Mirrors/totk-pc-recomp
1
0 Fork 0
mirror of https://github.com/valentderah/totk-pc-recomp.git synced 2026-11-11 01:41:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Order overlapping uniform overlay copies with a transfer barrier

Browse Source 
vk_exec_ub_flush recorded the copies of a pass's overlaid uniform updates back to back behind one barrier. Copies
with no barrier between them may run in any order, and ov_add only drops an older pending copy of exactly the same
range, so two updates that overlap in part could leave the older bytes in the buffer where they overlap. A copy that
overlaps one recorded since the last barrier now waits for it behind a transfer-to-transfer barrier; the perf line
counts those barriers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BspNcezsiV8zT8wcnXrrME
This commit is contained in:
Claude committed 2026-11-06 22:33:24 +00:00
1 parent eda417fd1d
commit b317f1c37e
1 file changed
+19 -4
Download Patch File Download Diff File Expand all files Collapse all files
runtime/vk_exec_draw.c
+19 -4
View File
@@ -175,7 +175,7 @@ static struct {
struct { uint64_t dst; VkBuffer src; VkDeviceSize soff; VkMemSpan sp; uint64_t size; } p[OV_N]; // to copy
struct { uint64_t lo, hi; } f[OV_FOREIGN]; // GPU writes of other kinds
// since the last perf line (vk_exec_ub_perf)
uint64_t c_update, c_overlaid, c_flush, c_bind, c_merged, c_mixed, c_inpass, c_outside, c_early;
uint64_t c_update, c_overlaid, c_flush, c_bind, c_merged, c_mixed, c_inpass, c_outside, c_early, c_order;
} OV = {.mode = -1};
// A binding without a size reaches to the end of its backing: as far as the overlays go, for ov_at.
@@ -3349,7 +3349,22 @@ void vk_exec_ub_flush(VkExec *ex) {
VkDependencyInfo di = {.sType = VK_STRUCTURE_TYPE_DEPENDENCY_INFO, .memoryBarrierCount = 1, .pMemoryBarriers = &mb};
vkCmdPipelineBarrier2(ex->cb, &di);
ex->recorded++;
// Copies without a barrier between them may run in any order, and ov_add only drops an older copy of exactly the
// same range: a copy that overlaps one recorded since the last barrier waits for it, so the newer bytes land last.
VkMemoryBarrier2 ww = {.sType = VK_STRUCTURE_TYPE_MEMORY_BARRIER_2,
.srcStageMask = VK_PIPELINE_STAGE_2_COPY_BIT, .srcAccessMask = VK_ACCESS_2_TRANSFER_WRITE_BIT,
.dstStageMask = VK_PIPELINE_STAGE_2_COPY_BIT, .dstAccessMask = VK_ACCESS_2_TRANSFER_WRITE_BIT};
VkDependencyInfo wdi = {.sType = VK_STRUCTURE_TYPE_DEPENDENCY_INFO, .memoryBarrierCount = 1, .pMemoryBarriers = &ww};
uint32_t since = 0; // the first copy recorded after the last barrier
for (uint32_t i = 0; i < OV.np; i++) {
for (uint32_t k = since; k < i; k++)
if (OV.p[i].dst < OV.p[k].dst + OV.p[k].size && OV.p[k].dst < OV.p[i].dst + OV.p[i].size) {
vkCmdPipelineBarrier2(ex->cb, &wdi);
ex->recorded++;
OV.c_order++;
since = i;
break;
}
VkBufferCopy cp = {OV.p[i].soff, OV.p[i].sp.offset, OV.p[i].size};
vkCmdCopyBuffer(ex->cb, OV.p[i].src, OV.p[i].sp.buffer, 1, &cp);
ex->recorded++;
@@ -3365,11 +3380,11 @@ void vk_exec_ub_perf(void) {
const double k = 1 / 600.0;
rt_log("perf: uniform updates per submission %.1f: %.1f overlaid in a pass (copied in %.2f batches), %.1f copied "
"in a pass, %.1f outside one; bindings from an overlay %.1f (%.1f merged, %.1f over other GPU writes), %.2f "
"batches brought forward for a storage write",
"batches brought forward for a storage write, %.2f barriers between overlapping copies",
OV.c_update * k, OV.c_overlaid * k, OV.c_flush * k, OV.c_inpass * k, OV.c_outside * k, OV.c_bind * k,
OV.c_merged * k, OV.c_mixed * k, OV.c_early * k);
OV.c_merged * k, OV.c_mixed * k, OV.c_early * k, OV.c_order * k);
OV.c_update = OV.c_overlaid = OV.c_flush = OV.c_bind = OV.c_merged = OV.c_mixed = 0;
OV.c_inpass = OV.c_outside = OV.c_early = 0;
OV.c_inpass = OV.c_outside = OV.c_early = OV.c_order = 0;
}
// The scratch bytes of a uniform or storage binding [addr, addr+n) an overlay of this submission touches: 1 with *out