REVIEW 6 cited by
Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code and compiler optimization remains underexplored. Training LLMs is resource-intensive, requiring substantial GPU hours and extensive data collection, which can be prohibitive. To address this gap, we introduce Meta Large Language Model Compiler (LLM Compiler), a suite of robust, openly available, pre-trained models specifically designed for code optimization tasks. Built on the foundation of Code Llama, LLM Compiler enhances the understanding of compiler intermediate representations (IRs), assembly language, and optimization techniques. The model has been trained on a vast corpus of 546 billion tokens of LLVM-IR and assembly code and has undergone instruction fine-tuning to interpret compiler behavior. LLM Compiler is released under a bespoke commercial license to allow wide reuse and is available in two sizes: 7 billion and 13 billion parameters. We also present fine-tuned versions of the model, demonstrating its enhanced capabilities in optimizing code size and disassembling from x86_64 and ARM assembly back into LLVM-IR. These achieve 77% of the optimising potential of an autotuning search, and 45% disassembly round trip (14% exact match). This release aims to provide a scalable, cost-effective foundation for further research and development in compiler optimization by both academic researchers and industry practitioners.
Forward citations
Cited by 6 Pith papers
-
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.
-
Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
LLM-based RTL optimizers degrade on timing-heavy mutants, but the study's own data and methods do not fully support the headline claim.
-
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.
-
CompilerGPT: Leveraging Large Language Models for Analyzing and Acting on Compiler Optimization Reports
An open-source framework in which GPT-4o or Claude reads Clang/GCC optimization reports and iteratively rewrites C++ code, achieving up to 6.5x speedups on some benchmarks but not consistently.
-
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
A two-stage SFT+RL pipeline trains LLM agents to call compiler-analysis tools and select pass sequences, achieving 8.46% mean IR instruction reduction, but the tool's own contribution is not controlled.
-
GRACE: Cluster-Specific Sequence Reuse for Compiler Auto-Tuning
GRACE pre-computes cluster-specific compiler-pass sequences via contrastive embeddings and evolution, cutting LLVM IR instruction count about 10% over opt -Oz in under 1 second per program.
Discussion (0). Sign in to comment.