skip to main content

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: ASIC Accelerator in 28 nm for the Post-Quantum Digital Signature Scheme XMSS
This paper presents the first 28 nm ASIC implementation of an accelerator for the post-quantum digital signature scheme XMSS. In particular, this paper presents an architecture for a novel, pipelined XMSS Leaf accelerator for accelerating the most compute-intensive step in the XMSS algorithm. This paper then presents the ASIC designs for both an existing non-pipelined accelerator architecture and the novel, pipelined XMSS Leaf accelerator. In addition, the performance of the28 nm ASIC is compared to the same designs on 28 nm Artix-7FPGAs. The novel pipelined XMSS Leaf accelerator is 25% faster compared to the non-pipelined version in the ASIC, and both accelerator architectures have a 10×lower power consumption than on the FPGAs. The evaluation shows that the pipelining increases the frequency by 1.7×on the FPGA but only 1.2×on the ASIC, due to the critical path in the ASIC being in the memory. The non-pipelined XMSS Leaf accelerator is shown to have a significantly better area-delay and energy-delay metric on the ASIC, while the pipelined accelerator wins out in these metrics on the FPGA. Consequently, this work shows the different architectural decisions that need to be made between FPGA and ASIC designs, when selecting how to best implement a post-quantum cryptographic accelerator in hardware.  more » « less
Award ID(s):
1716541
PAR ID:
10204679
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
International Conference on Computer Design (ICCD)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems)
    In this paper, we propose an energy-efficient reconfigurable platform for in-memory processing based on novel 4-terminal spin Hall effect-driven domain wall motion devices that could be employed as both non-volatile memory cell and in-memory logic unit. The proposed designs lead to unity of memory and logic. The device to system level simulation results show that, with 28% area increase in memory structure, the proposed in-memory processing platform achieves a write energy ~15.6 fJ/bit with 79% reduction compared to that of SOT-MRAM counterpart while keeping the identical 1ns writing speed. In addition, the proposed in-memory logic scheme improves the operating energy by 61.3%, as compared with the recent non-volatile in-memory logic designs. An extensive reliability analysis is also performed over the proposed circuits. We employ Advanced Encryption Standard (AES) algorithm as a case study to elucidate the efficiency of the proposed platform at application level. Simulation results exhibit that the proposed platform can show up to 75.7% and 30.4% lower energy consumption compared to CMOS-ASIC and recent pipelined domain wall (DW) AES implementations, respectively. In addition, the AES Energy-Delay Product (EDP) can show 15.1% and 6.1% improvements compared to the DW-AES and CMOS-ASIC implementations, respectively. 
    more » « less
  2. ; ; ; ; ( , Springer, Part of the Lecture Notes in Computer Science book series (LNCS,volume 13986))
    In this paper, we explore the prospect of accelerating tree-based genetic programming (TGP) by way of modern field-programmable gate array (FPGA) devices, which is motivated by the fact that FPGAs can sometimes leverage larger amounts of data/function parallelism, as well as better energy efficiency, when compared to general-purpose CPU/GPU systems. In our preliminary study, we introduce a fixed-depth, tree-based architecture capable of evaluating type-consistent primitives that can be fully unrolled and pipelined. The current primitive constraints preclude arbitrary control structures, but they allow for entire programs to be evaluated every clock cycle. Using a variety of floating-point primitives and random programs, we compare to the recent TensorGP tool executing on a modern 8 nm GPU, and we show that our accelerator implemented on a 14 nm FPGA achieves an average speedup of 43×. When compared to the popular baseline tool DEAP executing across all cores of a 2-socket, 28-core (56-thread), 14 nm CPU server, our accelerator achieves an average speedup of 4,902×. Finally, when compared to the recent state-of-the-art tool Operon executing on the same 2-processor CPU system, our accelerator executes about 2.4× slower on average. Despite not achieving an average speedup over every tool tested, our single-FPGA accelerator is the fastest in several instances, and we describe five future extensions that could allow for a 32–144× speedup over our current design as well as allow for larger program depths/sizes. Overall, we estimate that a future version of our accelerator will constitute a state-of-the-art GP system for many applications. 
    more » « less
  3. ; ; ; ( , 2022 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS))
    Ring-Binary-Learning-with-Errors (RBLWE)-based post-quantum cryptography (PQC) is a promising scheme suitable for lightweight applications. This paper presents an efficient hardware systolic accelerator for RBLWE-based PQC, targeting high-performance applications. We have briefly given the algorithmic background for the proposed design. Then, we have transferred the proposed algorithmic operation into a new systolic accelerator. Lastly, field-programmable gate array (FPGA) implementation results have confirmed the efficiency of the proposed accelerator. 
    more » « less
  4. ; ; ( , 2022 IEEE International Symposium on Hardware Oriented Security and Trust (HOST))
    Following the rapid progress in the post-quantum cryptography (PQC) field that many efforts have been gradually switched to the hardware implementation side, this paper presents a novel systolic accelerator for polynomial multiplication within two lattice-based PQC algorithms, key encapsulation mechanism (KEM) Saber and binary Ring-Learning-with-Errors (BRLWE)-based encryption scheme. Based on the observation that polynomial multiplication over ring is the key arithmetic operation for the two PQC schemes, we have proposed a novel systolic accelerator for the targeted polynomial multiplications (applicable to two PQC schemes). Mathematical formulation is given to illustrate the proposed algorithmic operation for both schemes. Then, the proposed systolic accelerator is presented. Finally, field-programmable gate array (FPGA) implementation results have been provided to confirm the efficiency of the proposed systolic accelerator under two schemes. The proposed accelerator is highly efficient, and the following work may focus on cryptoprocessor design and side-channel attacks. 
    more » « less
  5. ; ; ; ; ( , ACM Transactions on Reconfigurable Technology and Systems)
    With reduced data reuse and parallelism, recent convolutional neural networks (CNNs) create new challenges for FPGA acceleration. Systolic arrays (SAs) are efficient, scalable architectures for convolutional layers, but without proper optimizations, their efficiency drops dramatically for reasons: 1) the different dimensions within same-type layers, 2) the different convolution layers especially transposed and dilated convolutions, and 3) CNN’s complex dataflow graph. Furthermore, significant overheads arise when integrating FPGAs into machine learning frameworks. Therefore, we present a flexible, composable architecture called FlexCNN, which delivers high computation efficiency by employing dynamic tiling, layer fusion, and data layout optimizations. Additionally, we implement a novel versatile SA to process normal, transposed, and dilated convolutions efficiently. FlexCNN also uses a fully-pipelined software-hardware integration that alleviates the software overheads. Moreover, with an automated compilation flow, FlexCNN takes a CNN in the ONNX representation, performs a design space exploration, and generates an FPGA accelerator. The framework is tested using three complex CNNs: OpenPose, U-Net, and E-Net. The architecture optimizations achieve 2.3 × performance improvement. Compared to a standard SA, the versatile SA achieves close-to-ideal speedups, with up to 15.98 × and 13.42 × for transposed and dilated convolutions, with a 6% average area overhead. The pipelined integration leads to a 5 × speedup for OpenPose. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email