high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming

Unified Deep Learning with CPU, GPU, and FPGA Technologies

Allen Rush, Ashish Sirasao, Mike Ignatowski

View

Download (PDF)

Tags: Computer science, Deep learning, FPGA, Heterogeneous systems, Machine learning, OpenCL

November 21, 2017 by hgpu

Hydra: a C++11 framework for data analysis in massively parallel platforms

A. A. Alves Junior, M. D. Sokoloff

View

Download (PDF)

Source codes

Tags: Computational Physics, Computer science, CUDA, Mathematical Software, nVidia, OpenMP, Package, Tesla K40

November 16, 2017 by hgpu

Launch-time Optimization of OpenCL Kernels

Andrew Siu Doug Lee

View

Download (PDF)

Tags: Computer science, LLVM, nVidia, nVidia GeForce GTX 780, OpenCL, Performance, Thesis

November 16, 2017 by hgpu

Domain-Specific Acceleration and Auto-Parallelization of Legacy Scientific Code in FORTRAN 77 using Source-to-Source Compilation

Wim Vanderbauwhede, Gavin Davidson

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, Fortran, Heterogeneous systems, Mathematical Software, Numerical Analysis, nVidia, nVidia GeForce GTX Titan X, OpenACC, OpenCL, OpenMP, Package

November 16, 2017 by hgpu

Vectorized algorithm for multidimensional Monte Carlo integration on modern GPU, CPU and MIC architectures

Przemyslaw Stpiczynski

View

Download (PDF)

Tags: Algorithms, Computer science, Intel Xeon Phi, Monte Carlo integration, nVidia, OpenACC, OpenMP, Pseudo-random number generators, Tesla K40

November 12, 2017 by hgpu

Scalable and massively parallel Monte Carlo photon transport simulations for heterogeneous computing platforms

Leiming Yu, Fanny Nina-Paravecino, David Kaeli, Qianqian Fang

View

Download (PDF)

Source codes

Tags: Algorithms, AMD R9 Nano, AMD Radeon RX 480, ATI, Computational Physics, Heterogeneous systems, nVidia, nVidia GeForce GTX 1050 Ti, nVidia GeForce GTX 1080 Ti, nVidia GeForce GTX 590, nVidia GeForce GTX 980 Ti, nVidia GeForce GTX Titan X, OpenCL, Package, Physics

November 12, 2017 by hgpu

Best Practice Guide – GPGPU

Momme Allalen, Vali Codreanu, Nevena Ilieva-Litova, Alan Gray, Anders Sjostrom, Volker Weinberg

View

Download (PDF)

Tags: Computer science, CUDA, OpenACC, OpenCL, OpenMP, Review

November 12, 2017 by hgpu

Low-power System-on-Chip Processors for Energy Efficient High Performance Computing: The Texas Instruments Keystone II

Gaurav Mitra

View

Download (PDF)

Tags: ARM, Benchmarking, Computer science, DSP, Heterogeneous systems, Matrix multiplication, nVidia, nVidia Jetson TK1, nVidia Tegra TX1, OpenCL, SoC, Thesis

November 12, 2017 by hgpu

Performance Evaluation of Deep Learning Tools in Docker Containers

Pengfei Xu, Shaohuai Shi, Xiaowen Chu

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Deep learning, nVidia, nVidia GeForce GTX 980, nVidia GeForce GTX Titan X, Package, Performance

November 12, 2017 by hgpu

Comparison of Parallelisation Approaches, Languages, and Compilers for Unstructured Mesh Algorithms on GPUs

G. D. Balogh, I. Z. Reguly, G. R. Mudalige

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, MPI, nVidia, OpenACC, OpenMP, Performance, Tesla K40, Tesla P100

November 7, 2017 by hgpu

Scalable Streaming Tools for Analyzing N-body Simulations: Finding Halos and Investigating Excursion Sets in One Pass

Nikita Ivkin, Zaoxing Liu, Lin F. Yang, Srinivas Suresh Kumar, Gerard Lemson, Mark Neyrinck, Alexander S. Szalay, Vladimir Braverman, Tamas Budavari

View

Download (PDF)

Tags: Algorithms, Astrophysics, CUDA, Instrumentation and Methods for Astrophysics, N-body simulation, nVidia, nVidia GeForce GTX 1080, Tesla C2050, Tesla C2070

November 7, 2017 by hgpu

Radeon PRO Solid State Graphics (SSG) API User Manual

AMD

View

Download (PDF)

Tags: AMD Radeon Pro SSG, ATI, Computer science, DirectX, OpenCL, OpenGL

November 7, 2017 by hgpu

CFAL-bench

Comparing Parallel Functional Array Languages: Programming and Performance

Efficient Graph Embedding at Scale: Optimizing CPU-GPU-SSD Integration

Can Large Language Models Predict Parallel Code Performance?

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

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

Unified Deep Learning with CPU, GPU, and FPGA Technologies

Hydra: a C++11 framework for data analysis in massively parallel platforms

Launch-time Optimization of OpenCL Kernels

Domain-Specific Acceleration and Auto-Parallelization of Legacy Scientific Code in FORTRAN 77 using Source-to-Source Compilation

Vectorized algorithm for multidimensional Monte Carlo integration on modern GPU, CPU and MIC architectures

Scalable and massively parallel Monte Carlo photon transport simulations for heterogeneous computing platforms

Best Practice Guide – GPGPU

Low-power System-on-Chip Processors for Energy Efficient High Performance Computing: The Texas Instruments Keystone II

Performance Evaluation of Deep Learning Tools in Docker Containers

Comparison of Parallelisation Approaches, Languages, and Compilers for Unstructured Mesh Algorithms on GPUs

Scalable Streaming Tools for Analyzing N-body Simulations: Finding Halos and Investigating Excursion Sets in One Pass

Radeon PRO Solid State Graphics (SSG) API User Manual

Recent source codes

CFAL-bench

Efficient Graph Embedding at Scale: Optimizing CPU-GPU-SSD Integration

Can Large Language Models Predict Parallel Code Performance?

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

Most viewed papers (last 30 days)