high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Easy-to-Use On-the-Fly Binary Program Acceleration on Many-Cores

Marvin Damschen, Christian Plessl

View

Download (PDF)

Source codes

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

December 15, 2014 by hgpu

Heuristics for Conversion Process of GPU’s Kernels for Multiples Kernels with Concurrent Optimization Divergence

Jose Ritomar Carneiro Torquato, Esteban Walter Gonzalez Clua

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 680, Performance, Tesla K10, Tesla K20

December 14, 2014 by hgpu

Lattice QCD with Domain Decomposition on Intel Xeon Phi Co-Processors

Simon Heybrock, Balint Joo, Dhiraj D. Kalamkar, Mikhail Smelyanskiy, Karthikeyan Vaidyanathan, Tilo Wettig, Pradeep Dubey

View

Download (PDF)

Tags: Algorithms, Computational Physics, High Energy Physics - Lattice, Intel Xeon Phi, Performance, Physics, QCD

December 9, 2014 by hgpu

Improving GPU Performance by Regrouping CPU-Memory Data

Deepthi Gummadi

View

Download (PDF)

Tags: ARM, Computer science, CUDA, nVidia, Performance, Tesla C2075, Tesla K20, Thesis

November 25, 2014 by hgpu

A Self-Optimizing Framework for Developing Metrology Software on Massive Parallel Processor Architectures

T. Beier

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 7750, Computer science, nVidia, nVidia GeForce GTX 480, OpenCL, Performance

November 25, 2014 by hgpu

Automatic Performance Tuning of Pipeline Patterns for Heterogeneous Parallel Architectures

E. Bajrovic, S. Benkner

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, OpenCL, OpenCV, Performance, Tesla C2050, Tesla K20

November 20, 2014 by hgpu

The Implementation of a Real-Time Polyphase Filter

Karel Adamek, Jan Novotny, Wes Armour

View

Download (PDF)

Tags: CUDA, Intel Xeon Phi, nVidia, nVidia GeForce GTX 580, nVidia GeForce GTX 750 Ti, Performance, Signal processing, Tesla K40

November 16, 2014 by hgpu

Locality-Aware Mapping of Nested Parallel Patterns on GPUs

HyoukJoong Lee, Kevin J. Brown, Arvind K. Sujeeth, Tiark Rompf, Kunle Olukotun

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, Performance, Tesla K20

November 12, 2014 by hgpu

Code Optimization on Kepler GPUs and Xeon Phi

Yong-Chull Jang, Hwancheol Jeong, Jangho Kim, Weonjong Lee, Jeonghwan Pak, Yuree Chung (SWME Collaboration)

View

Download (PDF)

Tags: CUDA, High Energy Physics - Lattice, Intel Xeon Phi, Maxwell's equations, MPI, nVidia, nVidia GeForce GTX 980, nVidia GeForce GTX Titan, OpenMP, Performance, Physics, QCD, Tesla K40

November 12, 2014 by hgpu

Profiling of Data-Parallel Processors

Daniel Kruck, Holger Froening

View

Download (PDF)

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

November 3, 2014 by hgpu

Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUs

Wangdong Yang, Kenli Li, Zeyao Mo, Keqin Li

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 460, Performance, Probability, Sparse matrix

November 3, 2014 by hgpu

GPGPU Acceleration for Skeletal Animation-comparing OpenCL with CUDA and GLSL

Shousheng Liu, Ge Chen, Chunyong Ma, Yong Han

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7750, Computer science, CUDA, GLSL, nVidia, nVidia GeForce GTS 250, nVidia GeForce GTX 670, OpenCL, OpenGL, Performance, Rendering

October 25, 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

Easy-to-Use On-the-Fly Binary Program Acceleration on Many-Cores

Heuristics for Conversion Process of GPU’s Kernels for Multiples Kernels with Concurrent Optimization Divergence

Lattice QCD with Domain Decomposition on Intel Xeon Phi Co-Processors

Improving GPU Performance by Regrouping CPU-Memory Data

A Self-Optimizing Framework for Developing Metrology Software on Massive Parallel Processor Architectures

Automatic Performance Tuning of Pipeline Patterns for Heterogeneous Parallel Architectures

The Implementation of a Real-Time Polyphase Filter

Locality-Aware Mapping of Nested Parallel Patterns on GPUs

Code Optimization on Kepler GPUs and Xeon Phi

Profiling of Data-Parallel Processors

Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUs

GPGPU Acceleration for Skeletal Animation-comparing OpenCL with CUDA and GLSL

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)