high performance computing on graphics processing units: hgpu.org

hgpu.org » Computer science

Understanding Data Movement in AMD Multi-GPU Systems with Infinity Fabric

Gabin Schieffer, Ruimin Shi, Stefano Markidis, Andreas Herten, Jennifer Faj, Ivy Peng

View

Download (PDF)

Tags: AMD, AMD Radeon Instinct MI250X, ATI, Computer science, HIP, Machine learning, Memory, Performance

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

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

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

RenderKernel: High-level programming for real-time rendering systems

Jinyuan Yang, Soumyabrata Dev, Abraham G. Campbell

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, nVidia GeForce RTX 2080 Ti, Rendering, Vulkan

September 22, 2024 by hgpu

A Study of Performance Programming of CPU, GPU accelerated Computers and SIMD Architecture

Xinyao Yi

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, HPC, nVidia, nVidia A100, OpenMP, Performance, Programming techniques

September 22, 2024 by hgpu

Optimal Workload Placement on Multi-Instance GPUs

Bekir Turkkan, Pavankumar Murali, Pavithra Harsha, Rohan Arora, Gerard Vanloo, Chandra Narayanaswami

View

Download (PDF)

Tags: Benchmarking, Computer science, nVidia, nVidia A100, nVidia H100, Performance

September 15, 2024 by hgpu

Enhancing Code Portability, Problem Scale, and Storage Efficiency in Exascale Applicationsin Exascale Applications

Nigel Tan

View

Download (PDF)

Tags: AMD Radeon Vega VII, ATI, Computer science, CUDA, Heterogeneous systems, HPC, nVidia, nVidia A100, nVidia DGX-A100, nVidia Quadro RTX 5000, OpenMP, OpenMPI, Particle-in-cell methods, performance portability, Tesla V100, Thesis

September 15, 2024 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Understanding Data Movement in AMD Multi-GPU Systems with Infinity Fabric

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

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

The Landscape of GPU-Centric Communication

Challenging Portability Paradigms: FPGA Acceleration Using SYCL and OpenCL

Collection skeletons: declarative abstractions for data collections

RenderKernel: High-level programming for real-time rendering systems

A Study of Performance Programming of CPU, GPU accelerated Computers and SIMD Architecture

Optimal Workload Placement on Multi-Instance GPUs

Enhancing Code Portability, Problem Scale, and Storage Efficiency in Exascale Applicationsin Exascale Applications

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Most viewed papers (last 30 days)