Omniwise fine-tunes LLaMA 3.2 3B to predict GPU performance counters from HIP kernel source code, reporting over 90% of test predictions within 10% relative error on AMD MI250 and MI300X.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Omniwise: Predicting GPU Kernels Performance with LLMs
Omniwise fine-tunes LLaMA 3.2 3B to predict GPU performance counters from HIP kernel source code, reporting over 90% of test predictions within 10% relative error on AMD MI250 and MI300X.