Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

Bus error (core dumped) calling `ipex.optimize` on Arc A770

See original GitHub issue

The test example code given fails when attempting to call ipex.optimize. The code works when commenting out this line:

import torch
import torchvision.models as models
import intel_extension_for_pytorch as ipex

model = models.resnet50(pretrained=True)
model.eval()
data = torch.rand(1, 3, 224, 224)

model = model.to('xpu')
data = data.to('xpu')
model = ipex.optimize(model)

out = model(data)
print(out.shape)

Error:

[1] 297018 bus error (core dumped) python f32_example.py

Environment:

Ubuntu 22.04
ipex.version == ‘1.10.200+gpu’
torch.version == ‘1.10.0a0+git3d5f2d4’

➜  ~ sycl-ls
[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device 1.2 [2022.14.10.0.20_160000.xmain-hotfix]
[opencl:cpu:1] Intel(R) OpenCL, AMD EPYC 7443P 24-Core Processor                3.0 [2022.14.10.0.20_160000.xmain-hotfix]
[opencl:gpu:2] Intel(R) OpenCL HD Graphics, Intel(R) Graphics [0x56a0] 3.0 [22.32.23937]
[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Graphics [0x56a0] 1.3 [1.3.23937]
[host:host:0] SYCL host platform, SYCL host device 1.2 [1.2]

Partial gdb stacktrace:

Thread 1 "python" received signal SIGBUS, Bus error.
0x00007ffecd1a4070 in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
(gdb) backtrace
#0  0x00007ffecd1a4070 in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
#1  0x00007ffecd18c6bb in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
#2  0x00007ffeccfd6406 in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
#3  0x00007ffeccfd6d57 in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
#4  0x00007ffeccfeb3c3 in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
#5  0x00007ffeccff3c90 in ?? () from /lib/x86_64-linux-gnu/libze_intel_gpu.so.1
#6  0x00007fffdfa74dbb in _pi_context::getAvailableCommandList(_pi_queue*, std::__1::__hash_map_iterator<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::__hash_value_type<_ze_command_list_handle
_t*, pi_command_list_info_t>, void*>*> >&, bool, bool) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libpi_level_zero.so
#7  0x00007fffdfa8bda7 in enqueueMemCopyHelper(_pi_command_type, _pi_queue*, void*, unsigned int, unsigned long, void const*, unsigned int, _pi_event* const*, _pi_event**, bool) ()
   from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libpi_level_zero.so
#8  0x00007fffdfa8cbab in piEnqueueMemBufferWrite () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libpi_level_zero.so
#9  0x00007ffed151aedd in cl::sycl::detail::copyH2D(cl::sycl::detail::SYCLMemObjI*, char*, std::shared_ptr<cl::sycl::detail::queue_impl>, unsigned int, cl::sycl::range<3>, cl::sycl::range<3>, cl::sycl::id
<3>, unsigned int, _pi_mem*, std::shared_ptr<cl::sycl::detail::queue_impl>, unsigned int, cl::sycl::range<3>, cl::sycl::range<3>, cl::sycl::id<3>, unsigned int, std::vector<_pi_event*, std::allocator<_pi_
event*> >, _pi_event*&) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#10 0x00007ffed151e1fc in cl::sycl::detail::MemoryManager::copy(cl::sycl::detail::SYCLMemObjI*, void*, std::shared_ptr<cl::sycl::detail::queue_impl>, unsigned int, cl::sycl::range<3>, cl::sycl::range<3>,
cl::sycl::id<3>, unsigned int, void*, std::shared_ptr<cl::sycl::detail::queue_impl>, unsigned int, cl::sycl::range<3>, cl::sycl::range<3>, cl::sycl::id<3>, unsigned int, std::vector<_pi_event*, std::alloc
ator<_pi_event*> >, _pi_event*&) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#11 0x00007ffed1587e88 in cl::sycl::detail::MemCpyCommand::enqueueImp() () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#12 0x00007ffed157e521 in cl::sycl::detail::Command::enqueue(cl::sycl::detail::EnqueueResultT&, cl::sycl::detail::BlockingT, std::vector<cl::sycl::detail::Command*, std::allocator<cl::sycl::detail::Comman
d*> >&) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#13 0x00007ffed15a6b94 in cl::sycl::detail::Scheduler::GraphProcessor::enqueueCommand(cl::sycl::detail::Command*, cl::sycl::detail::EnqueueResultT&, std::vector<cl::sycl::detail::Command*, std::allocator<
cl::sycl::detail::Command*> >&, cl::sycl::detail::BlockingT) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#14 0x00007ffed159ffdb in cl::sycl::detail::Scheduler::addCG(std::unique_ptr<cl::sycl::detail::CG, std::default_delete<cl::sycl::detail::CG> >, std::shared_ptr<cl::sycl::detail::queue_impl>) ()
   from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#15 0x00007ffed15e045b in cl::sycl::handler::finalize() () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#16 0x00007ffed16147f9 in void cl::sycl::detail::queue_impl::finalizeHandler<cl::sycl::handler>(cl::sycl::handler&, cl::sycl::detail::CG::CGTYPE const&, cl::sycl::event&) ()
   from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#17 0x00007ffed16142fc in cl::sycl::detail::queue_impl::submit_impl(std::function<void (cl::sycl::handler&)> const&, std::shared_ptr<cl::sycl::detail::queue_impl> const&, std::shared_ptr<cl::sycl::detail:
:queue_impl> const&, std::shared_ptr<cl::sycl::detail::queue_impl> const&, cl::sycl::detail::code_location const&, std::function<void (bool, bool, cl::sycl::event&)> const*) ()
   from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#18 0x00007ffed1613895 in cl::sycl::detail::queue_impl::submit(std::function<void (cl::sycl::handler&)> const&, std::shared_ptr<cl::sycl::detail::queue_impl> const&, cl::sycl::detail::code_location const&
, std::function<void (bool, bool, cl::sycl::event&)> const*) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#19 0x00007ffed1613855 in cl::sycl::queue::submit_impl(std::function<void (cl::sycl::handler&)>, cl::sycl::detail::code_location const&) () from /opt/intel/oneapi/compiler/2022.2.1/linux/lib/libsycl.so.5
#20 0x00007fff0c35855f in dnnl::impl::gpu::sycl::sycl_interop_gpu_kernel_t::parallel_for(dnnl_stream&, dnnl::impl::gpu::compute::nd_range_t const&, dnnl::impl::gpu::compute::kernel_arg_list_t const&) ()

Issue Analytics

State:
Created 9 months ago
Comments:5 (3 by maintainers)

Top GitHub Comments

1reaction

jingxu10commented, Dec 14, 2022

Probably it is a driver issue. https://intel.github.io/intel-extension-for-pytorch/xpu/latest/tutorials/installation.html The 419.40 driver we verified doesn’t support Ubuntu 22.04. We will release the next version soon. The new version supports Ubuntu 22.04. Would you have a try later on with this new version?

0reactions

jingxu10commented, Dec 20, 2022

Would you check https://dgpu-docs.intel.com/releases/index.html? We didn’t verified on other driver versions.

Top Results From Across the Web

How to solve Bus error (core dumped) in python?

I was running python script on EC2 instance. Due to out of storage, I had to extend the storage by 4GB . After...

~/iley - BIS.doc.gov

tire cord wire rod, Japanese wire rod, light-gauge corrosion resistant steel ("CORE") for use in the heating, ventilation, and air ...

Untitled

Is hair design malaga, Intel core i7 vs amd fx. Budowa nowolipie 7a, Cm400dy-24nf, Tung thanh vien cua super junior, 120 munds mountain...

Untitled

Sotilaallisen, Snaporaz wiki, Potassium ethyl xanthate mw, Austudy eligibility test, Ruttenbergs, Dump gn 85 hd, Certificatul de conformitate.

Untitled

Constraint optimization in r, Smashbox cream eyeshadow topaz, ... Necc stroke boston, Moyes man utd wiki, 154 first bus timing, Matt malpass twitter?...