high performance computing on graphics processing units: hgpu.org

hgpu.org » Computer science

UVMBench: A Comprehensive Benchmark Suite for Researching Unified Virtual Memory in GPUs

Yongbin Gu, Wenxuan Wu, Yunfan Li, Lizhong Chen

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Memory, nVidia, nVidia GeForce GTX 1080 Ti, Package, Performance

July 26, 2020 by hgpu

Offload Annotations: Bringing Heterogeneous Computing to Existing Libraries and Workloads

Gina Yuan, Shoumik Palkar, Deepak Narayanan, Matei Zaharia

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, Package, Python, Tesla P100

July 19, 2020 by hgpu

Compyle: a Python package for parallel computing

Aditya Bhosale, Prabhu Ramachandran

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, HPC, nVidia, OpenCL, Package, Python, Tesla P100

July 19, 2020 by hgpu

Accelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs

Xueying Wang, Guangli Li, Xiao Dong, Jiansong Li, Lei Liu, Xiaobing Feng

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Neural networks, nVidia, nVidia GeForce GTX Titan XP, Tesla P4

July 19, 2020 by hgpu

A load balance multi-scheduling model for OpenCL kernel tasks in an integrated cluster

Usman Ahmed, Jerry Chun-Wei Lin, Gautam Srivastava, Muhammad Aleem

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, Machine learning, nVidia, nVidia GeForce GT 740 M, nVidia GeForce GTX 760, OpenCL

July 19, 2020 by hgpu

Deep Graph Library Optimizations for Intel(R) x86 Architecture

Sasikanth Avancha, Vasimuddin Md, Sanchit Misra, Ramanarayan Mohanty

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Machine learning, Neural networks, nVidia, Package

July 19, 2020 by hgpu

Investigating Input Representations and Representation Models of Source Code for Machine Learning

Alexander Brauckmann

View

Download (PDF)

Tags: AMD Radeon HD 7970, ATI, Code generation, Computer science, LLVM, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 1080 Ti, nVidia GeForce GTX 970, OpenCL, Thesis

July 12, 2020 by hgpu

Bayesian inference for artificial perception using OpenCL on FPGAs and GPUs

Rodrigo de Oliveira Lourenço Lopes

View

Download (PDF)

Tags: Bayesian, Computer science, FPGA, nVidia, nVidia GeForce GTX Titan, OpenCL, Thesis

July 12, 2020 by hgpu

Automated Partitioning of Data-Parallel Kernels using Polyhedral Compilation

Alexander Matz, Johannes Doerfert, Holger Fröning

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, LLVM, nVidia, Package, Tesla K80

July 12, 2020 by hgpu

GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks

Guyue Huang, Guohao Dai, Yu Wang, Huazhong Yang

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Linear Algebra, Matrix multiplication, Neural networks, nVidia, nVidia GeForce GTX 1080 Ti, nVidia GeForce RTX 2080, Package, Sparse matrix

July 12, 2020 by hgpu

SYCL-Bench: A Versatile Cross-Platform Benchmark Suite for Heterogeneous Computing

Sohan Lal, Aksel Alpay, Philip Salzmann, Biagio Cosenza, Alexander Hirsch, Nicolai Stawinoga, Peter Thoman, Thomas Fahringer, Vincent Heuveline

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, FPGA, Heterogeneous systems, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package, Performance, PTX, SYCL

July 5, 2020 by hgpu

Studies on CUDA Offloading for Real-Time Simulation and Visualization

Edgar Josafat Martinez-Noriega

View

Download (PDF)

Tags: Computer science, CUDA, Image processing, nVidia, nVidia GeForce GTX 1070, nVidia GeForce GTX 970 M, nVidia GeForce RTX 2080, nVidia Jetson K1, Rendering, Thesis, Virtualization, Visualization

July 5, 2020 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

UVMBench: A Comprehensive Benchmark Suite for Researching Unified Virtual Memory in GPUs

Offload Annotations: Bringing Heterogeneous Computing to Existing Libraries and Workloads

Compyle: a Python package for parallel computing

Accelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs

A load balance multi-scheduling model for OpenCL kernel tasks in an integrated cluster

Deep Graph Library Optimizations for Intel(R) x86 Architecture

Investigating Input Representations and Representation Models of Source Code for Machine Learning

Bayesian inference for artificial perception using OpenCL on FPGAs and GPUs

Automated Partitioning of Data-Parallel Kernels using Polyhedral Compilation

GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks

SYCL-Bench: A Versatile Cross-Platform Benchmark Suite for Heterogeneous Computing

Studies on CUDA Offloading for Real-Time Simulation and Visualization

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)