Niranjan Hasabnis

Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed et al.

Large language models (LLMs) have become increasingly prominent in academia and industry due to their remarkable performance in diverse applications. As these models evolve with increasing parameters, they excel in tasks like sentiment analysis and machine translation. However, even models with billions of parameters face challenges in tasks demanding multi-step reasoning. Code generation and comprehension, especially in C and C++, emerge as significant challenges. While LLMs trained on code datasets demonstrate competence in many tasks, they struggle with rectifying non-compilable C and C++ code. Our investigation attributes this subpar performance to two primary factors: the quality of the training dataset and the inherent complexity of the problem which demands intricate reasoning. Existing "Chain of Thought" (CoT) prompting techniques aim to enhance multi-step reasoning. This approach, however, retains the limitations associated with the latent drawbacks of LLMs. In this work, we propose CompCodeVet, a compiler-guided CoT approach to produce compilable code from non-compilable ones. Diverging from the conventional approach of utilizing larger LLMs, we employ compilers as a teacher to establish a more robust zero-shot thought process. The evaluation of CompCodeVet on two open-source code datasets shows that CompCodeVet has the ability to improve the training dataset quality for LLMs.

Niranjan Hasabnis

Open-source repositories provide wealth of information and are increasingly being used to build artificial intelligence (AI) based systems to solve problems in software engineering. Open-source repositories could be of varying quality levels, and bad-quality repositories could degrade performance of these systems. Evaluating quality of open-source repositories, which is not available directly on code hosting sites such as GitHub, is thus important. In this hackathon, we utilize known code quality measures and GrimoireLab toolkit to implement a framework, named GitRank, to rank open-source repositories on three different criteria. We discuss our findings and preliminary evaluation in this hackathon report.

Niranjan Hasabnis

Machine programming (MP) is an emerging field at the intersection of deterministic and probabilistic computing, and it aims to assist software and hardware engineers, among other applications. Along with powerful compute resources, MP systems often rely on vast amount of open-source code to learn interesting properties about code and programming and solve problems in the areas of debugging, code recommendation, auto-completion, etc. Unfortunately, several of the existing MP systems either do not consider quality of code repositories or use atypical quality measures than those typically used in software engineering community to select them. As such, impact of quality of code repositories on the performance of these systems needs to be studied. In this preliminary paper, we evaluate impact of different quality repositories on the performance of a candidate MP system. Towards that objective, we develop a framework, named GitRank, to rank open-source repositories on quality, maintainability, and popularity by leveraging existing research on this topic. We then apply GitRank to evaluate correlation between the quality measures used by the candidate MP system and the quality measures used by our framework. Our preliminary results reveal some correlation between the quality measures used in GitRank and ControlFlag's performance, suggesting that some of the measures used in GitRank are applicable to ControlFlag. But it also raises questions around right quality measures for code repositories used in MP systems. We believe that our findings also generate interesting insights towards code quality measures that affect performance of MP systems.

Gregory Bolet, Giorgis Georgakoudis, Konstantinos Parasyris et al.

Modern GPU software stacks demand developers who can anticipate performance bottlenecks before ever launching a kernel; misjudging floating-point workloads upstream can derail tuning, scheduling, and even hardware procurement. Yet despite rapid progress in code generation, today's Large Language Models (LLMs) are rarely tested on this kind of forward-looking reasoning. We close that gap with gpuFLOPBench, a benchmark that asks models to "count without running" by predicting single and double-precision FLOP counts for 577 CUDA kernels drawn from HeCBench, annotated with ground-truth profiles and eight execution attributes that distinguish trivially analyzable code from kernels whose FLOPs depend on hidden compiler or runtime behavior. Evaluating current closed-source reasoning models shows clear but uneven progress: the newest LLMs achieve perfect classification on straightforward kernels but still incur multiple order-of-magnitude errors whenever implicit FLOPs arise from division, intrinsic math functions, or common subexpressions. These results surface a core limitation of existing code assistants -- the inability to internalize hardware-specific microcode effects -- and position gpuFLOPBench as a focused testbed for developing LLM tooling that can reason about performance with the same rigor as experienced GPU developers. Sources are available at our repository: https://github.com/Scientific-Computing-Lab/gpuFLOPBench

Tal Kadosh, Niranjan Hasabnis, Vy A. Vo et al.

With easier access to powerful compute resources, there is a growing trend in the field of AI for software development to develop larger and larger 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 (e.g., billions of parameters) and demand expensive compute resources for training. We found this design choice confusing - why do we need large LLMs trained on natural languages and programming languages unrelated to HPC for HPC-specific tasks? In this line of work, we aim to question design choices made by existing LLMs by developing smaller LLMs for specific domains - we call them domain-specific LLMs. Specifically, we start off with HPC as a domain and propose a novel tokenizer named Tokompiler, designed specifically for preprocessing code in HPC and compilation-centric tasks. Tokompiler leverages knowledge of language primitives to generate language-oriented tokens, providing a context-aware understanding of code structure while avoiding human semantics attributed to code structures completely. We applied Tokompiler to pre-train two state-of-the-art models, SPT-Code and Polycoder, for a Fortran code corpus mined from GitHub. We evaluate the performance of these models against the conventional LLMs. Results demonstrate that Tokompiler significantly enhances code completion accuracy and semantic understanding compared to traditional tokenizers in normalized-perplexity tests, down to ~1 perplexity score. This research opens avenues for further advancements in domain-specific LLMs, catering to the unique demands of HPC and compilation tasks.

Tal Kadosh, Niranjan Hasabnis, Prema Soundararajan et al.

Manual parallelization of code remains a significant challenge due to the complexities of modern software systems and the widespread adoption of multi-core architectures. This paper introduces OMPar, an AI-driven tool designed to automate the parallelization of C/C++ code using OpenMP pragmas. OMPar integrates Large Language Models (LLMs) through two key components: OMPify, which assesses loop parallelization potential, and MonoCoder-OMP, a new fine-tuned model which generates precise OpenMP pragmas. The evaluation of OMPar follows the same rigorous process applied to traditional tools like source-to-source AutoPar and ICPC compilers: (1) ensuring the generated code compiles and runs correctly in serial form, (2) assessing performance with the gradual addition of threads and corresponding physical cores, and (3) verifying and validating the correctness of the code's output. Benchmarks from HeCBench and ParEval are used to evaluate accuracy and performance. Experimental results demonstrate that OMPar significantly outperforms traditional methods, achieving higher accuracy in identifying parallelizable loops and generating efficient pragmas. Beyond accuracy, OMPar offers advantages such as the ability to work on partial or incomplete codebases and the capacity to continuously learn from new code patterns, enhancing its parallelization capabilities over time. These results underscore the potential of LLMs in revolutionizing automatic parallelization techniques, paving the way for more efficient and scalable parallel computing systems.

Mohammad Hossain, Derssie Mebratu, Niranjan Hasabnis et al.

Workloads in modern cloud data centers are becoming increasingly complex. The number of workloads running in cloud data centers has been growing exponentially for the last few years, and cloud service providers (CSP) have been supporting on-demand services in real-time. Realizing the growing complexity of cloud environment and cloud workloads, hardware vendors such as Intel and AMD are increasingly introducing cloud-specific workload acceleration features in their CPU platforms. These features are typically targeted towards popular and commonly-used cloud workloads. Nonetheless, uncommon, customer-specific workloads (unknown workloads), if their characteristics are different from common workloads (known workloads), may not realize the potential of the underlying platform. To address this problem of realizing the full potential of the underlying platform, we develop a machine learning based technique to characterize, profile and predict workloads running in the cloud environment. Experimental evaluation of our technique demonstrates good prediction performance. We also develop techniques to analyze the performance of the model in a standalone manner.

Nadav Schneider, Niranjan Hasabnis, Vy A. Vo et al.

The imperative need to scale computation across numerous nodes highlights the significance of efficient parallel computing, particularly in the realm of Message Passing Interface (MPI) integration. The challenging parallel programming task of generating MPI-based parallel programs has remained unexplored. This study first investigates the performance of state-of-the-art language models in generating MPI-based parallel programs. Findings reveal that widely used models such as GPT-3.5 and PolyCoder (specialized multi-lingual code models) exhibit notable performance degradation, when generating MPI-based programs compared to general-purpose programs. In contrast, domain-specific models such as MonoCoder, which are pretrained on MPI-related programming languages of C and C++, outperform larger models. Subsequently, we introduce a dedicated downstream task of MPI-based program generation by fine-tuning MonoCoder on HPCorpusMPI. We call the resulting model as MPIrigen. We propose an innovative preprocessing for completion only after observing the whole code, thus enabling better completion with a wider context. Comparative analysis against GPT-3.5 zero-shot performance, using a novel HPC-oriented evaluation method, demonstrates that MPIrigen excels in generating accurate MPI functions up to 0.8 accuracy in location and function predictions, and with more than 0.9 accuracy for argument predictions. The success of this tailored solution underscores the importance of domain-specific fine-tuning in optimizing language models for parallel computing code generation, paving the way for a new generation of automatic parallelization tools. The sources of this work are available at our GitHub MPIrigen repository: https://github.com/Scientific-Computing-Lab-NRCN/MPI-rigen

Arijit Bhattacharjee, Ali TehraniJamsaz, Le Chen et al.

Recent advances in large language models (LLMs) have significantly accelerated progress in code translation, enabling more accurate and efficient transformation across programming languages. While originally developed for natural language processing, LLMs have shown strong capabilities in modeling programming language syntax and semantics, outperforming traditional rule-based systems in both accuracy and flexibility. These models have streamlined cross-language conversion, reduced development overhead, and accelerated legacy code migration. In this paper, we introduce OMPILOT, a novel domain-specific encoder-decoder transformer tailored for translating C++ code into OpenMP, enabling effective shared-memory parallelization. OMPILOT leverages custom pre-training objectives that incorporate the semantics of parallel constructs and combines both unsupervised and supervised learning strategies to improve code translation robustness. Unlike previous work that focused primarily on loop-level transformations, OMPILOT operates at the function level to capture a wider semantic context. To evaluate our approach, we propose OMPBLEU, a novel composite metric specifically crafted to assess the correctness and quality of OpenMP parallel constructs, addressing limitations in conventional translation metrics.

Renato Golin, Lorenzo Chelini, Adam Siemieniuk et al.

This work proposes a compilation flow using open-source compiler passes to build a framework to achieve ninja performance from a generic linear algebra high-level abstraction. We demonstrate this flow with a proof-of-concept MLIR project that uses input IR in Linalg-on-Tensor from TensorFlow and PyTorch, performs cache-level optimizations and lowering to micro-kernels for efficient vectorization, achieving over 90% of the performance of ninja-written equivalent programs. The contributions of this work include: (1) Packing primitives on the tensor dialect and passes for cache-aware distribution of tensors (single and multi-core) and type-aware instructions (VNNI, BFDOT, BFMMLA), including propagation of shapes across the entire function; (2) A linear algebra pipeline, including tile, fuse and bufferization strategies to get model-level IR into hardware friendly tile calls; (3) A mechanism for micro-kernel lowering to an open source library that supports various CPUs.

Tal Kadosh, Nadav Schneider, Niranjan Hasabnis et al.

There is an ever-present need for shared memory parallelization schemes to exploit the full potential of multi-core architectures. The most common parallelization API addressing this need today is OpenMP. Nevertheless, writing parallel code manually is complex and effort-intensive. Thus, many deterministic source-to-source (S2S) compilers have emerged, intending to automate the process of translating serial to parallel code. However, recent studies have shown that these compilers are impractical in many scenarios. In this work, we combine the latest advancements in the field of AI and natural language processing (NLP) with the vast amount of open-source code to address the problem of automatic parallelization. Specifically, we propose a novel approach, called OMPify, to detect and predict the OpenMP pragmas and shared-memory attributes in parallel code, given its serial version. OMPify is based on a Transformer-based model that leverages a graph-based representation of source code that exploits the inherent structure of code. We evaluated our tool by predicting the parallelization pragmas and attributes of a large corpus of (over 54,000) snippets of serial code written in C and C++ languages (Open-OMP-Plus). Our results demonstrate that OMPify outperforms existing approaches, the general-purposed and popular ChatGPT and targeted PragFormer models, in terms of F1 score and accuracy. Specifically, OMPify achieves up to 90% accuracy on commonly-used OpenMP benchmark tests such as NAS, SPEC, and PolyBench. Additionally, we performed an ablation study to assess the impact of different model components and present interesting insights derived from the study. Lastly, we also explored the potential of using data augmentation and curriculum learning techniques to improve the model's robustness and generalization capabilities.

Nadav Schneider, Tal Kadosh, Niranjan Hasabnis et al.

Message Passing Interface (MPI) plays a crucial role in distributed memory parallelization across multiple nodes. However, parallelizing MPI code manually, and specifically, performing domain decomposition, is a challenging, error-prone task. In this paper, we address this problem by developing MPI-RICAL, a novel data-driven, programming-assistance tool that assists programmers in writing domain decomposition based distributed memory parallelization code. Specifically, we train a supervised language model to suggest MPI functions and their proper locations in the code on the fly. We also introduce MPICodeCorpus, the first publicly available corpus of MPI-based parallel programs that is created by mining more than 15,000 open-source repositories on GitHub. Experimental results have been done on MPICodeCorpus and more importantly, on a compiled benchmark of MPI-based parallel programs for numerical computations that represent real-world scientific applications. MPI-RICAL achieves F1 scores between 0.87-0.91 on these programs, demonstrating its accuracy in suggesting correct MPI functions at appropriate code locations.. The source code used in this work, as well as other relevant sources, are available at: https://github.com/Scientific-Computing-Lab-NRCN/MPI-rical

Le Chen, Nesreen K. Ahmed, Akash Dutta et al.

Recently, language models (LMs), especially large language models (LLMs), have revolutionized the field of deep learning. Both encoder-decoder models and prompt-based techniques have shown immense potential for natural language processing and code-based tasks. Over the past several years, many research labs and institutions have invested heavily in high-performance computing, approaching or breaching exascale performance levels. In this paper, we posit that adapting and utilizing such language model-based techniques for tasks in high-performance computing (HPC) would be very beneficial. This study presents our reasoning behind the aforementioned position and highlights how existing ideas can be improved and adapted for HPC tasks.

Le Chen, Arijit Bhattacharjee, Nesreen Ahmed et al.

Large language models (LLMs)such as ChatGPT have significantly advanced the field of Natural Language Processing (NLP). This trend led to the development of code-based large language models such as StarCoder, WizardCoder, and CodeLlama, which are trained extensively on vast repositories of code and programming languages. While the generic abilities of these code LLMs are useful for many programmers in tasks like code generation, the area of high-performance computing (HPC) has a narrower set of requirements that make a smaller and more domain-specific model a smarter choice. This paper presents OMPGPT, a novel domain-specific model meticulously designed to harness the inherent strengths of language models for OpenMP pragma generation. Furthermore, we leverage prompt engineering techniques from the NLP domain to create Chain-of-OMP, an innovative strategy designed to enhance OMPGPT's effectiveness. Our extensive evaluations demonstrate that OMPGPT outperforms existing large language models specialized in OpenMP tasks and maintains a notably smaller size, aligning it more closely with the typical hardware constraints of HPC environments. We consider our contribution as a pivotal bridge, connecting the advantage of language models with the specific demands of HPC tasks.

Tal Kadosh, Niranjan Hasabnis, Vy A. Vo et al.

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.

Gregory Bolet, Giorgis Georgakoudis, Harshitha Menon et al.

Accurate determination of the performance of parallel GPU code typically requires execution-time profiling on target hardware -- an increasingly prohibitive step due to limited access to high-end GPUs. This paper explores whether Large Language Models (LLMs) can offer an alternative approach for GPU performance prediction without relying on hardware. We frame the problem as a roofline classification task: given the source code of a GPU kernel and the hardware specifications of a target GPU, can an LLM predict whether the GPU kernel is compute-bound or bandwidth-bound? For this study, we build a balanced dataset of 340 GPU kernels, obtained from HeCBench benchmark and written in CUDA and OpenMP, along with their ground-truth labels obtained via empirical GPU profiling. We evaluate LLMs across four scenarios: (1) with access to profiling data of the kernel source, (2) zero-shot with source code only, (3) few-shot with code and label pairs, and (4) fine-tuned on a small custom dataset. Our results show that state-of-the-art LLMs have a strong understanding of the Roofline model, achieving 100% classification accuracy when provided with explicit profiling data. We also find that reasoning-capable LLMs significantly outperform standard LLMs in zero- and few-shot settings, achieving up to 64% accuracy on GPU source codes, without profiling information. Lastly, we find that LLM fine-tuning will require much more data than what we currently have available. This work is among the first to use LLMs for source-level roofline performance prediction via classification, and illustrates their potential to guide optimization efforts when runtime profiling is infeasible. Our findings suggest that with better datasets and prompt strategies, LLMs could become practical tools for HPC performance analysis and performance portability.

Erel Kaplan, Tomer Bitan, Lian Ghrayeb et al.

Parallel programming is central to HPC and AI, but producing code that is correct and fast remains challenging, especially for OpenMP GPU offload, where data movement and tuning dominate. Autonomous coding agents can compile, test, and profile on target hardware, but outputs are brittle without domain scaffolding. We present ParaCodex, an HPC-engineer workflow that turns a Codex-based agent into an autonomous OpenMP GPU offload system using staged hotspot analysis, explicit data planning, correctness gating, and profiling-guided refinement. We evaluate translation from serial CPU kernels to OpenMP GPU offload kernels on HeCBench, Rodinia, and NAS. After excluding five kernels, ParaCodex succeeded on all 31 valid kernels. The generated kernels improved GPU time over reference OpenMP implementations in 25/31 cases, achieving geometric-mean speedups of 3x on HeCBench and 5x on Rodinia, and outperforming a zero-shot Codex baseline on all suites. We also evaluate CUDA to OpenMP offload translation on ParEval, where ParaCodex maintains high compilation and validation rates in code-only and end-to-end settings.

Derssie Mebratu, Niranjan Hasabnis, Pietro Mercati et al.

Modern deep learning (DL) applications are built using DL libraries and frameworks such as TensorFlow and PyTorch. These frameworks have complex parameters and tuning them to obtain good training and inference performance is challenging for typical users, such as DL developers and data scientists. Manual tuning requires deep knowledge of the user-controllable parameters of DL frameworks as well as the underlying hardware. It is a slow and tedious process, and it typically delivers sub-optimal solutions. In this paper, we treat the problem of tuning parameters of DL frameworks to improve training and inference performance as a black-box optimization problem. We then investigate applicability and effectiveness of Bayesian optimization (BO), genetic algorithm (GA), and Nelder-Mead simplex (NMS) to tune the parameters of TensorFlow's CPU backend. While prior work has already investigated the use of Nelder-Mead simplex for a similar problem, it does not provide insights into the applicability of other more popular algorithms. Towards that end, we provide a systematic comparative analysis of all three algorithms in tuning TensorFlow's CPU backend on a variety of DL models. Our findings reveal that Bayesian optimization performs the best on the majority of models. There are, however, cases where it does not deliver the best results.

Niranjan Hasabnis, Justin Gottschlich

Software debugging has been shown to utilize upwards of half of developers' time. Yet, machine programming (MP), the field concerned with the automation of software (and hardware) development, has recently made strides in both research and production-quality automated debugging systems. In this paper we present ControlFlag, a self-supervised MP system that aims to improve debugging by attempting to detect idiosyncratic pattern violations in software control structures. ControlFlag also suggests possible corrections in the event an anomalous pattern is detected. We present ControlFlag's design and provide an experimental evaluation and analysis of its efficacy in identifying potential programming errors in production-quality software. As a first concrete evidence towards improving software quality, ControlFlag has already found an anomaly in CURL that has been acknowledged and fixed by its developers. We also discuss future extensions of ControlFlag.

Fangke Ye, Shengtian Zhou, Anand Venkat et al.

Code semantics similarity can be used for many tasks such as code recommendation, automated software defect correction, and clone detection. Yet, the accuracy of such systems has not yet reached a level of general purpose reliability. To help address this, we present Machine Inferred Code Similarity (MISIM), a neural code semantics similarity system consisting of two core components: (i)MISIM uses a novel context-aware semantics structure, which was purpose-built to lift semantics from code syntax; (ii)MISIM uses an extensible neural code similarity scoring algorithm, which can be used for various neural network architectures with learned parameters. We compare MISIM to four state-of-the-art systems, including two additional hand-customized models, over 328K programs consisting of over 18 million lines of code. Our experiments show that MISIM has 8.08% better accuracy (using MAP@R) compared to the next best performing system.

Niranjan Hasabnis

TensorFlow is a popular deep learning framework used by data scientists to solve a wide-range of machine learning and deep learning problems such as image classification and speech recognition. It also operates at a large scale and in heterogeneous environments --- it allows users to train neural network models or deploy them for inference using GPUs, CPUs and deep learning specific custom-designed hardware such as TPUs. Even though TensorFlow supports a variety of optimized backends, realizing the best performance using a backend may require additional efforts. For instance, getting the best performance from a CPU backend requires careful tuning of its threading model. Unfortunately, the best tuning approach used today is manual, tedious, time-consuming, and, more importantly, may not guarantee the best performance. In this paper, we develop an automatic approach, called TensorTuner, to search for optimal parameter settings of TensorFlow's threading model for CPU backends. We evaluate TensorTuner on both Eigen and Intel's MKL CPU backends using a set of neural networks from TensorFlow's benchmarking suite. Our evaluation results demonstrate that the parameter settings found by TensorTuner produce 2% to 123% performance improvement for the Eigen CPU backend and 1.5% to 28% performance improvement for the MKL CPU backend over the performance obtained using their best-known parameter settings. This highlights the fact that the default parameter settings in Eigen CPU backend are not the ideal settings; and even for a carefully hand-tuned MKL backend, the settings may be sub-optimal. Our evaluations also revealed that TensorTuner is efficient at finding the optimal settings --- it is able to converge to the optimal settings quickly by pruning more than 90% of the parameter search space.