Tristan Vanderbruggen

Tristan Vanderbruggen

Auto-generated profile, based on publicly available information

Tristan Vanderbruggen

Lawrence Livermore National Laboratory, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2023
Verified
Conference Paper
Open access
XDXianzhong Ding
Xianzhong Ding
LCLe Chen
Le Chen
MEMurali Emani
Murali Emani
CLChunhua Liao
Chunhua Liao
PLPeihung Lin
Peihung Lin
Wan DuWan Du
Wan Du
Large Language Models (LLMs), including the LLaMA model, have exhibited their efficacy across various general-domain natural language processing (NLP) tasks. However, their performance in high-performance computing (HPC) domain tasks has been less than optimal due to the specialized expertise required to interpret the model’s responses. In response to this challenge, we propose HPC-GPT, a novel LLaMA-based model that has been supervised fine-tuning using generated QA (Question-Answer) instances for the HPC domain. To evaluate its effectiveness, we concentrate on two HPC tasks: managing AI models and datasets for HPC, and data race detection. By employing HPC-GPT, we demonstrate comparable performance with existing methods on both tasks, exemplifying its excellence in HPC-related scenarios. Our experiments on open-source benchmarks yield extensive results, underscoring HPC-GPT’s potential to bridge the performance gap between LLMs and HPC-specific tasks. With HPC-GPT, we aim to pave the way for LLMs to excel in HPC domains, simplifying the utilization of language models in complex computing applications.

12 November 2023
Verified
Conference Paper
Open access
LCLe Chen
Le Chen
XDXianzhong Ding
Xianzhong Ding
MEMurali Emani
Murali Emani
TVTristan Vanderbruggen
Tristan Vanderbruggen
PLPeihung Lin
Peihung Lin
CLChunhua Liao
Chunhua Liao
Large language models (LLMs) are demonstrating significant promise as an alternate strategy to facilitate analyses and optimizations of high-performance computing programs, circumventing the need for resource-intensive manual tool creation. In this paper, we explore a novel LLM-based data race detection approach combining prompting engineering and fine-tuning techniques. We create a dedicated dataset named DRB-ML, which is derived from DataRaceBench, with fine-grain labels showing the presence of data race pairs and their associated variables, line numbers, and read/write information. DRB-ML is then used to evaluate representative LLMs and fine-tune open-source ones. Our experiment shows that LLMs can be a viable approach to data race detection. However, they still cannot compete with traditional data race detection tools when we need detailed information about variable pairs causing data races.

1 November 2019
Verified
Conference Paper
Open access
MLMichael O. Lam
Michael O. Lam
TVTristan Vanderbruggen
Tristan Vanderbruggen
HMHarshitha Menon
Harshitha Menon
MSMarkus Schordan
Markus Schordan
Mixed-precision computing offers potential data size reduction and performance improvement at the cost of accuracy, a tradeoff that many practitioners in high-performance computing and related fields are becoming more interested in as workloads become increasingly communication-bound. However, it can be difficult to build valid mixed-precision configurations and navigate the performance/accuracy space without the help of automated tools. We present FloatSmith, an open-source, end-to-end source-level mixed-precision tuner that incorporates several software tools (CRAFT, TypeForge, and ADAPT) into an integrated tool chain.