Starcoder 2 and the stack v2: The next generation

A Lozhkov, R Li, LB Allal, F Cassano… - arxiv preprint arxiv …, 2024 - arxiv.org
The BigCode project, an open-scientific collaboration focused on the responsible
development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In …

Meta large language model compiler: Foundation models of compiler optimization

C Cummins, V Seeker, D Grubisic, B Roziere… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated remarkable capabilities across a
variety of software engineering and coding tasks. However, their application in the domain of …

Domain-Specific Code Language Models: Unraveling the Potential for HPC Codes and Tasks

T Kadosh, N Hasabnis, VA Vo, N Schneider… - arxiv preprint arxiv …, 2023 - arxiv.org
With easier access to powerful compute resources, there is a growing trend in AI for software
development to develop larger language models (LLMs) to address a variety of …

Input-Gen: Guided Generation of Stateful Inputs for Testing, Tuning, and Training

IR Ivanov, J Meyer, A Grossman, WS Moses… - arxiv preprint arxiv …, 2024 - arxiv.org
The size and complexity of software applications is increasing at an accelerating pace.
Source code repositories (along with their dependencies) require vast amounts of labor to …

Optimistic and Scalable Global Function Merging

K Lee, M Ren, E Hoag - Proceedings of the 25th ACM SIGPLAN/SIGBED …, 2024 - dl.acm.org
Function merging is a pivotal technique for reducing code size by combining identical or
similar functions into a single function. While prior research has extensively explored this …

Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization

TV Marinov, A Agarwal, M Trofin - arxiv preprint arxiv:2403.19462, 2024 - arxiv.org
This work studies a Reinforcement Learning (RL) problem in which we are given a set of
trajectories collected with K baseline policies. Each of these policies can be quite …

Optimistic Global Function Merger

K Lee, M Ren, E Hoag - arxiv preprint arxiv:2312.03214, 2023 - arxiv.org
Function merging is a pivotal technique for reducing code size by combining identical or
similar functions into a single function. While prior research has extensively explored this …

Assurance of Reasoning Enabled Systems (ARES)

A Marquez, TC Fujimoto, TJ Stavenger - 2024 - osti.gov
ARES was in part motivated by the determination of President's Council of Advisors on
Science and Technology (PCAST) on May 13th, 2023 that published a set of inquiries: In an …

[PDF][PDF] Scalable RL for Systems via Offline Imitation from Multiple Baselines: A Case Study in Compiler Optimization

TV Marinov, A Agarwal, M Trofin - mlforsystems.org
From scheduling, to resource allocation to optimization of complex workflows, systems are
replete with decision-making problems which are typically addressed with hand-designed …