Showing 1–13 of 13 results for author: Raffenetti, K

Implementing True MPI Sessions and Evaluating MPI Initialization Scalability

Authors: Hui Zhou, Kenneth Raffenetti, Yanfei Guo, Michael Wilkins, Rajeev Thakur

Abstract: Sessions is one of the major features introduced in the MPI-4 standard. It offers an alternative to the traditional world communicator model by allowing applications to construct communicators from process sets, thereby eliminating the dependency on MPI_COMM_WORLD. The Sessions model was proposed as a more scalable solution for exascale systems, where MPI_COMM_WORLD was viewed as a potential scala… ▽ More Sessions is one of the major features introduced in the MPI-4 standard. It offers an alternative to the traditional world communicator model by allowing applications to construct communicators from process sets, thereby eliminating the dependency on MPI_COMM_WORLD. The Sessions model was proposed as a more scalable solution for exascale systems, where MPI_COMM_WORLD was viewed as a potential scalability bottleneck. However, supporting Sessions is a significant challenge for established codebases like MPICH due to the deep integration of the world model in traditional MPI implementations. Although MPICH added support for the MPI-4 standard upon its release, it still internally relied on a global world communicator. This approach enabled applications written using the Sessions model to function, but it did not fulfill the full design intent of Sessions, which meant to decouple MPI from MPI_COMM_WORLD. We describe MPICH effort to support true MPI Sessions, including a major internal refactoring. We describe the architectural changes required to support true Sessions and evaluate the resulting implementation scalability. Our results demonstrate that true Sessions can offer significant scalability benefits by adopting explicit hierarchical designs. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Comments: European MPI Users' Group Meeting. 2025

FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access

Authors: Aditya Tanikanti, Benoit Côté, Yanfei Guo, Le Chen, Nickolaus Saint, Ryan Chard, Ken Raffenetti, Rajeev Thakur, Thomas Uram, Ian Foster, Michael E. Papka, Venkatram Vishwanath

Abstract: We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FIRST provides cloud-like access to diverse AI models, like Large Language Models (LLMs), on existing HPC infrastructure. Leveraging Globus Auth and Globus Compute, the system allows researchers to run parallel inference w… ▽ More We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FIRST provides cloud-like access to diverse AI models, like Large Language Models (LLMs), on existing HPC infrastructure. Leveraging Globus Auth and Globus Compute, the system allows researchers to run parallel inference workloads via an OpenAI-compliant API on private, secure environments. This cluster-agnostic API allows requests to be distributed across federated clusters, targeting numerous hosted models. FIRST supports multiple inference backends (e.g., vLLM), auto-scales resources, maintains "hot" nodes for low-latency execution, and offers both high-throughput batch and interactive modes. The framework addresses the growing demand for private, secure, and scalable AI inference in scientific workflows, allowing researchers to generate billions of tokens daily on-premises without relying on commercial cloud infrastructure. △ Less

Submitted 15 October, 2025; originally announced October 2025.

Journal ref: SC Workshops '25, Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, ACM, pp. 52-60, 2025

ZCCL: Significantly Improving Collective Communication With Error-Bounded Lossy Compression

Authors: Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Zhaorui Zhang, Jinyang Liu, Xiaoyi Lu, Ken Raffenetti, Hui Zhou, Kai Zhao, Khalid Alharthi, Zizhong Chen, Franck Cappello, Yanfei Guo, Rajeev Thakur

Abstract: With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communication turns out to be a critical bottleneck in large-scale distributed and parallel processing. The large message size in MPI collectives is particularly concerning because it can significantly degrade overall parallel performance. To address this is… ▽ More With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communication turns out to be a critical bottleneck in large-scale distributed and parallel processing. The large message size in MPI collectives is particularly concerning because it can significantly degrade overall parallel performance. To address this issue, prior research simply applies off-the-shelf fixed-rate lossy compressors in the MPI collectives, leading to suboptimal performance, limited generalizability, and unbounded errors. In this paper, we propose a novel solution, called ZCCL, which leverages error-bounded lossy compression to significantly reduce the message size, resulting in a substantial reduction in communication costs. The key contributions are three-fold. (1) We develop two general, optimized lossy-compression-based frameworks for both types of MPI collectives (collective data movement as well as collective computation), based on their particular characteristics. Our framework not only reduces communication costs but also preserves data accuracy. (2) We customize fZ-light, an ultra-fast error-bounded lossy compressor, to meet the specific needs of collective communication. (3) We integrate ZCCL into multiple collectives, such as Allgather, Allreduce, Scatter, and Broadcast, and perform a comprehensive evaluation based on real-world scientific application datasets. Experiments show that our solution outperforms the original MPI collectives as well as multiple baselines by 1.9--8.9X. △ Less

Submitted 25 February, 2025; originally announced February 2025.

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

Authors: Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus, Aditya Tanikanti, Ken Raffenetti, Valerie Taylor, Murali Emani, Venkatram Vishwanath

Abstract: Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges, requiring efficient hardware acceleration. Benchmarking the performance of LLMs across diverse hardware platforms is crucial to understanding their scalability a… ▽ More Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational demands of these complex models pose significant challenges, requiring efficient hardware acceleration. Benchmarking the performance of LLMs across diverse hardware platforms is crucial to understanding their scalability and throughput characteristics. We introduce LLM-Inference-Bench, a comprehensive benchmarking suite to evaluate the hardware inference performance of LLMs. We thoroughly analyze diverse hardware platforms, including GPUs from Nvidia and AMD and specialized AI accelerators, Intel Habana and SambaNova. Our evaluation includes several LLM inference frameworks and models from LLaMA, Mistral, and Qwen families with 7B and 70B parameters. Our benchmarking results reveal the strengths and limitations of various models, hardware platforms, and inference frameworks. We provide an interactive dashboard to help identify configurations for optimal performance for a given hardware platform. △ Less

Submitted 31 October, 2024; originally announced November 2024.

MPI Progress For All

Authors: Hui Zhou, Robert Latham, Ken Raffenetti, Yanfei Guo, Rajeev Thakur

Abstract: The progression of communication in the Message Passing Interface (MPI) is not well defined, yet it is critical for application performance, particularly in achieving effective computation and communication overlap. The opaque nature of MPI progress poses significant challenges in advancing MPI within modern high-performance computing (HPC) practices. Firstly, the lack of clarity hinders the devel… ▽ More The progression of communication in the Message Passing Interface (MPI) is not well defined, yet it is critical for application performance, particularly in achieving effective computation and communication overlap. The opaque nature of MPI progress poses significant challenges in advancing MPI within modern high-performance computing (HPC) practices. Firstly, the lack of clarity hinders the development of explicit guidelines for enhancing computation and communication overlap in applications. Secondly, it prevents MPI from seamlessly integrating with contemporary programming paradigms, such as task-based runtimes and event-driven programming. Thirdly, it limits the extension of MPI functionalities from the user space. In this paper, we examine the role of MPI progress by analyzing the implementation details of MPI messaging. We then generalize the asynchronous communication pattern and identify key factors influencing application performance. Based on this analysis, we propose a set of MPI extensions designed to enable users to explicitly construct and manage an efficient progress engine. We provide example codes to demonstrate the use of these proposed APIs in achieving improved performance, adapting MPI to task-based or event-driven programming styles, and constructing collective algorithms that rival the performance of native implementations. Our approach is compared to previous efforts in the field, highlighting its reduced complexity and increased effectiveness. △ Less

Submitted 12 July, 2024; v1 submitted 22 May, 2024; originally announced May 2024.

Comments: Not submitted

Designing and Prototyping Extensions to MPI in MPICH

Authors: Hui Zhou, Ken Raffenetti, Yanfei Guo, Thomas Gillis, Robert Latham, Rajeev Thakur

Abstract: As HPC system architectures and the applications running on them continue to evolve, the MPI standard itself must evolve. The trend in current and future HPC systems toward powerful nodes with multiple CPU cores and multiple GPU accelerators makes efficient support for hybrid programming critical for applications to achieve high performance. However, the support for hybrid programming in the MPI s… ▽ More As HPC system architectures and the applications running on them continue to evolve, the MPI standard itself must evolve. The trend in current and future HPC systems toward powerful nodes with multiple CPU cores and multiple GPU accelerators makes efficient support for hybrid programming critical for applications to achieve high performance. However, the support for hybrid programming in the MPI standard has not kept up with recent trends. The MPICH implementation of MPI provides a platform for implementing and experimenting with new proposals and extensions to fill this gap and to gain valuable experience and feedback before the MPI Forum can consider them for standardization. In this work, we detail six extensions implemented in MPICH to increase MPI interoperability with other runtimes, with a specific focus on heterogeneous architectures. First, the extension to MPI generalized requests lets applications integrate asynchronous tasks into MPI's progress engine. Second, the iovec extension to datatypes lets applications use MPI datatypes as a general-purpose data layout API beyond just MPI communications. Third, a new MPI object, MPIX stream, can be used by applications to identify execution contexts beyond MPI processes, including threads and GPU streams. MPIX stream communicators can be created to make existing MPI functions thread-aware and GPU-aware, thus providing applications with explicit ways to achieve higher performance. Fourth, MPIX Streams are extended to support the enqueue semantics for offloading MPI communications onto a GPU stream context. Fifth, thread communicators allow MPI communicators to be constructed with individual threads, thus providing a new level of interoperability between MPI and on-node runtimes such as OpenMP. Lastly, we present an extension to invoke MPI progress, which lets users spawn progress threads with fine-grained control. △ Less

Submitted 19 February, 2024; originally announced February 2024.

Comments: 14 pages. Submitted IJHPCA special issue

Frustrated with MPI+Threads? Try MPIxThreads!

Authors: Hui Zhou, Ken Raffenetti, Junchao Zhang, Yanfei Guo, Rajeev Thakur

Abstract: MPI+Threads, embodied by the MPI/OpenMP hybrid programming model, is a parallel programming paradigm where threads are used for on-node shared-memory parallelization and MPI is used for multi-node distributed-memory parallelization. OpenMP provides an incremental approach to parallelize code, while MPI, with its isolated address space and explicit messaging API, affords straightforward paths to ob… ▽ More MPI+Threads, embodied by the MPI/OpenMP hybrid programming model, is a parallel programming paradigm where threads are used for on-node shared-memory parallelization and MPI is used for multi-node distributed-memory parallelization. OpenMP provides an incremental approach to parallelize code, while MPI, with its isolated address space and explicit messaging API, affords straightforward paths to obtain good parallel performance. However, MPI+Threads is not an ideal solution. Since MPI is unaware of the thread context, it cannot be used for interthread communication. This results in duplicated efforts to create separate and sometimes nested solutions for similar parallel tasks. In addition, because the MPI library is required to obey message-ordering semantics, mixing threads and MPI via MPI_THREAD_MULTIPLE can easily result in miserable performance due to accidental serializations. We propose a new MPI extension, MPIX Thread Communicator (threadcomm), that allows threads to be assigned distinct MPI ranks within thread parallel regions. The threadcomm extension combines both MPI processes and OpenMP threads to form a unified parallel environment. We show that this MPIxThreads (MPI Multiply Threads) paradigm allows OpenMP and MPI to work together in a complementary way to achieve both cleaner codes and better performance. △ Less

Submitted 29 January, 2024; originally announced January 2024.

Generating Bindings in MPICH

Authors: Hui Zhou, Ken Raffenetti, Wesley Bland, Yanfei Guo

Abstract: The MPI Forum has recently adopted a Python scripting engine for generating the API text in the standard document. As a by-product, it made available reliable and rich descriptions of all MPI functions that are suited for scripting tools. Using these extracted API information, we developed a Python code generation toolbox to generate the language binding layers in MPICH. The toolbox replaces nearl… ▽ More The MPI Forum has recently adopted a Python scripting engine for generating the API text in the standard document. As a by-product, it made available reliable and rich descriptions of all MPI functions that are suited for scripting tools. Using these extracted API information, we developed a Python code generation toolbox to generate the language binding layers in MPICH. The toolbox replaces nearly 70,000 lines of manually maintained C and Fortran 2008 binding code with around 5,000 lines of Python scripts plus some simple configuration. In addition to completely eliminating code duplication in the binding layer and avoiding bugs from manual code copying , the code generation also minimizes the effort for API extension and code instrumentation. This is demonstrated in our implementation of MPI-4 large count functions and the prototyping of a next generation MPI profiling interface, QMPI. △ Less

Submitted 29 January, 2024; originally announced January 2024.

gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters

Authors: Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Jinyang Liu, Yafan Huang, Ken Raffenetti, Hui Zhou, Kai Zhao, Xiaoyi Lu, Zizhong Chen, Franck Cappello, Yanfei Guo, Rajeev Thakur

Abstract: GPU-aware collective communication has become a major bottleneck for modern computing platforms as GPU computing power rapidly rises. A traditional approach is to directly integrate lossy compression into GPU-aware collectives, which can lead to serious performance issues such as underutilized GPU devices and uncontrolled data distortion. In order to address these issues, in this paper, we propose… ▽ More GPU-aware collective communication has become a major bottleneck for modern computing platforms as GPU computing power rapidly rises. A traditional approach is to directly integrate lossy compression into GPU-aware collectives, which can lead to serious performance issues such as underutilized GPU devices and uncontrolled data distortion. In order to address these issues, in this paper, we propose gZCCL, a first-ever general framework that designs and optimizes GPU-aware, compression-enabled collectives with an accuracy-aware design to control error propagation. To validate our framework, we evaluate the performance on up to 512 NVIDIA A100 GPUs with real-world applications and datasets. Experimental results demonstrate that our gZCCL-accelerated collectives, including both collective computation (Allreduce) and collective data movement (Scatter), can outperform NCCL as well as Cray MPI by up to 4.5X and 28.7X, respectively. Furthermore, our accuracy evaluation with an image-stacking application confirms the high reconstructed data quality of our accuracy-aware framework. △ Less

Submitted 6 May, 2024; v1 submitted 9 August, 2023; originally announced August 2023.

Comments: 12 pages, 13 figures, and 2 tables. ICS '24

Quantifying the Performance Benefits of Partitioned Communication in MPI

Authors: Thomas Gillis, Ken Raffenetti, Hui Zhou, Yanfei Guo, Rajeev Thakur

Abstract: Partitioned communication was introduced in MPI 4.0 as a user-friendly interface to support pipelined communication patterns, particularly common in the context of MPI+threads. It provides the user with the ability to divide a global buffer into smaller independent chunks, called partitions, which can then be communicated independently. In this work we first model the performance gain that can be… ▽ More Partitioned communication was introduced in MPI 4.0 as a user-friendly interface to support pipelined communication patterns, particularly common in the context of MPI+threads. It provides the user with the ability to divide a global buffer into smaller independent chunks, called partitions, which can then be communicated independently. In this work we first model the performance gain that can be expected when using partitioned communication. Next, we describe the improvements we made to \mpich{} to enable those gains and provide a high-quality implementation of MPI partitioned communication. We then evaluate partitioned communication in various common use cases and assess the performance in comparison with other MPI point-to-point and one-sided approaches. Specifically, we first investigate two scenarios commonly encountered for small partition sizes in a multithreaded environment: thread contention and overhead of using many partitions. We propose two solutions to alleviate the measured penalty and demonstrate their use. We then focus on large messages and the gain obtained when exploiting the delay resulting from computations or load imbalance. We conclude with our perspectives on the benefits of partitioned communication and the various results obtained. △ Less

Submitted 11 August, 2023; v1 submitted 7 August, 2023; originally announced August 2023.

MSC Class: 68M10; 68M14

Accelerating MPI Collectives with Process-in-Process-based Multi-object Techniques

Authors: Jiajun Huang, Kaiming Ouyang, Yujia Zhai, Jinyang Liu, Min Si, Ken Raffenetti, Hui Zhou, Atsushi Hori, Zizhong Chen, Yanfei Guo, Rajeev Thakur

Abstract: In the exascale computing era, optimizing MPI collective performance in high-performance computing (HPC) applications is critical. Current algorithms face performance degradation due to system call overhead, page faults, or data-copy latency, affecting HPC applications' efficiency and scalability. To address these issues, we propose PiP-MColl, a Process-in-Process-based Multi-object Inter-process… ▽ More In the exascale computing era, optimizing MPI collective performance in high-performance computing (HPC) applications is critical. Current algorithms face performance degradation due to system call overhead, page faults, or data-copy latency, affecting HPC applications' efficiency and scalability. To address these issues, we propose PiP-MColl, a Process-in-Process-based Multi-object Inter-process MPI Collective design that maximizes small message MPI collective performance at scale. PiP-MColl features efficient multiple sender and receiver collective algorithms and leverages Process-in-Process shared memory techniques to eliminate unnecessary system call, page fault overhead, and extra data copy, improving intra- and inter-node message rate and throughput. Our design also boosts performance for larger messages, resulting in comprehensive improvement for various message sizes. Experimental results show that PiP-MColl outperforms popular MPI libraries, including OpenMPI, MVAPICH2, and Intel MPI, by up to 4.6X for MPI collectives like MPI_Scatter and MPI_Allgather. △ Less

Submitted 17 May, 2023; originally announced May 2023.

Comments: Accepted by ACM HPDC 2023

An Optimized Error-controlled MPI Collective Framework Integrated with Lossy Compression

Authors: Jiajun Huang, Sheng Di, Xiaodong Yu, Yujia Zhai, Zhaorui Zhang, Jinyang Liu, Xiaoyi Lu, Ken Raffenetti, Hui Zhou, Kai Zhao, Zizhong Chen, Franck Cappello, Yanfei Guo, Rajeev Thakur

Abstract: With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communications turns out to be a critical bottleneck in large-scale distributed and parallel processing. The large message size in MPI collectives is particularly concerning because it can significantly degrade the overall parallel performance. To address th… ▽ More With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communications turns out to be a critical bottleneck in large-scale distributed and parallel processing. The large message size in MPI collectives is particularly concerning because it can significantly degrade the overall parallel performance. To address this issue, prior research simply applies the off-the-shelf fix-rate lossy compressors in the MPI collectives, leading to suboptimal performance, limited generalizability, and unbounded errors. In this paper, we propose a novel solution, called C-Coll, which leverages error-bounded lossy compression to significantly reduce the message size, resulting in a substantial reduction in communication cost. The key contributions are three-fold. (1) We develop two general, optimized lossy-compression-based frameworks for both types of MPI collectives (collective data movement as well as collective computation), based on their particular characteristics. Our framework not only reduces communication cost but also preserves data accuracy. (2) We customize SZx, an ultra-fast error-bounded lossy compressor, to meet the specific needs of collective communication. (3) We integrate C-Coll into multiple collectives, such as MPI_Allreduce, MPI_Scatter, and MPI_Bcast, and perform a comprehensive evaluation based on real-world scientific datasets. Experiments show that our solution outperforms the original MPI collectives as well as multiple baselines and related efforts by 1.8-2.7X. △ Less

Submitted 17 January, 2024; v1 submitted 7 April, 2023; originally announced April 2023.

Comments: 13 pages, 18 figures, 6 tables, IPDPS '24

MPIX Stream: An Explicit Solution to Hybrid MPI+X Programming

Authors: Hui Zhou, Ken Raffenetti, Yanfei Guo, Rajeev Thakur

Abstract: The hybrid MPI+X programming paradigm, where X refers to threads or GPUs, has gained prominence in the high-performance computing arena. This corresponds to a trend of system architectures growing more heterogeneous. The current MPI standard only specifies the compatibility levels between MPI and threading runtimes. No MPI concept or interface exists for applications to pass thread context or GPU… ▽ More The hybrid MPI+X programming paradigm, where X refers to threads or GPUs, has gained prominence in the high-performance computing arena. This corresponds to a trend of system architectures growing more heterogeneous. The current MPI standard only specifies the compatibility levels between MPI and threading runtimes. No MPI concept or interface exists for applications to pass thread context or GPU stream context to MPI implementations explicitly. This lack has made performance optimization complicated in some cases and impossible in other cases. We propose a new concept in MPI, called MPIX stream, to represent the general serial execution context that exists in X runtimes. MPIX streams can be directly mapped to threads or GPU execution streams. Passing thread context into MPI allows implementations to precisely map the execution contexts to network endpoints. Passing GPU execution context into MPI allows implementations to directly operate on GPU streams, lowering the CPU/GPU synchronization cost. △ Less

Submitted 29 August, 2022; v1 submitted 29 August, 2022; originally announced August 2022.

Comments: 10 pages, EuroMPI/USA'22