# Global memory to shared memory without passing registers

**URL:** <https://forums.developer.nvidia.com/t/global-memory-to-shared-memory-without-passing-registers/166559>\
**Category:** CUDA-GDB\
**Created:** [January 22, 2021, 7:41pm UTC](https://forums.developer.nvidia.com/t/global-memory-to-shared-memory-without-passing-registers/166559 "2021-01-22T19:41:05Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Daniel\_Wong](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/daniel_wong/32/60786_2.png) [@Daniel\_Wong](https://forums.developer.nvidia.com/u/Daniel_Wong)\
**Post date:** [January 22, 2021, 7:41pm UTC](https://forums.developer.nvidia.com/t/global-memory-to-shared-memory-without-passing-registers/166559/1 "2021-01-22T19:41:05Z")

</div>

Hi, All

is there an option in CUDA that we can directly load data from global to shared memory without passing the thread-local registers?

Thanks!

---

<div class="post-metadata">

**Author:** ![steveu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/steveu/32/14047_2.png) [@steveu](https://forums.developer.nvidia.com/u/steveu)\
**Post date:** [February 3, 2021, 9:55pm UTC](https://forums.developer.nvidia.com/t/global-memory-to-shared-memory-without-passing-registers/166559/2 "2021-02-03T21:55:41Z")

</div>

This is better addressed on our CUDA Programming and Performance forum. You can find that forum at:

> **[CUDA Programming and Performance](https://forums.developer.nvidia.com/c/accelerated-computing/cuda/cuda-programming-and-performance/7)**
>
> General discussion area for algorithms, optimizations, and approaches to GPU Computing with CUDA C, C++, Thrust, Fortran, Python (pyCUDA), etc.