A fine-tuned LLM combined with static normalization and a Z3 verifier can produce correct register allocations for GEMM and MHA kernels across NVIDIA and AMD GPUs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM
A fine-tuned LLM combined with static normalization and a Z3 verifier can produce correct register allocations for GEMM and MHA kernels across NVIDIA and AMD GPUs.