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
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
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
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
Using the Restrict Qualifier for Kernel Arguments
Consider using the restrict (defined by the C99) type qualifier for kernel arguments (pointers) in the kernel signature. The qualifier declares that pointers do not alias each other, which helps the compiler limit the effects of pointer aliasing, while aiding the caching optimizations.
__kernel void foo( __constant float* restrict a, __constant float* restrict b, __global float* restrict result)
NOTE:You can use the restrict qualifier only with kernel arguments. In the specific example above, it enables the compiler to assume that pointers a, b, and result do point to the different locations. So you must ensure that the pointers do not point to overlapping memory regions.
Did you find the information on this page useful?