high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Anatomy Of High-Performance Deep Learning Convolutions On SIMD Architectures

Evangelos Georganas, Sasikanth Avancha, Kunal Banerjee, Dhiraj Kalamkar, Greg Henry, Hans Pabst, Alexander Heinecke

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, Intel Xeon Phi, OpenMP, Package, Performance

August 19, 2018 by hgpu

A Cross-platform Evaluation of Graphics Shader Compiler Optimization

Lewis Crawford, Michael O'Boyle

View

Download (PDF)

Tags: 3D Graphics and Realism, Computer science, Optimization, Performance, Real-time graphics, Shaders, Virtual reality, Vulkan

August 11, 2018 by hgpu

Elementary functions: towards automatically generated, efficient, and vectorizable implementations

Hugues De Lassus Saint-Genies

View

Download (PDF)

Tags: Algorithms, Code generation, Computer science, Elementary functions, Performance, Thesis

July 28, 2018 by hgpu

Block-Size Independence for GPU Programs

Rajeev Alur, Joseph Devietti, Nimit Singhania

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX Titan X, Performance

July 28, 2018 by hgpu

Revisiting Online Autotuning for Sparse-Matrix Vector Multiplication Kernels on High-Performance Accelerators

Simon Garcia De Gonzalo, Wen-Mei Hwu, Simon D. Hammond, Christian R. Trott

View

Download (PDF)

Tags: Computer science, Intel Xeon Phi, nVidia, Performance, Sparse matrix, Tesla P100

July 15, 2018 by hgpu

Analysis-driven Engineering of Comparison-based Sorting Algorithms on GPUs

Ben Karsin, Volker Weichert, Henri Casanova, John Iacono, Nodari Sitchinava

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 770, nVidia Quadro M 4000, Performance, Sorting, Tesla K40

July 1, 2018 by hgpu

Improving tasks throughput on accelerators using OpenCL command concurrency

A.J. Lazaro-Munoz, J.M. Gonzalez-Linares, J. Gomez-Luna, N. Guil

View

Download (PDF)

Tags: AMD Radeon R9, ATI, Computer science, Heterogeneous systems, Intel Xeon Phi, nVidia, OpenCL, Performance, Task scheduling, Tesla K20

June 28, 2018 by hgpu

Optimizing Sparse Matrix-Vector Multiplication on Emerging Many-Core Architectures

Shizhao Chen, Jianbin Fang, Donglin Chen, Chuanfu Xu, Zheng Wang

View

Download (PDF)

Tags: Computer science, Intel Xeon Phi, Machine learning, OpenMP, Performance, Sparse matrix

June 9, 2018 by hgpu

Modeling and Evaluation of Synchronous Stochastic Gradient Descent in Distributed Deep Learning on Multiple GPUs

Shaohuai Shi, Qiang Wang, Xiaowen Chu, Bo Li

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Benchmarking, Computer science, CUDA, Deep learning, nVidia, nVidia GeForce GTX 1080, nVidia GeForce GTX 980, Package, Performance, Tesla K80

May 12, 2018 by hgpu

Auto-tuning Streamed Applications on Intel Xeon Phi

Peng Zhang, Jianbin Fang, Tao Tang, Canqun Yang, Zheng Wang

View

Download (PDF)

Source codes

Tags: Computer science, Intel Xeon Phi, Machine learning, Package, Performance

May 5, 2018 by hgpu

A Strategy for Automatic Performance Tuning of Stencil Computations on GPUs

Joseph D. Garvey, Tarek S. Abdelrahman

View

Download (PDF)

Tags: AMD Radeon R9 390, ATI, Computer science, Machine learning, nVidia, nVidia GeForce GTX Titan, OpenCL, Performance, Stencil computation

April 28, 2018 by hgpu

Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking

Zhe Jia, Marco Maggioni, Benjamin Staiger, Daniele P. Scarpazza

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, nVidia, Performance, PTX, Tesla V100

April 22, 2018 by hgpu

PTXBench: an open-source environment for kernel agents with architecture-specific CUDA/PTX

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

Harness Engineering for LLM-Driven GPU Kernel Generation

CANNBot Skills

Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization

NVIDIA Object Oriented Agents

NVIDIA-labs OO Agents: Native Python Object-Oriented Agents

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Anatomy Of High-Performance Deep Learning Convolutions On SIMD Architectures

A Cross-platform Evaluation of Graphics Shader Compiler Optimization

Elementary functions: towards automatically generated, efficient, and vectorizable implementations

Block-Size Independence for GPU Programs

Revisiting Online Autotuning for Sparse-Matrix Vector Multiplication Kernels on High-Performance Accelerators

Analysis-driven Engineering of Comparison-based Sorting Algorithms on GPUs

Improving tasks throughput on accelerators using OpenCL command concurrency

Optimizing Sparse Matrix-Vector Multiplication on Emerging Many-Core Architectures

Modeling and Evaluation of Synchronous Stochastic Gradient Descent in Distributed Deep Learning on Multiple GPUs

Auto-tuning Streamed Applications on Intel Xeon Phi

A Strategy for Automatic Performance Tuning of Stencil Computations on GPUs

Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking

Recent source codes

PTXBench: an open-source environment for kernel agents with architecture-specific CUDA/PTX

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

TensorCorePTX: PTX Tensor Core GEMM Exploration

FlashPDE: Triton-fused PDE stencil kernels for physics-informed neural networks

PortLBM: Portable GPU-accelerated Lattice Boltzmann Method Simulations

Harness Engineering for LLM-Driven GPU Kernel Generation

CANNBot Skills

NVIDIA Object Oriented Agents

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries

Most viewed papers (last 30 days)