Visible to Intel only — GUID: GUID-0B202000-502B-46D1-9FEF-61524C403DD8
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-0B202000-502B-46D1-9FEF-61524C403DD8
Use Restrict Qualifier for Kernel Arguments
Consider using restrict type qualifier (defined by the C99) for kernel arguments (pointers) in the kernel signature. You can use the restrict qualifier only with kernel arguments. The qualifier is a hint to the compiler that helps to limit the effects of pointer aliasing, while also aiding caching optimizations. In the example below, it enables the compiler to assume that pointers a, b, and c point to the different locations. You must ensure that the pointers do not point to overlapping locations.
__kernel void foo( const float i,
__global const float* restrict a,
__global const float* restrict b,
__global float* restrict result)
{
//…
}