high performance computing on graphics processing units: hgpu.org

hgpu.org » StarPU

Visual Performance Analysis of Memory Behavior in a Task-Based Runtime on Hybrid Platforms

Lucas Leandro Nesi, Samuel Thibault, Luka Stanisic, Lucas Mello Schnorr

View

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 1080 Ti, Performance, StarPU

September 1, 2019 by hgpu

On Runtime Systems for Task-based Programming on Heterogeneous Platforms

Samuel Thibault

View

Tags: Computer science, CUDA, Distributed computing, Heterogeneous systems, nVidia, nVidia Quadro FX 5800, OpenCL, Operating systems, StarPU, Task scheduling, Tesla C2050, Tesla K20, Tesla M2075, Thesis

December 23, 2018 by hgpu

Asynchronous Task-Based Polar Decomposition on Single Node Manycore Architectures

Dalal Sukkari, Hatem Ltaief, Mathieu Faverge, David Keyes

View

Tags: Algorithms, Benchmarking, Computer science, Factorization, Intel Xeon Phi, nVidia, StarPU, Task scheduling, Tesla K80, Tesla P100

September 21, 2017 by hgpu

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

LC Framework

Characterizing the Performance of Parallel Data-Compression Algorithms across Compilers and GPUs

pplx-garden: Perplexity open source garden for inference technology

RDMA Point-to-Point Communication for LLM Systems

Atlas CLI: Machine Learning (ML) Lifecycle & Transparency Manager

Scalable GPU-Based Integrity Verification for Large Machine Learning Models

transformers_tvm: Implementation of Encoder Decoder transformer on TVM

Enhancing Transformer Performance and Portability through Auto-tuning Frameworks

OpScanner

A Study of Floating-Point Precision Tuning in Deep Learning Operators Implementations

INT v.s. FP: A framework to compare low-bit integer and float-point formats

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

AutoDock-GPU: AutoDock for GPUs and other accelerators

Architecting Tensor Core-Based Reductions for Irregular Molecular Docking Kernels

NCCLX: collective communication framework

Collective Communication for 100k+ GPUs

Tutoring LLM into a Better CUDA Optimizer

Tutoring LLM into a Better CUDA Optimizer

See all packages

* * *

* * *

HGPU group © 2010-2025 hgpu.org

All rights belong to the respective authors

Login | Sitemap | Feedback | Policy

Contact us: