October 13, 2017
Taylor and team recently designed the Tiered Accelerator Fabric architecture, and with collaborators taped out a 511-core RISC-V implementation in TSMC 16 nm, including 5 Linux-capable RISC-V cores, 496-core RISC-V manycore, and a binarized neural network.
Taylor was lead architect of the 16-core MIT Raw tiled multicore processor, one of the earliest multicore processors, which was commercialized into the Tilera TILE64 architecture. Recently, in 2017, Intel Skylake SP has adopted our scalable mesh of cores architecture that we proposed.
Taylor co-authored the earliest published research on dark silicon, including a paper that derives the utilization wall that causes dark silicon, and a prototype massively specialized processor called GreenDroid. I also wrote a paper that establishes the definitive taxonomy, the Four Horsemen, for the semiconductor industry’s approaches to dealing with the problem, and a follow-on paper on the Landscape of the Dark…
Taylor wrote the first academic paper on Bitcoin mining chips and is the world’s foremost academic expert.
Our vision is to create a path that allows researchers to prototype their ideas without worrying about all of the intricacies of I/O, packaging, PC board design and FPGA coding. Moreover, we provide a polymorphic library for SystemVerilog called BaseJump STL.
We make the case that datacenters full of ASICs are in our near future, and show a prototypical ASIC Cloud architecture, how they should be designed, and how they save TCO. We proposed neural network ASIC Clouds before Google announced their TPU, and also proposed the use of video transcoding clouds for YouTube.
September 20, 2017
The goal of this project is to reveal underlying mechanisms of brain plasticity that lead to functional recovery from stroke, which can provide us with vital insight to develop stimulation-based therapies not only for stroke but also for a broad range of neurological disorders.
The focus of this project is to develop a large-scale interface that provides stable access for optical stimulation and concurrent monitoring of neural activity by incorporating novel technological advances and multi-modal stimulation and recording.
Non-human primate (NHP) models are critical for preclinical, translational stroke studies to address potential discrepancies between rodent and human studies. Due to the scarcity of stroke studies in NHPs, few experimental models have been developed. The goal of this project is to develop and test practical model of ischemic stroke in these animals.
Post-stroke cognitive impairment in various domains from attention deficits to memory problems are very common in stroke victims. The goal of this project is to investigate cortical and hippocampal oscillations following cortical stroke in rats to understand the underlying neural mechanisms.