HLS Optimization: Local Memory Bandwidth

最新推荐文章于 2024-06-11 23:37:05 发布

转载最新推荐文章于 2024-06-11 23:37:05 发布 · 104 阅读

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/wordchao/p/10964294.html

本文详细解析了HLS指令中的ArrayPartition和ArrayReshape，通过实例展示了如何使用这些指令来重塑和分区数组，以提高内存带宽和硬件性能。介绍了不同映射方式（block、cyclic、complete）以及factor和dim参数的使用方法。

Array Partition

#pragma HLS array_partition variable=<variable> <block, cyclic, complete> factor=<int> dim=<int>

Array Reshape

#pragma HLS array_reshape variable=<variable> <block, cyclic, complete> factor=<int> dim=<int>

Example 1

Reshapes (partition and maps) an 8-bit array with 17 elements, AB[17], into a new 32-bit array with five elements using block mapping.

#pragma HLS array_reshape variable=AB block factor=4

TIP: factor=4 indicates that the array should be divided into four. So 17 elements is reshaped into an array of 5 elements, with four times the bit-width. In this case, the last element, AB[17], is mapped to the lower eight bits of the fifth element, and the rest of the fifth element is empty.

Example 2

Reshapes the two-dimensional array AB[6][4] into a new array of dimension [6][2], in which dimension 2 has twice the bit-width:

#pragma HLS array_reshape variable=AB block factor=2 dim=2

Example 3

Reshapes the three-dimensional 8-bit array, AB[4][2][2] in function foo, into a new single element array (a register), 128 bits wide (4*2*2*8):

#pragma HLS array_reshape variable=AB complete dim=0

TIP: dim=0 means to reshape all dimensions of the array.

Reference:

1. https://www.xilinx.com/support/documentation/sw_manuals/xilinx2015_2/sdsoc_doc/topics/calling-coding-guidelines/concept_increasing_local_memory_bandwidth.html

2. https://japan.xilinx.com/html_docs/xilinx2017_4/sdaccel_doc/mrl1504034361747.html

转载于:https://www.cnblogs.com/wordchao/p/10964294.html