Skip to content

@ParCoreLab ParCoreLab

Change the repository type filter

All

    Repositories list

    29 repositories

    • parcorelab.github.io

      Public
      TypeScript
      •0•0•0•1•Updated Sep 11, 2025Sep 11, 2025

    • Uniconn

      Public
      Uniconn is a unified, portable high-level C++ communication library that supports both point-to-point and collective operations across GPU clusters. Uniconn enables seamless switching between backends and APIs (host or device) with minimal or no changes to application code.
      Cuda
      •
      MIT License
      •0•0•0•0•Updated Aug 31, 2025Aug 31, 2025

    • aCG

      Public
      GPU-accelerated linear solvers based on the conjugate gradient (CG) method, supporting NVIDIA and AMD GPUs with GPU-aware MPI, NCCL, RCCL or NVSHMEM
      hpcgpucudahipconjugate-gradientrcclmulti-gpulinear-solversncclexascale-computing
      C
      •
      MIT License
      •0•1•0•0•Updated Aug 25, 2025Aug 25, 2025

    • ParCoreTools

      Public
      C++
      •1•2•0•0•Updated Mar 27, 2025Mar 27, 2025

    • snoopie-ucx-tracking-ucx

      Public
      Modified ucx library to track communications
      C
      •
      Other
      •483•0•0•0•Updated Mar 10, 2025Mar 10, 2025

    • multi-GPU-comm-bench

      Public
      Cuda
      •1•4•1•0•Updated Jun 13, 2024Jun 13, 2024

    • Snoopie

      Public
      Multi-GPU communication profiler and visualizer
      C
      •
      Other
      •3•32•3•0•Updated Jun 10, 2024Jun 10, 2024

    • gpu-fusion

      Public
      GPU fusion code and algorithm
      gpucudakernel-fusion
      Cuda
      •
      MIT License
      •0•1•0•0•Updated May 24, 2024May 24, 2024

    • barnes

      Public
      C
      •0•0•0•0•Updated May 15, 2024May 15, 2024

    • snoopie-visualiser

      Public
      0•0•2•0•Updated May 10, 2024May 10, 2024

    • CPU-Free-model

      Public
      Source code for the CPU-Free model - a fully autonomous execution model for multi-GPU applications that completely excludes the involvement of the CPU beyond the initial kernel launch.
      stencilhigh-performancecudaconjugate-gradientjacobimulti-gpujacobi-iterationiterative-solversnvshmempersistent-kernels
      Cuda
      •
      MIT License
      •3•20•0•0•Updated Apr 25, 2024Apr 25, 2024

    • PES-artifact

      Public
      C
      •0•2•0•0•Updated Apr 25, 2024Apr 25, 2024

    • BeyondMoore

      Public
      BeyondMoore has an ambitious goal to develop a software framework that performs static and dynamic optimizations, issues accelerator-initiated data transfers, and reasons about parallel execution strategies that exploit both processor and memory heterogeneity.
      high-performance-computingheterogeneous-parallel-programmingheterogeneous-computingmoores-lawerc20-horizon
      0•2•0•0•Updated Apr 25, 2024Apr 25, 2024

    • .github

      Public
      Homepage README.
      readme
      0•0•0•0•Updated Apr 4, 2024Apr 4, 2024

    • gpucommanalyzer

      Public
      C
      •
      Other
      •0•0•0•0•Updated Mar 22, 2024Mar 22, 2024

    • CPU-Free-Model-Compiler

      Public
      DaCe - Data Centric Parallel Programming
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •141•0•0•0•Updated Feb 2, 2024Feb 2, 2024

    • splash2

      Public
      Splash 2 Benchmarks
      C
      •12•0•0•0•Updated Nov 28, 2023Nov 28, 2023

    • ComScribe

      Public
      ComScribe is a tool to identify communication among all GPU-GPU and CPU-GPU pairs in a single-node multi-GPU system.
      C++
      •
      BSD 3-Clause "New" or "Revised" License
      •4•25•1•2•Updated Jul 6, 2023Jul 6, 2023

    • cha-aware-result-parser

      Public
      C++
      •0•0•0•0•Updated Jun 13, 2023Jun 13, 2023

    • hpctoolkit

      Public
      HPCToolkit performance tools: measurement and analysis components
      C++
      •60•0•0•1•Updated Mar 17, 2023Mar 17, 2023

    • accuracy-verification-microbenchmarks

      Public
      The microbenchmarks that are used to verify the accuracy of ComDetective.
      Makefile
      •2•0•0•0•Updated Mar 17, 2023Mar 17, 2023

    • mixed-and-multi-spmv

      Public
      Mixed and Multi-Precision SpMV for GPUs with Row-wise Precision Selection.
      cudasparsegpu-accelerationspmv
      Cuda
      •
      MIT License
      •1•5•1•0•Updated Mar 12, 2023Mar 12, 2023

    • ReuseTracker

      Public
      A fast and accurate reuse distance analyzer for multi-threaded applications. It leverages existing hardware features in commodity CPUs.
      Shell
      •3•20•1•0•Updated Feb 3, 2023Feb 3, 2023

    • hpctoolkit-externals

      Public
      HPCToolkit performance tools: essential third party libraries for hpctoolkit
      Shell
      •
      Other
      •6•0•0•0•Updated Oct 9, 2022Oct 9, 2022

    • AMD_IBS_Toolkit

      Public
      AMD Research Instruction Based Sampling Toolkit
      C
      •17•0•0•0•Updated Aug 6, 2022Aug 6, 2022

    • pardnn

      Public
      C++
      •1•1•0•0•Updated May 20, 2022May 20, 2022

    • pes-benchs

      Public
      C
      •1•0•0•0•Updated Apr 16, 2022Apr 16, 2022

    • Split_SpTRSV

      Public
      The split execution framework can automatically determine the suitability of an SpTRSV for split-execution, find the appropriate split point, and execute SpTRSV in a split fashion using two SpTRSV algorithms while automatically managing any required inter-platform communication. The model is implemented as a C++/CUDA library supporting multiple …
      C++
      •
      Other
      •0•4•0•0•Updated Sep 7, 2021Sep 7, 2021

    • SpTRSV_Framework

      Public
      The SpTRSV prediction framework is an automated prediction framework for the fastest sparse triangular solve (SpTRSV) algorithm for a given input sparse matrix on a CPU-GPU platform.
      C++
      •
      Other
      •2•6•0•0•Updated Aug 17, 2020Aug 17, 2020