Hi @jacobpostman,
Yes, I'm able to install tvmrpc app to the device from Xcode, while installing
the app I'm giving all the permission whichever you are noted but still, the
issue is the same.
if I connect iPhone to MAC via the USB cable(RPC connected), I'm not getting
the above error, but wh
Hey @jcf94,
I was looking into the opencl_device_type.cc file and noticed that depending
on which context was used in the python code like (tvm.cpu, tvm.gpu,
tvm.opencl) it chooses a device type and sets the dtype accordingly.
When exactly is the dtype set to the CL_DEVICE_TYPE_ACCELERATOR,
@Dileep - Are you able to install and run the tvmrpc app to the device from
xcode?
It may just be that you need to give the app permission to be installed on your
device.
On the iPhone you do this by going to Settings -> General -> Device Management
-> Select Developer App -> Verify App
-
Hi @jacobpostman, Thank you for your suggestion.
I tried with the above changes whichever you noted, but my bad while tuning the
model I got the Xcode build error, I don't know what is the cause of the below
error
[Task 1/12] Current/Best:0.00/ 0.00 GFLOPS | Progress: (0/100) |
0
Thank you @jroesch, that definitely brings in more clarity.
The way I was using this pass in its previous version was to call it on stmt
within my own pass as a step after some IR transformations, and it worked
flawlessly.
Looking at your answer, it seems that what I am looking for is the P
