high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

Scheduling Languages: A Past, Present, and Future Taxonomy

Mary Hall, Cosmin Oancea, Anne C. Elster, Ari Rasch, Sameeran Joshi, Amir Mohammad Tavakkoli, Richard Schulze

View

Download (PDF)

Tags: Auto-Tuning, Compilers, Computer science, Performance, Programming Languages, Task scheduling

November 3, 2024 by hgpu

Data-Driven Dynamic Autotuning: Optimizing Autotuning Overhead with Prior Tuning Data

Jaroslav Oľha

View

Download (PDF)

Tags: AMD Radeon RX Vega 56, ATI, Auto-Tuning, Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 1070, nVidia GeForce GTX 680, nVidia GeForce GTX 750, nVidia GeForce RTX 2080 Ti, OpenCL, Performance, Tesla K20, Thesis

November 3, 2024 by hgpu

Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs

Ferdi Kossmann, Bruce Fontaine, Daya Khudia, Michael Cafarella, Samuel Madden

View

Download (PDF)

Tags: Computer science, LLM, NLP, nVidia, nVidia A100, nVidia H100, Task scheduling

November 3, 2024 by hgpu

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Xiaoman Liu

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Machine learning, nVidia, nVidia GeForce RTX 4090, Package, Performance, TensorFlow

November 3, 2024 by hgpu

Jailbreaking LLM-Controlled Robots

Alexander Robey, Zachary Ravichandran, Vijay Kumar, Hamed Hassani, George J. Pappas

View

Download (PDF)

Tags: Artificial intelligence, Computer science, LLM, Robotics, Security

October 27, 2024 by hgpu

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

Matteo Croci, Garth N. Wells

View

Download (PDF)

Source codes

Tags: AVX, Computer science, Finite element method, Floating point error, Intel, Matrix multiplication, Mixed precision, Package

October 27, 2024 by hgpu

Fastrack: Fast IO for Secure ML using GPU TEEs

Yongqin Wang, Rachit Rajat, Jonghyun Lee, Tingting Tang, Murali Annavaram

View

Download (PDF)

Tags: Cloud, Computer science, CUDA, Machine learning, nVidia, nVidia H100, Security

October 27, 2024 by hgpu

General-Purpose Computing on Tensor Processors

Kuan-Chieh Hsu

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Computer science, CUDA, Heterogeneous systems, Machine learning, nVidia, nVidia GeForce RTX 2080, nVidia GeForce RTX 3090, nVidia Jetson Nano, Package, Sparse matrix, Thesis, TPU

October 27, 2024 by hgpu

Using modern C++ to improve CUDA programs

Mythreya Kuricheti

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia Quadro RTX 5000, Performance, PTX, Thesis

October 27, 2024 by hgpu

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

Xiongxiao Xu, Solomon Abera Bekele, Brice Videau, Kai Shu

View

Download (PDF)

Source codes

Tags: Computer science, Energy-efficient computing, HPC, Intel, Intel Data Center GPU Max 1550, Package

October 20, 2024 by hgpu

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

Reza Abbasi, Sernam Lim

View

Download (PDF)

Source codes

Tags: AI, Artificial intelligence, Computer science, CUDA, LLM, Machine learning, Memory, nVidia, nVidia GeForce RTX 3090, nVidia Quadro RTX 8000, Package

October 20, 2024 by hgpu

Accelerating Drug Discovery in AutoDock-GPU with Tensor Cores

Gabin Schieffer, Ivy Peng

View

Download (PDF)

Tags: Chemistry, Computer science, CUDA, Macromolecule, molecular docking, nVidia, nVidia A100, nVidia V100, Physics, Tesla T4

October 20, 2024 by hgpu

Reproducible Study and Performance Analysis of GPU Programming Paradigms: OpenACC vs. CUDA in Key Linear Algebra Computations

SW#SYCL

Analyzing the Performance Portability of SYCL across CPUs, GPUs, and Hybrid Systems with Protein Database Search

tdg-benchs: benchmarks used to test the performance of taskgraph

Leveraging the potential of task-based programming with OpenMP task graphs

LLOR: Automatic Repair of OpenMP Programs

LLOR: Automated Repair of OpenMP Programs

Solomon: Simple Off-LOading Macros Orchestrating multiple Notations

Unified schemes for directive-based GPU offloading

CLUEstering: a high-performance density-based clustering library for scientific computing

PyOMP: OpenMP for Python in Numba

PyOMP: Parallel programming for CPUs and GPUs with OpenMP and Python

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

Scheduling Languages: A Past, Present, and Future Taxonomy

Data-Driven Dynamic Autotuning: Optimizing Autotuning Overhead with Prior Tuning Data

Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Jailbreaking LLM-Controlled Robots

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

General-Purpose Computing on Tensor Processors

Using modern C++ to improve CUDA programs

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

Accelerating Drug Discovery in AutoDock-GPU with Tensor Cores

Recent source codes

Matrix multiplication using Tensor Cores in CUDA

CPP Joules: Energy Measurement tool for CPP/CUDA programs

HPC-Coder-v2

Reproducible Study and Performance Analysis of GPU Programming Paradigms: OpenACC vs. CUDA in Key Linear Algebra Computations

SW#SYCL

tdg-benchs: benchmarks used to test the performance of taskgraph

LLOR: Automatic Repair of OpenMP Programs

Solomon: Simple Off-LOading Macros Orchestrating multiple Notations

CLUEstering: a high-performance density-based clustering library for scientific computing

PyOMP: OpenMP for Python in Numba

Most viewed papers (last 30 days)