SC12 Home > SC12 Schedule > SC12 Presentation - A Scalable, Numerically Stable, High-Performance Tridiagonal Solver Using GPUs

SCHEDULE: NOV 10-16, 2012

When viewing the Technical Program schedule, on the far righthand side is a column labeled "PLANNER." Use this planner to build your own schedule. Once you select an event and want to add it to your personal schedule, just click on the calendar icon of your choice (outlook calendar, ical calendar or google calendar) and that event will be stored there. As you select events in this manner, you will have your own schedule to guide you through the week.

A Scalable, Numerically Stable, High-Performance Tridiagonal Solver Using GPUs

SESSION: Maximizing Performance on Multi-Core and Many-Core Architectures

EVENT TYPE: Papers

TIME: 2:00PM - 2:30PM

SESSION CHAIR: Atsushi Hori

AUTHOR(S):Li-Wen Chang, John A. Stratton, Hee-Seok Kim, Wen-Mei W. Hwu

ROOM:255-BC

ABSTRACT:
In this paper, we present a scalable, numerically stable, high-performance tridiagonal solver. The solver is based on the SPIKE algorithm, a method 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 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 NVIDIA 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.

Chair/Author Details:

Atsushi Hori (Chair) - RIKEN

Li-Wen Chang - University of Illinois at Urbana-Champaign

John A. Stratton - University of Illinois at Urbana-Champaign

Hee-Seok Kim - University of Illinois at Urbana-Champaign

Wen-Mei W. Hwu - University of Illinois at Urbana-Champaign

Add to iCal  Click here to download .ics calendar file

Add to Outlook  Click here to download .vcs calendar file

Add to Google Calendarss  Click here to add event to your Google Calendar

A Scalable, Numerically Stable, High-Performance Tridiagonal Solver Using GPUs

SESSION: Maximizing Performance on Multi-Core and Many-Core Architectures

EVENT TYPE:

TIME: 2:00PM - 2:30PM

SESSION CHAIR: Atsushi Hori

AUTHOR(S):Li-Wen Chang, John A. Stratton, Hee-Seok Kim, Wen-Mei W. Hwu

ROOM:255-BC

ABSTRACT:
In this paper, we present a scalable, numerically stable, high-performance tridiagonal solver. The solver is based on the SPIKE algorithm, a method 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 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 NVIDIA 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.

Chair/Author Details:

Atsushi Hori (Chair) - RIKEN

Li-Wen Chang - University of Illinois at Urbana-Champaign

John A. Stratton - University of Illinois at Urbana-Champaign

Hee-Seok Kim - University of Illinois at Urbana-Champaign

Wen-Mei W. Hwu - University of Illinois at Urbana-Champaign

Add to iCal  Click here to download .ics calendar file

Add to Outlook  Click here to download .vcs calendar file

Add to Google Calendarss  Click here to add event to your Google Calendar