high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Improving Communication Performance and Scalability of Native Applications on Intel Xeon Phi Coprocessor Clusters

Karthikeyan Vaidyanathan, Kiran Pamnany, Dhiraj D. Kalamkar, Alexander Heinecke, Mikhail Smelyanskiy, Jongsoo Park, Daehyun Kim, Aniruddha Shet G, Bharat Kaul, Balint Joo, Pradeep Dubey

View

Download (PDF)

Tags: Cluster computing, Computer science, FFT, Intel Xeon Phi, Performance, QCD

August 15, 2014 by hgpu

Design and Evaluation of Scalable Concurrent Queues for Many-Core Architectures

Thomas R. W. Scogland, Wu-chun Feng

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, Computer science, Intel Xeon Phi, nVidia, nVidia GeForce GTX 280, OpenCL, Performance, Tesla K20

August 15, 2014 by hgpu

Energy Evaluation for Applications with Different Thread Affinities on the Intel Xeon Phi

Gary Lawson, Masha Sosonkina, Yuzhong Shen

View

Download (PDF)

Tags: Computer science, Energy-efficient computing, Intel Xeon Phi, Performance

August 15, 2014 by hgpu

GPU-SPARC: Accelerating Parallelism in Multi-GPU Real-Time Systems

Wookhyun Han, Hwidong Bae, Hyosu Kim, Jiyoen Lee, Insik Shin

View

Download (PDF)

Source codes

Tags: Computer science, nVidia, nVidia GeForce GTX 560 Ti, OpenCL, Package, Performance

August 13, 2014 by hgpu

Optimising Purely Functional GPU Programs (Thesis)

Trevor L. McDonell

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, nVidia, Package, Performance, Tesla T10, Thesis

August 10, 2014 by hgpu

Direct Numerical Simulation of Turbulent Flows with Parallel Algorithms for Various Computing Architectures

A. Gorobets, F.X. Trias, R. Borrell, G. Oyarzun, A. Oliva

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5870, ATI Radeon HD 6970, ATI Radeon HD 7970, Fluid dynamics, Intel Xeon Phi, MPI, Numerical simulation, nVidia, nVidia GeForce GTX 470, nVidia GeForce GTX Titan, OpenCL, OpenMP, Performance, Tesla C1060, Tesla C2050

August 10, 2014 by hgpu

Optimizing performance per watt on GPUs in High Performance Computing: temperature, frequency and voltage effects

D. C. Price, M. A. Clark, B. R. Barsdell, R. Babich, L. J. Greenhill

View

Download (PDF)

Source codes

Tags: Astrophysics, CUDA, Energy-efficient computing, Instrumentation and Methods for Astrophysics, nVidia, nVidia GeForce GTX 780, Package, Performance, Signal processing, Tesla K20

August 1, 2014 by hgpu

Automatic Parallelization of Tiled Stencil Loop Nests on GPUs

Peng Di

View

Download (PDF)

Tags: Algorithms, Compilers, Computer science, CUDA, nVidia, Performance, Tesla C1060, Tesla C2050, Thesis

July 30, 2014 by hgpu

Aristotle: A Performance Impact Indicator for the OpenCL Kernels Using Local Memory

Jianbin Fang, Henk Sips, Ana Lucia Varbanescu

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 7970, Computer science, Intel Xeon Phi, Local memory, nVidia, OpenCL, Performance, Portability, Tesla C1060, Tesla C2050, Tesla K20

July 29, 2014 by jfang

GPU Computing to Improve Game Engine Performance

Abu Asaduzzaman, Hin Y. Lee

View

Download (PDF)

Tags: Computer science, CUDA, Data parallelism, Games, Image processing, nVidia, nVidia GeForce 8800 GTX, Performance

July 28, 2014 by hgpu

Performance-efficient mechanisms for managing irregularity in throughput processors

Minsoo Rhu

View

Download (PDF)

Tags: Computer science, CUDA, GPGPU-sim, nVidia, nVidia GeForce GTX 480, Performance, Prefetch, Thesis

July 20, 2014 by hgpu

Optimal Periods for Probing Convergence of Infinite-stage Dynamic Programmings on GPUs

Tsutomu Inamoto, Yoshinobu Higami, Shin-ya Kobayashi

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 680, Performance

July 17, 2014 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Improving Communication Performance and Scalability of Native Applications on Intel Xeon Phi Coprocessor Clusters

Design and Evaluation of Scalable Concurrent Queues for Many-Core Architectures

Energy Evaluation for Applications with Different Thread Affinities on the Intel Xeon Phi

GPU-SPARC: Accelerating Parallelism in Multi-GPU Real-Time Systems

Optimising Purely Functional GPU Programs (Thesis)

Direct Numerical Simulation of Turbulent Flows with Parallel Algorithms for Various Computing Architectures

Optimizing performance per watt on GPUs in High Performance Computing: temperature, frequency and voltage effects

Automatic Parallelization of Tiled Stencil Loop Nests on GPUs

Aristotle: A Performance Impact Indicator for the OpenCL Kernels Using Local Memory

GPU Computing to Improve Game Engine Performance

Performance-efficient mechanisms for managing irregularity in throughput processors

Optimal Periods for Probing Convergence of Infinite-stage Dynamic Programmings on GPUs

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Most viewed papers (last 30 days)