2021 · 21 citations · 10 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureMicroelectronicsSystem-on-chip DesignAccelerator ArchitectureField-programmable Gate Array ArchitectureHardware AccelerationHeterogeneous System ArchitectureInstruction Set ArchitectureProcessor MicroarchitectureAccelerator MicroarchitectureAcceleratorsEnergy-efficient ArchitectureNeuromorphic HardwarePower-efficient Accelerator DesignRisc ArchitecturesRisc-v Core DesignSystolic Arrays
This work presents a 16mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> heterogeneous RISC-V system-on-a-chip (SoC) composed of a high-performance out-of-order core, energy-efficient in-order core, data-parallel vector accelerator, and systolic array deep neural network (DNN) accelerator in low-power Intel 22FFL for general-purpose compute, DNN, and vector workloads. The heterogeneous RISC-V SoC is composed of fully open-source components, including a second-generation Berkeley Out-of-Order Machine (BOOM) with a non-speculative mode attached to a Hwacha vector accelerator, a Rocket in-order core attached to a Gemmini systolic array DNN accelerator, as well as a IMiB L2 cache and off-chip I/Os. Combined, the variety of heterogeneous compute allows for wide programmability while providing up to a 286x MOPS/W improvement or 282x MOPS improvement over the RISC-V in-order core.
10
Florian Zaruba, Luca Benini · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · 2019 · 402 citations · Full text
Adam Izraelevitz, Jack Koenig, Patrick Li et al. · 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) · 2017 · 141 citations