Skip to content

ROCm Profiling and Monitoring

See the Quick Start guide on how to install Graphsignal.

Graphsignal profiles AMD ROCm workloads via AMD’s rocprofiler-sdk — no code instrumentation required. Attach the profiler to any HIP/ROCm program (PyTorch, vLLM, SGLang, raw HIP, custom Triton kernels) and the GPU side comes through automatically.

  • GPU kernel profiles (low overhead): per-kernel timelines — cumulative time, call count, peak concurrency, and theoretical occupancy — for the top kernels by GPU time.
  • Memory transfers: host↔device and device↔device copies — cumulative time, call count, and bytes per direction.
  • Synchronization: cumulative host-blocking time on hipDeviceSynchronize / hipStreamSynchronize / hipEventSynchronize, attributed back to the GPU work the host waited on.

The Graphsignal profiler runs as a sidecar process — never co-located with the workload. It collects GPU activity from the workload and processes it externally in the sidecar.

Set GRAPHSIGNAL_API_KEY and wrap your launch command with graphsignal-run:

Terminal window
export GRAPHSIGNAL_API_KEY=<my-api-key>
graphsignal-run <my-app>

Collection starts automatically once the workload begins using the GPU. Requires ROCm 7+; if ROCm isn’t found, Graphsignal skips ROCm profiling without affecting the workload. See the Quick Start for details and the Profiler CLI reference for options.