high performance computing on graphics processing units: hgpu.org

hgpu.org » CUDA

Reveal training performance mystery between TensorFlow and PyTorch in the single GPU environment

Hulin Dai, Xuan Peng, Xuanhua Shi, Ligang He, Qian Xiong, Hai Jin

View

Tags: Benchmarking, Computer science, CUDA, Deep learning, Neural networks, nVidia, Performance, PyTorch, TensorFlow, Tesla P100

January 9, 2022 by hgpu

Analysis of High Level implementations for Recursive Methods on GPUs

Cheng Cao, Justin Kalloor

View

Download (PDF)

Tags: Computer science, CUDA, DSL, nVidia, nVidia GeForce RTX 3080, OpenGL, Vulkan

January 9, 2022 by hgpu

Dynamic GPU Energy Optimization for Machine Learning Training Workloads

Farui Wang, Weizhe Zhang, Shichao Lai, Meng Hao, Zheng Wang

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Energy-efficient computing, Machine learning, nVidia, nVidia GeForce RTX 3080 Ti, Package

January 9, 2022 by hgpu

Domain-Specific On-Device Object Detection Method

Seongju Kang, Jaegi Hwang, Kwangsue Chung

View

Download (PDF)

Tags: Computer science, Computer vision, CUDA, Neural networks, nVidia, nVidia GeForce RTX 2060

January 9, 2022 by hgpu

System-Level Optimization and Code Generation for Graphics Processors using a Domain-Specific Language

Bo Qiao

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, Image processing, Machine learning, nVidia, nVidia GeForce GTX 680, nVidia GeForce RTX 2080, OpenCL, Package, performance portability, Tesla K20, Thesis

January 2, 2022 by hgpu

GPU-accelerated Faster Mean Shift with euclidean distance metrics

Le You, Han Jiang, Jinyong Hu, Chorng Chang, Lingxi Chen, Xintong Cui, Mengyang Zhao

View

Download (PDF)

Source codes

Tags: Algorithms, Clustering, CUDA, Image processing, nVidia, nVidia GeForce RTX 3070, nVidia GeForce RTX 3080 Ti, nVidia Quadro P 5000, Package, Pattern recognition, Tesla P100

January 2, 2022 by hgpu

A Unified FPGA Virtualization Framework for General-Purpose Deep Neural Networks in the Cloud

Shulin Zeng, Guohao Dai, Hanbo Sun, Jun Liu, Shiyao Li, Guangjun Ge, Kai Zhong, Kaiyuan Guo, Yu Wang, Huazhong Yang

View

Download (PDF)

Tags: Cloud, Computer science, CUDA, FPGA, Neural networks, nVidia, Tesla V100, Virtualization

January 2, 2022 by hgpu

A Variant of Concurrent Constraint Programming on GPU

Pierre Talbot, Frederic Pinel, Pascal Bouvry

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, nVidia, nVidia Quadro RTX 5000, Package, Performance

January 2, 2022 by hgpu

COX: CUDA on X86 by Exposing Warp-Level Functions to CPUs

Ruobing Han, Jaewon Lee, Jaewoong Sim, Hyesoon Kim

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, CUDA, nVidia

December 26, 2021 by hgpu

TCUDB: Accelerating Database with Tensor Processors

Yu-Ching Hu, Yuliang Li, Hung-Wei Tseng

View

Download (PDF)

Tags: Computer science, CUDA, Databases, Machine learning, Matrix multiplication, Neural networks, nVidia, nVidia GeForce RTX 3090

December 19, 2021 by hgpu

Evaluation of Pseudo-Random Number Generation on GPU Cards

Tair Askar, Bekdaulet Shukirgaliyev, Martin Lukac, Ernazar Abdikamalov

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 1080, nVidia GeForce GTX 1080 Ti, nVidia GeForce RTX 3080, nVidia GeForce RTX 3090, Pseudo-random number generators

December 19, 2021 by hgpu

Fast Neural Representations for Direct Volume Rendering

Sebastian Weiss, Philipp Hermüller, Rüdiger Westermann

View

Download (PDF)

Source codes

Tags: 3D Graphics and Realism, CUDA, GLSL, nVidia, nVidia GeForce RTX 2070, Package, Raytracing, Rendering, Visualization

December 12, 2021 by hgpu

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

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

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

* * *

high performance computing on graphics processing units: hgpu.org

Reveal training performance mystery between TensorFlow and PyTorch in the single GPU environment

Analysis of High Level implementations for Recursive Methods on GPUs

Dynamic GPU Energy Optimization for Machine Learning Training Workloads

Domain-Specific On-Device Object Detection Method

System-Level Optimization and Code Generation for Graphics Processors using a Domain-Specific Language

GPU-accelerated Faster Mean Shift with euclidean distance metrics

A Variant of Concurrent Constraint Programming on GPU

COX: CUDA on X86 by Exposing Warp-Level Functions to CPUs

TCUDB: Accelerating Database with Tensor Processors

Evaluation of Pseudo-Random Number Generation on GPU Cards

Fast Neural Representations for Direct Volume Rendering

Recent source codes

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)