high performance computing on graphics processing units: hgpu.org

Anderson Faustino da Silva, Bruno Conde Kind, Jose Wesley de Souza Magalhaes, Jeronimo Nunes Rocha, Breno Campos Ferreira Guimaraes, Fernando Magno Quintao Pereira

View

Download (PDF)

Source codes

Tags: Algorithms, Benchmarking, Code generation, Compiler, Computer science, LLVM, Package

December 20, 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

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

LLVM-based automation of memory decoupling for OpenCL applications on FPGAs

Arnab A Purkayastha, Samuel Rogers, Suhas A Shiddhibhabi, Hamed Tabkhi

View

Download (PDF)

Source codes

Tags: Computer science, FPGA, LLVM, OpenCL, Package

January 5, 2020 by hgpu

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

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

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

* * *

high performance computing on graphics processing units: hgpu.org

Efficient Execution of OpenMP on GPUs

Supporting CUDA for an extended RISC-V GPU architecture

neoSYCL: a SYCL implementation for SX-Aurora TSUBASA

Effective GPU Sharing Under Compiler Guidance

Experience Report: Writing A Portable GPU Runtime with OpenMP 5.1

Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs

triSYCL for Xilinx FPGA

Interactive Parallelization of C Programs in SAPFOR

ANGHABENCH: a Suite with One Million Compilable C Benchmarks for Code-Size Reduction

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

Automated Partitioning of Data-Parallel Kernels using Polyhedral Compilation

LLVM-based automation of memory decoupling for OpenCL applications on FPGAs

Recent source codes

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)