This example demonstrates an Open Computing Language (OpenCLTM) implementation of a 3D finite difference stencil-only computation. In an order-k stencil computation, each output point is a function of 3k+1 input points (k adjacent points in each direction). Due to the structure of the computation, there is a significant amount of data reuse across different output points, leading to optimizations that try to minimize redundant memory accesses.
The kernel in this example takes advantage of the data reuse by using a sliding volume computation pattern (the 3D analog of the sliding window design pattern) to reduce memory bandwidth requirements compared to traditional OpenCL implementations. Additional details can be found in the example package.
3D Finite Difference Computation Performance
- Efficient 3D sliding volume
- Single work-item kernel
The design example provides source code for the OpenCL device (.cl) as well as the host application. For compiling the host application, the Linux* package includes a Makefile and the Windows* package includes a Microsoft Visual Studio 2010 project.
The following downloads are provided for this example:
The use of this design is governed by, and subject to, the terms and conditions of the hardware reference design license agreement.
Software and Hardware Requirements
This design example requires the following tools:
- Intel® FPGA software v17.1 or later
- Intel® FPGA SDK for OpenCL v17.1 or later
- On Linux: GNU Make and gcc
- On Windows*: Microsoft Visual Studio 2010*
To download the Intel design tools, visit the OpenCL download page. The requirements for the underlying operating system are the same as those of the Intel FPGA SDK for OpenCL.
OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos.
* Product is based on a published Khronos Specification, and has passed the Khronos Conformance Testing Process. Current conformance status can be found at www.khronos.org/conformance.