Gemm Optimization

Comprehensive guide to optimizing GEMM (General Matrix Multiply) kernels in FlyDSL on AMD CDNA GPUs. Covers tiling strategy, LDS ping-pong double-buffer, XOR bank-conflict swizzle, A/B data prefetch pipeline, 2-stage software pipelining, MFMA instruction scheduling (hot_loop_scheduler), epilogue strategies (direct store vs CShuffle), TFLOPS/bandwidth calculation, main-loop instruction count analysis, and bottleneck identification from ATT traces. Based on the production preshuffle_gemm kernel. Usage: /gemm-optimization

rocm Updated 550 repo stars

File contents

rocm/flydsl commit 874c86ebfc

Frequently asked questions

npx get-skill add rocm/gemm-optimization