intel-extension-for-pytorch
intel-extension-for-pytorch copied to clipboard
intel
Distortions in using IPEX with triplane NeRF on TripoSR
Describe the bug
Issue:
I am trying to run TripoSR (original repository: https://github.com/VAST-AI-Research/TripoSR) on an Intel Developer Cloud instance. I made the necessary changes to the main repo to use IPEX and optimize the model for float32. The model is running successfully. However, when I check the results, the output file is distorted significantly. I optimized and ran this for CPU as well, and the results there look fine. You can see the outputs in the following image:
The glb on the left is from the CPU and on the right is from an Intel GPU, performed on the same image.
Reproducing the error:
- You can checkout the following repository and move to the ipex branch:
git clone https://github.com/Dimensify/TripoSR/
cd TripoSR
git checkout ipex
pip install -r requirements.txt
-
To run the code, use the command
python run.py examples/chair.png --output-dir output/ --model-save-format glb --render -
You can check the render in
output/0/render.mp4
Versions
Collecting environment information... PyTorch version: 2.1.0a0+cxx11.abi PyTorch CXX11 ABI: Yes IPEX version: 2.1.10+xpu IPEX commit: a12f9f650 Build type: Release
OS: Ubuntu 22.04.2 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 Clang version: N/A IGC version: 2024.0.2 (2024.0.2.20231213) CMake version: version 3.28.3 Libc version: glibc-2.35
Python version: 3.9.18 (tags/v3.9.18-26-g6b320c3b2f6-dirty:6b320c3b2f6, Sep 28 2023, 00:35:27) [GCC 13.2.0] (64-bit runtime) Python platform: Linux-5.15.0-73-generic-x86_64-with-glibc2.35 Is XPU available: True DPCPP runtime version: 2024.0 MKL version: 2024.0 GPU models and configuration: [0] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [1] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [2] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [3] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [4] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [5] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [6] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [7] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [8] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [9] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [10] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [11] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [12] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [13] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [14] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) [15] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=65536MB, max_compute_units=512, gpu_eu_count=512) Intel OpenCL ICD version: 23.30.26918.50-736~22.04 Level Zero version: 1.3.26918.50-736~22.04
CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 192 On-line CPU(s) list: 0-191 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8468V CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 48 Socket(s): 2 Stepping: 8 Frequency boost: enabled CPU max MHz: 2401.0000 CPU min MHz: 800.0000 BogoMIPS: 4800.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities L1d cache: 4.5 MiB (96 instances) L1i cache: 3 MiB (96 instances) L2 cache: 192 MiB (96 instances) L3 cache: 195 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-47,96-143 NUMA node1 CPU(s): 48-95,144-191 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Retbleed: Not affected 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
Versions of relevant libraries: [pip3] intel-extension-for-pytorch==2.1.10+xpu [pip3] numpy==1.26.4 [pip3] pytorch-lightning==2.2.0.post0 [pip3] torch==2.1.0a0+cxx11.abi [pip3] torchaudio==2.1.0a0+cxx11.abi [pip3] torchmcubes==0.1.0 [pip3] torchmetrics==1.3.1 [pip3] torchvision==0.16.0a0+cxx11.abi [conda] intel-extension-for-pytorch 2.1.10+xpu pypi_0 pypi [conda] numpy 1.26.4 pypi_0 pypi [conda] torch 2.1.0a0+cxx11.abi pypi_0 pypi [conda] torchaudio 2.1.0a0+cxx11.abi pypi_0 pypi [conda] torchmcubes 0.1.0 pypi_0 pypi [conda] torchvision 0.16.0a0+cxx11.abi pypi_0 pypi
@SAint7579 Thanks for reporting it, we will investigate and get back to you.
Hey @Vasud-ha, the distortions seems to be observed with latest IPEX version(v2.1.20+xpu) as well.
Hi @rskasturi, thanks for sharing the updates, we can reproduce the issue on our end and are currently in the process of debugging it.
The first output difference on CPU and GPU is occurring at this layer of the model.
image_tokenizer.model.embeddings.dropout
Hi @SAint7579 could you please try with the latest ipex 2.1.30+xpu, results seem good with the latest version on GPU Max 1100.
@Vasud-ha, yes, it works on our IDC machine with IPEX 2.1.30. Thanks a lot for the help!
