Visible to Intel only — GUID: GUID-2086BBA5-29B0-4AE1-8E4B-CD24F4D2AE7E
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-2086BBA5-29B0-4AE1-8E4B-CD24F4D2AE7E
Host-Side Timing
The following code snippet is a host-side timing routine around a kernel call (error handling is omitted):
float start = …;//getting the first time-stamp
clEnqueueNDRangeKernel(g_cmd_queue, …);
clFinish(g_cmd_queue);// to make sure the kernel completed
float end = …;//getting the last time-stamp
float time = (end-start);
In this example, host-side timing is implemented using the following functions:
- clEnqueueNDRangeKernel adds a kernel to a queue and immediately returns
- clFinish explicitly indicates the completion of kernel execution. You can also use clWaitForEvents.
Wrapping the Right Set of Operations
When using any host-side routine for evaluating performance of your kernel, ensure you wrapped the proper set of operations.
For example, avoid potentially costly and/or serializing routine, like:
- Including various printf calls
- File input or output operations
- and so on
Also profile kernel execution and data transferring separately by using OpenCL™ profiling events. Similarly, keep track of compilation and general initialization costs, like buffer creation separately from the actual execution flow.