high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

CudaChain: A Practical GPU-accelerated 2D Convex Hull Algorithm

Gang Mei

View

Download (PDF)

Tags: Computational Geometry, Computer science, CUDA, nVidia, nVidia GeForce GT 640, nVidia GeForce GTX 660 M, Sorting

August 27, 2015 by hgpu

gScan: Accelerating Graham Scan on the GPU

Gang Mei

View

Download (PDF)

Tags: Algorithms, Computational Geometry, Computer science, CUDA, Filtering, nVidia, nVidia GeForce GT 640, nVidia GeForce GTX 660 M, Sorting

August 27, 2015 by hgpu

Adaptive Multi-GPU Exchange Monte Carlo for the 3D Random Field Ising Model

C. A. Navarro, Huang Wei, Youjin Deng

View

Download (PDF)

Tags: Algorithms, Computational Physics, CUDA, Ising model, Monte Carlo simulation, nVidia, Physics, Spin Systems, Tesla K40

August 27, 2015 by hgpu

Accelerated Deep Learning using Intel Xeon Phi

Andre Viebke

View

Download (PDF)

Tags: Computer science, Computer vision, Deep learning, Intel Xeon Phi, Machine learning, Neural networks, OpenMP, Thesis

August 27, 2015 by hgpu

MemcachedGPU: Scaling-up Scale-out Key-value Stores

Tayler H. Hetherington, Mike O'Connor, Tor M. Aamodt

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Databases, Energy-efficient computing, nVidia, nVidia GeForce GTX 750 Ti, Package, Tesla K20, Tesla K40

August 27, 2015 by hgpu

Performance Evaluations of Document-Oriented Databases using GPU and Cache Structure

Shin Morishima, Hiroki Matsutani

View

Download (PDF)

Tags: Computer science, CUDA, Databases, nVidia, nVidia GeForce GTX 980, Performance

August 24, 2015 by hgpu

Viability of Feature Detection on Sony Xperia Z3 using OpenCL

Max Danielsson, Thomas Sievert

View

Download (PDF)

Source codes

Tags: Android, Computer science, Computer vision, Embedded high-performance computing, nVidia, nVidia GeForce GTX 660, OpenCL, Package, Thesis

August 24, 2015 by hgpu

Scheduling for new computing platforms with GPUs

Florence Monna

View

Download (PDF)

Tags: Computer science, Data Structures and Algorithms, nVidia, OpenCL, Task scheduling, Tesla C2050, Thesis

August 24, 2015 by hgpu

Source-to-Source Automatic Program Transformations for GPU-like Hardware Accelerators

Mehdi Amini

View

Download (PDF)

Tags: ATI, ATI Radeon HD 6970, Code generation, Computer science, CUDA, nVidia, nVidia GeForce 8800 GTX, nVidia GeForce GTX 670, OpenCL, Tesla C1060, Tesla C2070, Thesis

August 24, 2015 by hgpu

Semi-Global Filtering of Airborne LiDAR Data for Fast Extraction of Digital Terrain Models

Xiangyun Hu, Lizhi Ye, Shiyan Pang, Jie Shan

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Filtering, nVidia, nVidia GeForce GTX 690, Sensing

August 24, 2015 by hgpu

A Parallelizing Matlab Compiler Framework and Run time for Heterogeneous Systems

Sam Skalicky, Sonia Lopez, Marcin Lukowiak, Andrew G. Schmidt

View

Download (PDF)

Tags: Code generation, Computer science, FPGA, Heterogeneous systems, Matlab

August 21, 2015 by hgpu

Implementing Computer Vision Functions with OpenCL on the Qualcomm Adreno 420

Staff of Berkeley Design Technology

View

Download (PDF)

Tags: Algorithms, ARM, Computer science, Computer vision, OpenCL

August 21, 2015 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

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

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

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

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

* * *

high performance computing on graphics processing units: hgpu.org

Applications

CudaChain: A Practical GPU-accelerated 2D Convex Hull Algorithm

gScan: Accelerating Graham Scan on the GPU

Adaptive Multi-GPU Exchange Monte Carlo for the 3D Random Field Ising Model

Accelerated Deep Learning using Intel Xeon Phi

MemcachedGPU: Scaling-up Scale-out Key-value Stores

Performance Evaluations of Document-Oriented Databases using GPU and Cache Structure

Viability of Feature Detection on Sony Xperia Z3 using OpenCL

Scheduling for new computing platforms with GPUs

Source-to-Source Automatic Program Transformations for GPU-like Hardware Accelerators

Semi-Global Filtering of Airborne LiDAR Data for Fast Extraction of Digital Terrain Models

A Parallelizing Matlab Compiler Framework and Run time for Heterogeneous Systems

Implementing Computer Vision Functions with OpenCL on the Qualcomm Adreno 420

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

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

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

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

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)