85
edits
Changes
GPU
,→Grids and NDRange
== Grids and NDRange ==
While warps, blocks, wavefronts and workgroups are concepts that the machine executes... Grids and NDRanges are the scope of the problem specified by a programmer. For example, the 1920x1080 screen could be defined as a Grid with 2073600 threads to execute (likely organized as a 2-dimensional 1920x1080 grid for convenience). Specifying these 2,073,600 work items is the purpose of a CUDA Grid or OpenCL NDRange.
These blocks and workgroups will execute with as much parallel processing as the underlying hardware can support. Roughly 150 CUDA Blocks or OpenCL Workgroups at a time on a typical midrange GPU circa from 2019 (such as a NVidia 2060 Super or AMD 5700). The most important note is that blocks within a Grid grid (or workgroups within an NDRange) may not execute concurrently with each other. Some degree of sequential processing may happen. As such, communication across a Grid or NDRange is difficult to achieve. If thread #0 creates a Spinlock waiting for thread #1000000 to communicate with it, modern hardware will probably never have the two threads executing concurrently with each other, and the code would likely timeout. In practice, the easiest mechanism for Grid or NDRange sized synchronization is to wait for the kernel to finish executing: to have the CPU wait and process the results in between Grid or NDRanges.
For example: LeelaZero will schedule an NDRange for each [https://github.com/leela-zero/leela-zero/blob/next/src/kernels/convolve1.opencl Convolve operation], as well as merge and other primitives. The convolve operation is over a 3-dimensional NDRange for <channel, output, row_batch>. To build up a full CNN operation, the CPU will schedule different operations for the GPU: convolve, merge, transform and more.