Performance model

ROCm Compute Profiler exposes detailed metrics for AMD Instinct™ / CDNA™ architecture-based MI-series GPUs and for select AMD Ryzen™ / RDNA™ architecture-based APUs with supported analysis configurations.

Use the following pages for architecture-specific naming, panel layout, and conceptual overview:

• Instinct (CDNA) — AMD CDNA architecture (CDNA-CDNA4): Architecture and data-type tables, top-level CDNA block diagrams, MI-series terminology, and chapters for: * System Speed-of-Light

  • Compute unit (CU)

  • L2 cache (TCC)

  • Shader engine (SE)

  • Command processor (CP)

  • References

• Ryzen APU (RDNA) — RDNA3: Architecture, top-level RDNA3 block diagram, GCEA, gfx1151 panel layout, and chapters for: * System Speed-of-Light

  • Workgroup processor (WGP)

  • GL0

  • GL1

  • GL2

  • Shader engine

  • Command processor (CP)

  • References

For practical profiling walkthroughs, see Profiling by example.