The success of Deep Artificial Neural Networks (DNNs) in many domains created a rich body of research concerned with hardwareaccelerators for compute-intensive DNN operators. However, implementing such operators efficiently with complex hardwareintrinsics such as matrix multiply is a task not yet automated gracefully. Solving this task often requires joint program and data layouttransformations. First solutions to this problem have been proposed, such as TVM, UNIT or ISAMIR, which work on a loop-levelrepresentation of operators and specify data layout and possible program transformations before the embedding into the operator isperformed. This top-down approach creates a tension between exploration range and search space complexity, especially when alsoexploring data layout transformations such as im2col, channel packing or padding.In this work, we propose a new approach to this problem. We created a bottom-up method that allows the joint transformation ofboth compuation and data layout based on the found embedding. By formulating the embedding as a constraint satisfaction problemover the scalar dataflow, every possible embedding solution is contained in the search space. Adding additional constraints andoptmization targets to the solver generates the subset of preferable solutions.An evaluation using the VTA hardware accelerator with the Baidu DeepBench inference benchmark shows that our approach canautomatically generate code competitive to reference implementations. Further, we show that dynamically determining the data layoutbased on intrinsic and workload is beneficial for hardware utilization and performance. In cases where the reference implementationhas low hardware utilization due to its fixed deployment strategy, we achieve a geomean speedup of up to x2.813, while individualoperators can improve as much as x170.

翻译：深人工神经网络(DNNS)在许多领域的成功创造了大量与计算密集的 DNN 操作员的硬件加速器有关的大量研究。 但是, 以像矩阵倍增这样的复杂硬件加速器高效率地执行这些操作员的任务还不是光滑的。 解决这项任务通常需要联合程序和数据布局转换。 已经提出了解决这个问题的最初解决方案, 例如 TVM、 UNIT 或 ISAMIR, 它在操作员嵌入操作器之前, 工作于一个循环水平的操作员, 并指定数据布局和可能的程序转换。 这种自上而下的方法在勘探范围和搜索空间复杂性之间造成了一种紧张, 特别是当还探索数据布局转换如 im2col、 频道包装或挂接。 在这项工作中, 我们提出了一个新的方法, 使得基于所发现的嵌入的对调和数据布局的两种方法的联合转换。 将基于一个基于一个循环的运行的运行方的运行方的运行方, 将一个基于正值的对调数据流的满意度嵌成一个限制, 将每个可能的对向上方的运行的精确数据流的连接的配置解决方案 。 在搜索空间中, 将一个快速配置中, 将一个运行中, 将一个快速的运行的运行的运行的运行中, 将它将一个显示的硬化为一个额外的配置的硬化为一个测试显示的硬度的硬度的硬度 显示的硬度的硬度 显示到显示的硬度 。