The IIS Chip Gallery
Vega (2020)
by
| Application | Pulp |
| Technology | 22 |
| Manufacturer | GF |
| Type | Industrial |
| Package | BGA169 |
| Dimensions | 4000μm x 3000μm |
| Gates | 100 MGE |
| Voltage | 0.5-0.8 V |
| Power | 49.4 mW @ 0.8 V, 450 MHz |
| Clock | 32kHz-450 MHz |
Vega is an always-on IoT end-node SoC capable of scaling from a 1.7uW fully retentive COGNITIVE sleep mode up to 32.2GOPS (@49.4mW) peak performance on NSAAs, including mobile DNN inference, exploiting 1.6MB of state- retentive SRAM, and 4MB of non-volatile MRAM. To meet the performance and flexibility requirements of NSAAs, the SoC features 10 RISC-V cores: one core for SoC and IO management and a 9-core cluster supporting multi-precision SIMD integer and floating- point computation. Two programmable machine-learning (ML) accelerators boost energy efficiency in sleep and active state, respectively.
Vega has been developed by Greenwaves Technologies, based on the open source PULP platform in collaboration with ETH Zurich and University of Bologna
.The name of the chip continues the tradition of naming chips from characters from the movie Pulp Fiction by Quentin Tarantino. It is inspired by Vincent Vega, as it is a project by a commercial company, lawyers advised against using the full name.