high performance computing on graphics processing units: hgpu.org

hgpu.org » paper

Hierarchical Resource Partitioning on Modern GPUs: A Reinforcement Learning Approach

Urvij Saroliya, Eishi Arima, Dai Liu, Martin Schulz

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Machine learning, nVidia, nVidia A100, PC cluster, Task scheduling

May 20, 2024 by hgpu

Predicting NVIDIA’s Next-Day Stock Price: A Comparative Analysis of LSTM, MLP, ARIMA, and ARIMA-GARCH Models

Yiluan Xing, Chao Yan, Cathy Chang Xie

View

Download (PDF)

Tags: Deep learning, Finance, LSTM, nVidia

May 20, 2024 by hgpu

Workload Scheduling on Heterogeneous Devices

Harsh Khetawat, Frank Mueller

View

Download (PDF)

Tags: Computer science, FPGA, Heterogeneous systems, nVidia, nVidia GeForce RTX 2060, OpenCL, Task scheduling

May 20, 2024 by hgpu

Direct Numerical Simulation of Turbulence on Heterogenous Computer Systems: Architectures, Algorithms, and Applications

Martin Karp

View

Download (PDF)

Tags: AMD Radeon Instinct MI250X, ATI, cfd, Fluid dynamics, FPGA, Heterogeneous systems, Numerical simulation, nVidia, nVidia A100, nVidia P100, nVidia V100, OpenCL, Spectral elements, Thesis

May 12, 2024 by hgpu

Automated Deep Learning Optimization via DSL-Based Source Code Transformation

Ruixin Wang, Minghai Lu, Cody Hao Yu, Yi-Hsiang Lai, Tianyi Zhang

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, DSL, nVidia, Package, Performance, PyTorch, Tesla T4

May 12, 2024 by hgpu

Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls

Sicong Liu, Wentao Zhou, Zimu Zhou, Bin Guo, Minfan Wang, Cheng Fang, Zheng Lin, Zhiwen Yu

View

Download (PDF)

Tags: Computer science, Deep learning, Heterogeneous systems

May 12, 2024 by hgpu

Optimizing Hardware Resource Partitioning and Job Allocations on Modern GPUs under Power Caps

Eishi Arima, Minjoon Kang, Issa Saba, Josef Weidendorfer, Carsten Trinitis, Martin Schulz

View

Download (PDF)

Tags: Computer science, CUDA, Energy-efficient computing, Heterogeneous systems, nVidia, nVidia A100, Performance

May 12, 2024 by hgpu

CuPBoP: Making CUDA a Portable Language

Ruobing Han, Jun Chen, Bhanu Garg, Xule Zhou, John Lu, Jeffrey Young, Jaewoong Sim, Hyesoon Kim

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, HIP, nVidia, nVidia A30, OpenCL, Package, Portability, SYCL

May 12, 2024 by hgpu

A Survey of Deep Learning Library Testing Methods

Xiaoyu Zhang, Weipeng Jiang, Chao Shen, Qi Li, Qian Wang, Chenhao Lin, Xiaohong Guan

View

Download (PDF)

Tags: Computer science, Deep learning, Security, survey

May 5, 2024 by hgpu

Porting HPC Applications to AMD Instinct MI300A Using Unified Memory and OpenMP

Suyash Tandon, Leopold Grinberg, Gheorghe-Teodor Bercea, Carlo Bertolli, Mark Olesen, Simone Bnà, Nicholas Malaya

View

Download (PDF)

Tags: AMD Radeon Instinct MI210, AMD Radeon Instinct MI300A, ATI, cfd, Computer science, Fluid dynamics, HPC, nVidia, nVidia A100, nVidia H100, OpenMP

May 5, 2024 by hgpu

Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper

Junjie Li, Yinzhi Wang, Xiao Liang, Hang Liu

View

Download (PDF)

Tags: BLAS, Chemistry, CUDA, nVidia, nVidia GH200, nVidia H100, Performance, Physics

May 5, 2024 by hgpu

Experiences with implementing Kokkos’ SYCL backend

Daniel Arndt, Damien Lebrun-Grandie, Christian Trott

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, HPC, Intel, Intel Data Center GPU Max 1550, Package, performance portability

May 5, 2024 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

Hierarchical Resource Partitioning on Modern GPUs: A Reinforcement Learning Approach

Predicting NVIDIA’s Next-Day Stock Price: A Comparative Analysis of LSTM, MLP, ARIMA, and ARIMA-GARCH Models

Workload Scheduling on Heterogeneous Devices

Direct Numerical Simulation of Turbulence on Heterogenous Computer Systems: Architectures, Algorithms, and Applications

Automated Deep Learning Optimization via DSL-Based Source Code Transformation

Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls

Optimizing Hardware Resource Partitioning and Job Allocations on Modern GPUs under Power Caps

CuPBoP: Making CUDA a Portable Language

A Survey of Deep Learning Library Testing Methods

Porting HPC Applications to AMD Instinct MI300A Using Unified Memory and OpenMP

Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper

Experiences with implementing Kokkos’ SYCL backend

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)