high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Parallel For Loops on Heterogeneous Resources

Frederick Edward Weber

View

Tags: ATI, ATI Radeon HD 7970, Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 480, OpenCL, Performance, Thesis

May 1, 2013 by hgpu

Improving Numerical Accuracy for Non-Negative Matrix Multiplication on GPUs using Recursive Algorithms

Matthew Badin, Paolo D'Alberto, Lubomir Bic, Michael Dillencourt, Alexandru Nicolau

View

Download (PDF)

Tags: Algorithms, BLAS, Computer science, CUDA, Matrix multiplication, nVidia, Performance, Tesla C2070

April 30, 2013 by hgpu

Split tiling for GPUs: automatic parallelization using trapezoidal tiles

Tobias Grosser, Albert Cohen, Paul H J Kelly, J. Ramanujam, P. Sadayappan, Sven Verdoolaege

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, CUDA, nVidia, nVidia GeForce GTX 470, nVidia Quadro NVS 5200 M, Package, Performance

April 29, 2013 by hgpu

Orchestrated Scheduling and Prefetching for GPGPUs

Adwait Jog, Onur Kayiran, Asit K. Mishra, Mahmut T. Kandemir, Onur Mutlu, Ravishankar Iyer, Chita R. Das

View

Download (PDF)

Tags: Computer science, CUDA, GPGPU-sim, nVidia, nVidia GeForce GTX 285, Performance, Prefetch

April 27, 2013 by hgpu

Valar: A Benchmark Suite to Study the Dynamic Behavior of Heterogeneous Systems

Perhaad Mistry, Yash Ukidave, Dana Schaa, David Kaeli

View

Download (PDF)

Tags: APU, ATI, ATI Radeon HD 7850, ATI Radeon HD 7970, Benchmarking, Computer science, Computer vision, Heterogeneous systems, OpenCL, Performance

April 22, 2013 by hgpu

One OpenCL to Rule Them All?

Romain Dolbeau, Francois Bodin, Guillaume Colin de Verdiere

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, Computer science, Intel, Intel Phi, nVidia, OpenACC, OpenCL, Performance, Portability, Tesla K20

April 21, 2013 by hgpu

An Automatic Input-Sensitive Approach for Heterogeneous Task Partitioning

Klaus Kofler, Ivan Grasso, Biagio Cosenza, Thomas Fahringer

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5870, Code generation, Compilers, Computer science, Heterogeneous systems, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 480, OpenCL, Performance, Task scheduling

April 21, 2013 by hgpu

SemCache: Semantics-aware Caching for Efficient GPU Offloading

Nabeel AlSaber, Milind Kulkarni

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Programming techniques, Tesla C2070

April 19, 2013 by hgpu

Comparison based sorting for systems with multiple GPUs

Ivan Tanasic, Lluis Vilanova, Marc Jorda, Javier Cabezas, Isaac Gelado, Nacho Navarro, Wen-mei Hwu

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, Performance, Sorting, Tesla C2070

April 18, 2013 by hgpu

A Framework for Profiling and Performance Monitoring of Heterogeneous Applications

Perhaad Mistry, Yash Ukidave, Dana Schaa, David Kaeli

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5870, ATI Radeon HD 6550, Computer science, Computer vision, Heterogeneous systems, OpenCL, Performance, Signal processing

April 17, 2013 by hgpu

Load Balancing in a Changing World: Dealing with Heterogeneity and Performance Variability

Michael Boyer, Kevin Skadron, Shuai Che, Nuwan Jayasena

View

Download (PDF)

Tags: ATI, ATI Radeon HD 6550, ATI Radeon HD 6670, Computer science, Heterogeneous systems, OpenCL, Performance, Task scheduling

April 8, 2013 by hgpu

Atomic-free Irregular Computations on GPUs

Rupesh Nasre, Martin Burtscher, Keshav Pingali

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Graph theory, nVidia, Package, Performance, Tesla K20

April 7, 2013 by hgpu

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

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

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Parallel For Loops on Heterogeneous Resources

Improving Numerical Accuracy for Non-Negative Matrix Multiplication on GPUs using Recursive Algorithms

Split tiling for GPUs: automatic parallelization using trapezoidal tiles

Orchestrated Scheduling and Prefetching for GPGPUs

Valar: A Benchmark Suite to Study the Dynamic Behavior of Heterogeneous Systems

One OpenCL to Rule Them All?

An Automatic Input-Sensitive Approach for Heterogeneous Task Partitioning

SemCache: Semantics-aware Caching for Efficient GPU Offloading

Comparison based sorting for systems with multiple GPUs

A Framework for Profiling and Performance Monitoring of Heterogeneous Applications

Load Balancing in a Changing World: Dealing with Heterogeneity and Performance Variability

Atomic-free Irregular Computations on GPUs

Recent source codes

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

CUDA Kernel Fusion Benchmarks

IntelliKit: Agent-first tooling for AMD hardware

DITRON: Distributed Compiler based on Triton for Parallel Systems

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

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

Device Virtual Machine (DVM)

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

Most viewed papers (last 30 days)