Is it possible to increase dynamically allocated SM (cudaFuncAttributeMaxDynamicSharedMemorySize) for the kernels launched with Dynamic Parallelism? My kernel runs OK with <= 48K of the dynamically allocated SM with Dynamic Parallelism, I can also directly launch kernel from the host code with >48K,…

[image] andrey17: Is it possible to increase dynamically allocated SM (cudaFuncAttributeMaxDynamicSharedMemorySize) for the kernels launched with Dynamic Parallelism? I don’t believe it is possible. If this is an important feature for you, you may wish to file a bug , requesting an enhancemen…

Robert, thank you for your reply. I am not an experienced CUDA developer, so I’m trying first to understand if this functionality is not yet implemented or I’m just doing something wrong. I think it is an important feature and not just for me, especially for the devices with later compute capability…

Hello Robert, I followed your advice and filed a bug report https://developer.nvidia.com/nvidia_bug/3503453 . It all went well at first, but since 01/24, I could not post my reply. I tried many times, from different computers and browsers, but I’m getting the same error message: An AJAX HTTP error…

Yuki, Thank you. I still have to reply here, as that AJAX error did not go away (I hoped the state would change after you last post there). Andrey

Yuki, maybe I’m wrong but I suspect that the website problem maybe somehow related to the “publicly visible log.txt” - I do not see any. Where should it be? Search does not find another “log.txt” on the page itself and in the source view. Maybe it broke something with permissions and now only NVIDI…

Hi Yuki, I’m still getting that AJAX error trying to reply you on the bug report page - https://developer.nvidia.com/nvidia_bug/3503453 Additionallly, I asked another developer who is registered at NVIDIA - he can not access that page at all. Where should I respond you? For now I’m doing it here,…

Hi Andrey , I just saw your reply here to my latest email . Sorry for the bug report system breakage .We’ve been checking with our IT engineers on it . What about we focus on email chat and bring back the ticket result here ? Thanks .

Yuki, Maybe we should restart this bug report as a new one to fix the web problems? Andrey

Could this be related to a problem I’m having configuring the shared memory of a kernel which calls device kernels? I have 1 kernel which calls three device kernels, and I need to configure the shared memory to one of the device kernels. I’m currently setting the functionAttribute of the global ke…

I don’t know what you mean by global kernels and device kernels. The entry point for a CUDA kernel is a function that is decorated with the __global__ keyword. If you are referring to something that is decorated with __device__ and not __global__, that function, by itself, is not a kernel. cudaFu…

Dynamic SM with Dynamic Parallelism

Accelerated Computing CUDA CUDA Programming and Performance

Robert_Crovella December 15, 2021, 2:33am 2

I don’t believe it is possible. If this is an important feature for you, you may wish to file a bug, requesting an enhancement..

Topic		Replies	Views
cudaFuncSetAttribute and dynamic parallelism CUDA Programming and Performance	2	719	January 10, 2023
Default value of max dynamic shared memory CUDA Programming and Performance cuda	8	530	December 23, 2024
Dynamic shared memory can not allocate problem(on 3050PC) CUDA Programming and Performance	1	547	July 20, 2022
Is cudaFuncAttributeMaxDynamicSharedMemorySize a supported attriburw? Legacy PGI Compilers (archived)	8	3084	June 16, 2020
Can't launch 1 block with 1024 threads when maximizing shared memory using cudaFuncSetAttribute CUDA Programming and Performance	2	435	August 11, 2023
NCU dynamic shared memory display question Nsight Compute	1	585	April 3, 2024
Max shared memory CUDA Programming and Performance	0	1370	July 28, 2020
Dynamic shared memory calculated by ncu larger than Max_shared_memory_per_block Nsight Compute cuda	3	932	September 7, 2023
Shared memory to Global memory data transfer nvc, nvc++ and nvfortran cuda	4	812	June 12, 2023
How to allocate more than 48KB shared memory on A100? CUDA Programming and Performance	3	1293	April 29, 2023

Dynamic SM with Dynamic Parallelism

Related topics