@inproceedings{3e280c37ef2445008d21dfff669af3da,
title = "A scalable, numerically stable, high-performance tridiagonal solver using GPUs",
abstract = "In this paper, we present a scalable, numerically stable, high-performance tridiagonal solver. The solver is based on the SPIKE algorithm for partitioning a large matrix into small independent matrices, which can be solved in parallel. For each small matrix, our solver applies a general 1-by-1 or 2-by-2 diagonal pivoting algorithm, which is also known to be numerically stable. Our paper makes two major contributions. First, our solver is the first numerically stable tridiagonal solver for GPUs. Our solver provides comparable quality of stable solutions to Intel MKL and Matlab, at speed comparable to the GPU tridiagonal solvers in existing packages like CUSPARSE. It is also scalable to multiple GPUs and CPUs. Second, we present and analyze two key optimization strategies for our solver: a high-throughput data layout transformation for memory efficiency, and a dynamic tiling approach for reducing the memory access footprint caused by branch divergence.",
keywords = "GPGPU, GPU Computing, SPIKE, Tridiagonal Solver",
author = "Chang, {Li Wen} and Stratton, {John A.} and Kim, {Hee Seok} and Hwu, {Wen-Mei W}",
year = "2012",
month = dec,
day = "1",
doi = "10.1109/SC.2012.12",
language = "English (US)",
isbn = "9781467308069",
series = "International Conference for High Performance Computing, Networking, Storage and Analysis, SC",
booktitle = "2012 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012",
note = "2012 24th International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012 ; Conference date: 10-11-2012 Through 16-11-2012",
}