SHF: Small: Bitstream Processing

SHF：小型：比特流处理

• 批准号: 1813434
• 负责人: Mikko Lipasti
• 金额: $ 45万
• 依托单位: University of Wisconsin-Madison
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1813434&HistoricalAwards=false
• 关键词: SHF; Small; Bitstream; Processing

Embedded computing systems are becoming very common in today's world, ranging from wearable devices, to in-home smart speakers, to autonomous appliances and vehicles. Many of the computational tasks that these systems implement require very high performance hardware for tasks like audio voice recognition, visual object recognition, path optimization, and autonomous control. Historically, such high-performance hardware relied on binary fixed-point algorithms deployed on low-power microcontrollers or digital signal processors. However, the sensing and control interfaces themselves do not use binary number representations, but instead use bitstreams, which encode numeric input and output values using the density of ones over time. Conventional computing substrates requires conversion of both inputs and outputs to interface with physical systems that utilize bitstreams. This project is developing novel, biologically-inspired approaches for directly operating on data represented in the native bitstream format. Compute hardware that directly operates on these bitstreams can be seamlessly integrated into systems that sense the real world, process sensory data, and issue control commands based on the processed data as well as learned actions based on rewards from the environment. The capability of these new approaches will be demonstrated through two experimental platforms: a very low power speech recognition system that operates on bitstream audio data, and an autonomous airborne vehicle that learns to navigate its environment. This research has broad industry- and economy-wide impact since it will lead to the discovery and realization of novel, powerful, and energy-efficient approaches for implementing power- and energy-constrained embedded computing systems.This research advocates development of novel, biologically-inspired approaches for processing data represented as bitstreams. Bitstreams, which encode numeric values using density of ones (unary) or ones and zeroes (binary) are a natural representation for data sensed from the environment (input) as well as robotic control (output), and can be inexpensively generated using low-cost, yet accurate, sigma-delta modulators. The initial phase of this research project focuses on developing the theoretical and algorithmic underpinnings for visual, auditory, and inertial sensory processing, including feature extraction, bandpass filtering, perspective and coordinate transforms, linear optimization, and memory formation, which are grounded in principles from the speech processing, computer vision, spiking neural networks, reinforcement learning, and signal processing domains. The novel sensory processing capabilities are then deployed in two experimental platforms: first, an ultra-low power acoustic model for speech recognition that can demonstrate the suitability of bitstream processing for feature extraction and sequence learning via long short-term memory. Next, bitstream sensory processing technology is coupled directly to a control system that enables an unmanned aerial vehicle to navigate in a controlled indoor environment while learning, with increasing efficiency, to identify and target sources of rewards. Both demonstration platforms rely on concepts from biological spiking neural networks, stochastic computing for arithmetic operations, as well as oversampled sigma-delta modulation theory for data representation and signal processing tasks, and provide unprecedented levels of efficiency in terms of energy consumption, compute density, and autonomous operation.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

嵌入式计算系统在当今世界变得非常普遍，范围从可穿戴设备到家用智能扬声器，再到自主电器和车辆。这些系统实现的许多计算任务需要非常高性能的硬件来完成音频语音识别、视觉对象识别、路径优化和自主控制等任务。 从历史上看，这种高性能硬件依赖于部署在低功耗微控制器或数字信号处理器上的二进制定点算法。然而，感测和控制接口本身不使用二进制数表示，而是使用比特流，比特流使用1随时间的密度对数字输入和输出值进行编码。传统的计算基板需要输入和输出两者的转换以与利用比特流的物理系统接口。 该项目正在开发新颖的，生物启发的方法，用于直接操作以本地比特流格式表示的数据。直接在这些比特流上操作的计算硬件可以无缝地集成到系统中，该系统感测真实的世界、处理感测数据、并基于经处理的数据以及基于来自环境的奖励的学习动作来发出控制命令。这些新方法的能力将通过两个实验平台来证明：一个是基于比特流音频数据的非常低功耗的语音识别系统，另一个是学习导航环境的自主飞行器。这项研究具有广泛的行业和经济范围的影响，因为它将导致发现和实现新颖的，强大的，节能的方法来实现功率和能源受限的嵌入式计算systems.This研究提倡开发新颖的，生物启发的方法来处理数据表示为bitstream。使用1（一元）或1和0（二进制）的密度对数值进行编码的比特流是从环境（输入）以及机器人控制（输出）感测到的数据的自然表示，并且可以使用低成本但准确的Σ-Δ调制器廉价地生成。该研究项目的初始阶段侧重于开发视觉，听觉和惯性感觉处理的理论和算法基础，包括特征提取，带通滤波，透视和坐标变换，线性优化和记忆形成，这些都是基于语音处理，计算机视觉，尖峰神经网络，强化学习和信号处理领域的原则。新的感官处理能力，然后部署在两个实验平台：第一，超低功耗的语音识别声学模型，可以证明比特流处理的特征提取和序列学习通过长短期记忆的适用性。接下来，比特流感觉处理技术直接耦合到控制系统，该控制系统使得无人驾驶飞行器能够在受控室内环境中导航，同时以增加的效率学习识别和瞄准奖励源。这两个演示平台都依赖于生物尖峰神经网络的概念，算术运算的随机计算，以及用于数据表示和信号处理任务的过采样Σ-Δ调制理论，并在能耗，计算密度，该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的评估被认为值得支持。影响审查标准。

项目成果

BitSAD: A Domain-Specific Language for Bitstream Computing

BitSAD：用于比特流计算的领域特定语言

• 发表时间: 2019
• 期刊: Proceedings of the First ISCA Workshop on Unary Computing (WUC'19
• 作者: Kyle Daruwalla, Heng Zhuo

Modeling Architectural Support for Tightly-Coupled Accelerators

紧耦合加速器的建模架构支持

• DOI: 10.1109/ispass48437.2020.00045
• 发表时间: 2020
• 期刊: ISPASS Proceedings
• 作者: Schlais, David J.;Zhuo, Heng;Lipasti, Mikko H.
• 通讯作者: Lipasti, Mikko H.

Value Locality Based Approximation With ODIN

使用 ODIN 进行基于值局部性的近似

• DOI: 10.1109/lca.2020.3002542
• 发表时间: 2020
• 期刊: IEEE Computer Architecture Letters
• 影响因子: 2.3
• 作者: Singh, Rahul;Ravi, Gokul Subramanian;Lipasti, Mikko;Miguel, Joshua San
• 通讯作者: Miguel, Joshua San

BlurNet: Defense by Filtering the Feature Maps

• DOI: 10.1109/dsn-w50199.2020.00016
• 发表时间: 2019-08
• 期刊: 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)
• 作者: Ravi Raju;Mikko H. Lipasti

BitBench: a benchmark for bitstream computing

• DOI: 10.1145/3316482.3326355
• 发表时间: 2019-06
• 期刊: Proceedings of the 20th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems
• 作者: Kyle Daruwalla;Heng Zhuo;C. Schulz;Mikko H. Lipasti