<span class="var-sub_title">Domain-Specific System on Chips (DSSoC)</span> SC18 Proceedings

The International Conference for High Performance Computing, Networking, Storage, and Analysis

The 3rd International Workshop on Post-Moore Era Supercomputing (PMES)


Domain-Specific System on Chips (DSSoC)

Authors: Tom Rondeau (Defense Advanced Research Projects Agency (DARPA), Domain-Specific System on Chip (DSSoC) Program)

Abstract: The invention of the digital computer came about as a proof of computable numbers, and so numerical processing was solved by the Turing Machine that has led to the general purpose computer. These computers are good at solving multiple types of problems with a single machine. However, within the scope of computable numbers are specific computational problems where purpose-built machines can solve them faster while using less energy. An example of this is the digital signal processor (DSP) that performs the multiply and accumulate operation important to signal processing, or the more recent development of the tensor processing unit (TPU) to compute dense matrix multiplies that are at the core of deep neural networks. These specialized machines solve a single problem but with optimized efficiency.

As a result, there exists a tension between the flexibility in general purpose processors and the efficiency of specialized processors. Domain-Specific System on Chip (DSSoC) intends to demonstrate that the tradeoff between flexibility and efficiency is not fundamental. The program will develop a method for determining the right amount and type of specialization while making a system as programmable and flexible as possible. It will take a vertical view of integrating today’s programming environment with a goal of full-stack integration. DSSoC will de-couple the programmer from the underlying hardware with enough abstraction but still be able to utilize the hardware optimally through intelligent scheduling. DSSoC specifically targets embedded systems where the domain of applications sits at the edge and near the sensor. Workloads consist of small chunks of data but often with a large number of algorithms required in the processing, meaning that high compute power and low latency at low power are required.

This presentation will explore the concepts being developed in the DSSoC program, including an overview of the projects being funded to study the research questions and produce technology that furthers industry’s ability to effectively use specialization within our SoCs.





Back to The 3rd International Workshop on Post-Moore Era Supercomputing (PMES) Archive Listing

Back to Full Workshop Archive Listing