Liyang Ling
Community@leonling-ll · Shanghai, China
AI Compiler Engineer
Agent Skills by Liyang Ling
Showing 8 vetted skills indexed across 1 GitHub repositories.
leonling-llgluon-mm-inst-opt
Replace global memory loads with AMD-native buffer instructions in Gluon GEMM kernels.
leonling-llgluon-pipeline-opt
Implement two-stage pipeline optimizations for Gluon GEMM kernels on CDNA3 and CDNA4 GPUs.
leonling-lltriton-to-gluon
Translate Triton GPU kernels to explicit AMD Gluon kernels for CDNA GPUs.
leonling-llgluon-beyond-loop-opt
Apply XCD remapping and epilogue slicing to Gluon GEMM kernels.
leonling-llgluon-gpr-opt
Apply loop unroll and N-slice tiling to reduce GPR pressure in Gluon GEMM kernels.
leonling-llkernel-perf-analysis
Collect timing, hardware counters, ATT traces, and memory-hierarchy data from AMD GPU kernels.
leonling-llgluon-lds-opt
Optimizes Gluon GEMM kernel layouts to eliminate LDS bank conflicts on Coprocessor Design's NEXT-GEN GPUs.
leonling-lllds-bank-conflict
Measure LDS bank conflicts in AMD GPU kernels using rocprofv3 hardware counters.