|go to week of May 1, 2011||1||2||3||4||5||6||7|
|go to week of May 8, 2011||8||9||10||11||12||13||14|
|go to week of May 15, 2011||15||16||17||18||19||20||21|
|go to week of May 22, 2011||22||23||24||25||26||27||28|
|go to week of May 29, 2011||29||30||31||1||2||3||4|
Title: High Performance Compute with Low Power Multi-Core DSP
Speaker: Dr. Murtaza Ali
Distinguished Member of Technical Staff
Date: Monday, May 7, 2012
Time: 2:30-3:30 p.m.
Location: 141 Coordinated Science Lab
Abstract: Digital Signal Processors (DSPs) are commonly employed in embedded systems. The increase of processing needs in cellular base-stations, radio controllers and industrial/medical imaging systems, has led to the development of multi-core DSPs as well as inclusion of floating point operations while maintaining low power dissipation. The eight-core DSP from Texas Instruments, codenamed TMS320C6678, provides a peak performance of 128 single precision GFLOPS or 48 double precision GFLOPS for a power dissipation of 10 watts. The potential for DSPs in High Performance Compute (HPC) is clear. It can provide the best power efficiency of all available platforms. The question is how it fares for HPC applications. In this talk, we take two typical applications common in HPC- dense linear algebra and seismic imaging and describe how they can be implemented on multi-core DSPs. We will go over the steps to efficiently map these applications to multi-core DSPs and discuss the advantages and challenges of using DSP based platform for compute acceleration of HPC applications.
Biography: Murtaza Ali is a Distinguished Member of Technical Staff (DMTS) at Texas Instruments (TI). He leads the High Performance Signal Processing Applications R&D activity in the Systems and Applications R&D Center. His activities are focused on novel applications of TI’s embedded multi-core Digital Signal Processors. Murtaza is currently involved in researching advanced computational techniques for implementation in TI solutions as well as for defining TI’s roadmap in this space. His activities include linear algebra, seismic imaging, and medical imaging.
Dr. Ali received his Bachelor’s degree in Electrical and Electronics Engineering from Bangladesh University of Engineering and Technology in 1989. He obtained his Master’s and Ph.D. from University of Minnesota all in Electrical Engineering in 1992 and 1995 respectively. In the past, he led R&D teams for mobile WiMAX, ADSL and voice-band modem technologies in TI and has represented TI in various national and international standards organizations including TIA, ITU, HomePlug, HPNA, and IEEE. Dr. Ali holds 15 U.S. patents and has published over 30 papers in refereed and invited forums. He is a senior member of the IEEE.