high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Benchmarking the Memory Hierarchy of Modern GPUs

Xinxin Mei, Kaiyong Zhao, Chengjian Liu, Xiaowen Chu

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Memory, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 560 Ti, nVidia GeForce GTX 780, Package, Performance

July 14, 2014 by hgpu

Understanding the SIMD Efficiency of Graph Traversal on GPU

Yichao Cheng, Hong An, Zhitao Chen, Feng Li, Zhaohui Wang, Xia Jiang, Yi Peng

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Graph theory, nVidia, Performance, Tesla C2050

July 10, 2014 by hgpu

Utilizing state-of-art NeuroES and GPGPU to optimize Mario AI

Hasse Lovgren

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 5870, Computer science, Mathematics, Neural networks, nVidia, nVidia GeForce GTX 580, OpenCL, Package, Performance, Tesla C1060, Thesis

July 9, 2014 by hgpu

On Static Timing Analysis of GPU Kernels

Vesa Hirvisalo

View

Download (PDF)

Tags: Computer science, OpenCL, Performance, Timing analysis

July 4, 2014 by hgpu

SIMD Implementation of a Multiplicative Schwarz Smoother for a Multigrid Poisson Solver on an Intel Xeon Phi Coprocessor

Masatoshi Kawai, Takeshi Iwashita, Hiroshi Nakashima

View

Download (PDF)

Tags: Computer science, Intel Xeon Phi, Performance, Poisson equation

July 4, 2014 by hgpu

Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications

Shahzeb Siddiqui, Saber Feki

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, OpenACC, Performance, Tesla K20

July 3, 2014 by hgpu

Toward Auto-tuned Krylov Basis Computations with minimized Communication on Clusters of Accelerators

Langshi Chen, Serge Petiton, Leroy Drummond, Maxime Hugues

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, Performance, Tesla K20

July 3, 2014 by hgpu

Mixed-precision Orthogonalization Scheme and Adaptive Step Size for CA-GMRES on GPUs

Ichitaro Yamazaki, Stanimire Tomov, Tingxing Dong, Jack Dongarra

View

Download (PDF)

Tags: Computer science, Linear Algebra, nVidia, Performance, Tesla K20, Tesla K40, Tesla M2090

July 1, 2014 by hgpu

Performance and Efficiency Analysis of Modern Accelerators: Fine-Grained Parallelism on the Intel Xeon Phi

Robrecht Dewaele

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Intel Xeon Phi, Package, Performance, Thesis

June 28, 2014 by hgpu

Evaluation of DGEMM Implementation on Intel Xeon Phi Coprocessor

Pawel Gepner, Victor Gamayunov, David L. Fraser, Eric Houdard, Ludovic Sauge, Damien Declat, Mathieu Dubois

View

Download (PDF)

Tags: Algorithms, Computer science, Intel Xeon Phi, Linear Algebra, Matrix multiplication, Performance

June 28, 2014 by hgpu

On the Characterization of OpenCL Dwarfs on Fixed and Reconfigurable Platforms

Konstantinos Krommydas, Wu-chun Feng, Muhsen Owaida, Christos D. Antonopoulos, Nikolaos Bellas

View

Download (PDF)

Source codes

Tags: APU, ATI, ATI Radeon HD 7970, Benchmarking, Computer science, FPGA, Heterogeneous systems, Intel Xeon Phi, OpenCL, Package, Performance

June 26, 2014 by hgpu

Preemptive Thread Block Scheduling with Online Structural Runtime Prediction for Concurrent GPGPU Kernels

Sreepathi Pai, R. Govindarajan, Matthew J. Thazhuthaveetil

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Operating systems, Performance, Tesla K20

June 25, 2014 by hgpu

CuPBoP-AMD: Extending CUDA to AMD Platforms

CuPBoP: Making CUDA a Portable Language

Adopter: Automated Deep Learning Optimization via DSL-based Source Code Transformation

Automated Deep Learning Optimization via DSL-Based Source Code Transformation

ROCm's implementation of Gromacs

GROMACS on AMD GPU-Based HPC Platforms: Using SYCL for Performance and Portability

Code examples for paper on SYCL backend of Kokkos - IWOCL 2024

Experiences with implementing Kokkos’ SYCL backend

SimSYCL: Synchronous, single-threaded, library-only SYCL implementation for debugging and verification

SimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance

gpu_tracker: Context manager and CLI that tracks the computational-resource-usage of a code block or shell command, particularly the GPU usage

gpu_tracker: Python package for tracking and profiling GPU utilization in both desktop and high-performance computing environments

CIFAR-10 Airbench: 94% on CIFAR-10 in 3.29 second

94% on CIFAR-10 in 3.29 Seconds on a Single GPU

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Benchmarking the Memory Hierarchy of Modern GPUs

Understanding the SIMD Efficiency of Graph Traversal on GPU

Utilizing state-of-art NeuroES and GPGPU to optimize Mario AI

On Static Timing Analysis of GPU Kernels

SIMD Implementation of a Multiplicative Schwarz Smoother for a Multigrid Poisson Solver on an Intel Xeon Phi Coprocessor

Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications

Toward Auto-tuned Krylov Basis Computations with minimized Communication on Clusters of Accelerators

Mixed-precision Orthogonalization Scheme and Adaptive Step Size for CA-GMRES on GPUs

Performance and Efficiency Analysis of Modern Accelerators: Fine-Grained Parallelism on the Intel Xeon Phi

Evaluation of DGEMM Implementation on Intel Xeon Phi Coprocessor

On the Characterization of OpenCL Dwarfs on Fixed and Reconfigurable Platforms

Preemptive Thread Block Scheduling with Online Structural Runtime Prediction for Concurrent GPGPU Kernels

Recent source codes

CuPBoP-AMD: Extending CUDA to AMD Platforms

Adopter: Automated Deep Learning Optimization via DSL-based Source Code Transformation

ROCm's implementation of Gromacs

Code examples for paper on SYCL backend of Kokkos - IWOCL 2024

SimSYCL: Synchronous, single-threaded, library-only SYCL implementation for debugging and verification

GPU plugin for PySCF

QArray

Celerity: High-level C++ for Accelerator Clusters

gpu_tracker: Context manager and CLI that tracks the computational-resource-usage of a code block or shell command, particularly the GPU usage

CIFAR-10 Airbench: 94% on CIFAR-10 in 3.29 second

Most viewed papers (last 30 days)