Skip to content

About

Bronze medal / top 6 of 47, OpenAtom Open Source Contest 2024: GPU-accelerated ILU(0)-preconditioned BiCGStab for large asymmetric indefinite banded linear systems (C++/CUDA)

Topics

Resources

Stars

4 stars

Watchers

1 watching

Forks

Repository files navigation

GPU-Accelerated ILU(0)-Preconditioned BiCGStab Solver

English | 中文

Rank Contest Language

6th-place (bronze medal) solution of the 2024 OpenAtom Open Source Contest — Solving Large-Scale Asymmetric Indefinite Banded Systems of Linear Equations.

Method

An ILU(0)-preconditioned stabilized bi-conjugate gradient method (BiCGStab), where the incomplete LU factorization is computed via dependency analysis.

The entire framework is implemented from scratch in C/C++ with CUDA kernels at every algorithmic bottleneck — no vendor library hot path is reused:

  • Dependency-analysis-driven ILU(0) factorization for the preconditioner
  • Custom triangular solves for large sparse L/U systems
  • 10–20× beyond common baseline implementations on key kernels
  • The L-shaped sparse triangular solve reaches ~50× cuSPARSE (NVIDIA CUDA Toolkit) within this contest's scenario

Benchmark

GPU: NVIDIA V100 32 GB · CPU: 8-core Xeon · RAM: 64 GB

benchmark

Build & run

mkdir build && cd build
cmake ../
make
./megasolve <data_dir> <matrix_file> <rhs_file> <init_guess_file> \
            <num_grids> <num_nonzeros> <output_file> [max_iterations]

About

Bronze medal / top 6 of 47, OpenAtom Open Source Contest 2024: GPU-accelerated ILU(0)-preconditioned BiCGStab for large asymmetric indefinite banded linear systems (C++/CUDA)

Topics

Resources

Stars

4 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages