how to workaround the error "don't have an op for vulkan_prepack::create_linear_context" ? #102966
Description
🐛 Describe the bug
I have a modified resnet-50 network, which I want to run on android using vulkan backend.
The custom build of pytorch with USE_VULKAN=1 works fine, but I got the error message "We don't have an op for vulkan_prepack::create_linear_context but it isn't a special case." during "optimize_for_mobile" API invocation.
What's the problem here, and how to deal with it?
(I tried on both release 1.13 and release v2.0.1 tags, but got the same error message above).
git clone -b release/1.13 --recursive https://github.com/pytorch/pytorch
cd pytorch
git submodule sync
git submodule update --init --recursive
export CMAKE_PREFIX_PATH=${CONDA_PREFIX:-"$(dirname $(which conda))/../"}
python setup.py build --cmake-only
ccmake build # or cmake-gui build
BUILD_LITE_INTERPRETER=0 USE_VULKAN=1 USE_VULKAN_SHADERC_RUNTIME=1 USE_VULKAN_WRAPPER=0 python setup.py develop
BUILD_LITE_INTERPRETER=0 ANDROID_ABI=arm64-v8a USE_VULKAN=1 USE_VULKAN_SHADERC_RUNTIME=1 USE_VULKAN_WRAPPER=0 bash ./scripts/build_android.sh
BUILD_LITE_INTERPRETER=0 ANDROID_ABI=arm64-v8a USE_VULKAN=1 USE_VULKAN_SHADERC_RUNTIME=1 USE_VULKAN_WRAPPER=0 bash ./scripts/build_pytorch_android.sh
>>> import torch
>>> import os
>>>
>>> from torch.utils.mobile_optimizer import optimize_for_mobile
>>>
>>> #file_dir = '.'
>>> file_dir = '../pytorch-script/'
>>> model = torch.jit.load(file_dir + '/modified-resnet50-image.pt')
>>> model.eval()
RecursiveScriptModule(original_name=ImageModel)
>>> script_model = torch.jit.script(model)
>>> script_model_vulkan = optimize_for_mobile(script_model, backend='vulkan')
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/mnt/DataExt/devroot/src/pytorch/torch/utils/mobile_optimizer.py", line 67, in optimize_for_mobile
optimized_cpp_module = torch._C._jit_pass_vulkan_optimize_for_mobile(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: 0 INTERNAL ASSERT FAILED at "/mnt/DataExt/devroot/src/pytorch/torch/csrc/jit/ir/alias_analysis.cpp":615, please report a bug to PyTorch. We don't have an op for vulkan_prepack::create_linear_context but it isn't a special case. Argument types: Tensor, Tensor,
Candidates:
>>> exit()
Versions
Collecting environment information...
PyTorch version: 2.0.0a0+gite9ebda2
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 10.3.0-1ubuntu1~20.04) 10.3.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.31
Python version: 3.11.3 (main, Apr 19 2023, 23:54:32) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-73-generic-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA RTX A4000
Nvidia driver version: 530.30.02
cuDNN version: Probably one of the following:
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn.so.8
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_adv_train.so.8
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8
/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_ops_train.so.8
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 45 bits physical, 48 bits virtual
CPU(s): 16
On-line CPU(s) list: 0-15
Thread(s) per core: 1
Core(s) per socket: 16
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Xeon(R) Gold 5218N CPU @ 2.30GHz
Stepping: 7
CPU MHz: 2294.609
BogoMIPS: 4589.21
Hypervisor vendor: VMware
Virtualization type: full
L1d cache: 512 KiB
L1i cache: 512 KiB
L2 cache: 16 MiB
L3 cache: 22 MiB
NUMA node0 CPU(s): 0-15
Vulnerability Itlb multihit: KVM: Mitigation: VMX unsupported
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed: Mitigation; Enhanced IBRS
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat pku ospke avx512_vnni md_clear flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] numpy==1.24.3
[pip3] torch==1.13.0a0+gitd922c29
[conda] blas 1.0 mkl
[conda] magma-cuda110 2.5.2 1 pytorch
[conda] mkl 2023.1.0 h6d00ec8_46342
[conda] mkl-include 2023.1.0 h06a4308_46342
[conda] mkl-service 2.4.0 py311h5eee18b_1
[conda] mkl_fft 1.3.6 py311ha02d727_1
[conda] mkl_random 1.2.2 py311ha02d727_1
[conda] numpy 1.24.3 py311h08b1b3b_1
[conda] numpy-base 1.24.3 py311hf175353_1
[conda] torch 1.13.0a0+gitd922c29 pypi_0 pypi