Реклама

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

#PTXBench #Benchmark #Adapt #LLMs #Kernel

arXiv:2608.17379v1 Announce Type: new Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, whether selected target instructions execute at…