i.mx6q darknet opencl error: out of resource

cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

i.mx6q darknet opencl error: out of resource

777 Views
chris_lee
Contributor II

I'm porting GitHub - lincolnhard/darknet-clblast: Run darknet using OpenCL backend with CLBlast sgemm  

 on i.mx6q board, I got some errors, here's the log:

r$ ./clb-darknet detect cfg/yolov2-tiny.cfg yolov2-tiny.weights data/dog.jpg > run.log
layer filters size input output
0 conv 16 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 16
1 max 2 x 2 / 2 416 x 416 x 16 -> 208 x 208 x 16
2 conv 32 3 x 3 / 1 208 x 208 x 16 -> 208 x 208 x 32
3 max 2 x 2 / 2 208 x 208 x 32 -> 104 x 104 x 32
4 conv 64 3 x 3 / 1 104 x 104 x 32 -> 104 x 104 x 64
5 max 2 x 2 / 2 104 x 104 x 64 -> 52 x 52 x 64
6 conv 128 3 x 3 / 1 52 x 52 x 64 -> 52 x 52 x 128
7 max 2 x 2 / 2 52 x 52 x 128 -> 26 x 26 x 128
8 conv 256 3 x 3 / 1 26 x 26 x 128 -> 26 x 26 x 256
9 max 2 x 2 / 2 26 x 26 x 256 -> 13 x 13 x 256
10 conv 512 3 x 3 / 1 13 x 13 x 256 -> 13 x 13 x 512
11 max 2 x 2 / 1 13 x 13 x 512 -> 13 x 13 x 512
12 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024
13 conv 512 3 x 3 / 1 13 x 13 x1024 -> 13 x 13 x 512
14 conv 425 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 425
15 detection
mask_scale: Using default '1.000000'
Loading weights from yolov2-tiny.weights...Done!
CLBlast: OpenCL error: clCreateKernel: -5
CLBlast: OpenCL error: clCreateKernel: -5
CLBlast: OpenCL error: clCreateKernel: -5
CLBlast: OpenCL error: clCreateKernel: -5
CLBlast: OpenCL error: clCreateKernel: -5
CLBlast: OpenCL error: clCreateKernel: -5
CLBlast: OpenCL error: clEnqueueNDRangeKernel: -54
CLBlast: OpenCL error: clEnqueueNDRangeKernel: -54
CLBlast: OpenCL error: clCreateKernel: -5

the opencl error -5 means 'out of resource'

I traced the code that caused the problem was the attached file 'xgemm_direct_part3.opencl'

Is there any document about i.mx6q gpu for opencl resource limitation?

How can I optimize the xgemm opencl code to use less resources?

Any suggestion would be appreciated.

Labels (1)
0 Kudos
1 Reply

465 Views
gusarambula
NXP TechSupport
NXP TechSupport

Hello Chris Lee,

There are a couple of GPU tools. There is a GPU Demo Framework SDK which you can find on the link below (please note you may need to login to download).

https://www.nxp.com/webapp/Download?colCode=FSL_GPU_SDK_2.3&appType=license&Parent_nodeId=1337637154...

There is also a profiler tool for the GPU available on the link below (for Kernel 4.1.15)

https://www.nxp.com/webapp/Download?colCode=IMX6_L4-1-15_2-0-0_GPU-TOOL&appType=license&Parent_nodeI...

Darknet is not currently supported on the i.MX6Q BSP. Maybe some Community users can comment on this but perhaps you should ask this question in forums more focused on Darknet.

Regards,

0 Kudos