Aaron Welch
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
Research Interests
Aaron Welch has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Oscar Hernandez
Oak Ridge National Laboratory, Oak Ridge, USA
7 shared publications - Stephen Poole
Los Alamos National Laboratory, Los Alamos, USA
6 shared publications - Akihiro Hayashi
Georgia Institute of Technology, Atlanta, USA
3 shared publications - Shubhendra Pal Singhal
Georgia Institute of Technology, Atlanta, USA
3 shared publications - Vivek Sarkar
Georgia Institute of Technology, Atlanta, USA
3 shared publications - Nathan Wichmann
Hewlett Packard Enterprise, Bloomington, USA
2 shared publications
Latest Publications
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 620-627
Performance Analysis of Conveyors: Memory Dominates?
Small-message aggregation is critical for scaling irregular, communication intensive applications in high-performance computing. In this paper, contrary to conventional wisdom, we present the first systematic study showing that memory contention, not network bandwidth, is the dominant bottleneck in message aggregation runtimes. Using the state-of-the-art conveyors library as our reference implementation, we conducted extensive experiments on HPC systems featuring Slingshot 11 and InfiniBand interconnects, scaling to 16k cores (256 nodes) and processing 10s–100s GB of data. Our measurements reveal that interference between user data and aggregation buffers drives LLC miss rates to 77%, inflating memory costs by 2–3× over the algorithmic baseline. Consequently, we advocate for dedicated near-memory subsystems to improve the scalability and performance of message aggregation runtimes. This paper also demonstrates up to an order of magnitude higher latency for conveyor termination compared to a traditional HPC barrier, and it examines the impact of communication context isolation and the critical challenge of programmability.
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 620-627
Open AccessPerformance Analysis of Conveyors: Memory Dominates?
Small-message aggregation is critical for scaling irregular, communication intensive applications in high-performance computing. In this paper, contrary to conventional wisdom, we present the first systematic study showing that memory contention, not network bandwidth, is the dominant bottleneck in message aggregation runtimes. Using the state-of-the-art conveyors library as our reference implementation, we conducted extensive experiments on HPC systems featuring Slingshot 11 and InfiniBand interconnects, scaling to 16k cores (256 nodes) and processing 10s–100s GB of data. Our measurements reveal that interference between user data and aggregation buffers drives LLC miss rates to 77%, inflating memory costs by 2–3× over the algorithmic baseline. Consequently, we advocate for dedicated near-memory subsystems to improve the scalability and performance of message aggregation runtimes. This paper also demonstrates up to an order of magnitude higher latency for conveyor termination compared to a traditional HPC barrier, and it examines the impact of communication context isolation and the critical challenge of programmability.
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 238-252
Toward a Unified GPU-Aware OpenSHMEM Specification
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 238-252
Open AccessToward a Unified GPU-Aware OpenSHMEM Specification
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 217-228
Heading Towards Energy Savings or Just Performance: Case-Study on Message Aggregation-Based Runtimes
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 217-228
Open AccessHeading Towards Energy Savings or Just Performance: Case-Study on Message Aggregation-Based Runtimes
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 828-833
Rapid Quantum Network Simulation Design with a Path to Scalable Execution
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 828-833
Open AccessRapid Quantum Network Simulation Design with a Path to Scalable Execution
- 28 June 2025
- Published by Springer Nature
- p. 103-113
Scalable Small Message Aggregation on Modern Interconnects
- 28 June 2025
- Published by Springer Nature
- p. 103-113
Scalable Small Message Aggregation on Modern Interconnects
- 28 June 2025
- Published by Springer Nature
- p. 114-120
Preliminary Study on Message Aggregation Optimizations for Energy Savings in PGAS Models
- 28 June 2025
- Published by Springer Nature
- p. 114-120
Preliminary Study on Message Aggregation Optimizations for Energy Savings in PGAS Models
- Open Access
A Short Scalability Study on the SeQUeNCe Parallel Quantum Network Simulator
As quantum networking continues to grow in importance, its study is of interest to an ever wider community and at an increasing scale. However, the development of its physical infrastructure remains burdensome, and services providing third party access are not enough to meet demand. A variety of simulation frameworks provide a method for testing aspects of such systems on commodity hardware, but are predominantly serial and thus unable to scale to larger networks and/or workloads. One effort to address this was focused on parallelising the SeQUeNCe discrete event simulator, though it has yet to be proven to work well across system architectures or at larger scales. Therein lies the contribution of this work - to more deeply examine its scalability using ORNL Frontier. Our results provide new insight into its scalability behaviour, and we examine its strategy and how it may be able to be improved.
Open AccessA Short Scalability Study on the SeQUeNCe Parallel Quantum Network Simulator
As quantum networking continues to grow in importance, its study is of interest to an ever wider community and at an increasing scale. However, the development of its physical infrastructure remains burdensome, and services providing third party access are not enough to meet demand. A variety of simulation frameworks provide a method for testing aspects of such systems on commodity hardware, but are predominantly serial and thus unable to scale to larger networks and/or workloads. One effort to address this was focused on parallelising the SeQUeNCe discrete event simulator, though it has yet to be proven to work well across system architectures or at larger scales. Therein lies the contribution of this work - to more deeply examine its scalability using ORNL Frontier. Our results provide new insight into its scalability behaviour, and we examine its strategy and how it may be able to be improved.
- 24 August 2023
- Published by Springer Nature
- p. 32-46
Extending OpenSHMEM with Aggregation Support for Improved Message Rate Performance
- 24 August 2023
- Published by Springer Nature
- p. 32-46
Extending OpenSHMEM with Aggregation Support for Improved Message Rate Performance
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 420-429
Combining Static and Dynamic Analysis to Query Characteristics of HPC Applications
Emerging HPC platforms are becoming more difficult to program as a result of systems with different node architectures, some with a small number of "fat" heterogenous nodes (consisting of multiple accelerators) and others with a large number of "thin" homogenous nodes consisting of multi-core CPUs connected with high speed interconnects. New programming models are emerging to address performance portability of the applications as well as a set of scientific libraries that applications can use to exploit these architectures efficiently. To port applications to new architectures, developers need information about their source code characteristics including static and dynamic (e.g. performance) information to refactor the code, understand their data and code structure, and library usage as well as program information to direct their optimisation efforts and make key decisions. In this paper, we describe a tool that combines compiler and profiler information to query program characteristics in a given programming environment. Static and dynamic data about applications is collected and stored together in an SQL database that can be later queried to study application characteristics and patterns. We will demonstrate the capabilities of this tool with an application-driven case study that aims at understanding application code and its use of scientific libraries via a real world example from the molecular simulation application CP2K.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 420-429
Combining Static and Dynamic Analysis to Query Characteristics of HPC Applications
Emerging HPC platforms are becoming more difficult to program as a result of systems with different node architectures, some with a small number of "fat" heterogenous nodes (consisting of multiple accelerators) and others with a large number of "thin" homogenous nodes consisting of multi-core CPUs connected with high speed interconnects. New programming models are emerging to address performance portability of the applications as well as a set of scientific libraries that applications can use to exploit these architectures efficiently. To port applications to new architectures, developers need information about their source code characteristics including static and dynamic (e.g. performance) information to refactor the code, understand their data and code structure, and library usage as well as program information to direct their optimisation efforts and make key decisions. In this paper, we describe a tool that combines compiler and profiler information to query program characteristics in a given programming environment. Static and dynamic data about applications is collected and stored together in an SQL database that can be later queried to study application characteristics and patterns. We will demonstrate the capabilities of this tool with an application-driven case study that aims at understanding application code and its use of scientific libraries via a real world example from the molecular simulation application CP2K.
- 15 December 2016
- Published by Springer Nature
- p. 82-94
On Synchronisation and Memory Reuse in OpenSHMEM
- 15 December 2016
- Published by Springer Nature
- p. 82-94
On Synchronisation and Memory Reuse in OpenSHMEM