A similar request was made here. The OP there filed a bug with NVIDIA (3503453), and that bug is in the late stages of being finalized. The development work is done, and based on my read of the bug, it should become available in CUDA 12.1 (if it is not already available in 12.0. I haven’t tested 12.0, but based on what I see in the bug it doesn’t appear to be in 12.0). There is no guarantee that it will be in 12.1, that is just my best guess based on what I see so far.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Dynamic SM with Dynamic Parallelism | 12 | 1803 | September 8, 2025 | |
| Is cudaFuncAttributeMaxDynamicSharedMemorySize a supported attriburw? | 8 | 3081 | June 16, 2020 | |
| Default value of max dynamic shared memory | 8 | 514 | December 23, 2024 | |
| NCU dynamic shared memory display question | 1 | 578 | April 3, 2024 | |
| Template function set cudaFuncAttributeMaxDynamicSharedMemorySize error | 3 | 636 | February 5, 2024 | |
| Can't launch 1 block with 1024 threads when maximizing shared memory using cudaFuncSetAttribute | 2 | 434 | August 11, 2023 | |
| Dynamic shared memory can not allocate problem(on 3050PC) | 1 | 541 | July 20, 2022 | |
| cuFuncSetAttribute locks until H2D/D2H async memcpy finishes | 3 | 233 | February 11, 2025 | |
| Max shared memory | 0 | 1370 | July 28, 2020 | |
| C1060 and Shared Memory size | 2 | 1226 | April 10, 2011 |