high performance computing on graphics processing units: hgpu.org

hgpu.org » Applications » Computer science

Block Conjugate Gradient Solver in OpenCL

Kert Tali, Eero Vainikko

View

Download (PDF)

Tags: Algorithms, Computer science, Conjugate gradient solver, Linear Algebra, nVidia, nVidia GeForce RTX 2080, OpenCL

July 11, 2021 by hgpu

Opening the Black Box: Performance Estimation during Code Generation for GPUs

Dominik Ernst, Georg Hager, Markus Holzer, Matthias Knorr, Gerhard Wellein

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, Lattice Boltzmann model, Machine learning, nVidia, Performance, Stencil computation, Tesla V100

July 11, 2021 by hgpu

A Sorting Library for FPGA Implementation in OpenCL Programming

Ryohei Kobayashi, Kento Miura, Norihisa Fujita, Taisuke Boku, Toshiyuki Amagasa

View

Download (PDF)

Tags: Algorithms, Computer science, FPGA, nVidia, OpenCL, Sorting, Tesla V100

July 4, 2021 by hgpu

Productivity, Portability, Performance: Data-Centric Python

Alexandros Nikolaos Ziogas, Timo Schneider, Tal Ben-Nun, Alexandru Calotoiu, Tiziano De Matteis, Johannes de Fine Licht, Luca Lavarini, Torsten Hoefler

View

Download (PDF)

Tags: Computer science, FPGA, HPC, nVidia, Python, Tesla V100

July 4, 2021 by hgpu

Optimization of Heterogeneous Parallel Computing Systems using Machine Learning

Devi Abhiseshu Adurti, Mohit Battu

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Machine learning, Matrix multiplication, nVidia, nVidia GeForce GTX 1050 Ti, Thesis

July 4, 2021 by hgpu

HALF: Holistic Auto Machine Learning for FPGAs

Jonas Ney, Dominik Loroch, Vladimir Rybalkin, Nico Weber, Jens Krüger, Norbert Wehn

View

Download (PDF)

Tags: Computer science, Design space exploration, FPGA, HLS, Machine learning, Neural networks

July 4, 2021 by hgpu

Improving Performance and Energy Efficiency of Heterogeneous Systems with rCUDA

Javier Prades Gasulla

View

Download (PDF)

Tags: Cloud, Computer science, CUDA, Heterogeneous systems, nVidia, Tesla K20, Tesla K40, Tesla P100, Thesis, Virtualization

June 27, 2021 by hgpu

Sigmoid: An auto-tuned load balancing algorithm for heterogeneous systems

Borja Pérez, E. Stafford, J.L. Bosque, R. Beivide

View

Download (PDF)

Tags: Algorithms, Computer science, Heterogeneous systems, load balancing, nVidia, nVidia GeForce GTX Titan Black, OpenCL, Tesla K20

June 27, 2021 by hgpu

Efficient heterogeneous matrix profile on a CPU + High Performance FPGA with integrated HBM

Jose Carlos Romero, Angeles Navarro, Antonio Vilches, Andrés Rodríguez, Francisco Corbera, Rafael Asenjo

View

Download (PDF)

Tags: Algorithms, Analytical model, Computer science, FPGA, Heterogeneous systems, OpenCL

June 27, 2021 by hgpu

APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores

Boyuan Feng, Yuke Wang, Tong Geng, Ang Li, Yufei Ding

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Deep learning, Neural networks, nVidia, nVidia GeForce RTX 3090, Package, Precision, Python, Tesla A100

June 27, 2021 by hgpu

GPUAPI: Multi-level Chapel Runtime API for GPUs

Akihiro Hayashi, Sri Raj Paul, Vivek Sarkar

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, Heterogeneous systems, HIP, nVidia, OpenCL, Package, SYCL, Tesla V100

June 20, 2021 by hgpu

Study and evaluation of improved automatic GPU offloading method

Yoji Yamato

View

Download (PDF)

Tags: Computer science, CUDA, FPGA, Heterogeneous systems, nVidia, nVidia Quadro P 4000, OpenACC, OpenCL

June 20, 2021 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

Applications

Block Conjugate Gradient Solver in OpenCL

Opening the Black Box: Performance Estimation during Code Generation for GPUs

A Sorting Library for FPGA Implementation in OpenCL Programming

Productivity, Portability, Performance: Data-Centric Python

Optimization of Heterogeneous Parallel Computing Systems using Machine Learning

HALF: Holistic Auto Machine Learning for FPGAs

Sigmoid: An auto-tuned load balancing algorithm for heterogeneous systems

Efficient heterogeneous matrix profile on a CPU + High Performance FPGA with integrated HBM

APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores

GPUAPI: Multi-level Chapel Runtime API for GPUs

Study and evaluation of improved automatic GPU offloading method

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)