high performance computing on graphics processing units: hgpu.org

hgpu.org » Applications » Computer science

Benchmarking the Nvidia GPU Lineage: From Early K80 to Modern A100 with Asynchronous Memory Transfers

Martin Svedin, Steven W. D. Chien, Gibson Chikafa, Niclas Jansson, Artur Podobas

View

Tags: Benchmarking, Computer science, MPI, nVidia, nVidia GeForce GTX 1050 Ti, nVidia Quadro K 2200, Tesla A100, Tesla K80, Tesla P100, Tesla V100

June 20, 2021 by hgpu

StreamBrain: An HPC Framework for Brain-like Neural Networks on CPUs, GPUs and FPGAs

Artur Podobas, Martin Svedin, Steven W. D. Chien, Ivy B. Peng, Naresh Balaji Ravichandran, Pawel Herman, Anders Lansner, Stefano Markidis

View

Download (PDF)

Source codes

Tags: Bayesian, Computer science, CUDA, Deep learning, FPGA, HPC, Machine learning, MPI, nVidia, OpenMPI, Package, Tesla A100, Tesla V100

June 20, 2021 by hgpu

Experience Report: Writing A Portable GPU Runtime with OpenMP 5.1

Shilei Tian, Jon Chesterfield, Johannes Doerfert, Barbara Chapman

View

Download (PDF)

Tags: Computer science, CUDA, HIP, LLVM, MPI, nVidia, OpenMP, Portability, Tesla V100

June 20, 2021 by hgpu

DLIO: A Data-Centric Benchmark for Scientific Deep Learning Applications

Hariharan Devarajan, Huihuo Zheng, Anthony Kougkas, Xian-He Sun, Venkatram Vishwanath

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Deep learning, MPI, Neural networks, Package, TensorFlow

June 6, 2021 by hgpu

Data-Driven Analysis and Design of Vulkan Ray-Tracing Applications using Automatic Instrumentation

David Pankratz

View

Download (PDF)

Tags: Computer science, nVidia, nVidia GeForce GTX 1660 Ti, nVidia GeForce RTX 3080, Rasterization, Raytracing, Rendering, Thesis, Visualization, Vulkan

June 6, 2021 by hgpu

Optimization of Heterogeneous Systems with AI Planning Heuristics and Machine Learning: A Performance and Energy Aware Approach

Suejb Memeti, Sabri Pllana

View

Download (PDF)

Tags: Artificial intelligence, Computer science, Heterogeneous systems, Intel Xeon Phi, Machine learning

June 6, 2021 by hgpu

Exploiting co-execution with oneAPI: heterogeneity from a modern perspective

Raúl Nozal, Jose Luis Bosque

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, Intel UHD 630, load balancing, SYCL

June 6, 2021 by hgpu

Early Experiences Migrating CUDA codes to oneAPI

Manuel Costanzo, Enzo Rucci, Carlos García Sanchez, Marcelo Naiouf

View

Download (PDF)

Tags: Computer science, CUDA, FPGA, Heterogeneous systems, nVidia, nVidia GeForce RTX 2070, Portability, SYCL

June 6, 2021 by hgpu

Using Workload Characterization to Guide High Performance Graph Processing

Mohamed W. Hassan

View

Download (PDF)

Tags: Computer science, FPGA, Heterogeneous systems, HLS, nVidia, OpenCL, Optimization, Tesla K20, Thesis

May 30, 2021 by hgpu

kEDM: A Performance-portable Implementation of Empirical Dynamic Modeling using Kokkos

Keichi Takahashi, Wassapon Watanakeesuntorn, Kohei Ichikawa, Joseph Park, Ryousei Takano, Jason Haga, George Sugihara, Gerald M. Pao

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, HPC, nVidia, OpenCL, Package, Performance, performance portability

May 30, 2021 by hgpu

Sequence Parallelism: Making 4D Parallelism Possible

Shenggui Li, Fuzhao Xue, Yongbin Li, Yang You

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, nVidia, Tesla P100

May 30, 2021 by hgpu

TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system

Kaixin Zhang, Hongzhi Wang, Tongxin Li, Han Hu, Jiye Qiu, Songling Zou

View

Download (PDF)

Tags: Computer science, CUDA, Databases, Deep learning, Machine learning, nVidia, nVidia GeForce RTX 2080 Ti, Task scheduling

May 30, 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

Benchmarking the Nvidia GPU Lineage: From Early K80 to Modern A100 with Asynchronous Memory Transfers

StreamBrain: An HPC Framework for Brain-like Neural Networks on CPUs, GPUs and FPGAs

Experience Report: Writing A Portable GPU Runtime with OpenMP 5.1

DLIO: A Data-Centric Benchmark for Scientific Deep Learning Applications

Data-Driven Analysis and Design of Vulkan Ray-Tracing Applications using Automatic Instrumentation

Optimization of Heterogeneous Systems with AI Planning Heuristics and Machine Learning: A Performance and Energy Aware Approach

Exploiting co-execution with oneAPI: heterogeneity from a modern perspective

Early Experiences Migrating CUDA codes to oneAPI

Using Workload Characterization to Guide High Performance Graph Processing

kEDM: A Performance-portable Implementation of Empirical Dynamic Modeling using Kokkos

Sequence Parallelism: Making 4D Parallelism Possible

TENSILE: A Tensor granularity dynamic GPU memory scheduler method towards multiple dynamic workloads system

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)