Source-to-Source Transformations for GPU Code Generation
2026-05-15T08:51:59Z•fc7caeb7a837a0709d9e7e750329cc22fbbedc9909d1086087f06ff4104096a9
CUDACVE-analysisDSLGPUHPCPDE-solversT-gate-optimizationbinary-translationcode-translation-lmcompilersconcurrency-safetydata-race-freedomdeadlock-freedompatch-impact-analysisprogram-verificationprogramming-languagesproof-preserving compilationquantitative-equivalencequantum-computingreverse-engineeringstatic-analysissymbolic-analysisvulnerability-assessmentwhole-binary-translationx86-64-to-AArch64
What happened
Collection of recent PL and systems research from arXiv covering: OptiGPU — a proof-preserving, source-to-source refinement pipeline to generate verified, low-level CUDA with data-race/deadlock/functional guarantees; Quantitative Symbolic Patch Impact Analysis — a symbolic approach to measure and localize behavioral divergence between vulnerable and patched code (evaluated on 90 CVE patches and Juliet/CWE benchmarks); TZAP — a linear-time randomized static analysis and tool for massive-scale T‑gate optimization in quantum circuits; Mat2Boundary — a DSL/compiler modeling many boundary-condition
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_pl
- Record identifier
- fc7caeb7a837a0709d9e7e750329cc22fbbedc9909d1086087f06ff4104096a9
- Enrichment time
- 2026-05-15T08:51:59Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.