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.
What’s captured
Section titled “What’s captured”- 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.
How it works
Section titled “How it works”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.
Integration
Section titled “Integration”Set GRAPHSIGNAL_API_KEY and wrap your launch command with graphsignal-run:
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.