MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916401820729344 |
|---|---|
| author | Kadosh, Tal Hasabnis, Niranjan Vo, Vy A. Schneider, Nadav Krien, Neva Capota, Mihai Wasay, Abdul Ahmed, Nesreen Willke, Ted Tamir, Guy Pinter, Yuval Mattson, Timothy Oren, Gal |
| author_facet | Kadosh, Tal Hasabnis, Niranjan Vo, Vy A. Schneider, Nadav Krien, Neva Capota, Mihai Wasay, Abdul Ahmed, Nesreen Willke, Ted Tamir, Guy Pinter, Yuval Mattson, Timothy Oren, Gal |
| contents | With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks from the high-performance computing (HPC) domain are huge in size and demand expensive compute resources for training. This is partly because LLMs for HPC tasks are obtained by finetuning existing LLMs that support several natural and/or programming languages. We found this design choice confusing - why do we need LLMs trained on natural languages and programming languages unrelated to HPC for HPC-specific tasks? In this line of work, we aim to question choices made by existing LLMs by developing smaller language models (LMs) for specific domains - we call them domain-specific LMs. Specifically, we start with HPC as a domain and build an HPC-specific LM, named MonoCoder, which is orders of magnitude smaller than existing LMs but delivers better performance on non-HPC and HPC codes. Specifically, we pre-trained MonoCoder on an HPC-specific dataset (named HPCorpus) of C and C++ programs mined from GitHub. We evaluated the performance of MonoCoder against state-of-the-art multi-lingual LLMs. Results demonstrate that MonoCoder, although much smaller than existing LMs, outperforms other LLMs on normalized-perplexity tests (in relation to model size) while also delivering competing CodeBLEU scores for high-performance and parallel code generations. In other words, results suggest that MonoCoder understands HPC code better than state-of-the-art LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_13322 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks Kadosh, Tal Hasabnis, Niranjan Vo, Vy A. Schneider, Nadav Krien, Neva Capota, Mihai Wasay, Abdul Ahmed, Nesreen Willke, Ted Tamir, Guy Pinter, Yuval Mattson, Timothy Oren, Gal Programming Languages Artificial Intelligence Machine Learning Software Engineering With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks from the high-performance computing (HPC) domain are huge in size and demand expensive compute resources for training. This is partly because LLMs for HPC tasks are obtained by finetuning existing LLMs that support several natural and/or programming languages. We found this design choice confusing - why do we need LLMs trained on natural languages and programming languages unrelated to HPC for HPC-specific tasks? In this line of work, we aim to question choices made by existing LLMs by developing smaller language models (LMs) for specific domains - we call them domain-specific LMs. Specifically, we start with HPC as a domain and build an HPC-specific LM, named MonoCoder, which is orders of magnitude smaller than existing LMs but delivers better performance on non-HPC and HPC codes. Specifically, we pre-trained MonoCoder on an HPC-specific dataset (named HPCorpus) of C and C++ programs mined from GitHub. We evaluated the performance of MonoCoder against state-of-the-art multi-lingual LLMs. Results demonstrate that MonoCoder, although much smaller than existing LMs, outperforms other LLMs on normalized-perplexity tests (in relation to model size) while also delivering competing CodeBLEU scores for high-performance and parallel code generations. In other words, results suggest that MonoCoder understands HPC code better than state-of-the-art LLMs. |
| title | MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks |
| topic | Programming Languages Artificial Intelligence Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2312.13322 |