OpenCL™ Developer Guide for Intel® Processor Graphics

Download PDF
ID 773088
Date 3/20/2019
Public
Document Table of Contents
Document Table of Contents x
OpenCL™ Optimization Guide for Visual Computing Systems
OpenCL™ Optimization Guide for Visual Computing Systems x
Legal Information Getting Help and Support Introduction Coding for the Intel® Processor Graphics Platform-Level Considerations Application-Level Optimizations Optimizing OpenCL™ Usage with Intel® Processor Graphics Check-list for OpenCL™ Optimizations Performance Debugging Using Multiple OpenCL™ Devices Coding for the Intel® CPU OpenCL™ Device OpenCL™ Kernel Development for Intel® CPU OpenCL™ device
Introduction x
About this Document Basic Concepts Using Data Parallelism Related Products
Coding for the Intel® Processor Graphics x
Execution of OpenCL™ Work-Items: the SIMD Machine Memory Hierarchy
Platform-Level Considerations x
Intel® Turbo Boost Technology Support Global Memory Size
Application-Level Optimizations x
Minimizing Data Copying Avoiding Needless Synchronization Reusing Compilation Results with clCreateProgramWithBinary Interoperability with Other APIs
Interoperability with Other APIs x
Interoperability between OpenCL and OpenGL Using Microsoft DirectX* Resources Aligning Pointers to Microsoft DirectX* Buffers Upon Mapping Note on Working with other APIs Note on Intel® Quick Sync Video
Optimizing OpenCL™ Usage with Intel® Processor Graphics x
Optimizing Utilization of Execution Units Work-Group Size Recommendations Summary Memory Access Considerations Using Loops
Memory Access Considerations x
Memory Access Overview Recommendations Kernel Memory Access Optimization Summary
Recommendations x
Granularity __global Memory and __constant Memory __private Memory __local Memory
Check-list for OpenCL™ Optimizations x
Mapping Memory Objects Using Buffers and Images Appropriately Using Floating Point for Calculations Using Compiler Options for Optimizations Using Built-In Functions Loading and Storing Data in Greatest Chunks Applying Shared Local Memory Using Specialization in Branching Considering native_ and half_ Versions of Math Built-Ins Using the Restrict Qualifier for Kernel Arguments Avoiding Handling Edge Conditions in Kernels
Performance Debugging x
Host-Side Timing Profiling Operations Using OpenCL™ Profiling Events Comparing OpenCL™ Kernel Performance with Performance of Native Code Getting Credible Performance Numbers Using Tools
Using Multiple OpenCL™ Devices x
Using Shared Context for Multiple OpenCL™ Devices Sharing Resources Efficiently Synchronization Caveats Writing to a Shared Resource Partitioning the Work Keeping Kernel Sources the Same Basic Frequency Considerations Eliminating Device Starvation Limitations of Shared Context with Respect to Extensions
Coding for the Intel® CPU OpenCL™ Device x
Vectorization Basics for Intel® Architecture Processors Benefitting From Implicit Vectorization Vectorizer Knobs Using Vector Data Types Writing Kernels to Directly Target the Intel® Architecture Processors Work-Group Size Considerations Work-Group Level Parallelism
OpenCL™ Kernel Development for Intel® CPU OpenCL™ device x
Why Optimizing Kernel Code Is Important? Avoid Spurious Operations in Kernel Code Perform Initialization in a Separate Task Use Preprocessor for Constants Use Signed Integer Data Types Use Row-Wise Data Accesses Tips for Auto-Vectorization Local Memory Usage Avoid Extracting Vector Components Task-Parallel Programming Model Hints
OpenCL™ Optimization Guide for Visual Computing Systems

OpenCL™ Optimization Guide for Visual Computing Systems

Apply the optimizations described in this guide using the Intel® OpenCL™ Code Builder, which is available with:

  1. Intel® Media Server Studio
  2. Intel® Code builder for OpenCL™ API for Linux*
NOTE:
This publication, the OpenCL™ Developer Guide for Intel® Processor Graphics, was previously known as the OpenCL™ Optimization Guide for Intel® Processor Graphics.

OpenCL™ Code builder is a software development tool that enables development of OpenCL applications via well-known integrated development environments, targeting the Intel® Architecture processors with the Intel® Processor Graphics.

The tool supports local (host-based) and remote (target-based) development on the following platforms, IDEs, and devices:

Operating System Host/Target OpenCL™ Code Builder as part of Intel® Media Server Studio Intel® Code Builder for OpenCL™ API
Windows* Host - Yes
Target - Yes
Linux* Host Yes Yes
Target Yes Yes

To better understand which version of Code Builder is fitting to you, check the Which Version of the Code Builder to Pick? article.

Level Two Title