high performance computing on graphics processing units: hgpu.org

Nadav Rotem, Jordan Fix, Saleem Abdulrasool, Summer Deng, Roman Dzhabarov, James Hegeman, Roman Levenstein, Bert Maher, Satish Nadathur, Jakob Olesen, Jongsoo Park, Artem Rakhov, Misha Smelyanskiy

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, CUDA, Deep learning, Heterogeneous systems, Linear Algebra, Machine learning, Neural networks, nVidia, Package

May 20, 2018 by hgpu

Tiramisu: A Code Optimization Framework for High Performance Systems

Riyadh Baghdadi, Jessica Ray, Malek Ben Romdhane, Emanuele Del Sozzo, Patricia Suriana, Shoaib Kamil, Saman Amarasinghe

View

Download (PDF)

Tags: Algorithms, Code generation, Computer science, CUDA, Distributed computing, FPGA, Heterogeneous systems, Linear Algebra, LLVM, MPI, nVidia, OpenMPI, Tesla K40

May 5, 2018 by hgpu

Implementing Push-Pull Efficiently in GraphBLAS

Carl Yang, Aydin Buluc, John D. Owens

View

Download (PDF)

Tags: Algorithm optimization, Algorithms, BLAS, Computer science, CUDA, Graph theory, Linear Algebra, nVidia, Sparse matrix, Tesla K40

April 15, 2018 by hgpu

Optimization of Hierarchical Matrix Computation on GPU

Satoshi Ohshima, Ichitaro Yamazaki, Akihiro Ida, Rio Yokota

View

Download (PDF)

Tags: Computer science, CUDA, Intel Xeon Phi, Linear Algebra, nVidia, OpenMP, Tesla P100

March 25, 2018 by hgpu

Multithreaded Dense Linear Algebra on Asymmetric Multi-core Processors

Sandra Catalan Pallares

View

Download (PDF)

Tags: ARM, Benchmarking, Computer science, Factorization, Linear Algebra, Thesis

March 10, 2018 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

On the Representation of Partially Specified Implementations and its Application to the Optimization of Linear Algebra Kernels on GPU

Hierarchical Matrix Operations on GPUs: Matrix-Vector Multiplication and Compression

Exploring FPGA-specific Optimizations for Irregular OpenCL Applications

Dense and sparse parallel linear algebra algorithms on graphics processing units

Performance Evaluation and Tuning of An OpenCL based Matrix Multiplier

Implementing general matrix-matrix multiplication algorithm on the Intel Xeon Phi Knights Landing Processor

clMF: A fine-grained and portable alternating least squares algorithm for parallel matrix factorization

Glow: Graph Lowering Compiler Techniques for Neural Networks

Tiramisu: A Code Optimization Framework for High Performance Systems

Implementing Push-Pull Efficiently in GraphBLAS

Optimization of Hierarchical Matrix Computation on GPU

Multithreaded Dense Linear Algebra on Asymmetric Multi-core Processors

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)