Visible to Intel only — GUID: GUID-8E374EFB-0B2B-4040-8F3B-8EE080C3B2B6
Legal Information
Getting Help and Support
Introduction
Check-list for OpenCL™ Optimizations
Tips and Tricks for Kernel Development
Application-Level Optimizations
Debugging OpenCL™ Kernels on Linux* OS
Performance Debugging with Intel® SDK for OpenCL™ Applications
Coding for the Intel® Architecture Processors
Why Optimizing Kernels Is Important?
Avoid Spurious Operations in Kernels
Avoid Handling Edge Conditions in Kernels
Use the Preprocessor for Constants
Prefer (32-bit) Signed Integer Data Types
Prefer Row-Wise Data Accesses
Use Built-In Functions
Avoid Extracting Vector Components
Task-Parallel Programming Model Hints
Common Mistakes in OpenCL™ Applications
Introduction for OpenCL™ Coding on Intel® Architecture Processors
Vectorization Basics for Intel® Architecture Processors
Vectorization: SIMD Processing Within a Work Group
Benefitting from Implicit Vectorization
Vectorizer Knobs
Targeting a Different CPU Architecture
Using Vector Data Types
Writing Kernels to Directly Target the Intel® Architecture Processors
Work-Group Size Considerations
Threading: Achieving Work-Group Level Parallelism
Efficient Data Layout
Using the Blocking Technique
Intel® Turbo Boost Technology Support
Global Memory Size
Visible to Intel only — GUID: GUID-8E374EFB-0B2B-4040-8F3B-8EE080C3B2B6
About This Document
This guide describes the optimization guidelines of OpenCL™ applications targeting the Intel® Core™ and Intel® Xeon® Processors. In case your application targets Intel® processors with Intel® Graphics, refer to the correspondingOpenCL™ Developer Guide for Intel® Processor Graphics.
NOTE:
Intel® Xeon Phi™ coprocessor based on the Intel® Many Integrated Core (Intel® MIC) Architecture is supported only on OpenCL™ Runtime version 14.2.
This guide describes three basic factors most influence performance on the multi-socket systems:
- Threading scalability. Multi-socket Intel Xeon systems combine many Intel® CPU cores, thus utilizing thread parallelism is critical to achieving good performance.
- Vectorization. Intel Xeon processors support wide vector registers and associated SIMD operations.
- Memory bandwidth utilization.
This guide explains, which sections of code consume most compute cycles, and provides optimization best-known methods.
For better understanding of the optimizations described in this guide, you must be familiar with the following concepts:
- The OpenCL standard
- Threading and Single Instruction Multiple Data (SIMD) vector instruction sets
See Also
OpenCL™ 1.2 Specification at https://www.khronos.org/registry/OpenCL/specs/opencl-1.2.pdf
Overview Presentations of the OpenCL™ Standard at http://www.khronos.org/registry/OpenCL