Calling EnqueuTask multiple times is not working.

--- Quote Start ---

The code looks like it should work.

I'm wondering if the FC_weight_buf[0] isn't getting released somehow.

Could you try moving the the clCreateBuffer and clReleaseMemObject outside the for loop and see if you get the same error?

Doing an clEnqueueWriteBuffer should still work as expected but it'll just overwrite the data from the previous loop which isn't being used anymore.

--- Quote End ---

We already tried this. We are getting the same error.

We are trying to run the attached program and kernel and we now getting the following output. If this code works then it can directly be used in our real application.

This standalone code always terminates at 32732 iteration and Virtual memory in top command continuously increasing and after reaching at ~320GB, program gets the following error.

--- Quote Start ---

......

Kernal 32729 -> 1.374 ms

Kernal 32730 -> 1.309 ms

Kernal 32731 -> 1.275 ms

Context callback: Emulator: Could not start the kernel compute units.

Kernal 32732 -> 1.152 ms

host: acl_offline_hal.c:476: acl_emulator_hal_launch_kernel: Assertion `*thread == 0' failed.

Aborted (core dumped)

--- Quote End ---