skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

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


Title: Learning to Design Accurate Deep Learning Accelerators with Inaccurate Multipliers
Approximate computing is a promising way to improve the power efficiency of deep learning. While recent work proposes new arithmetic circuits (adders and multipliers) that consume substantially less power at the cost of computation errors, these approximate circuits decrease the end-to-end accuracy of common models. We present AutoApprox, a framework to automatically generate approximate low-power deep learning accelerators without any accuracy loss. AutoApprox generates a wide range of approximate ASIC accelerators with a TPUv3 systolic-array template. AutoApprox uses a learned router to assign each DNN layer to an approximate systolic array from a bank of arrays with varying approximation levels. By tailoring this routing for a specific neural network architecture, we discover circuit designs without the accuracy penalty from prior methods. Moreover, AutoApprox optimizes for the end-to-end performance, power and area of the the whole chip and PE mapping rather than simply measuring the performance of the arithmetic units in iso-lation. To our knowledge, our work is the first to demonstrate the effectiveness of custom-tailored approximate circuits in delivering significant chip-level energy savings with zero accuracy loss on a large-scale dataset such as ImageNet. AutoApprox synthesizes a novel approximate accelerator based on the TPU that reduces end-to-end power consumption by 3.2% and area by 5.2% at a sub-10nm process with no degradation in ImageNet validation top-1 and top-5 accuracy.  more » « less
Award ID(s):
1730628
PAR ID:
10399618
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Page Range / eLocation ID:
184 to 189
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, 2020 IEEE 38th International Conference on Computer Design (ICCD))
    null (Ed.)
    With the growing performance and wide application of deep neural networks (DNNs), recent years have seen enormous efforts on DNN accelerator hardware design for platforms from mobile devices to data centers. The systolic array has been a popular architectural choice for many proposed DNN accelerators with hundreds to thousands of processing elements (PEs) for parallel computing. Systolic array-based DNN accelerators for datacenter applications have high power consumption and nonuniform workload distribution, which makes power delivery network (PDN) design challenging. Server-class multicore processors have benefited from distributed on-chip voltage regulation and heterogeneous voltage regulation (HVR) for improving energy efficiency while guaranteeing power delivery integrity. This paper presents the first work on HVR-based PDN architecture and control for systolic array-based DNN accelerators. We propose to employ a PDN architecture comprising heterogeneous on-chip and off-chip voltage regulators and multiple power domains. By analyzing patterns of typical DNN workloads via a modeling framework, we propose a DNN workload-aware dynamic PDN control policy to maximize system energy efficiency while ensuring power integrity. We demonstrate significant energy efficiency improvements brought by the proposed PDN architecture, dynamic control, and power gating, which lead to a more than five-fold reduction of leakage energy and PDN energy overhead for systolic array DNN accelerators. 
    more » « less
  2. ; ; ; (, IEEE Annual International Symposium on Field-Programmable Custom Computing Machines)
    null (Ed.)
    Large Convolutional Neural Networks (CNNs) are often pruned and compressed to reduce the amount of parameters and memory requirement. However, the resulting irregularity in the sparse data makes it difficult for FPGA accelerators that contains systolic arrays of Multiply-and-Accumulate (MAC) units, such as Intel’s FPGA-based Deep Learning Accelerator (DLA), to achieve their maximum potential. Moreover, FPGAs with low-bandwidth off-chip memory could not satisfy the memory bandwidth requirement for sparse matrix computation. In this paper, we present 1) a sparse matrix packing technique that condenses sparse inputs and filters before feeding them into the systolic array of MAC units in the Intel DLA, and 2) a customization of the Intel DLA which allows the FPGA to efficiently utilize a high bandwidth memory (HBM2) integrated in the same package. For end-to-end inference with randomly pruned ResNet-50/MobileNet CNN models, our experiments demonstrate 2.7x/3x performance improvement compared to an FPGA with DDR4, 2.2x/2.1x speedup against a server-class Intel SkyLake CPU, and comparable performance with 1.7x/2x power efficiency gain as compared to an NVidia V100 GPU. 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al (, Design, Automation & Test in Europe Conference & Exhibition (DATE))
    As the number of weight parameters in deep neural networks (DNNs) continues growing, the demand for ultra-efficient DNN accelerators has motivated research on non-traditional architectures with emerging technologies. Resistive Random-Access Memory (ReRAM) crossbar has been utilized to perform insitu matrix-vector multiplication of DNNs. DNN weight pruning techniques have also been applied to ReRAM-based mixed-signal DNN accelerators, focusing on reducing weight storage and accelerating computation. However, the existing works capture very few peripheral circuits features such as Analog to Digital converters (ADCs) during the neural network design. Unfortunately, ADCs have become the main part of power consumption and area cost of current mixed-signal accelerators, and the large overhead of these peripheral circuits is not solved efficiently. To address this problem, we propose a novel weight pruning framework for ReRAM-based mixed-signal DNN accelerators, named TINYADC, which effectively reduces the required bits for ADC resolution and hence the overall area and power consumption of the accelerator without introducing any computational inaccuracy. Compared to state-of-the-art pruning work on the ImageNet dataset, TINYADC achieves 3.5× and 2.9× power and area reduction, respectively. TINYADC framework optimizes the throughput of state-of-the-art architecture design by 29% and 40% in terms of the throughput per unit of millimeter square and watt (GOPs/s×mm 2 and GOPs/w), respectively. 
    more » « less
  4. ; ; (, Proceedings International Symposium on Low Power Electronics and Design)
    In this paper we present an approximate division scheme for Scaled Population (SP) arithmetic, a technique that improves on the limitations of stochastic computing (SC). SP arithmetic circuits are designed (a) to perform all operations with a constant delay, and (b) they use scaling operations to help reduce errors compared to SC circuits. As part of this work, we also present a method to correlate two SP numbers with a constant delay. We compare our SP divider with SC dividers, as well as fixed-point dividers (in terms of area, power and delay). Our 512-bit SP divider has a delay (power) that is 0.08× (0.06×) that of the equivalent fixed-point binary divider. Compared to a equivalent SC divider, our power-delay-product is 13× better. Index Terms—Approximate Arithmetic, Stochastic Computing, Computer Arithmetic, Approximate Division, Fast Division 
    more » « less
  5. (, Proceedings International Symposium on Low Power Electronics and Design)
    IEEE (Ed.)
    In this paper we present an approximate division scheme for Scaled Population (SP) arithmetic, a technique that improves on the limitations of stochastic computing (SC). SP arithmetic circuits are designed (a) to perform all operations with a constant delay, and (b) they use scaling operations to help reduce errors compared to SC circuits. As part of this work, we also present a method to correlate two SP numbers with a constant delay. We compare our SP divider with SC dividers, as well as fixed-point dividers (in terms of area, power and delay). Our 512-bit SP divider has a delay (power) that is 0.08× (0.06×) that of the equivalent fixed-point binary divider. Compared to a equivalent SC divider, our power-delay-product is 13× better. Index Terms—Approximate Arithmetic, Stochastic Computing, Computer Arithmetic, Approximate Division, Fast Division 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email