high performance computing on graphics processing units: hgpu.org

hgpu.org » Mixed precision

On the accuracy and performance of the lattice Boltzmann method with 64-bit, 32-bit and novel 16-bit number formats

Moritz Lehmann, Mathias J. Krause, Giorgio Amati, Marcello Sega, Jens Harting, Stephan Gekle

View

Tags: AMD Radeon Instinct MI100, AMD Radeon VI, ATI, Fluid dynamics, lattice Boltzmann, Mixed precision, nVidia, OpenCL, Tesla K20, Tesla K40, Tesla K80, Tesla P100, Tesla V100

December 19, 2021 by hgpu

Mixed precision in Graphics Processing Unit

Quentin Gallouédec

View

Download (PDF)

Tags: Computer science, Machine learning, Mixed precision, Neural networks, nVidia, Tesla V100

October 31, 2021 by hgpu

A Study of Mixed Precision Strategies for GMRES on GPUs

Jennifer A. Loe, Christian A. Glusa, Ichitaro Yamazaki, Erik G. Boman, Sivasankaran Rajamanickam

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Linear Algebra, Mixed precision, nVidia, performance portability, Tesla V100

September 19, 2021 by hgpu

tcFFT: Accelerating Half-Precision FFT through Tensor Cores

Binrui Li, Shenggan Cheng, James Lin

View

Download (PDF)

Tags: Computer science, FFT, Mixed precision, nVidia, nVidia DGX-2, nVidia DGX-A100, Tesla V100

May 2, 2021 by hgpu

Mixed-Precision Embedding Using a Cache

Jie (Amy)Yang, Jianyu Huang, Jongsoo Park, Ping Tak Peter Tang, Andrew Tulloch

View

Download (PDF)

Tags: Artificial intelligence, Computer science, CUDA, Machine learning, Mixed precision, nVidia, Tesla V100

October 25, 2020 by hgpu

Flexible Performant GEMM Kernels on GPUs

Thomas Faingnaert, Tim Besard, Bjorn De Sutter

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Julia, Machine learning, Mathematical Software, Matrix multiplication, Mixed precision, nVidia, nVidia GeForce RTX 2080 Ti, Package, Performance

October 4, 2020 by hgpu

Accelerating Sparse Matrix-Matrix Multiplication with GPU Tensor Cores

Orestis Zachariadis, Nitin Satpute, Juan Gómez-Luna, Joaquín Olivares

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Matrix multiplication, Mixed precision, nVidia, nVidia GeForce RTX 2070, nVidia Titan RTX, Package, Performance, Sparse matrix

October 4, 2020 by hgpu

Performance Evaluation of Mixed Precision Algorithms for Solving Sparse Linear Systems

Mawussi Zounon, Nicholas J. Higham, Craig Lucas, Françoise Tisseur

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, Mixed precision, nVidia, Tesla P100, Tesla V100

September 27, 2020 by hgpu

Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning

Weile Jia, Han Wang, Mohan Chen, Denghui Lu, Jiduan Liu, Lin Lin, Roberto Car, Weinan E, Linfeng Zhang

View

Download (PDF)

Tags: Computational Physics, CUDA, HPC, Machine learning, Mixed precision, Molecular dynamics, Molecular simulation, MPI, nVidia, OpenMP, Physics, Tesla V100

May 10, 2020 by hgpu

Tools for Reduced Precision Computation: A Survey

Stefano Cherubin, Giovanni Agosta

View

Download (PDF)

Tags: Approximate computing and storage, Computer science, CUDA, HPC, Mixed precision, nVidia, OpenCL, Precision, survey

May 3, 2020 by hgpu

Tensor Processing Units for Financial Monte Carlo

Francois Belletti, Davis King, Kun Yang, Roland Nelet, Yusef Shafi, Yi-Fan Chen, John Anderson

View

Download (PDF)

Tags: Cloud, Deep learning, Finance, Mixed precision, Neural networks, nVidia, Option pricing, Tesla V100, TPU

June 12, 2019 by hgpu

Large Scale Language Modeling: Converging on 40GB of Text in Four Hours

Raul Puri, Robert Kirby, Nikolai Yakovenko, Bryan Catanzaro

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, LSTM, Mixed precision, Neural networks, nVidia, Package, Tesla V100, Torch

August 11, 2018 by hgpu

* * *

GPJSON: GPU-based JSON data processing system accessible via all GraalVM languages

GPU-based JSON data processing using structural indexes

NEPTUNE: Network- and GPU-aware management of serverless functions at the edge

NEPTUNE: Network- and GPU-aware Management of Serverless Functions at the Edge

HeCBench: a collection of Heterogeneous Computing benchmarks written with CUDA, HIP, SYCL (DPC++), and OpenMP-4.5

Experience of Migrating a Parallel Graph Coloring Program from CUDA to SYCL

cuPSO: GPU Parallelization for Particle Swarm Optimization Algorithms

WARPSPEED: An analytic Data Volume and Performance Estimator for GPU Kernels

Analytical Performance Estimation during Code Generation on Modern GPUs

Celerity HLA: A high-level API on top of Celerity to support functional, C++20 range-adaptors-like patterns

The Celerity High-level API: C++20 for Accelerator Clusters

GPU-Sched

CASE: A Compiler-Assisted SchEduling Framework for Multi-GPU Systems

Efficient Execution of OpenMP on GPUs

Explicit Caching HYB based SpMV

Explicit caching HYB: a new high-performance SpMV framework on GPGPU

matrix_inversion algorithm

Performance study on GPU offloading techniques using the Gauss matrix inverse algorithm

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

On the accuracy and performance of the lattice Boltzmann method with 64-bit, 32-bit and novel 16-bit number formats

Mixed precision in Graphics Processing Unit

A Study of Mixed Precision Strategies for GMRES on GPUs

tcFFT: Accelerating Half-Precision FFT through Tensor Cores

Mixed-Precision Embedding Using a Cache

Flexible Performant GEMM Kernels on GPUs

Accelerating Sparse Matrix-Matrix Multiplication with GPU Tensor Cores

Performance Evaluation of Mixed Precision Algorithms for Solving Sparse Linear Systems

Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning

Tools for Reduced Precision Computation: A Survey

Large Scale Language Modeling: Converging on 40GB of Text in Four Hours

Recent source codes

GPJSON: GPU-based JSON data processing system accessible via all GraalVM languages

NEPTUNE: Network- and GPU-aware management of serverless functions at the edge

HeCBench: a collection of Heterogeneous Computing benchmarks written with CUDA, HIP, SYCL (DPC++), and OpenMP-4.5

cuPSO: GPU Parallelization for Particle Swarm Optimization Algorithms

WARPSPEED: An analytic Data Volume and Performance Estimator for GPU Kernels

Celerity HLA: A high-level API on top of Celerity to support functional, C++20 range-adaptors-like patterns

GPU-Sched

Efficient Execution of OpenMP on GPUs

Explicit Caching HYB based SpMV

matrix_inversion algorithm

Most viewed papers (last 30 days)