An official website of the United States government
Brain-inspired Hyper-dimensional(HD) computing is a novel and efficient computing paradigm. However, highly parallel architectures such as Processing-in-Memory(PIM) are bottle-necked by reduction operations required such as accumulation. To reduce this bottle-neck of HD computing in PIM, we present Stochastic-HD that combines the simplicity of operations in Stochastic Computing (SC) with the complex task solving capabilities of the latest HD computing algorithms. Stochastic-HD leverages deterministic SC, which enables all of HD operations to be done as highly parallel bitwise operations and removes all reduction operations, thus improving the throughput of PIM. To this end, we propose an in-memory hardware design for Stochastic-HD that exploits its high level of parallelism and robustness to approximation. Our hardware uses in-memory bitwise operations along with associative memory-like operations to enable a fast and energy-efficient implementation. With Stochastic-HD, we were able to reach a comparable accuracy with the Baseline-HD. Furthermore, by proposing an integrated Stochastic-HD retraining approach Stochastic-HD is able to reduce the accuracy loss to just 0.3%. We additionally accelerate the retraining process in our hardware design to create an end-to-end accelerator for Stochastic-HD. Finally, we also add support for HD Clustering to Stochastic-HD, which is the first to map the HD Clustering operations to the stochastic domain. As compared to the best PIM design for HD, Stochastic-HD is also 4.4% more accurate and 43.1× more energy-efficient.
more »
« less
COSMO: Computing with Stochastic Numbers in Memory
Stochastic computing (SC) reduces the complexity of computation by representing numbers with long streams of independent bits. However, increasing performance in SC comes with either an increase in area or a loss in accuracy. Processing in memory (PIM) computes data in-place while having high memory density and supporting bit-parallel operations with low energy consumption. In this article, we propose COSMO, an architecture for co mputing with s tochastic numbers in me mo ry, which enables SC in memory. The proposed architecture is general and can be used for a wide range of applications. It is a highly dense and parallel architecture that supports most SC encodings and operations in memory. It maximizes the performance and energy efficiency of SC by introducing several innovations: (i) in-memory parallel stochastic number generation, (ii) efficient implication-based logic in memory, (iii) novel memory bit line segmenting, (iv) a new memory-compatible SC addition operation, and (v) enabling flexible block allocation. To show the generality and efficiency of our stochastic architecture, we implement image processing, deep neural networks (DNNs), and hyperdimensional (HD) computing on the proposed hardware. Our evaluations show that running DNN inference on COSMO is 141× faster and 80× more energy efficient as compared to GPU.
more »
« less
- PAR ID:
- 10345532
- Date Published:
- Journal Name:
- ACM Journal on Emerging Technologies in Computing Systems
- Volume:
- 18
- Issue:
- 2
- ISSN:
- 1550-4832
- Page Range / eLocation ID:
- 1 to 25
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Sorting is a fundamental function in many applications from data processing to database systems. For high performance, sorting-hardware based sorting designs are implemented by conventional binary or emerging stochastic computing (SC) approaches. Binary designs are fast and energy-efficient but costly to implement. SC-based designs, on the other hand, are area and power-efficient but slow and energy-hungry. So, the previous studies of the hardware-based sorting further faced scalability issues. In this work, we propose a novel scalable low-cost design for implementing sorting networks. We borrow the concept of SC for the area- and power efficiency but use weighted stochastic bit-streams to address the high latency and energy consumption issue of SC designs. A new lock and swap (LAS) unit is proposed to sort weighted bit-streams. The LAS-based sorting network can determine the result of comparing different input values early and then map the inputs to the corresponding outputs based on shorter weighted bit-streams. Experimental results show that the proposed design approach achieves much better hardware scalability than prior work. Especially, as increasing the number of inputs, the proposed scheme can reduce the energy consumption by about 3.8% - 93% compared to prior binary and SC-based designs.more » « less
-
Recently, in-DRAM computing is becoming one promising technique to address the notorious ‘memory-wall’ issue for big data processing. In this work, for the first time, we propose a novel ‘Min/Max-in-memory’ algorithm based on iterative XNOR bit-wise comparison, which supports parallel inmemory searching for minimum and maximum of bulk data stored in DRAM as unsigned & signed integers, fixed-point and floating numbers. We then develop a new processing-in-DRAM architecture, called Max-PIM, that supports complete bit-wise Boolean logic and beyond. Differentiating from prior works, Max-PIM is optimized with one-cycle fast XNOR logicin-DRAM operation and in-memory data transpose, which are heavily used and keys to accelerate the proposed Min/Max-in-memory algorithm efficiently. Extensive experiments of utilizing Max-PIM in big data sorting and graph processing applications show that it could speed up ~ 50X and ~ 1000X than GPU and CPU, while only consuming 10% and 1% energy, respectively. Moreover, comparing with recent representative In-DRAM computing platforms, i.e., Ambit [1], DRISA [2], our design could speed up ~ 3X - 10X.more » « less
-
Stochastic computing (SC) division circuits have gained importance in recent years compared to other arithmetic circuits due to their low complexity as a result of an accuracy tradeoff. Designing a division circuit is already complex in conventional binary-based hardware systems. Developing an accurate and efficient SC division circuit is an open research problem. Prior work proposed different SC division circuits by using multiplexers and JK-flip-flop units, which may require correlated or uncorrelated input bit-streams. This study is primarily centered on exploring a cost-effective and highly efficient bit-stream generator specifically designed for SC division circuits. In conjunction with this objective, we assess the performance of multiple bit-stream generators and analyze the impact of correlation on SC division. We compare different designs in terms of accuracy and hardware cost. Moreover, we discuss a low-cost and energy-efficient bit-stream generator via powers-of-2 Van der Corput (VDC) sequences. Among the tested sequence generators, our best results were achieved with VDC sequences. Our evaluation results demonstrate that the novel VDC-based design yields promising outputs, resulting in a 15.5% reduction in the area-delay product and an 18.05% saving in energy consumption for the same accuracy level compared to conventional bit-stream generators. Significantly, our investigation reveals that employing the proposed generator improves the precision compared to the state-of-the-art. We validate the proposed architecture with an image processing case study, achieving high PSNR and structural similarity values.more » « less
-
Low-cost and hardware-efficient design of trigonometric functions is challenging. Stochastic computing (SC), an emerging computing model processing random bit-streams, offers promising solutions for this problem. The existing implementations, however, often overlook the importance of the data converters necessary to generate the needed bit-streams. While recent advancements in SC bit-stream generators focus on basic arithmetic operations such as multiplication and addition, energy-efficient SC design of non-linear functions demands attention to both the computation circuit and the bit-stream generator. This work introduces TriSC, a novel approach for SC-based design of trigonometric functions enjoying state-of-the-art (SOTA) quasi-random bit-streams. Unlike SOTA SC designs of trigonometric functions that heavily rely on delay elements to decorrelate bit-streams, our approach avoids delay elements while improving the accuracy of the results. TriSC yields significant energy savings of up to 92% compared to SOTA. As two novel use cases studied for the first time in SC literature, we employ the proposed design for 2D image transformation and forward kinematics of a robotic arm, two computation-intensive applications demanding low-cost trigonometric designs.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3484731
