no code implementations • 18 Mar 2024 • Massinissa Merouani, Khaled Afif Boudaoud, Iheb Nassim Aouadj, Nassim Tchoulak, Islem Kara Bernou, Hamza Benyamina, Fatima Benbouzid-Si Tayeb, Karima Benatchba, Hugh Leather, Riyadh Baghdadi
In this paper, we introduce LOOPer, the first polyhedral autoscheduler that uses a deep-learning based cost model and covers a large set of affine transformations and programs.
no code implementations • 18 Mar 2024 • Dejan Grubisic, Chris Cummins, Volker Seeker, Hugh Leather
We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly.
no code implementations • 28 Feb 2024 • Dejan Grubisic, Chris Cummins, Volker Seeker, Hugh Leather
Large language models show great potential in generating and optimizing code.
no code implementations • 5 Jan 2024 • Alex Gu, Baptiste Rozière, Hugh Leather, Armando Solar-Lezama, Gabriel Synnaeve, Sida I. Wang
The best setup, GPT-4 with chain of thought (CoT), achieves a pass@1 of 75% and 81% on input and output prediction, respectively.
1 code implementation • 3 Oct 2023 • Anas Mahmoud, Mostafa Elhoushi, Amro Abbas, Yu Yang, Newsha Ardalani, Hugh Leather, Ari Morcos
We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.
no code implementations • 11 Sep 2023 • Chris Cummins, Volker Seeker, Dejan Grubisic, Mostafa Elhoushi, Youwei Liang, Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Kim Hazelwood, Gabriel Synnaeve, Hugh Leather
We explore the novel application of Large Language Models to code optimization.
no code implementations • 2 Mar 2023 • Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather
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.
no code implementations • 9 Jan 2023 • Youwei Liang, Kevin Stone, Ali Shameli, Chris Cummins, Mostafa Elhoushi, Jiadong Guo, Benoit Steiner, Xiaomeng Yang, Pengtao Xie, Hugh Leather, Yuandong Tian
Finding the optimal pass sequence of compilation can lead to a significant reduction in program size and/or improvement in program efficiency.
no code implementations • 21 Dec 2022 • Chris Lengerich, Gabriel Synnaeve, Amy Zhang, Hugh Leather, Kurt Shuster, François Charton, Charysse Redwood
Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization.
1 code implementation • 13 Aug 2022 • Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather
We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code.
1 code implementation • 30 Jun 2022 • Marc Szafraniec, Baptiste Roziere, Hugh Leather, Francois Charton, Patrick Labatut, Gabriel Synnaeve
Here we propose to augment code translation with IRs, specifically LLVM IR, with results on the C++, Java, Rust, and Go languages.
no code implementations • 8 Jun 2022 • Massinissa Merouani, Khaled Afif Boudaoud, Iheb Nassim Aouadj, Nassim Tchoulak, Fatima Benbouzid-Sitayeb, Karima Benatchba, Hugh Leather, Riyadh Baghdadi
In this paper, we present a work in progress about a deep learning based approach for automatic code optimization in polyhedral compilers.
1 code implementation • 2 May 2022 • Bram Wasti, José Pablo Cambronero, Benoit Steiner, Hugh Leather, Aleksandar Zlateski
We present LoopStack, a domain specific compiler stack for tensor operations, composed of a frontend, LoopTool, and an efficient optimizing code generator, LoopNest.
1 code implementation • 17 Sep 2021 • Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, Hugh Leather
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.
no code implementations • 27 Aug 2021 • Shikhar Singh, Benoit Steiner, James Hegarty, Hugh Leather
State-of-the-art deep-learning compilers like TVM and Halide incorporate a learning-based performance model to search the space of valid implementations of a given deep learning algorithm.
no code implementations • 30 Nov 2020 • Benoit Steiner, Chris Cummins, Horace He, Hugh Leather
As machine learning techniques become ubiquitous, the efficiency of neural network implementations is becoming correspondingly paramount.
no code implementations • 21 Nov 2020 • Chris Cummins, Hugh Leather, Zacharias Fisches, Tal Ben-Nun, Torsten Hoefler, Michael O'Boyle
Compiler architects increasingly look to machine learning when building heuristics for compiler optimization.
2 code implementations • 23 Mar 2020 • Chris Cummins, Zacharias V. Fisches, Tal Ben-Nun, Torsten Hoefler, Hugh Leather
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.
1 code implementation • 2017 26th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2017 • Chris Cummins, Pavlos Petoumenos, Zheng Wang, Hugh Leather
We develop a deep neural network that learns heuristics over raw code, entirely without using code features.
1 code implementation • 9 Nov 2015 • Paschalis Mpeis, Pavlos Petoumenos, Hugh Leather
Replaying the targeted functions allows us to evaluate the effectiveness of each set of optimizations for the actual way the user interacts with the application.
Programming Languages
1 code implementation • 8 Nov 2015 • Chris Cummins, Pavlos Petoumenos, Michel Steuwer, Hugh Leather
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