Xilinx Adaptive Compute Acceleration Platform: VersalTM Architecture

In this paper we describe Xilinx's Versal-Adaptive Compute Acceleration Platform (ACAP). ACAP is a hybrid compute platform that tightly integrates traditional FPGA programmable fabric, software programmable processors and software programmable accelerator engines. ACAP improves over the programmability of traditional reconfigurable platforms by introducing newer compute models in the form of software programmable accelerators and by separating out the data movement architecture from the compute architecture. The Versal architecture includes a host of new capabilities, including a chip-pervasive programmable Network-on-Chip (NoC), Imux Registers, compute shell, more advanced SSIT, adaptive deskew of global clocks, faster configuration, and other new programmable elements as well as enhancements to the CLB and interconnect. We discuss these architectural developments and highlight their key motivations and differences in relation to traditional FPGA architectures.

[1]  Jonathan Rose,et al.  Using bus-based connections to improve field-programmable gate-array density for implementing datapath circuits , 2005, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[2]  Ilya Ganusov,et al.  Time-borrowing platform in the Xilinx UltraScale+ family of FPGAs and MPSoCs , 2016, 2016 26th International Conference on Field Programmable Logic and Applications (FPL).

[3]  David A. Patterson,et al.  A new golden age for computer architecture , 2019, Commun. ACM.

[4]  Lee-Chung Lu.  Physical Design Challenges and Innovations to Meet Power, Speed, and Area Scaling Trend , 2017, ISPD.

[5]  Idit Keidar,et al.  NoC-Based FPGA: Architecture and Routing , 2007, First International Symposium on Networks-on-Chip (NOCS'07).

[6]  Dirk Grunwald,et al.  Exploring FPGA network on chip implementations across various application and network loads , 2008, 2008 International Conference on Field Programmable Logic and Applications.

[7]  John McGrath,et al.  An All-Programmable 16-nm RFSoC for Digital-RF Communications , 2018, IEEE Micro.

[8]  Hari Angepat,et al.  A cloud-scale acceleration architecture , 2016, 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[9]  Vaughn Betz,et al.  Design tradeoffs for hard and soft FPGA-based Networks-on-Chip , 2012, 2012 International Conference on Field-Programmable Technology.

[10]  Douglas L. Maskell,et al.  Throughput oriented FPGA overlays using DSP blocks , 2016, 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[11]  Jonathan Rose,et al.  Measuring the Gap Between FPGAs and ASICs , 2007, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[12]  Yang Li,et al.  Heterogeneous Computing Platform Based on CPU+FPGA and Working Modes , 2016, 2016 12th International Conference on Computational Intelligence and Security (CIS).

[13]  William J. Dally,et al.  Route packets, not wires: on-chip inteconnection networks , 2001, DAC '01.

[14]  Valavan Manohararajah,et al.  The Stratix™ 10 Highly Pipelined FPGA Architecture , 2016, FPGA.

[15]  Chirag Ravishankar,et al.  Placement Strategies for 2.5D FPGA Fabric Architectures , 2018, 2018 28th International Conference on Field Programmable Logic and Applications (FPL).

[16]  Chirag Ravishankar,et al.  SAT Based Place-And-Route for High-Speed Designs on 2.5D FPGAs , 2018, 2018 International Conference on Field-Programmable Technology (FPT).

[17]  Jonathan Rose,et al.  Measuring the Gap Between FPGAs and ASICs , 2006, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.