BitBench: a benchmark for bitstream computing
BitBench: a benchmark for bitstream computing
复制标题
DOI：
10.1145/3316482.3326355
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Kyle Daruwalla;Heng Zhuo;C. Schulz;Mikko H. Lipasti
中科院分区：
文献类型：
--
作者：
Kyle Daruwalla;Heng Zhuo;C. Schulz;Mikko H. Lipasti
随着最近超低功耗应用的增加，研究人员正在研究可以处理流输入数据的替代架构。这些目标用例需要复杂的算法，必须在实时截止日期下进行评估，但也要满足严格的可用功率预算。随机计算（SC）是另一种范式的一个例子，其中数据表示为单个比特流，允许设计人员使用简单的与门来实现乘法等操作。因此，最终的设计是低面积和低功耗。同样，传统的数字滤波器可以利用流输入来有效地选择系数，从而实现低成本。在这项工作中，我们构建了六个关键算法来表征比特流计算。我们将这些算法作为一个新的基准套件：BitBench。
With the recent increase in ultra-low power applications, researchers are investigating alternative architectures that can operate on streaming input data. These target use cases require complex algorithms that must be evaluated under a real-time deadline, but also satisfy the strict available power budget. Stochastic computing (SC) is an example of an alternative paradigm where the data is represented as single bitstreams, allowing designers to implement operations such as multiplication using a simple AND gate. Consequently, the resulting design is both low area and low power. Similarly, traditional digital filters can take advantage of streaming inputs to effectively choose coefficients, resulting in a low cost implementation. In this work, we construct six key algorithms to characterize bitstream computing. We present these algorithms as a new benchmark suite: BitBench.