_t)(ex->pass_ncolor < 8 ? ex->pass_ncolor : 8);
for (int i = 0; i < m->ncolor; i++) m->color[i] = ex->pass_color[i];
m->depth = ex->pass_depth ? ex->pass_depth : ex->pass_stencil;
@@ -1119,7 +1120,19 @@ static void set_rt(VkExec *ex, const p_set_rt *r) {
// command, it was 4% of the replay in Kokiri Forest.
static int split_n = -1, split_idle, split_in_pass, split_draws, split_at, part_start;
static uint64_t split_ns, part_t0;
static uint64_t n_parts, n_subs, n_idle_parts, n_pass_splits;
static uint64_t n_parts, n_subs, n_idle_parts, n_pass_splits, n_cuts;
int vk_exec_split_now(VkExec *ex) {
int in_pass = ex->in_pass;
if (in_pass) vk_exec_pass_end(ex);
VkCommandBuffer cb = vk_sync_cut(); // not handed to the queue: the texture pool set stays (vk_exec_pool_split)
if (!cb) return 0;
ex->cb = cb;
ex->dirty = VK_EXEC_DIRTY_ALL;
vk_exec_draw_new_cb();
n_cuts++;
return 1;
}
static int split_wanted(void) {
if (split_draws >= split_at) return 1;
@@ -2090,9 +2103,10 @@ static uint32_t group_peek(const VkExec *ex, const op_hdr *h, const op_hdr **end
int begun = 0;
const p_set_rt *rt = &ex->rt;
*why = GE_LIMIT;
// mesh draws stay on the submitting thread with the mesh fallback (its buffers are shared) and while
// NX2NAVI_GPU_PASSES copies their workgroup counts (one list)
int mesh_serial = vk_ctx()->mesh_fallback || vk_gpu_passes_capturing();
// mesh draws stay on the submitting thread with the mesh fallback (its buffers are shared), with the mesh emulation
// (no VK_EXT_mesh_shader: its arena, queue and the part's pre-pass command buffer are the submitting thread's) and
// while NX2NAVI_GPU_PASSES copies their workgroup counts (one list)
int mesh_serial = vk_ctx()->mesh_fallback || !vk_ctx()->has_mesh_shader || vk_gpu_passes_capturing();
for (uint32_t ops = 0; ops < GROUP_PEEK; ops++) {
if (h->size < sizeof *h || (h->size & 7) || h->op >= OP_COUNT_) { *why = GE_RUN; break; } // the walk reports it
const void *a = nvn_op_payload(h);
@@ -2587,10 +2601,10 @@ int vk_exec_record(VkCommandBuffer cb, const uint64_t *handles, int n, uint64_t
if (n) n_subs++;
if ((rt_trace & RT_TRACE_PERF) && n_subs >= 240) {
rt_log("perf: replay command buffer parts per submission %.2f (%.2f first parts sent while the GPU was idle, %.2f "
"splits inside a pass); event order: held %llu, resumed %llu (%llu without their signal), switches %llu, "
"splits inside a pass, %.2f cuts for emulated mesh stages); event order: held %llu, resumed %llu (%llu without their signal), switches %llu, "
"held now %d; waits a CPU signal met only after the submission's copies were taken: %llu",
(double)(n_subs + n_parts) / (double)n_subs, (double)n_idle_parts / (double)n_subs,
(double)n_pass_splits / (double)n_subs, (unsigned long long)evo_held, (unsigned long long)evo_resumed,
(double)n_pass_splits / (double)n_subs, (double)n_cuts / (double)n_subs, (unsigned long long)evo_held, (unsigned long long)evo_resumed,
(unsigned long long)evo_forced, (unsigned long long)evo_switches, evo_pending,
(unsigned long long)vk_exec_event_late_take());
uint64_t xw, xe, xl, xm, le, lc, lo;
@@ -2682,7 +2696,7 @@ int vk_exec_record(VkCommandBuffer cb, const uint64_t *handles, int n, uint64_t
}
RW.groups = RW.group_draws = RW.chunks = RW.serial_draws = RW.wait_ns = 0;
evo_held = evo_resumed = evo_forced = evo_switches = 0;
n_subs = n_parts = n_idle_parts = n_pass_splits = 0;
n_subs = n_parts = n_idle_parts = n_pass_splits = n_cuts = 0;
}
rec_spent_ns += kern_now_ns() - in_ns;
if (rec_spent_ns >= REC_CLAIM_NS) rec_claim();