24 citations · 59 across the 20 of their papers we have counts for
21 papers
ABC implies that Ramanujan's tau function misses almost all primes
David Kurniadi Angdinata, Evan Chen, Chris Cummins +21
Lehmer conjectured that Ramanujan's tau-function never vanishes. In a related direction, a folklore conjecture asserts that infinitely many primes arise as absolute values of Raman…
Dead ends in square-free digit walks
Evan Chen, Chris Cummins, Ben Eltschig +18
We study "dead ends" in square-free digit walks: square-free integers such that, in base , every one-digit extension is non-square-free. In base , the stochastic…
Fel's Conjecture on Syzygies of Numerical Semigroups
Evan Chen, Chris Cummins, GSM +18
Let be a numerical semigroup and its semigroup ring. The Hilbert numerator of determines normalized alternating syzygy power sums $K_…
Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs
Chris Cummins, Volker Seeker, Jordi Armengol-Estapé +3
Tools for rewriting, refactoring and optimizing code should be fast and correct. Large language models (LLMs), by their nature, possess neither of these qualities. Yet, there remai…
Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
Chris Cummins, Volker Seeker, Dejan Grubisic +4
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 a…
Compiler generated feedback for Large Language Models
Dejan Grubisic, Chris Cummins, Volker Seeker +1
We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly. The model takes unoptimiz…
Priority Sampling of Large Language Models for Compilers
Dejan Grubisic, Chris Cummins, Volker Seeker +1
Large language models show great potential in generating and optimizing code. Widely used sampling methods such as Nucleus Sampling increase the diversity of generation but often p…
Large Language Models for Compiler Optimization
Chris Cummins, Volker Seeker, Dejan Grubisic +8
We explore the novel application of Large Language Models to code optimization. We present a 7B-parameter transformer model trained from scratch to optimize LLVM assembly for code…
LoopTune: Optimizing Tensor Computations with Reinforcement Learning
Dejan Grubisic, Bram Wasti, Chris Cummins +2
Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tun…
SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly
Jordi Armengol-Estapé, Jackson Woodruff, Chris Cummins +1
Decompilation is a well-studied area with numerous high-quality tools available. These are frequently used for security tasks and to port legacy code. However, they regularly gener…
BenchDirect: A Directed Language Model for Compiler Benchmarks
Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu +4
The exponential increase of hardware-software complexity has made it impossible for compiler engineers to find the right optimization heuristics manually. Predictive models have be…
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
Youwei Liang, Kevin Stone, Ali Shameli +8
Finding the optimal pass sequence of compilation can lead to a significant reduction in program size and/or improvement in program efficiency. Prior works on compilation pass order…
BenchPress: A Deep Active Benchmark Generator
Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu +4
We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code. BenchPress synthesizes compiling functi…
Profile Guided Optimization without Profiles: A Machine Learning Approach
Nadav Rotem, Chris Cummins
Profile guided optimization is an effective technique for improving the optimization ability of compilers based on dynamic behavior, but collecting profile data is expensive, cumbe…
Caviar: An E-graph Based TRS for Automatic Code Optimization
Smail Kourta, Adel Namani, Fatima Benbouzid-Si Tayeb +4
Term Rewriting Systems (TRSs) are used in compilers to simplify and prove expressions. State-of-the-art TRSs in compilers use a greedy algorithm that applies a set of rewriting rul…
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
Chris Cummins, Bram Wasti, Jiadong Guo +9
Interest in applying Artificial Intelligence (AI) techniques to compiler optimizations is increasing rapidly, but compiler research has a high entry barrier. Unlike in other domain…
Learning Space Partitions for Path Planning
Kevin Yang, Tianjun Zhang, Chris Cummins +6
Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function. Popular approaches like…
Value Function Based Performance Optimization of Deep Learning Workloads
Benoit Steiner, Chris Cummins, Horace He +1
As machine learning techniques become ubiquitous, the efficiency of neural network implementations is becoming correspondingly paramount. Frameworks, such as Halide and TVM, separa…
Deep Data Flow Analysis
Chris Cummins, Hugh Leather, Zacharias Fisches +3
Compiler architects increasingly look to machine learning when building heuristics for compiler optimization. The promise of automatic heuristic design, freeing the compiler engine…
ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
Chris Cummins, Zacharias V. Fisches, Tal Ben-Nun +2
The increasing complexity of computing systems places a tremendous burden on optimizing compilers, requiring ever more accurate and aggressive optimizations. Machine learning offer…
Autotuning OpenCL Workgroup Size for Stencil Patterns
Chris Cummins, Pavlos Petoumenos, Michel Steuwer +1
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 im…