CUDA kernel MaxThreadsPerBlock not constant

2020 1 30
1 个回答
回答已采纳
更新时间：2020 2 3
3 次查看（30 天）

0 个投票

I create a CUDA kernel using KERN = parallel.gpu.CUDAKernel(PTXFILE,CUFILE,FUNC). Block size is computed from KERN.MaxThreadsPerBlock which may vary based on a function which is used to build the kernel. I presumed MaxThreadsPerBlock is only dependent on gpuDevice properties. So far, it seems there might be some connection to number of function parameters. Can someone explain how this is actually determined or am I missing something?
I'm using Matlab 2019b, GCC 8.3, CUDA Toolkit 10.1 with NVidia V100 (CC 7.0).

2 个评论
显示 无 隐藏 无

Joss Knight
Joss Knight 2020-2-2
I can't work out how you'd see this for the same device. Can you post some reproduction code?
Martin Strambach
Martin Strambach 2020-2-2
Hi Joss, thanks for your reply!
You can find an example in the attachement. It's not exactly minimal working example, but it should do. The file computeITT contains two entry points - one for single precision and the other one for double precision. I've also attached compiled ptx code (GCC 8.3, CUDA toolkit 10.1.243) compiled as follows: nvcc -ptx --gpu-architecture=compute_70. The rest of the files are just includes. When you construct a kernel with single precision entry point then KERN.MaxThreadsPerBlock is 1024, when you do the same thing for double precision entry point then KERN.MaxThreadsPerBlock is 512.
As odd as it sounds, the MaxThreadsPerBlock parameter isn't always half for double precision compared to single precision.

请先登录，再进行评论。

请先登录，再回答此问题。

 采纳的回答

Edric Ellis
Edric Ellis 2020-2-3

1 个投票

In your comment you mention that you see different values of MaxThreadsPerBlock for different kernels. This is expected. The CUDAKernel object builds on the underlying CUDA Driver API. Different kernel functions have different requirements in terms of shared memory, registers, and other resources, and this affects how many threads per block can be launched. This is described (briefly) in the CUDA Driver reference documentation here: https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__EXEC.html#group__CUDA__EXEC_1g5e92a1b0d8d1b82cb00dcfb2de15961b (In case that link goes stale - it describes the function cuFuncGetAttribute which allows you to query the CUDA attribute CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK).

更多回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Get Started with GPU Coder 的更多信息

产品

版本

R2019b

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by