1 مستودع
Flags invalid nested loop patterns in GPU kernels to prevent undefined behavior during compilation.
Distinct from Render Loop Validators: Distinct from Render Loop Validators: focuses on GPU kernel loop patterns, not rendering loops.
Explore 1 awesome GitHub repository matching user interface & experience · GPU Loop Pattern Validators. 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
Flags invalid nested loop patterns in GPU kernels to prevent undefined behavior during compilation.