thread-trace
Diagnoses why a compute kernel on an AMD GPU is slow, instruction by instruction, with Advanced Thread Trace (rocprofv3 --att) and the rocprof-trace-decoder Python API. Use when a kernel runs below its expected throughput and you need the instructions and source lines that hold the time, such as waves stalled on busy vector or matrix (MFMA) instructions, waiting on memory (s_waitcnt) or at barriers (__syncthreads), or idle; or when capturing or analyzing .att traces. Not for hardware counters, roofline, PC sampling, host-side timelines, or NVIDIA GPUs.
소스 정보
- 저장소
- ROCm/rocm-systems
- 최근 소스 활동
- 2026년 10월 29일 19:57
- 감지된 SKILL.md 언어
- 영어
- 스타
- 567
- 포크
- 507
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
SKILL.md 표시 중
| name | thread-trace |
|---|---|
| description | Diagnoses why a compute kernel on an AMD GPU is slow, instruction by instruction, with Advanced Thread Trace (rocprofv3 --att) and the rocprof-trace-decoder Python API. Use when a kernel runs below its expected throughput and you need the instructions and source lines that hold the time, such as waves stalled on busy vector or matrix (MFMA) instructions, waiting on memory (s_waitcnt) or at barriers (__syncthreads), or idle; or when capturing or analyzing .att traces. Not for hardware counters, roofline, PC sampling, host-side timelines, or NVIDIA GPUs. |