high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

FAST: fast architecture sensitive tree search on modern CPUs and GPUs

Changkyu Kim, Jatin Chhugani, Nadathur Satish, Eric Sedlar, Anthony D. Nguyen, Tim Kaldewey, Victor W. Lee, Scott A. Brandt, Pradeep Dubey

View

Download (PDF)

Tags: Algorithms, Computer science, Databases, nVidia, nVidia GeForce GTX 280, Performance

November 17, 2010 by hgpu

A Graphics Parallel Memory Organization Exploiting Request Correlations

George Lentaris, Dionysios Reisis

Tags: Computer science, Performance, Storage system

November 17, 2010 by hgpu

Benchmarking and Implementation of Probability-Based Simulations on Programmable Graphics Cards

S. Tomov, M. McGuigan, R. Bennett, G. Smith, J. Spiletic

View

Download (PDF)

Tags: Cg, Computer science, Ising model, Monte Carlo simulation, nVidia, Performance, Physics

November 13, 2010 by hgpu

Tiling for Performance Tuning on Different Models of GPUs

Chang Xu, Steven R. Kirk, Samantha Jenkins

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce 8800 GTS, nVidia GeForce GTX 260, Performance

November 13, 2010 by hgpu

RapidMind: Portability across Architectures and its Limitations

Iris Christadler, Volker Weinberg

View

Download (PDF)

Tags: Cell processor, Computer science, CUDA, nVidia, Performance, Programming Languages, Tesla C1060, Tesla S1070

November 12, 2010 by hgpu

Exploring the Limits of GPUs With Parallel Graph Algorithms

Frank Dehne, Kumanan Yogaratnam

View

Download (PDF)

Tags: Computer science, CUDA, Data Structures and Algorithms, nVidia, nVidia GeForce GTX 260, Performance

November 12, 2010 by hgpu

Magnetohydrodynamics on Heterogeneous architectures: a performance comparison

Bijia Pang, Ue-li Pen, Michael Perrone

View

Download (PDF)

Tags: Astrophysics, ATI, ATI Radeon HD 5870, Cell processor, Computational Physics, CUDA, Electrodynamics, Instrumentation and Methods for Astrophysics, nVidia, nVidia GeForce GTX 260, OpenCL, OpenMP, Performance

November 11, 2010 by hgpu

General purpose Molecular Dynamics Simulations on GPUs: Issues of Pair Forces and Scaling to large Clusters

Christian Trott, Lars Winterfeld

View

Download (PDF)

Source codes

Tags: Computational Physics, Condensed matter, CUDA, GPU cluster, Materials Science, Molecular dynamics, MPI, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 295, Package, Performance, Physics, Tesla C1060, Tesla S1070

November 9, 2010 by hgpu

Fast Histograms using Adaptive CUDA Streams

Sisir Koppaka, Dheevatsa Mudigere, Srihari Narasimhan, Babu Narayanan

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance

November 9, 2010 by hgpu

On Dynamic Load Balancing on Graphics Processors

Daniel Cederman, Philippas Tsigas

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce 8800 GT, nVidia GeForce 9600 GT, Optimization, Performance

November 5, 2010 by hgpu

An experimental approach to performance measurement of heterogeneous parallel applications using CUDA

Allen D. Malony,Scott Biersdorff,Wyatt Spear,Shangkar Mayanglambam

Tags: Computer science, CUDA, nVidia, Performance

November 5, 2010 by hgpu

Streamlining GPU applications on the fly: thread divergence elimination through runtime thread-data remapping

E. Z. Zhang, Y. Jiang, G. Ziyu, X. Shen

View

Download (PDF)

Tags: Compilers, Computer science, CUDA, nVidia, Performance, Programming Languages, Tesla C1060

November 5, 2010 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

FAST: fast architecture sensitive tree search on modern CPUs and GPUs

A Graphics Parallel Memory Organization Exploiting Request Correlations

Benchmarking and Implementation of Probability-Based Simulations on Programmable Graphics Cards

Tiling for Performance Tuning on Different Models of GPUs

RapidMind: Portability across Architectures and its Limitations

Exploring the Limits of GPUs With Parallel Graph Algorithms

Magnetohydrodynamics on Heterogeneous architectures: a performance comparison

General purpose Molecular Dynamics Simulations on GPUs: Issues of Pair Forces and Scaling to large Clusters

Fast Histograms using Adaptive CUDA Streams

On Dynamic Load Balancing on Graphics Processors

An experimental approach to performance measurement of heterogeneous parallel applications using CUDA

Streamlining GPU applications on the fly: thread divergence elimination through runtime thread-data remapping

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)