I was able to compile and run the code in the emulator as well as was able to build for FPGA hardware. But when I tried to run the code in FPGA, till the kernel called, the host code worked. But had this error popped up
terminate called after throwing an instance of 'cl::sycl::runtime_error'
what(): Native API failed. Native API returns: -46 (CL_INVALID_KERNEL_NAME) -46 (CL_INVALID_KERNEL_NAME)
I have attached the makefile I used.
Could you please confirm if you are using oneAPI devcloud or FPGA devcloud. Also share with us the qsub command that you are using to request compute node.
I'm using intel Devcloud and I'm using job submit script containing bellow line, where the script contains 'make run' the hardware binary.
qsub -l nodes=1:fpga_runtime:ppn=2 -d . $script
also, I print the platform and the device, before launching the kernel in the code and I get the output as,
Platform name: Intel(R) FPGA SDK for OpenCL(TM) Device name: pac_a10 : Intel PAC Platform (pac_ee00000)
After this verbose, at the point I call the kernel, I get the error.
Hope this message find you well, unfortunately as we do not receive any further on clarification provided. Hence, this thread will now be transitioned to community support. If you have new queries or further query on this thread, please feel free to open a new thread or reopen this thread to get support from Intel experts. Otherwise, the community users will further help you with doubts in this thread.