Menu
SkillsMP has collected 16 skills from ROCm/FlyDSL. Open a skill to review its source and details.
Showing 16 of 16 collected skills.
Comprehensive reference for authoring FlyDSL GPU kernels on AMD GPUs. Covers the layout algebra, tiled copy/MMA, buffer ops, loop-carried range loops, SharedAllocator (LDS), autotuning, and common patterns. Use when writing, reviewing, or understanding FlyDSL…
Modernize FlyDSL kernels: replace raw MLIR dialects (arith, scf, vector, llvm, memref, math), ArithValue, redundant fx.* wrapping, fx.Index, buffer_ops, SmemPtr/SmemAllocator, copy_atom_call/mma_atom_call (loop or single atom), and raw rocdl.mfma_* with the…
Add a new target-specific Mma / Copy Op type to a FlyDSL backend dialect (`lib/Dialect/Fly<TARGET>/<SUBTARGET>/` + `include/flydsl/Dialect/Fly<TARGET>/IR/`). Covers the MmaOp/CopyOp type design, the stateful-vs-stateless variants, and the `emitAtomCall` /…
Build and install FlyDSL (Flexible Layout Python DSL) on a remote host or Docker container. FlyDSL is a Python DSL and MLIR-based compiler stack for authoring high-performance GPU kernels with explicit layouts and tiling on AMD GPUs. Requires building…
Connect to a remote host via SSH and build a Docker image with rocprofv3, aiter, and FlyDSL. Use when user wants to build/rebuild the ROCm development image on a remote host. Usage: /build-rocm-image <hostname>
Capture GPU kernel ATT (Advanced Thread Trace) via rocprofv3 on a remote Docker container or locally. Discovers kernel names, configures input.yaml with the target kernel_include_regex, runs rocprofv3 -i input.yaml with FLYDSL_DEBUG_ENABLE_DEBUG_INFO=1, and…
Debug FlyDSL GPU kernels that produce NaN, inf, wrong results, or crash. Covers cache invalidation, tracing pitfalls (runtime conditionals, range vs range_constexpr), loop-carried state packing, buffer_load addressing, MFMA operand layout verification, LDS…
Guided step-by-step wizard for producing a new FlyDSL GPU kernel from a requirement: classify the kernel type, pick a skeleton, fill in compute, add control flow / sync / LDS, then test on GPU. Use when the user wants to WRITE a new kernel, port a Triton…
Format, clean up, and style-check changed files, matching the project's CI style gate. Formats Python with black + ruff and C/C++ with clang-format using the repository's .clang-format, and can also run check-only to reproduce the CI gate locally without…
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…
Profile GPU kernels using rocprofv3 to collect ATT instruction-level traces, then analyze the trace data using hotspot_analyzer.py to identify top-K stall hotspots (VMEM-load, VMEM-wait, LDS/SMEM-wait, barrier, MFMA stalls) mapped back to source lines, and…
Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels. Diagnose bank conflicts and high lgkmcnt stalls from ATT trace data, then apply swizzle or padding layouts to eliminate conflicts. Also increase the distance between LDS…
Apply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop tail via runtime loop-carried values. This overlaps data load…
Review a FlyDSL PR, commit, branch, kernel, or consuming module for API-stability compliance. Detect breaking changes to stable APIs, usage of unstable FlyDSL APIs, and direct upstream MLIR dialect operations. Use when asked to review API compatibility, a…
Detect out-of-bounds memory accesses in CPU or GPU code using static interval analysis and runtime assertions/printfs. Use when investigating OOB, buffer overrun, invalid memory access, HIP/ROCm illegal address, CUDA illegal memory access, silent tensor…
Find the exact commit that caused a GPU kernel performance regression using binary search (git bisect). Given a good commit (fast), a bad commit (slow, defaults to HEAD), and a benchmark command, automatically checks out commits, runs the benchmark, extracts…