Memory increases on GPU while performing modification inplace

6 Ansichten (letzte 30 Tage)
rinkert
rinkert am 21 Sep. 2021
Kommentiert: rinkert am 12 Okt. 2021
When I allocate squeeze a 3D array to output a 2D array, my memory is increasing while I think I performing the modification inplace. That way I would expect that since the number of elements in the array does not incease, the memory used on the GPU does not increase.
However, I see something different in the task manager. What is going on?
  • MATLAB Version: 9.8.0.1538580 (R2020a) Update 6
  • Operating System: Microsoft Windows 10 Enterprise Version 10.0 (Build 18363)
  • NVidia GeForce RTX 3090
data = zeros(5632000, 128, 2, 'int16');
testSO(data);
function testSO(RF)
whos RF % int16 2.75 GB
size(RF); % 5632000x128x2
% GPU memory at beginning 1.2 GB
RF = gpuArray(RF); % 3.9 GB
RF = squeezingSuperFrames(RF); % 6.6 GB
end
function RF = squeezingSuperFrames(RF)
% concatenate pages of 3D array to create tall RF array
RF = reshape(permute(RF, [1 3 2]), [], size(RF, 2), 1);
end

Antworten (2)

Joss Knight
Joss Knight am 10 Okt. 2021
MATLAB cannot perform this operation in place because data is a workspace variable. MATLAB has no way of knowing there won't be an error or user interrupt (Ctrl-C) during execution, so it takes a copy of data to ensure your workspace would not be corrupted.
  3 Kommentare
Joss Knight
Joss Knight am 11 Okt. 2021
Good point, I wasn't paying proper attention to when you were moving data to the GPU. As Matt points out, your culprit is permute.
MATLAB may be still holding onto the memory, but only because it is pooled, it is not preventing its use. This is a performance optimization. You can see that this memory is available for use by other MATLAB variables and operations by inspecting the AvailableMemory property in the output of gpuDevice.
rinkert
rinkert am 12 Okt. 2021
Thanks for the pointer to AvailableMemory, that indeed showed that there is still memory available while nvidia-smi shows it up as in use.

Melden Sie sich an, um zu kommentieren.


Matt J
Matt J am 10 Okt. 2021
reshape() does not result in data copying, but permute() does. It cannot be done in place, because it is reordering the data in memory.
  3 Kommentare
Matt J
Matt J am 10 Okt. 2021
Bearbeitet: Matt J am 10 Okt. 2021
The memory should be freed after the function call is complete. On my GPU (GTX 1080 Ti), this is what occurs. Maybe you should reset your GPU or even reboot the system to make sure your GPU didn't get stuck in some weird state.
rinkert
rinkert am 12 Okt. 2021
yes indeed the memory is freed after the function call is completed. Seems like the memory is already available before, if I look at g=gpuDevice(); g.AvailableMemory before the function exits.

Melden Sie sich an, um zu kommentieren.

Kategorien

Mehr zu Loops and Conditional Statements finden Sie in Help Center und File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by