mirror of https://github.com/wolfpld/tracy.git synced 2026-08-23 19:48:20 +00:00

Files

Basil Milanich 7bca9dcd90 Fix CUDA Graph GPU zones with proper cuGraphLaunch correlation

Replace the synthetic APICallInfo hack with proper correlation via
CUPTI_ACTIVITY_KIND_GRAPH_TRACE. When cuGraphLaunch fires an API
callback, its correlationId is stored in cudaCallSiteInfo. The
GRAPH_TRACE activity record carries the same correlationId plus the
graphId, which lets us build a graphId→APICallInfo map. Kernel/memcpy/
memset activities then look up this map via their graphId field.

Key changes:
- Add cuGraphLaunch/cuGraphLaunch_ptsz to cbidDriverTrackers so the
  API callback machinery captures the CPU call site
- Enable CUPTI_ACTIVITY_KIND_GRAPH_TRACE and handle it in
  DoProcessDeviceEvent to populate cudaGraphCurrentLaunch[graphId]
- Add cudaGraphCurrentLaunch map to PersistentState
- Two-pass buffer processing in OnBufferCompleted so GRAPH_TRACE
  records (which complete last on GPU) are processed before the
  kernel/memcpy/memset records that depend on them
- Replace graphId=0 fallback in kernel/memcpy/memset with proper
  cudaGraphCurrentLaunch lookup; fall through to matchError if
  the graphId is not found
- Update repro to include TracyCUDA headers and properly test
  GPU zone correlation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-06 11:03:58 -05:00

Makefile

Fix CUDA Graph GPU zones with proper cuGraphLaunch correlation

2026-04-06 11:03:58 -05:00

README.md

Add CUDA Graph GPU zone repro

2026-03-24 09:37:50 -05:00

repro.cu

Fix CUDA Graph GPU zones with proper cuGraphLaunch correlation

2026-04-06 11:03:58 -05:00

README.md

Tracy CUDA Graph GPU Zone Repro

Demonstrates that unpatched Tracy fails to show GPU zones for kernels launched via CUDA Graphs (cudaGraphLaunch).

Root cause

When kernels are launched through CUDA Graphs, CUPTI delivers CONCURRENT_KERNEL and MEMCPY activity records but no corresponding API callback fires for the individual kernel launches. Tracy's matchActivityToAPICall() always fails, and matchError() silently drops every GPU zone.

Build and run

make
./repro

What to expect

Tracy version	GPU zones shown
Unpatched	0
Patched (cuda-graph-gpu-zones.patch)	~30 (10 launches x 3 ops)

The graph structure

Each graph launch contains:

vector_add kernel (c = a + b)
Device-to-device memcpy
vector_add kernel (c = a + c)

The graph is launched 10 times, so 30 GPU operations total.