KPerfIR is a compiler-centric profiling infrastructure for Triton, demonstrated by a region-based timing tool that improved Triton's FlashAttention-3 by 24.1%.
AMD Instinct MI300
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
KPerfIR: Towards an Open and Compiler-centric Ecosystem for GPU Kernel Performance Tooling on Modern AI Workloads
KPerfIR is a compiler-centric profiling infrastructure for Triton, demonstrated by a region-based timing tool that improved Triton's FlashAttention-3 by 24.1%.