The Internet-of-Things (IoT) requires endnodes with ultra-low-power always-on capability for a long battery lifetime, as well as high performance, energy efficiency, and extreme flexibility to deal with complex and fast-evolving near-sensor analytics algorithms (NSAAs). We present Vega, an IoT endnode system on chip (SoC) capable of scaling from a 1.7- μW fully retentive cognitive sleep mode up to 32.2-GOPS (at 49.4 mW) peak performance on NSAAs, including mobile deep neural network (DNN) inference, exploiting 1.6 MB of state-retentive SRAM, and 4 MB of non-volatile magnetoresistive random access memory (MRAM). To meet the performance and flexibility requirements of NSAAs, the SoC features ten RISC-V cores: one core for SoC and IO management and a nine-core cluster supporting multi-precision single instruction multiple data (SIMD) integer and floating-point (FP) computation. Vega achieves the state-of-the-art (SoA)-leading efficiency of 615 GOPS/W on 8-bit INT computation (boosted to 1.3 TOPS/W for 8-bit DNN inference with hardware acceleration). On FP computation, it achieves the SoA-leading efficiency of 79 and 129 GFLOPS/W on 32- and 16-bit FP, respectively. Two programmable machine learning (ML) accelerators boost energy efficiency in cognitive sleep and active states.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Vega: A Ten-Core SoC for IoT Endnodes with DNN Acceleration and Cognitive Wake-Up from MRAM-Based State-Retentive Sleep Mode


    Beteiligte:
    Rossi D. (Autor:in) / Conti F. (Autor:in) / Eggiman M. (Autor:in) / Mauro A. D. (Autor:in) / Tagliavini G. (Autor:in) / Mach S. (Autor:in) / Guermandi M. (Autor:in) / Pullini A. (Autor:in) / Loi I. (Autor:in) / Chen J. (Autor:in)

    Erscheinungsdatum :

    2022-01-01



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Vega 2300

    Hughes, C. N. / Reuss, L. E. | SAE Technical Papers | 1971


    Vega project: Re-entry vehicle of “VEGA” spacecraft

    Kovtunenko, V.M. / Sagdeev, R.Z. / Barsukov, V.L. | Elsevier | 1986


    Vega 35

    Martin, Jr., B.A. | Engineering Index Backfile | 1941


    Vega 35

    Martin, Jr., B.A. | Engineering Index Backfile | 1941


    Unitwin Vega

    Short, M. | Engineering Index Backfile | 1939