#gpu

(all tags)

Publications

Interconnect Bandwidth Heterogeneity on AMD MI250x and Infinity Fabric
Carl Pearson
arXiv
02/23
Latency and Bandwidth Microbenchmarks of US Department of Energy Systems in the June 2023 Top 500 List
Christopher M. Siefert, Carl Pearson, Stephen L. Olivier, Andrey Prokopenko, Jonathan J. Hu, Timothy J. Fuller
in
14th IEEE International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems
11/23
Scalable Parallel DBIM Solutions of Inverse-Scattering Problems
Mert Hidayetoglu, Carl Pearson, Levent Gurel, Wen-mei Hwu, Weng Cho Chew
in
Computing and Electromagnetics International Workshop (CEM), 2017
06/17
Thoughts on Massively-Parallel Heterogeneous Computing for Solving Large Problems
Wen-mei Hwu, Mert Hidayetoglu, Weng Cho Chew, Carl Pearson, Simon Garcia de Gonzalo, Sitao Huang, Abdul Dakkak
in
Computing and Electromagnetics International Workshop 2017
06/17
Comparative Performance Evaluation of Multi-GPU MLFMM Implementation for 2-D VIE Problems
Carl Pearson, Mert Hidayetoglu, Wei Ren, Weng Cho Chew, Wen-Mei Hwu
in
Computing and Electromagnetics International Workshop, IEEE 2017
06/17
Large Inverse-Scattering Solutions with DBIM on GPU-Enabled Supercomputers
Mert Hidayetoglu, Carl Pearson, Weng Cho Chew, Levent Gurel, Wen-mei Hwu
in
Applied and Computational Electromagnetics Symposium, 2017
03/17
A Fast and Massively-Parallel Solver for Multiple-Scattering Tomographic Image Reconstruction
Mert Hidayetoglu, Carl Pearson, Izzat El Hajj, Levent Gurel, Weng Cho Chew, Wen-Mei Hwu
in
2018 IEEE International Parallel and Distributed Processing Symposium
05/18
Heterogeneous Application and System Modeling
Carl Pearson
M.S. Thesis, May 2018
06/18

Posts

Self-host GPU Continuous Integration with Azure Piplines and Docker!
PUMPS+AI 2019 Summer School
Nsight Systems and Nsight Compute Teaching Resources
Improving MPI_Pack performance in CUDA-aware MPI
Using nvtx-connector and Nsight Systems to Understand your Kokkos Application

Talks

Evaluating Characteristics of CUDA Communication Primitives on High-Bandwidth Interconnects
at
ACM/SPEC International Conference on Performance Engineering
04/10/19
Benchmarking CUDA Communication Primitives on High-Bandwidth Interconnects
at
ADA Liason Meeting
06/05/19
Node-Aware Stencil Communication for Heterogeneous Supercomputers
at
C3SR Bi-weekly Technical Seminar
02/28/20
Optimizing Communication for CPU/GPU Nodes
at
Sandia National Labs Seminar
03/11/20
Using Nsight Compute and Nsight Systems
at
ECE 408 Guest Lecture
04/16/20
Adding Fast GPU Derived Datatype Handing to Existing MPIs
at
University of New Mexico PSAAP Colloquium
02/15/21
Adding Fast GPU Derived Datatype Handing to Existing MPIs
at
UNM Computer Science Department Colloquium
05/05/21
Automatic Discovery of Implementation Rules for Fast GPU + MPI Operations
at
SIAM Parallel Processing
02/25/22
Latency and Bandwidth Microbenchmarks of Six US Department of Energy Systems in the Top500
at
Cluster 2023
11/02/23
Latency and Bandwidth Microbenchmarks of US Department of Energy Systems in the June 2023 Top500 List
at
Supercomputing 2023
11/13/23
Kokkos Kernels: State on Exascale Architectures
at
Kokkos User Group Meeting 2023
12/12/23
GPU Performance Nuggets
at
Blue Waters Symposium
06/15/16
Comparative Performance Evaluation of Multi-GPU MLFMM Implementation for 2-D VIE Problems
at
Computing and Electromagnetics International Workshop
06/23/17
RAI: A Scalable Submission System for GPU Applications
at
NVIDIA GPU Technology Conference 2017
05/08/17
Bigger GPUs and Bigger Nodes
at
Blue Waters User Symposium 2018
06/06/18
Towards Automatic Heterogeneous Computing Performance Analysis
at
Coordinated Science Lab Feedback Friday Spring 2018
03/30/18