high performance computing on graphics processing units: hgpu.org

hgpu.org » Heterogeneous systems

Towards global composition of performance-aware components for GPU-based systems

Usman Dastgeer, Christoph Kessler

View

Download (PDF)

Tags: Computer science, CUDA, Flow analysis, Heterogeneous systems, nVidia, Task scheduling, Tesla C2050

December 20, 2013 by hgpu

Heterogeneous Programming with Single Operation Multiple Data

Herve Paulino, Eduardo Marques

View

Download (PDF)

Tags: Computer science, CUDA, Data parallelism, Heterogeneous systems, Java, nVidia, nVidia GeForce GT 320 M, Tesla C2050

December 19, 2013 by hgpu

OpenCL Accelerated Multi-GPU Cone-Beam Reconstruction

Marc Kaseberg, Steffen Melnik, Erwin Keeve

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 5770, ATI Radeon HD 6970, Computed tomography, CT, Heterogeneous systems, Image processing, nVidia, nVidia GeForce GTX 480, nVidia GeForce GTX 580, nVidia GeForce GTX 680, nVidia Quadro 600, OpenCL, Tomography

December 17, 2013 by hgpu

Data Transfer Matters for GPU Computing

Yusuke Fujii, Takuya Azumi, Nobuhiko Nishio, Shinpei Kato, Masato Edahiro

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 480, Package, Performance

December 13, 2013 by hgpu

TuCCompi: A Multi-Layer Programing Model for Heterogeneous Systems with Auto-Tuning Capabilities

Hector Ortega-Arranz, Yuri Torres, Diego R. Llanos, Arturo Gonzalez-Escribano

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 480, nVidia GeForce GTX 680, OpenMP

December 13, 2013 by hgpu

Efficient Large-Scale Graph Processing on Hybrid CPU and GPU Systems

Abdullah Gharaibeh, Elizeu Santos-Neto, Lauro Beltrao Costa, Matei Ripeanu

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Graph theory, Heterogeneous systems, Hybrid computing, nVidia, Package

December 12, 2013 by hgpu

Runtime Support toward Transparent Memory Access in GPU-accelerated Heterogeneous Systems

Feng Ji

View

Download (PDF)

Tags: Computer science, Hadoop, Heterogeneous systems, MapReduce, MPI, nVidia, nVidia GeForce GTX 280, Tesla M2070, Thesis

December 11, 2013 by hgpu

A Distributed Data Mining Framework Accelerated with Graphics Processing Units

Nam-Luc Tran, Quentin Dugauthier, Sabri Skhiri

View

Download (PDF)

Tags: Clustering, Computer science, Data mining, Heterogeneous systems, nVidia, nVidia GeForce GTX Titan, Tesla K20

December 6, 2013 by hgpu

GPU-based Multi-stream Analyzer on Application Layer for Service-oriented Router

Kazumasa Ikeuchi, Janaka Wijekoon, Shinichi Ishida, Hiroaki Nishi

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 680, Software router, String matching

December 4, 2013 by hgpu

Exploiting Heterogeneous Systems: Keccak on OpenCL

Allan Mariano de Souza, Fabio Dacencio Pereira, Edward David Moreno

View

Download (PDF)

Tags: Algorithms, Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 295, OpenCL, Security

December 4, 2013 by hgpu

Benchmarking Parallel Performance on Many-Core Processors

Bryant C. Lam, Ajay Barboza, Ravi Agrawal, Alan D. George, Herman Lam

View

Download (PDF)

Tags: Benchmarking, Computer science, Heterogeneous systems, Intel Phi, Intel Xeon Phi, Performance

November 29, 2013 by hgpu

Autotuning of Pattern Runtimes for Accelerated Parallel Systems

Enes Bajrovic, Siegfried Benkner, Jiri Dokulil, Martin Sandrieser

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, Tesla C1060, Tesla C2050

November 27, 2013 by hgpu

Agentic Code Optimization via Compiler-LLM Cooperation

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

DVM: Real-Time Kernel Generation for Dynamic AI Models

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

* * *

high performance computing on graphics processing units: hgpu.org

Towards global composition of performance-aware components for GPU-based systems

Heterogeneous Programming with Single Operation Multiple Data

OpenCL Accelerated Multi-GPU Cone-Beam Reconstruction

Data Transfer Matters for GPU Computing

TuCCompi: A Multi-Layer Programing Model for Heterogeneous Systems with Auto-Tuning Capabilities

Efficient Large-Scale Graph Processing on Hybrid CPU and GPU Systems

Runtime Support toward Transparent Memory Access in GPU-accelerated Heterogeneous Systems

A Distributed Data Mining Framework Accelerated with Graphics Processing Units

GPU-based Multi-stream Analyzer on Application Layer for Service-oriented Router

Exploiting Heterogeneous Systems: Keccak on OpenCL

Benchmarking Parallel Performance on Many-Core Processors

Autotuning of Pattern Runtimes for Accelerated Parallel Systems

Recent source codes

Agentic Code Optimization via Compiler-LLM Cooperation

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

True 4-Bit Quantized CNN Training on CPU

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

Most viewed papers (last 30 days)