high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » Applications

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores

Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang

View

Tags: Computer science, CUDA, Data recovery, Extended precision, LLM, Matrix multiplication, nVidia, nVidia GeForce RTX 3090, Security

October 6, 2024 by hgpu

Event-Based OpenMP Tasks for Time-Sensitive GPU-Accelerated Systems

Cyril Cetre, Chenle Yu, Sara Royuela, Rémi Barrere, Eduardo Quiñones, Damien Gratadour

View

Download (PDF)

Tags: AMD Radeon Instinct MI100, ATI, Computer science, CUDA, HIP, HPC, nVidia, nVidia A100, Performance

October 6, 2024 by hgpu

Benchmarking Thread Block Cluster

Tim Lühnen, Tobias Marschner, Sohan Lal

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, nVidia, nVidia H100, PTX

October 6, 2024 by hgpu

Intel(R) SHMEM: GPU-initiated OpenSHMEM using SYCL

Alex Brooks, Philip Marshall, David Ozog, Md. Wasi-ur- Rahman, Lawrence Stewart, Rithwik Tom

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Computer science, Heterogeneous systems, Intel, Intel Data Center GPU Max 1550, oneAPI, Package, SYCL

October 6, 2024 by hgpu

miniLB: A Performance Portability Study of Lattice-Boltzmann Simulations

Luigi Crisci, Biagio Cosenza, Giorgio Amati, Matteo Turisini

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, ATI, cfd, Fluid dynamics, nVidia, Package, SYCL, Tesla V100

September 29, 2024 by hgpu

HPC acceleration of large (min, +) matrix products to compute domination-type parameters in graphs

E.M. Garzón, J.A. Martínez, J.J. Moreno, M.L. Puertas

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Graph theory, HPC, nVidia, OpenMP, Package, Tesla V100

September 29, 2024 by hgpu

Bitstream Database-Driven FPGA Programming Flow Based on Standard OpenCL

Topi Leppänen, Leevi Leppänen, Joonas Multanen, Pekka Jääskeläinen

View

Download (PDF)

Source codes

Tags: Computer science, Databases, FPGA, Heterogeneous systems, OpenCL, Package

September 29, 2024 by hgpu

Automatic Generation of OpenCL Code through Polyhedral Compilation with LLM

Marek Palkowski, Mateusz Gruzewski

View

Download (PDF)

Tags: AMD Radeon RX 6800, ATI, Code generation, Computer science, CUDA, LLM, nVidia, nVidia A100, OpenCL, OpenMP

September 29, 2024 by hgpu

OpenACC offloading of the MFC compressible multiphase flow solver on AMD and NVIDIA GPUs

Benjamin Wilfong, Anand Radhakrishnan, Henry A. Le Berre, Steve Abbott, Reuben D. Budiardja, Spencer H. Bryngelson

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI250X, ATI, cfd, Fluid dynamics, MPI, nVidia, OpenACC, Package, Tesla V100

September 29, 2024 by hgpu

The Landscape of GPU-Centric Communication

Didem Unat, Ilyas Turimbetov, Mohammed Kefah Taha Issa, Doğan Sağbili, Flavio Vella, Daniele De Sensi, Ismayil Ismayilov

View

Download (PDF)

Tags: Computer science, HPC, MPI, Performance, Review

September 22, 2024 by hgpu

Challenging Portability Paradigms: FPGA Acceleration Using SYCL and OpenCL

Manuel de Castro, Francisco J. andújar, Roberto R. Osorio, Rocío Carratalá-Sáez, Diego R. Llanos

View

Download (PDF)

Source codes

Tags: Computer science, FPGA, OpenCL, Optimization, performance portability, SYCL

September 22, 2024 by hgpu

Collection skeletons: declarative abstractions for data collections

Zhibo Li

View

Download (PDF)

Tags: Computer science, Data Structures and Algorithms, OpenCL, performance portability, SYCL, Thesis

September 22, 2024 by hgpu

bioagent-bench: Benchmark for evaluating LLM agents in bioinformatics

BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics

Benchmark suite for LLM inference on NVIDIA consumer GPUs

Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs

Theorizer: from the paper Generating Literature-Driven Scientific Discoveries at Scale

Generating Literature-Driven Scientific Theories at Scale

Nsight Python: a Python kernel profiling interface based on NVIDIA Nsight Tools

Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel Analysis (Tool)

Awesome LLM-Driven Kernel Generation

Towards Automated Kernel Generation in the Era of LLMs

PhysProver: Advancing Automatic Theorem Proving for Physics

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

SeedFold: Scaling Biomolecular Structure Prediction

Tilus: A Tile-Level GPU Kernel Programming Language

Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation

Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores

Event-Based OpenMP Tasks for Time-Sensitive GPU-Accelerated Systems

Benchmarking Thread Block Cluster

Intel(R) SHMEM: GPU-initiated OpenSHMEM using SYCL

miniLB: A Performance Portability Study of Lattice-Boltzmann Simulations

HPC acceleration of large (min, +) matrix products to compute domination-type parameters in graphs

Bitstream Database-Driven FPGA Programming Flow Based on Standard OpenCL

Automatic Generation of OpenCL Code through Polyhedral Compilation with LLM

OpenACC offloading of the MFC compressible multiphase flow solver on AMD and NVIDIA GPUs

The Landscape of GPU-Centric Communication

Challenging Portability Paradigms: FPGA Acceleration Using SYCL and OpenCL

Collection skeletons: declarative abstractions for data collections

Recent source codes

bioagent-bench: Benchmark for evaluating LLM agents in bioinformatics

Benchmark suite for LLM inference on NVIDIA consumer GPUs

Theorizer: from the paper Generating Literature-Driven Scientific Discoveries at Scale

Nsight Python: a Python kernel profiling interface based on NVIDIA Nsight Tools

Awesome LLM-Driven Kernel Generation

PhysProver: Advancing Automatic Theorem Proving for Physics

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

SeedFold: Scaling Biomolecular Structure Prediction

Tilus: A Tile-Level GPU Kernel Programming Language

Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

Most viewed papers (last 30 days)