high performance computing on graphics processing units: hgpu.org

René Caspart, Sebastian Ziegler, Arvid Weyrauch, Holger Obermaier, Simon Raffeiner, Leon Pascal Schuhmacher, Jan Scholtyssek, Darya Trofimova, Marco Nolden, Ines Reinartz, Fabian Isensee, Markus Götz, Charlotte Debus

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Computer science, Deep learning, Energy-efficient computing, Heterogeneous systems, nVidia, nVidia A100, nVidia V100, Package

December 11, 2022 by hgpu

Mixing Low-Precision Formats in Multiply-Accumulate Units for DNN Training

Mariko Tatsumi, Silviu-Ioan Filip, Caroline White, Olivier Sentieys, Guy Lemieux

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, FPGA, nVidia, Precision

December 11, 2022 by hgpu

SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems

Jiangsu Du, Dongsheng Li, Yingpeng Wen, Jiazhi Jiang, Dan Huang, Xiangke Liao, Yutong Lu

View

Download (PDF)

Tags: Artificial intelligence, Benchmarking, Computer science, CUDA, Deep learning, HPC, nVidia, PyTorch, Tesla V100

December 11, 2022 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

Arax: a runtime framework for decoupling applications from heterogeneous accelerators

Understanding the Impact of Input Entropy on FPU, CPU, and GPU Power

Extending MAGMA Portability with OneAPI

GPU Load Balancing

Code Generation from Functional to Imperative: Combining Destination-Passing Style and Views

Portable C++ Code that can Look and Feel Like Fortran Code with Yet Another Kernel Launcher (YAKL)

A Study on the Intersection of GPU Utilization and CNN Inference

Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems

Precise Energy Consumption Measurements of Heterogeneous Artificial Intelligence Workloads

Mixing Low-Precision Formats in Multiply-Accumulate Units for DNN Training

SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems

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)