high performance computing on graphics processing units: hgpu.org

hgpu.org » Applications

ndzip-gpu: Efficient Lossless Compression of Scientific Floating-Point Data on GPUs

Fabian Knorr, Peter Thoman, Thomas Fahringer

View

Download (PDF)

Source codes

Tags: Compression, Computer science, CUDA, nVidia, nVidia GeForce RTX 2070, nVidia GeForce RTX 3090, Package, SYCL, Tesla V100

August 8, 2021 by hgpu

ScaleHLS: Scalable High-Level Synthesis through MLIR

Hanchen Ye, Cong Hao, Jianyi Cheng, Hyunmin Jeong, Jack Huang, Stephen Neuendorffer, Deming Chen

View

Download (PDF)

Source codes

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

August 8, 2021 by hgpu

PoCL-R: A Scalable Low Latency Distributed OpenCL Runtime

Jan Solanti, Michal Babej, Julius Ikkala, Vinod Kumar Malamal Vadakital, Pekka Jääskeläinen

View

Download (PDF)

Source codes

Tags: Computer science, GPU cluster, Heterogeneous systems, Matrix multiplication, nVidia, nVidia GeForce GTX 1060, nVidia GeForce GTX 2080 Ti, OpenCL, Package, Rendering, Tesla P100, Tesla V100

August 8, 2021 by hgpu

Face.evoLVe: A High-Performance Face Recognition Library

Qingzhong Wang, Pengfei Zhang, Haoyi Xiong, Jian Zhao

View

Download (PDF)

Source codes

Tags: AI, Computer science, Deep learning, Package, PyTorch

July 25, 2021 by hgpu

StreamBlocks: A compiler for heterogeneous dataflow computing

Endri Bezati, Mahyar Emami, Jörn Janneck, James Larus

View

Download (PDF)

Source codes

Tags: Computer science, FPGA, Heterogeneous systems, HLS, OpenCL, Package, Performance

July 25, 2021 by hgpu

A method for decompilation of AMD GCN kernels to OpenCL

K.I. Mihajlenko, M.A. Lukin, A.S. Stankevich

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, OpenCL, Package, Python

July 25, 2021 by hgpu

DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors

Enrico Tabanelli, Giuseppe Tagliavini, Luca Benini

View

Download (PDF)

Source codes

Tags: Computer science, FPGA, Machine learning, Neural networks, nVidia, Package, SoC, Tesla A100

July 25, 2021 by hgpu

Designing a high-performance boundary element library with OpenCL and Numba

T. Betcke, M. W. Scroggs

View

Download (PDF)

Source codes

Tags: Computer science, HPC, nVidia, nVidia Quadro RTX 3000, OpenCL, Package, PyOpenCL, Python

July 18, 2021 by hgpu

Bringing OpenCL to Commodity RISC-V CPUs

Tine Blaise, Seyong Lee, Jeff Vetter, Hyesoon Kim

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, HPC, OpenCL, Package

July 11, 2021 by hgpu

KAISA: An Adaptive Second-order Optimizer Framework for Deep Neural Networks

J. Gregory Pauloski, Qi Huang, Lei Huang, Shivaram Venkataraman, Kyle Chard, Ian Foster, Zhao Zhang

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Machine learning, Neural networks, nVidia, nVidia A100, nVidia DGX-A100, Package, Tesla V100

July 11, 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

Lettuce: PyTorch-based Lattice Boltzmann Framework

Mario Christopher Bedrunka, Dominik Wilde, Martin Kliemank, Dirk Reith, Holger Foysi, Andreas Krämer

View

Download (PDF)

Source codes

Tags: Algorithms, Computational Physics, CUDA, Deep learning, Fluid dynamics, Lattice Boltzmann model, Machine learning, nVidia, nVidia GeForce RTX 2070, Package, Physics, Tesla V100

June 27, 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

Packages

ndzip-gpu: Efficient Lossless Compression of Scientific Floating-Point Data on GPUs

ScaleHLS: Scalable High-Level Synthesis through MLIR

PoCL-R: A Scalable Low Latency Distributed OpenCL Runtime

Face.evoLVe: A High-Performance Face Recognition Library

StreamBlocks: A compiler for heterogeneous dataflow computing

A method for decompilation of AMD GCN kernels to OpenCL

DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors

Designing a high-performance boundary element library with OpenCL and Numba

Bringing OpenCL to Commodity RISC-V CPUs

KAISA: An Adaptive Second-order Optimizer Framework for Deep Neural Networks

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

Lettuce: PyTorch-based Lattice Boltzmann Framework

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)