wouter/d4r
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

engine: per-layer GPU timestamps for the M / L network (D4R_ENGINE_M_LAYER_STAMPS)

Browse Source 
Timing only: with D4R_ENGINE_M_LAYER_STAMPS=1 the runtime writes a timestamp
after each of the ten network layers (queries first + 7 on) and d4r-m prints
the per-layer medians. RX 9070 XT, 1280x720 -> 1440p: enc1 210, enc2 115,
tube 6 x 50, dec2 114, dec1 209 us.

Signed-off-by: itchyfeetleech <[email protected]>
This commit is contained in:
itchyfeetleech committed 2026-10-19 21:02:50 +13:00
1 parent 912bef3fb8
commit 0ba235a05b
2 files changed
+16 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

engine/runtime_m.inc
+3
View File
@@ -512,9 +512,12 @@ void MEngine::recordFrame(VkCommandBuffer cb, VkQueryPool stamps, uint32_t first
auto& e = *impl; auto& m = e.model;
if (e.external) throw std::runtime_error("this engine's network is external: record the front and the back");
recordFront(cb, stamps, first);
// timing only: D4R_ENGINE_M_LAYER_STAMPS=1 also stamps after every network layer, from query first + 7 on
static const bool layerStamps = std::getenv("D4R_ENGINE_M_LAYER_STAMPS") != nullptr;
for (unsigned l = 0; l < MLayers; ++l) {
const uint32_t w = e.gw / 2 / MScale[l], h = e.gh / 2 / MScale[l];
dispatch(cb, m.network[l], e.layerSets[l], (w + (MShift[l] ^ ((e.frame & 1u) * 2u)) + 7) / 8, (h + MShift[l] + 7) / 8); emptyStage(cb);
if (stamps && layerStamps) vkCmdWriteTimestamp(cb, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, stamps, first + 7 + l);
}
recordBack(cb, stamps, stamps ? first + 3 : 0);
}