William Gropp
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
William Gropp has a total of 519 co-authors. Here are the top co-authors by number of shared publications:
Rajeev Thakur
59 shared publicationsEwing Lusk
Argonne National Laboratory, Argonne, IL
25 shared publicationsPavan Balaji
21 shared publicationsDarius Buntinas
13 shared publicationsDavid Goodell
11 shared publications- Luke N. Olson
Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
8 shared publications
Latest Publications
- 7 October 2026
- Published by Springer Nature
- p. 3-19
Core MPI
- Open Access
MIRGE: An Array-Based Computational Framework for Scientific Computing
MIRGE is a computational approach for scientific computing based on NumPy-like array computation, but using lazy evaluation to recast computation as data-flow graphs, where nodes represent immutable, multi-dimensional arrays. Evaluation of an array expression is deferred until its value is needed, at which point a pipeline is invoked that transforms high-level array expressions into lower-level intermediate representations (IR) and finally into executable code, through a multi-stage process. Domain-specific transformations, such as metadata-driven optimizations, GPU-parallelization strategies, and loop fusion techniques, improve performance and memory efficiency. MIRGE employs "array contexts" to abstract the interface between array expressions and heterogeneous execution environments (for example, lazy evaluation via OpenCL, or eager evaluation via NumPy or CuPy). The framework thus enables performance portability as well as separation of concerns between application logic, low-level implementation, and optimizations. By enabling scientific expressivity while facilitating performance tuning, MIRGE offers a robust, extensible platform for both computational research and scientific application development. This paper provides an overview of MIRGE. We further describe an application of MIRGE called MIRGE-Com, for supersonic combusting flows in a discontinuous Galerkin finite-element setting. We demonstrate its capabilities as a solver and highlight its performance characteristics on large-scale GPU hardware.
Open AccessMIRGE: An Array-Based Computational Framework for Scientific Computing
MIRGE is a computational approach for scientific computing based on NumPy-like array computation, but using lazy evaluation to recast computation as data-flow graphs, where nodes represent immutable, multi-dimensional arrays. Evaluation of an array expression is deferred until its value is needed, at which point a pipeline is invoked that transforms high-level array expressions into lower-level intermediate representations (IR) and finally into executable code, through a multi-stage process. Domain-specific transformations, such as metadata-driven optimizations, GPU-parallelization strategies, and loop fusion techniques, improve performance and memory efficiency. MIRGE employs "array contexts" to abstract the interface between array expressions and heterogeneous execution environments (for example, lazy evaluation via OpenCL, or eager evaluation via NumPy or CuPy). The framework thus enables performance portability as well as separation of concerns between application logic, low-level implementation, and optimizations. By enabling scientific expressivity while facilitating performance tuning, MIRGE offers a robust, extensible platform for both computational research and scientific application development. This paper provides an overview of MIRGE. We further describe an application of MIRGE called MIRGE-Com, for supersonic combusting flows in a discontinuous Galerkin finite-element setting. We demonstrate its capabilities as a solver and highlight its performance characteristics on large-scale GPU hardware.
- Open Access
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
DeltaAI: A National Resource for AI/ML Research
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessDeltaAI: A National Resource for AI/ML Research
- Open Access
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 426-436
CommBench: Micro-Benchmarking Hierarchical Networks with Multi-GPU, Multi-NIC Nodes
Modern high-performance computing systems have multiple GPUs and network interface cards (NICs) per node. The resulting network architectures have multilevel hierarchies of subnetworks with different interconnect and software technologies. These systems offer multiple vendor-provided communication capabilities and library implementations (IPC, MPI, NCCL, RCCL, OneCCL) with APIs providing varying levels of performance across the different levels. Understanding this performance is currently difficult because of the wide range of architectures and programming models (CUDA, HIP, OneAPI). We present CommBench, a library with cross-system portability and a high-level API that enables developers to easily build microbenchmarks relevant to their use cases and gain insight into the performance (bandwidth & latency) of multiple implementation libraries on different networks. We demonstrate CommBench with three sets of microbenchmarks that profile the performance of six systems. Our experimental results reveal the effect of multiple NICs on optimizing the bandwidth across nodes and also present the performance characteristics of four available communication libraries within and across nodes of NVIDIA, AMD, and Intel GPU networks.
- 30 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 426-436
Open AccessCommBench: Micro-Benchmarking Hierarchical Networks with Multi-GPU, Multi-NIC Nodes
Modern high-performance computing systems have multiple GPUs and network interface cards (NICs) per node. The resulting network architectures have multilevel hierarchies of subnetworks with different interconnect and software technologies. These systems offer multiple vendor-provided communication capabilities and library implementations (IPC, MPI, NCCL, RCCL, OneCCL) with APIs providing varying levels of performance across the different levels. Understanding this performance is currently difficult because of the wide range of architectures and programming models (CUDA, HIP, OneAPI). We present CommBench, a library with cross-system portability and a high-level API that enables developers to easily build microbenchmarks relevant to their use cases and gain insight into the performance (bandwidth & latency) of multiple implementation libraries on different networks. We demonstrate CommBench with three sets of microbenchmarks that profile the performance of six systems. Our experimental results reveal the effect of multiple NICs on optimizing the bandwidth across nodes and also present the performance characteristics of four available communication libraries within and across nodes of NVIDIA, AMD, and Intel GPU networks.
- Open Access
- 11 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Fine-grained Policy-driven I/O Sharing for Burst Buffers
A burst buffer is a common method to bridge the performance gap between the I/O needs of modern supercomputing applications and the performance of the shared file system on large-scale supercomputers. However, existing I/O sharing methods require resource isolation, offline profiling, or repeated execution that significantly limit the utilization and applicability of these systems. Here we present ThemisIO, a policy-driven I/O sharing framework for a remote-shared burst buffer: a dedicated group of I/O nodes, each with a local storage device. ThemisIO preserves high utilization by implementing opportunity fairness so that it can reallocate unused I/O resources to other applications. ThemisIO accurately and efficiently allocates I/O cycles among applications, purely based on real-time I/O behavior without requiring user-supplied information or offline-profiled application characteristics. ThemisIO supports a variety of fair sharing policies, such as user-fair, size-fair, as well as composite policies, e.g., group-then-user-fair. All these features are enabled by its statistical token design. ThemisIO can alter the execution order of incoming I/O requests based on assigned tokens to precisely balance I/O cycles between applications via time slicing, thereby enforcing processing isolation. Experiments using I/O benchmarks show that ThemisIO sustains 13.5--13.7% higher I/O throughput and 19.5--40.4% lower performance variation than existing algorithms. For real applications, ThemisIO significantly reduces the slowdown by 59.1--99.8% caused by I/O interference.
- 11 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessFine-grained Policy-driven I/O Sharing for Burst Buffers
A burst buffer is a common method to bridge the performance gap between the I/O needs of modern supercomputing applications and the performance of the shared file system on large-scale supercomputers. However, existing I/O sharing methods require resource isolation, offline profiling, or repeated execution that significantly limit the utilization and applicability of these systems. Here we present ThemisIO, a policy-driven I/O sharing framework for a remote-shared burst buffer: a dedicated group of I/O nodes, each with a local storage device. ThemisIO preserves high utilization by implementing opportunity fairness so that it can reallocate unused I/O resources to other applications. ThemisIO accurately and efficiently allocates I/O cycles among applications, purely based on real-time I/O behavior without requiring user-supplied information or offline-profiled application characteristics. ThemisIO supports a variety of fair sharing policies, such as user-fair, size-fair, as well as composite policies, e.g., group-then-user-fair. All these features are enabled by its statistical token design. ThemisIO can alter the execution order of incoming I/O requests based on assigned tokens to precisely balance I/O cycles between applications via time slicing, thereby enforcing processing isolation. Experiments using I/O benchmarks show that ThemisIO sustains 13.5--13.7% higher I/O throughput and 19.5--40.4% lower performance variation than existing algorithms. For real applications, ThemisIO significantly reduces the slowdown by 59.1--99.8% caused by I/O interference.
- Open Access
Fine-grained Policy-driven I/O Sharing for Burst Buffers
A burst buffer is a common method to bridge the performance gap between the I/O needs of modern supercomputing applications and the performance of the shared file system on large-scale supercomputers. However, existing I/O sharing methods require resource isolation, offline profiling, or repeated execution that significantly limit the utilization and applicability of these systems. Here we present ThemisIO, a policy-driven I/O sharing framework for a remote-shared burst buffer: a dedicated group of I/O nodes, each with a local storage device. ThemisIO preserves high utilization by implementing opportunity fairness so that it can reallocate unused I/O resources to other applications. ThemisIO accurately and efficiently allocates I/O cycles among applications, purely based on real-time I/O behavior without requiring user-supplied information or offline-profiled application characteristics. ThemisIO supports a variety of fair sharing policies, such as user-fair, size-fair, as well as composite policies, e.g., group-then-user-fair. All these features are enabled by its statistical token design. ThemisIO can alter the execution order of incoming I/O requests based on assigned tokens to precisely balance I/O cycles between applications via time slicing, thereby enforcing processing isolation. Experiments using I/O benchmarks show that ThemisIO sustains 13.5-13.7% higher I/O throughput and 19.5-40.4% lower performance variation than existing algorithms. For real applications, ThemisIO significantly reduces the slowdown by 59.1-99.8% caused by I/O interference.
Open AccessFine-grained Policy-driven I/O Sharing for Burst Buffers
A burst buffer is a common method to bridge the performance gap between the I/O needs of modern supercomputing applications and the performance of the shared file system on large-scale supercomputers. However, existing I/O sharing methods require resource isolation, offline profiling, or repeated execution that significantly limit the utilization and applicability of these systems. Here we present ThemisIO, a policy-driven I/O sharing framework for a remote-shared burst buffer: a dedicated group of I/O nodes, each with a local storage device. ThemisIO preserves high utilization by implementing opportunity fairness so that it can reallocate unused I/O resources to other applications. ThemisIO accurately and efficiently allocates I/O cycles among applications, purely based on real-time I/O behavior without requiring user-supplied information or offline-profiled application characteristics. ThemisIO supports a variety of fair sharing policies, such as user-fair, size-fair, as well as composite policies, e.g., group-then-user-fair. All these features are enabled by its statistical token design. ThemisIO can alter the execution order of incoming I/O requests based on assigned tokens to precisely balance I/O cycles between applications via time slicing, thereby enforcing processing isolation. Experiments using I/O benchmarks show that ThemisIO sustains 13.5-13.7% higher I/O throughput and 19.5-40.4% lower performance variation than existing algorithms. For real applications, ThemisIO significantly reduces the slowdown by 59.1-99.8% caused by I/O interference.
- Open Access
- 29 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Parallel Computing
- Vol. 10 (1) , 1-25
Performance Analysis and Optimal Node-aware Communication for Enlarged Conjugate Gradient Methods
Krylov methods are a key way of solving large sparse linear systems of equations but suffer from poor strong scalability on distributed memory machines. This is due to high synchronization costs from large numbers of collective communication calls alongside a low computational workload. Enlarged Krylov methods address this issue by decreasing the total iterations to convergence, an artifact of splitting the initial residual and resulting in operations on block vectors. In this article, we present a performance study of an enlarged Krylov method, Enlarged Conjugate Gradients (ECG), noting the impact of block vectors on parallel performance at scale. Most notably, we observe the increased overhead of point-to-point communication as a result of denser messages in the sparse matrix-block vector multiplication kernel. Additionally, we present models to analyze expected performance of ECG, as well as motivate design decisions. Most importantly, we introduce a new point-to-point communication approach based on node-aware communication techniques that increases efficiency of the method at scale.
- 29 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Parallel Computing
- Vol. 10 (1) , 1-25
Open AccessPerformance Analysis and Optimal Node-aware Communication for Enlarged Conjugate Gradient Methods
Krylov methods are a key way of solving large sparse linear systems of equations but suffer from poor strong scalability on distributed memory machines. This is due to high synchronization costs from large numbers of collective communication calls alongside a low computational workload. Enlarged Krylov methods address this issue by decreasing the total iterations to convergence, an artifact of splitting the initial residual and resulting in operations on block vectors. In this article, we present a performance study of an enlarged Krylov method, Enlarged Conjugate Gradients (ECG), noting the impact of block vectors on parallel performance at scale. Most notably, we observe the increased overhead of point-to-point communication as a result of denser messages in the sparse matrix-block vector multiplication kernel. Additionally, we present models to analyze expected performance of ECG, as well as motivate design decisions. Most importantly, we introduce a new point-to-point communication approach based on node-aware communication techniques that increases efficiency of the method at scale.
- 29 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 55 (12) , 12-17
Our Opportunities to Collaborate: In-Person and Virtual, Local and Global, the Society Welcomes New Connections
With a fresh appreciation for “normal,” we are again meeting in person, making new connections, and even enjoying some of the new platforms, perspectives, and strategies that emerged to support our activities during the COVID pandemic. As 2022 draws to a close, IEEE Computer Society President William Gropp talks with Forrest Shull (2021 Computer Society President) about the advantages we gained this year, and how we can continue to build on them in new collaborations and activities.
- 29 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 55 (12) , 12-17
Our Opportunities to Collaborate: In-Person and Virtual, Local and Global, the Society Welcomes New Connections
With a fresh appreciation for “normal,” we are again meeting in person, making new connections, and even enjoying some of the new platforms, perspectives, and strategies that emerged to support our activities during the COVID pandemic. As 2022 draws to a close, IEEE Computer Society President William Gropp talks with Forrest Shull (2021 Computer Society President) about the advantages we gained this year, and how we can continue to build on them in new collaborations and activities.
- Open Access
- 6 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IT Professional
- Vol. 24 (2) , C3
IEEE Computer Society
- 6 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IT Professional
- Vol. 24 (2) , C3
Open AccessIEEE Computer Society
- Open Access
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 42 (2) , 85
IEEE Computer Society
Provides a listing of current committee members and society officers.
- 28 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 42 (2) , 85
Open AccessIEEE Computer Society
Provides a listing of current committee members and society officers.