CUDA-MEME on Tesla GPUs

CUDA-MEME is a motif discovery software based on MEME (version 3.5.4). It accelerates MEME by taking advantage of the massively parallel CUDA architecture of NVIDIA Tesla GPUs. It supports the OOPS and ZOOPS models in MEME.

Download and Installation

Download CUDA-MEME

Installation instructions and user guide are also in the software download

Benchmark Data

CUDA-MEME running on one Tesla C1060 GPU is up to 23x faster than MEME running on a x86 CPU. This cuts compute time from hours on CPUs to minutes using GPUs. The data in the chart below are for the OOPS (one occurrence per sequence) model for 4 datasets.

Technical Papers

"CUDA-MEME: Accelerating Motif Discovery in Biological Sequences Using CUDA-enabled Graphics Processing Units, Y. Liu, B. Schmidt, W. Liu, D. Maskell: Pattern Recognition Letters, October 2009
"GPU-MEME: Using Graphics Hardware to Accelerate Motif Finding in DNA Sequences, C. Chen et al, Lecture Notes in Computer Science, Volume 5265, 2008
More publications on accelerating bio-informatics applications using GPUs

Discussion Forums

GPU computing communities on GPUcomputing.net

GPU SOLUTIONS

The Tesla Bio Workbench applications can be deployed on GPU-based desktop personal supercomputers or in data center solutions. Built on the revolutionary massively parallel CUDA architecture, these solutions are designed to accelerate the pace of computational science.

RECOMMENDED HARDWARE CONFIGURATION

Desktop Workstation Configuration	Data Center Configuration
GPUs 1 Tesla C1060 Computing GPU (CUDA-MEME supports single GPU so far) CPU and Main Memory 2.33 GHz x86 CPU >8 GB (4 GB main memory per Tesla C1060 GPU)	Not applicable (CUDA-MEME is not yet MPI enabled)

WORKSTATION SOLUTIONS
TESLA PERSONAL SUPERCOMPUTER
For personal supercomputing at your desk

Learn more >

Where to buy >

DATA CENTER SOLUTIONS
TESLA GPU COMPUTING CLUSTERS
For computing with large-scale installations

Learn more >

Where to buy >