high performance computing on graphics processing units: hgpu.org

hgpu.org » performance portability

HPVM: Heterogeneous Parallel Virtual Machine

Maria Kotsifakou, Prakalp Srivastava, Matthew D. Sinclair, Rakesh Komuravelli, Vikram Adve, Sarita Adve

View

Tags: Code generation, Computer science, FPGA, Heterogeneous systems, nVidia, nVidia GeForce GTX 680, OpenCL, performance portability, Virtualization

March 17, 2018 by hgpu

TVM: End-to-End Optimization Stack for Deep Learning

Tianqi Chen, Thierry Moreau, Ziheng Jiang, Haichen Shen, Eddie Yan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Computer science, CUDA, Deep learning, FPGA, Machine learning, nVidia, nVidia GeForce GTX 1080, OpenCL, Package, performance portability, TensorFlow, Tesla K80

February 15, 2018 by hgpu

ImageCL: Language and source-to-source compiler for performance portability, load balancing, and scalability prediction on heterogeneous systems

Thomas L. Falch, Anne C. Elster

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 7970, Compilers, Heterogeneous systems, Image processing, Machine learning, nVidia, nVidia GeForce GTX 960, OpenCL, Package, performance portability, Tesla K40

January 13, 2018 by hgpu

High Performance Stencil Code Generation with Lift

Bastian Hagedorn, Larisa Stoltzfus, Michel Steuwer, Sergei Gorlatch, Christophe Dubach

View

Download (PDF)

Source codes

Tags: ARM, ATI, ATI Radeon HD 7970, Code generation, Compilers, Computer science, Linear Algebra, nVidia, OpenCL, Package, performance portability, Scala, Tesla K20

January 13, 2018 by hgpu

Strategy Preserving Compilation for Parallel Functional Code

Robert Atkey, Michel Steuwer, Sam Lindley, Christophe Dubach

View

Download (PDF)

Tags: ATI, ATI Radeon 7970, Code generation, Computer science, nVidia, nVidia GeForce GTX Titan X, OpenCL, performance portability

October 29, 2017 by hgpu

Toward Performance Portability for CPUs and GPUs Through Algorithmic Compositions

Li-Wen Chang

View

Download (PDF)

Tags: Algorithms, Computer science, Heterogeneous systems, nVidia, OpenCL, performance portability, Tesla C2050, Tesla K20, Thesis

October 15, 2017 by hgpu

From MPI to MPI+OpenACC: Conversion of a legacy FORTRAN PCG solver for the spherical Laplace equation

Ronald M. Caplan, Zoran Mikic, Jon A. Linker

View

Download (PDF)

Tags: Computer science, CUDA, Fortran, Laplace and Poisson equation, Mathematical Software, MPI, nVidia, OpenACC, performance portability, Tesla P100

September 7, 2017 by hgpu

GPU Array Access Auto-Tuning

Nicolas Weber

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GT 440, nVidia GeForce GT 620, nVidia GeForce GT 730, nVidia GeForce GTX 1080, nVidia GeForce GTX 480, nVidia GeForce GTX 560 Ti, nVidia GeForce GTX 570, nVidia GeForce GTX 590, nVidia GeForce GTX 680, nVidia GeForce GTX 780, nVidia GeForce GTX 980, nVidia GeForce GTX Titan X, Performance, performance portability, Tesla C2070, Tesla K20, Thesis

August 8, 2017 by hgpu

Portable, high-performance containers for HPC

Lucas Benedicic, Felipe A. Cruz, Alberto Madonna, Kean Mariotti

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia Quadro K 110 M, OpenCL, performance portability, Tesla K40, Tesla K80, Tesla P100, Virtualization

April 15, 2017 by hgpu

Optimization of Lattice Boltzmann Simulations on Heterogeneous Computers

E. Calore, A. Gabbana, S. F. Schifano, R. Tripiccione

View

Download (PDF)

Tags: AMD FirePro W9100, ATI, Fluid dynamics, GPU cluster, Heterogeneous systems, Intel Xeon Phi, Lattice Boltzmann model, MPI, nVidia, OpenACC, OpenMP, Performance, performance portability, Tesla K80

March 20, 2017 by hgpu

Compiling Parallel Functional Code with Data Parallel Idealised Algol

Robert Atkey, Michel Steuwer, Sam Lindley, Christophe Dubach

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 7970, Computer science, nVidia, nVidia GeForce GTX Titan X, OpenCL, performance portability

March 14, 2017 by hgpu

Accelerating Workloads on FPGAs via OpenCL: A Case Study with OpenDwarfs

Anshuman Verma, Ahmed E. Helal, Konstantinos Krommydas, Wu-Chun Feng

View

Download (PDF)

Tags: Computer science, FPGA, Intel Xeon Phi, N-body simulation, nVidia, OpenCL, performance portability, Tesla C2070, Tesla K20

January 26, 2017 by hgpu

GPUODEBenchmarks: Comparsion of Julia's GPU Kernel based ODE solvers with other open-source GPU ODE solvers

Automating Heterogeneous Parallelism in Numerical Differential Equations

Dat3M: Memory Model Aware Verification

Towards Unified Analysis of GPU Consistency

NVIDIA Federated Learning Application Runtime Environment

Supercharging Federated Learning with Flower and NVIDIA FLARE

Chat AI: A Seamless Slurm-Native Solution for HPC-Based Services

PSCToolkit: solving sparse linear systems with a large number of GPUs

CATBench: Benchmarking Framework

CATBench: A Compiler Autotuning Benchmarking Suite for Black-box Optimization

General-purpose Polyhedral Compilers

A Survey of General-purpose Polyhedral Compilers

Optimal Kernel Orchestration for Tensor Programs with Korch

Astaroth: A Scalable Multi-GPU Library for Stencil Computations

Stencil Computations on AMD and Nvidia Graphics Processors: Performance and Tuning Strategies

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

HPVM: Heterogeneous Parallel Virtual Machine

TVM: End-to-End Optimization Stack for Deep Learning

ImageCL: Language and source-to-source compiler for performance portability, load balancing, and scalability prediction on heterogeneous systems

High Performance Stencil Code Generation with Lift

Strategy Preserving Compilation for Parallel Functional Code

Toward Performance Portability for CPUs and GPUs Through Algorithmic Compositions

From MPI to MPI+OpenACC: Conversion of a legacy FORTRAN PCG solver for the spherical Laplace equation

GPU Array Access Auto-Tuning

Portable, high-performance containers for HPC

Optimization of Lattice Boltzmann Simulations on Heterogeneous Computers

Compiling Parallel Functional Code with Data Parallel Idealised Algol

Accelerating Workloads on FPGAs via OpenCL: A Case Study with OpenDwarfs

Recent source codes

GPUODEBenchmarks: Comparsion of Julia's GPU Kernel based ODE solvers with other open-source GPU ODE solvers

Dat3M: Memory Model Aware Verification

NVIDIA Federated Learning Application Runtime Environment

Chat AI: A Seamless Slurm-Native Solution for HPC-Based Services

PSCToolkit: solving sparse linear systems with a large number of GPUs

CATBench: Benchmarking Framework

General-purpose Polyhedral Compilers

Optimal Kernel Orchestration for Tensor Programs with Korch

Astaroth: A Scalable Multi-GPU Library for Stencil Computations

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking

Most viewed papers (last 30 days)