high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

GPUNet: Searching the Deployable Convolution Neural Networks for GPUs

Linnan Wang, Chenhan Yu, Satish Salian, Slawomir Kierat, Szymon Migacz, Alex Fit Florea

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Neural networks, nVidia, nVidia Quadro GV100, Performance, Tesla A100

May 8, 2022 by hgpu

Improving performance of SYCL applications on CPU architectures using LLVM-directed compilation flow

Pietro Ghiglio, Uwe Dolinsky, Mehdi Goli, Kumudha Narasimhan

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, OpenCL, Performance, performance portability, SYCL

May 1, 2022 by hgpu

Performance Comparison of Different OpenCL Implementations of LBM Simulation on Commodity Computer Hardware

Jelena Tekic, Predrag Tekic, Milos Rackovic

View

Download (PDF)

Tags: AMD Radeon R5 M420, AMD Radeon R5 M430, ATI, cfd, Fluid dynamics, Heterogeneous systems, Lattice Boltzmann model, nVidia, nVidia GeForce GTX 940, nVidia GeForce GTX 960, OpenCL, Performance, Tesla C2070

April 17, 2022 by hgpu

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

Yannik Könneker

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Linear Algebra, nVidia, nVidia GeForce GTX 1080, OpenACC, OpenCL, Package, Performance, Tesla V100, Thesis

April 17, 2022 by hgpu

Optimizing Performance and Energy Efficiency in Massively Parallel Systems

Raúl Nozal González

View

Download (PDF)

Source codes

Tags: AMD Radeon RX 5700 XT, ATI, Computer science, Heterogeneous systems, HPC, nVidia, nVidia GeForce GTX 950, nVidia GeForce GTX Titan X, OpenCL, Package, Performance, SYCL, Tesla K20, Thesis

April 10, 2022 by hgpu

Performance Models for Heterogeneous Iterative Programs

Aparna Sasidharan

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, Performance, Tesla V100

April 10, 2022 by hgpu

HipBone: A performance-portable GPU-accelerated C++ version of the NekBone benchmark

Noel Chalmers, Abhishek Mishra, Damon McDougall, Tim Warburton

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, AMD Radeon Instinct MI250X, ATI, Benchmarking, Computer science, CUDA, HIP, HPC, MPI, nVidia, Package, Performance, Tesla V100

March 11, 2022 by hgpu

Romou: Rapidly Generate High-Performance Tensor Kernels for Mobile GPUs

Rendong Liang, Ting Cao, Jicheng Wen, Manni Wang, Yang Wang, Jianhua Zou, Yunxin Liu

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, OpenCL, Package, Performance, Vulkan

March 6, 2022 by hgpu

Lightning: Scaling the GPU Programming Model Beyond a Single GPU

Stijn Heldens, Pieter Hijma, Ben van Werkhoven, Jason Maassen, Rob V. van Nieuwpoort

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Distributed computing, nVidia, OpenCL, Package, Performance, Tesla P100

February 20, 2022 by hgpu

FC_ACCEL: Enabling Efficient, Low-Latency and Flexible Inference in DNN Fully Connected Layers, using Optimized Checkerboard Block matrix decomposition, fast scheduling, and a resource efficient 1D PE array with a custom HBM2 memory subsystem

Nick Iliev, Amit R Trivedi

View

Download (PDF)

Tags: CNN, Computer science, Deep learning, FPGA, Matrix decomposition, Neural networks, nVidia, nVidia Jetson AGX Xavier, Performance

February 13, 2022 by hgpu

Performance prediction of deep learning applications training in GPU as a service systems

Marco Lattuada, Eugenio Gianniti, Danilo Ardagna, Li Zhang

View

Download (PDF)

Tags: Computer science, Deep learning, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 1080 Ti, Performance, Tesla K80, Tesla M60

January 30, 2022 by hgpu

Reusing Auto-Schedules for Efficient DNN Compilation

Perry Gibson, José Cano

View

Download (PDF)

Tags: Algorithms, Computer science, Machine learning, Neural networks, Performance, Programming Languages

January 23, 2022 by hgpu

MSCCL++: A GPU-driven communication stack for scalable AI applications

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

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

* * *

high performance computing on graphics processing units: hgpu.org

GPUNet: Searching the Deployable Convolution Neural Networks for GPUs

Improving performance of SYCL applications on CPU architectures using LLVM-directed compilation flow

Performance Comparison of Different OpenCL Implementations of LBM Simulation on Commodity Computer Hardware

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

Optimizing Performance and Energy Efficiency in Massively Parallel Systems

Performance Models for Heterogeneous Iterative Programs

HipBone: A performance-portable GPU-accelerated C++ version of the NekBone benchmark

Romou: Rapidly Generate High-Performance Tensor Kernels for Mobile GPUs

Lightning: Scaling the GPU Programming Model Beyond a Single GPU

FC_ACCEL: Enabling Efficient, Low-Latency and Flexible Inference in DNN Fully Connected Layers, using Optimized Checkerboard Block matrix decomposition, fast scheduling, and a resource efficient 1D PE array with a custom HBM2 memory subsystem

Performance prediction of deep learning applications training in GPU as a service systems

Reusing Auto-Schedules for Efficient DNN Compilation

Recent source codes

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)