Georgios Michelogiannakis (AMCR) Digital computation in cryo-cooled environments using RSFQ with novel methods
by
B59 3101
Biography:
George Michelogiannakis is a staff scientist for the computer architecture group (CAG) in the AMCR division. He has extensive work on networking (both off- and on-chip) and computer architecture. His latest work focuses on post Moore's law era looking into superconducting digital logic with novel compute models, compute and memory architectures, specialization, emerging devices (transistors), photonics, and 3D integration. He is also currently characterizing the use of key resources in modern HPC systems to reveal opportunities for resource disaggregation and is designing photonically resource-disaggregated racks.
Abstract:
Superconducting digital computing uses Josephon junctions (JJs) as the fundamental switching device to compute in the cryogenic environment of approximately 4 K or a few hundred mK. This technology promises large increases in performance per unit power for key scientific applications but also quantum control and sensing in cryogenic environments. One particularly promising direction is moving digital computation from room temperature to cryogenic sensors in order to reduce cabling and data transfers but also increase computation efficiency. In this talk, we will present an overview of digital computing using RSFQ followed by a synopsis of our recent work that proposes a novel computational model to better fit the realities of RSFQ, along with examples of key compute accelerators we designed such as FFT, FIR filters, and others including on-chip networks. We will then end with thoughts on how this technology and our past work can apply to cryogenic instrumentation and sensing.
Zoom link:
https://lbnl.zoom.us/j/92076879461?pwd=ZW91TUVtZFZXSEhhelFFTFNHb3o2dz09
Video recording:
https://youtu.be/OBmJV29ACus