Ray Simar
Texas Instruments

The Changing Impact of Semiconductor Technology on Processor Architecture

We stand on the brink of a fundamental discontinuity in silicon process-technology unlike anything most of us have seen. For almost two decades, a period of time spanning the entire education and careers of many engineers, we have been beneficiaries of a silicon process-technology which would let us build almost anything we could imagine. Now, all of that is about to change.

For the past five years, capacitive loading of interconnect has grown to be a significant factor in logic speed, and has limited the scaling of integrated-circuit performance. To compound the problem, recently interconnect resistance has also started to limit circuit speed. These factors can render obsolete current signs and current thinking as interconnect-dominated designs and architectures will become increasingly irrelevant.

Given these fundamental interconnect challenges, we must turn to architecture, logic design and programming solutions. The background on these dramatic changes in semiconductor technology will be discussed in the hopes that the solutions for the future may very well come from the attendees of HPCC 2007!

About Ray Simar
Ray Simar is a TI Fellow. He is the chief architect of the TMS320C6000, among the first DSPs to use an advanced very-long-instruction-word (VLIW) architecture, to achieve very high performance at low cost. Before the 'C6000, he was the chief architect and program manager for the TMS320C3x family (the first CMOS floating-point DSPs) and the TMS320C4x family (the first multiprocessor DSPs). Before that, Ray was an application engineer for the TMS320 product line and authored the first two TMS320 DSP application notes.

Ray received his Bachelor of Science degree at Texas A&M University and Master of Science degree in electrical engineering from Rice University. He holds more than 10 patents in DSP technology.

Ray is currently focused on developed DSP architectures which deal effectively with the complexity of advanced IC processes.