# cudaMallocManaged Fails 

**URL:** <https://forums.developer.nvidia.com/t/cudamallocmanaged-fails/71250>\
**Category:** CUDA Programming and Performance\
**Created:** [March 6, 2019, 9:52pm UTC](https://forums.developer.nvidia.com/t/cudamallocmanaged-fails/71250 "2019-03-06T21:52:18Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![thirdvalve](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@thirdvalve](https://forums.developer.nvidia.com/u/thirdvalve)\
**Post date:** [March 6, 2019, 9:52pm UTC](https://forums.developer.nvidia.com/t/cudamallocmanaged-fails/71250/1 "2019-03-06T21:52:18Z")

</div>

Hope this is the right forum…

I’ve installed the CUDA\_8.0.61 kit for Windows 7.

Compiling and debugging with Visual Studio 2015.

When I call cudaMallocManaged() it returns “cudaErrorNotSupported”.

My NVidia adapter is a Quadro 2000M.

I am compiling for x64.

What could the problem be?

---

<div class="post-metadata">

**Author:** ![thirdvalve](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@thirdvalve](https://forums.developer.nvidia.com/u/thirdvalve)\
**Post date:** [March 6, 2019, 10:15pm UTC](https://forums.developer.nvidia.com/t/cudamallocmanaged-fails/71250/2 "2019-03-06T22:15:39Z")

</div>

OK - it appears my device does not support Unified memory.

So there must be an alternative?

---

<div class="post-metadata">

**Author:** ![njuffa](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@njuffa](https://forums.developer.nvidia.com/u/njuffa)\
**Post date:** [March 6, 2019, 10:22pm UTC](https://forums.developer.nvidia.com/t/cudamallocmanaged-fails/71250/3 "2019-03-06T22:22:27Z")

</div>

Quadro 2000M is a Fermi-family device, with compute capability 2.1. It should be supported by CUDA 8. I am reasonably sure that cudaMallocManaged requires compute capability \>= 3.0.

---

<div class="post-metadata">

**Author:** ![thirdvalve](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@thirdvalve](https://forums.developer.nvidia.com/u/thirdvalve)\
**Post date:** [March 7, 2019, 2:02pm UTC](https://forums.developer.nvidia.com/t/cudamallocmanaged-fails/71250/4 "2019-03-07T14:02:32Z")

</div>

OK. I see from examples, that for this level of compute, I need to do a cudaMalloc and a cudaMemcpy to get data back and forth from Host to Device.
