Intel® High Level Synthesis Compiler Standard Edition: Reference Manual

ID 683310
Date 12/18/2019
Public
Document Table of Contents

7. Component Concurrency

The Intel® HLS Compiler assumes that you want a fully pipelined data path in your component. In the C++ implementation, think of a fully pipelined data path as calling a function multiple times before the first call has returned (see also and Intel HLS Compiler Pipeline Approach). The behavior of multiple component invocations within the synthesized data path is subject to the concurrency model, so the Intel® HLS Compiler might not be able to deliver a component with a component initiation interval (II) of 1, or even any pipelining.

The Intel® HLS Compiler provides you with the hls_max_concurrency component attribute to help you control the maximum concurrency of your component.