Search Results for author:
Found 20 papers, 7 papers with code
What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces
Code generation and understanding are critical capabilities for large language models (LLMs).
Finding Missed Code Size Optimizations in Compilers using LLMs
To date we have reported 24 confirmed bugs in production compilers, and conclude that LLM-assisted testing is a promising avenue for detecting optimization bugs in real world compilers.
Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs
Unlike the direct rewrite approach, LLM-generated transformations are easy to inspect, debug, and validate.
Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
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.
Compiler generated feedback for Large Language Models
We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly.
Priority Sampling of Large Language Models for Compilers
Large language models show great potential in generating and optimizing code.
Large Language Models for Compiler Optimization
We explore the novel application of Large Language Models to code optimization.
LoopTune: Optimizing Tensor Computations with Reinforcement Learning
Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries introduce unsustainable costs.
SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly
SLaDe is up to 6 times more accurate than Ghidra, a state-of-the-art, industrial-strength decompiler and up to 4 times more accurate than the large language model ChatGPT and generates significantly more readable code than both.
BenchDirect: A Directed Language Model for Compiler Benchmarks
We improve this with BenchDirect which utilizes a directed LM that infills programs by jointly observing source code context and the compiler features that are targeted.
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
Finding the optimal pass sequence of compilation can lead to a significant reduction in program size and/or improvement in program efficiency.
BenchPress: A Deep Active Benchmark Generator
We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code.
Profile Guided Optimization without Profiles: A Machine Learning Approach
We perform offline training using information that is collected from a large corpus of binaries that have branch probabilities information.
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
What is needed is an easy, reusable experimental infrastructure for real world compiler optimization tasks that can serve as a common benchmark for comparing techniques, and as a platform to accelerate progress in the field.
Learning Space Partitions for Path Planning
Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function.
Value Function Based Performance Optimization of Deep Learning Workloads
As machine learning techniques become ubiquitous, the efficiency of neural network implementations is becoming correspondingly paramount.
Deep Data Flow Analysis
Compiler architects increasingly look to machine learning when building heuristics for compiler optimization.
ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
We introduce ProGraML - Program Graphs for Machine Learning - a novel graph-based program representation using a low level, language agnostic, and portable format; and machine learning models capable of performing complex downstream tasks over these graphs.
End-to-End Deep Learning of Optimization Heuristics
We develop a deep neural network that learns heuristics over raw code, entirely without using code features.
Autotuning OpenCL Workgroup Size for Stencil Patterns
Selecting an appropriate workgroup size is critical for the performance of OpenCL kernels, and requires knowledge of the underlying hardware, the data being operated on, and the implementation of the kernel.
Distributed, Parallel, and Cluster Computing
