arXiv:2606. 20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks.
By Dipankar Sarkar
arXiv:2610.28429v1 Announce Type: cross
Abstract: GPU kernels are critical to the performance of today's AI services, yet the same operators are rewritten repeatedly: for each GPU generation, numeric...
By Tuan Truong Vu, Cheng Tan
arXiv:2608. 12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates.
By Rishi Shah, Rishav Shrestha
The paper examines how large‑language‑model (LLM) decompilers, which produce clean, idiomatic C code, are currently evaluated mainly on recompilability and passing shipped tests. It shows that these metrics can mask significant behavioral differences: a decompiled function may recompile and pass all tests yet diverge on other inputs or lose disclosed vulnerabilities. To address this, the authors propose Decompile‑Diverge, a behavioral oracle that synthesizes drivers, fuzzes inputs, and compares the decompiled code’s behavior to the original, revealing divergences in up to 13% of cases and exposing gaps in current evaluation suites.
By Chang Liu, Edward Raff, Kristopher Micinski
arXiv:2606. 27396v1 Announce Type: cross Abstract: Test-input generation for tensor kernels is folkloric.
By Dipankar Sarkar
arXiv:2609.23889v1 Announce Type: cross
Abstract: Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but
still lacks an effective and...
By Xingyu Li, Juefei Pu, Haonan Li, Arrdya Srivastav, Kareem Shehada, Srikanth V. Krishnamurthy, Zhiyun Qian