From 2e5b0761757fc4668d5c562f652f1c95a3782258 Mon Sep 17 00:00:00 2001 From: Basil Milanich Date: Mon, 6 Apr 2026 11:18:20 -0500 Subject: [PATCH] Also track cudaGraphLaunch runtime API for graph correlation The repro uses cudaGraphLaunch (runtime API) not cuGraphLaunch (driver API). Add cudaGraphLaunch_v10000 and its _ptsz variant to cbidRuntimeTrackers so that graphs launched via the runtime API also get their CPU call site captured for GPU zone correlation. Co-Authored-By: Claude Sonnet 4.6 --- public/tracy/TracyCUDA.hpp | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/public/tracy/TracyCUDA.hpp b/public/tracy/TracyCUDA.hpp index 1fdb3158..4bce1c91 100644 --- a/public/tracy/TracyCUDA.hpp +++ b/public/tracy/TracyCUDA.hpp @@ -786,6 +786,10 @@ namespace tracy { CUPTI_RUNTIME_TRACE_CBID_cudaEventQuery_v3020, NON_STREAM_FUNC() }, { CUPTI_RUNTIME_TRACE_CBID_cudaStreamWaitEvent_v3020, NON_STREAM_FUNC() }, { CUPTI_RUNTIME_TRACE_CBID_cudaDeviceSynchronize_v3020, NON_STREAM_FUNC() }, + // Graph launch: tracked so we can correlate GPU activities back to + // the cudaGraphLaunch call site via CUPTI_ACTIVITY_KIND_GRAPH_TRACE + { CUPTI_RUNTIME_TRACE_CBID_cudaGraphLaunch_v10000, GET_STREAM_FUNC(cudaGraphLaunch_v10000_params, stream) }, + { CUPTI_RUNTIME_TRACE_CBID_cudaGraphLaunch_ptsz_v10000, GET_STREAM_FUNC(cudaGraphLaunch_v10000_params, stream) }, }; #undef NON_STREAM_FUNC #undef GET_STREAM_FUNC