The Next 700 Accelerator Design Languages

 Every field in computing stands to benefit from specialized hardware accelerators. The tools we have to design custom accelerators, however, are preventing acceleration from going mainstream. We need a new class of *accelerator design languages* (ADLs) to make implementing an accelerator less like wiring up a breadboard and more like software development. We also need a new category of compilers and a new foundation for representing the hardware they generate. This talk is partly a call to action: in the area of programming languages for hardware design, almost any research problem you can think of is still completely unsolved. It is also partly a research talk: I will describe our lab's open-source infrastructure for implementing ADLs and our work on new low-level foundation for hardware descriptions.

Bio:

Adrian Sampson is an associate professor in the computer science department at Cornell. He works on programming languages, computer architecture, and the abstractions that separate them. He is especially excited about languages and compilers that make it easy for anyone to construct and exploit specialized hardware accelerators. In a different era, he worked on approximate computing, the idea that we should design computers that compute worse answers.