Visible to Intel only — GUID: GUID-19EFDDD7-685C-4566-85C2-FDB79143DAA2
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
Visible to Intel only — GUID: GUID-19EFDDD7-685C-4566-85C2-FDB79143DAA2
Perform Initialization in a Separate Task
Consider the following code snippet:
__kernel void something(const __global int* data)
{
int tid = get_global_id(0);
if (0 == tid)
{
//Do some one-shot work
}
barrier(CLK_GLOBAL_MEM_FENCE);
//Regular kernel code
}
In this example, all work-items encounter the first branch, while the branch is relevant to only one of them. A better solution is to move the initialization phase outside the kernel code, either to a separate kernel, or to the host code.
If you need to run some kernel only once (for a single work-item), use clEnqueueTask, which is specially crafted for this purpose.