Philip Carns
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Philip Carns has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Robert Ross
Argonne National Laboratory, Lemont, USA
14 shared publications - Shane Snyder
Argonne National Laboratory, Lemont, IL, USA
7 shared publications - Robert Latham
Argonne National Laboratory, Lemont, IL, USA
6 shared publications - Dong Dai
University of Delaware, Newark, USA
5 shared publications - Matthieu Dorier
Argonne National Laboratory, Lemont, IL, USA
5 shared publications - Jerome Soumagne
HPE, Spring, TX, USA
4 shared publications
Latest Publications
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 305-318
GLANCED-IO: Taming I/O Optimization for Deep Learning at Scale
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 305-318
Open AccessGLANCED-IO: Taming I/O Optimization for Deep Learning at Scale
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2281-2292
RESILIO : A Scalable and Composable Architecture for Tomographic Reconstruction Workflows
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2281-2292
Open AccessRESILIO : A Scalable and Composable Architecture for Tomographic Reconstruction Workflows
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1252-1266
STELLAR: Storage Tuning Engine Leveraging LLM Autonomous Reasoning for High Performance Parallel File Systems
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1252-1266
Open AccessSTELLAR: Storage Tuning Engine Leveraging LLM Autonomous Reasoning for High Performance Parallel File Systems
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 216-217
STEP: Software Tools Ecosystem Project
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 216-217
Open AccessSTEP: Software Tools Ecosystem Project
- Open Access
- 4 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 37-49
Expanding Community Access to Real-World HPC Application I/O Characterization Data Using Darshan
- 4 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 37-49
Open AccessExpanding Community Access to Real-World HPC Application I/O Characterization Data Using Darshan
- Open Access
- 4 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 7-18
Enhancing RPC on Slingshot for Aurora’s DAOS Storage System
- 4 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 7-18
Open AccessEnhancing RPC on Slingshot for Aurora’s DAOS Storage System
- Open Access
- 4 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 79-92
Towards Empirical Roofline Modeling of Distributed Data Services: Mapping the Boundaries of RPC Throughput
- 4 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 79-92
Open AccessTowards Empirical Roofline Modeling of Distributed Data Services: Mapping the Boundaries of RPC Throughput
- Open Access
Thallus: An RDMA-based Columnar Data Transport Protocol
The volume of data generated and stored in contemporary global data centers is experiencing exponential growth. This rapid data growth necessitates efficient processing and analysis to extract valuable business insights. In distributed data processing systems, data undergoes exchanges between the compute servers that contribute significantly to the total data processing duration in adequately large clusters, necessitating efficient data transport protocols. Traditionally, data transport frameworks such as JDBC and ODBC have used TCP/IP-over-Ethernet as their underlying network protocol. Such frameworks require serializing the data into a single contiguous buffer before handing it off to the network card, primarily due to the requirement of contiguous data in TCP/IP. In OLAP use cases, this serialization process is costly for columnar data batches as it involves numerous memory copies that hurt data transport duration and overall data processing performance. We study the serialization overhead in the context of a widely-used columnar data format, Apache Arrow, and propose leveraging RDMA to transport Arrow data over Infiniband in a zero-copy manner. We design and implement Thallus, an RDMA-based columnar data transport protocol for Apache Arrow based on the Thallium framework from the Mochi ecosystem, compare it with a purely Thallium RPC-based implementation, and show substantial performance improvements can be achieved by using RDMA for columnar data transport.
Open AccessThallus: An RDMA-based Columnar Data Transport Protocol
The volume of data generated and stored in contemporary global data centers is experiencing exponential growth. This rapid data growth necessitates efficient processing and analysis to extract valuable business insights. In distributed data processing systems, data undergoes exchanges between the compute servers that contribute significantly to the total data processing duration in adequately large clusters, necessitating efficient data transport protocols. Traditionally, data transport frameworks such as JDBC and ODBC have used TCP/IP-over-Ethernet as their underlying network protocol. Such frameworks require serializing the data into a single contiguous buffer before handing it off to the network card, primarily due to the requirement of contiguous data in TCP/IP. In OLAP use cases, this serialization process is costly for columnar data batches as it involves numerous memory copies that hurt data transport duration and overall data processing performance. We study the serialization overhead in the context of a widely-used columnar data format, Apache Arrow, and propose leveraging RDMA to transport Arrow data over Infiniband in a zero-copy manner. We design and implement Thallus, an RDMA-based columnar data transport protocol for Apache Arrow based on the Thallium framework from the Mochi ecosystem, compare it with a purely Thallium RPC-based implementation, and show substantial performance improvements can be achieved by using RDMA for columnar data transport.
- Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1380-1391
Enabling Agile Analysis of I/O Performance Data with PyDarshan
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1380-1391
Open AccessEnabling Agile Analysis of I/O Performance Data with PyDarshan
- Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1216-1222
The I/O Trace Initiative: Building a Collaborative I/O Archive to Advance HPC
HPC application developers and administrators need to understand the complex interplay between compute clusters and storage systems to make effective optimization decisions. Ad hoc investigations of this interplay based on isolated case studies can lead to conclusions that are incorrect or difficult to generalize. The I/O Trace Initiative aims to improve the scientific community’s understanding of I/O operations by building a searchable collaborative archive of I/O traces from a wide range of applications and machines, with a focus on high-performance computing and scalable AI/ML. This initiative advances the accessibility of I/O trace data by enabling users to locate and compare traces based on user-specified criteria. It also provides a visual analytics platform for in-depth analysis, paving the way for the development of advanced performance optimization techniques. By acting as a hub for trace data, the initiative fosters collaborative research by encouraging data sharing and collective learning.
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1216-1222
Open AccessThe I/O Trace Initiative: Building a Collaborative I/O Archive to Advance HPC
HPC application developers and administrators need to understand the complex interplay between compute clusters and storage systems to make effective optimization decisions. Ad hoc investigations of this interplay based on isolated case studies can lead to conclusions that are incorrect or difficult to generalize. The I/O Trace Initiative aims to improve the scientific community’s understanding of I/O operations by building a searchable collaborative archive of I/O traces from a wide range of applications and machines, with a focus on high-performance computing and scalable AI/ML. This initiative advances the accessibility of I/O trace data by enabling users to locate and compare traces based on user-specified criteria. It also provides a visual analytics platform for in-depth analysis, paving the way for the development of advanced performance optimization techniques. By acting as a hub for trace data, the initiative fosters collaborative research by encouraging data sharing and collective learning.