high performance computing on graphics processing units: hgpu.org

Miles D. Cranmer, Benjamin R. Barsdell, Danny C. Price, Jayce Dowell, Hugh Garsden, Veronica Dike, Tarraneh Eftekhari, Alexander M. Hegedus, Joseph Malins, Kenneth S. Obenberger, Frank Schinzel, Kevin Stovall, Gregory B. Taylor, Lincoln J. Greenhill

View

Download (PDF)

Source codes

Tags: Astrophysics, Computer science, CUDA, nVidia, Package, Python, Tesla K80

August 8, 2017 by hgpu

Optimized Broadcast for Deep Learning Workloads on Dense-GPU InfiniBand Clusters: MPI or NCCL?

Ammar Ahmad Awan, Ching-Hsiang Chu, Hari Subramoni, Dhabaleswar K. Panda

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, GPU cluster, MPI, nVidia, nVidia DGX-1, OpenMPI, Tesla V100

August 1, 2017 by hgpu

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

Faial: finds bugs in CUDA kernels

Sound and Partially-Complete Static Analysis of Data-Races in GPU Programs

Effects of OpenCL-Based Parallelization Methods on Explicit Numerical Methods to Solve the Heat Equation

Intel® SHMEM: Device initiated shared memory based communication library

Intel(R) SHMEM: GPU-initiated OpenSHMEM using SYCL

miniLB: Lattice Botlzmann miniapp w/SYCL

miniLB: A Performance Portability Study of Lattice-Boltzmann Simulations

AFOCL

Bitstream Database-Driven FPGA Programming Flow Based on Standard OpenCL

2domination

HPC acceleration of large (min, +) matrix products to compute domination-type parameters in graphs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Integer sorting on multicores: some (experiments and) observations

Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded Modes

Large Integer Arithmetic in GPU for Cryptography

Dynamic Parallelism in GPU Optimized Barnes Hut Trees for Molecular Dynamics Simulations

Performance Characterization of Multi-threaded Graph Processing Applications on Intel Many-Integrated-Core Architecture

Gpufit: An open-source toolkit for GPU-accelerated curve fitting

GARDENIA: A Domain-specific Benchmark Suite for Next-generation Accelerators

Using Graph Properties to Speed-up GPU-based Graph Traversal: A Model-driven Approach

GPU Array Access Auto-Tuning

Practically efficient methods for performing bit-reversed permutation in C++11 on the x86-64 architecture

Bifrost: a Python/C++ Framework for High-Throughput Stream Processing in Astronomy

Optimized Broadcast for Deep Learning Workloads on Dense-GPU InfiniBand Clusters: MPI or NCCL?

Recent source codes

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

EnergyUCB-Bandit