Technical information

Software Examples and Labs

XAPP1206 v1.1 June 12, 2014 www.xilinx.com 2

only options. So, in some situations, you might need to re-write time-critical code in NEON

intrinsics to achieve better performance. Lab 2 provides a hands-on example.

• Optimizing NEON Assembler Code

In some situations, the compiler might be unable to generate the highest performance

binary. When this happens, you must write functions in NEON assembler code, with

everything under developer control. Lab 3 provides a hands-on example.

Boost NEON Performance by Improving Memory Access Efficiency

When discussing NEON performance, there is usually an underlying assumption that the

memory subsystem can follow the pace of the CPU. In practice, this means that all data and

instructions are using L1 cache. This cannot always be true, however, especially when a data

set is very large. This application note discusses three techniques for improving cache

efficiency:

• Loading and Storing Multiple Data in a Burst

• Using the Preload Engine to Improve the Cache Hit Rate

• Using Tiles to Prevent Cache Thrashing

These techniques can benefit not only NEON code, but software code generally.

Prerequisites

This application note assumes that you know how to use Xilinx SDK (Software Development

Kit) to create a new project, import source files, debug, and run standalone applications on

hardware.

Software

Examples and

Labs

Software examples and labs are available for this application note. You can download a ZIP file

containing these from the following location:

https://secure.xilinx.com/webreg/clickthrough.do?cid=359072.

The design matrix is shown in Ta ble 1.

Table 1: Design Matrix

Parameters Description

General

Targeted devices All Zynq-7000 devices

Source code provided Yes

Source code format C and assembler

Uses code/IP from existing Xilinx application note

reference designs, CORE™ Generator software, or

third-party

Verification

Verified on hardware Yes

Software development tools SDK 2013.4

Hardware platform used for verification ZC702 evaluation kit