KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.
An automated tool for analysis and tuning of gpu-accelerated code in hpc applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.PF 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
KEET: Explaining Performance of GPU Kernels Using LLM Agents
KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.