Intel® oneAPI Base Toolkit
Support for the core tools and libraries within the base toolkit that are used to build and deploy high-performance data-centric applications.
428 Discussions

Using l_BaseKit_p_2022.3.1.17310.sh package and facing Internal compiler error

shivashankark
Employee
1,001 Views

Hi Team,

Earlier, I downloaded  l_BaseKit_p_2022.3.1.sh package and ran oneAPI based programs on GPU, it worked and now I have downloaded l_BaseKit_p_2022.3.1.17310.sh (latest available) but I am not able to detect the GPU and when I run my program, it gives the below error

Running on Genuine Intel(R) 0000
Configuration Loaded Successfully.
**Internal compiler error** Do not know how to split the result of this operator!

Please report the issue on Intel OpenCL forum
https://software.intel.com/en-us/forums/opencl for assistance.
Aborted (core dumped)

 

Regards,

Shiva Shankar K.

WWID:12132441

0 Kudos
4 Replies
NoorjahanSk_Intel
Moderator
964 Views

Hi,


Thanks for reaching out to us.


Could you please let us know whether you are observing similar issue while building your code with CPU?


Also please share your Hardware details(Driver version), complete running log, OneAPI code you are trying to build along with compiler version being used.


Thanks & Regards,

Noorjahan.


0 Kudos
shivashankark
Employee
934 Views

Hi Noorjahan,

 

Please find the details below:

 

Hardware details(Driver version):

00:02.0 VGA compatible controller [0300]: Intel Corporation Device [8086:46d1]
Kernel driver in use: i915

DeviceName: To Be Filled by O.E.M.
Subsystem: Intel Corporation Device 7270
Flags: bus master, fast devsel, latency 0, IRQ 190, IOMMU group 1
Memory at 60e8000000 (64-bit, non-prefetchable) [size=16M]
Memory at 4000000000 (64-bit, prefetchable) [size=256M]
I/O ports at 3000 [size=64]
Expansion ROM at 000c0000 [virtual] [disabled] [size=128K]
Capabilities: <access denied>
Kernel driver in use: i915
Kernel modules: i915

 

Running Log:

terminate called after throwing an instance of 'cl::sycl::compile_program_error'
what(): The program was built for 1 devices
Build program log for 'Intel(R) Graphics [0x46d1]':
-6 (CL_OUT_OF_HOST_MEMORY)
Aborted (core dumped)

 

Source code from which I am getting the above error:

#include <CL/sycl.hpp>
#include <iostream>

using namespace sycl;

static const int N = 16;

int main() {

queue q;
std::cout << "Device: " << q.get_device().get_info<info::device::name>() << "\n";
queue q1;
device my_device = q1.get_device();
std::cout << "Device: " << my_device.get_info<info::device::name>() <<"\n";
#if 1
int *data = malloc_shared<int>(N,q);

for (int i=0; i<N; i++)
data[i] = i;

q.parallel_for(range<1>(N), [=] (id<1> i) {
data[i] *= 2;
}).wait();

for (int i=0; i<N; i++)
std::cout << data[i] << "\n";
#endif
return 0;
}

 

Base tool kit version: l_BaseKit_p_2022.2.0.262_offline.sh

 

Compiler version: 2022.1.0

/opt/intel/oneapi/compiler/2022.1.0

 

 

 

0 Kudos
Anita_Intel
Employee
679 Views

Dear User,

As per our conversation on MS Teams,

  • Issue is disappeared with kernel upgrade to 5.19.8 iotg and OneAPI 2022.1.0 on Ubuntu 20
    • tester@tester-Alder-Lake-Client-Platform:~$ uname -a
      Linux tester-Alder-Lake-Client-Platform 5.19.8-iotg #1 SMP PREEMPT_DYNAMIC Mon Sep 19 15:20:26 IST 2022 x86_64 x86_64 x86_64 GNU/Linux
    • OS VERSION="20.04.5 LTS (Focal Fossa)"
  • It is found that there is no issue with OneAPI Basekit and the issue seems to be with this particular Kernel version compatibility with Ubuntu-22 and OneAPI 2023. 
  • We are investing the same with Ubuntu 22, as per your consent, you will reproduce the issue again on the same Alder Lake platform in coming week and then handover again to me.
  • Meanwhile, we are reproducing the issue and resolution with this configuration at our end and let you know.

Thanks

Snapshot Attached for the reference:

 

Anita_Intel_1-1673584848304.png

 

0 Kudos
Anita_Intel
Employee
544 Views

Dear User,


As per your consent, we are closing this thread now. You can use OneAPI BaseKit latest version 2023 and try your code when you resume your work again. If you need further assistance, please post a new question.


Thanks & Regards,

Anita



0 Kudos
Reply