1 repository
Features to retrieve host, device, or generated source code of compiled kernels for debugging.
Distinct from Generated Kernel Code Inspectors: Distinct from general Generated Kernel Code Inspectors: specifically retrieves both host and device source code separately.
Explore 1 awesome GitHub repository matching operating systems & systems programming · Host-Device Source Retrievers. Refine with filters or upvote what's useful.
TileLang is a Python-embedded domain-specific language compiler that JIT-compiles and autotunes GPU kernels. It uses a tile-based DSL, automatic software pipelining, and parallel autotuning to generate optimized GPU kernels at runtime. It supports tensor core operations with Pythonic syntax, automatic memory management, and thread mapping. The compiler searches over tile sizes, thread counts, and scheduling policies, compiling and benchmarking candidates in parallel to find the fastest kernel. It also caches compiled binaries and tuning results to disk for reuse across sessions. TileLang inc
Retrieves host, device, and generated source code of compiled kernels for debugging.