Skip to content

Instantly share code, notes, and snippets.

View surak's full-sized avatar

Alexandre Strube surak

View GitHub Profile
@surak
surak / TensorFlow-2.7.1-foss-2021b-CUDA-11.4.1_partial.log
Created June 8, 2022 20:53
(partial) EasyBuild log for failed build of /tmp/eb-6vgj5474/files_pr14990/t/TensorFlow/TensorFlow-2.7.1-foss-2021b-CUDA-11.4.1.eb (PR(s) #14990)
== 2022-06-08 20:53:31,946 easyblock.py:303 INFO This is EasyBuild 4.5.5 (framework: 4.5.5, easyblocks: 4.5.5) on host haicluster1.fz-juelich.de.
== 2022-06-08 20:53:31,946 easyblock.py:309 INFO This is easyblock PythonBundle from module easybuild.easyblocks.generic.pythonbundle (/easybuild/2020/software/EasyBuild/4.5.5/lib/python3.8/site-packages/easybuild/easyblocks/generic/pythonbundle.py)
== 2022-06-08 20:53:31,946 easyblock.py:969 INFO Build dir set to /easybuild/2020/build/TensorFlow/2.7.1/foss-2021b-CUDA-11.4.1
== 2022-06-08 20:53:31,946 easyblock.py:1026 INFO Software install dir set to /easybuild/2020/software/TensorFlow/2.7.1-foss-2021b-CUDA-11.4.1
== 2022-06-08 20:53:31,946 easyblock.py:1031 INFO Module install dir set to /easybuild/2020/modules/all
== 2022-06-08 20:53:31,946 easyblock.py:278 INFO Init completed for application name TensorFlow version 2.7.1
== 2022-06-08 20:53:31,947 pythonbundle.py:74 INFO Detection of downloaded extension dependencies is enabled
== 2022-06-08 20:53:31,947 pythonb
name = 'PyTorch'
version = '1.11'
versionsuffix = '-CUDA-%(cudaver)s'
homepage = 'https://pytorch.org/'
description = """Tensors and Dynamic neural networks in Python with strong GPU acceleration.
PyTorch is a deep learning framework that puts Python first."""
toolchain = {'name': 'gcccoremkl', 'version': '11.2.0-2021.4.0'}
toolchainopts = {'openmp': True}
@surak
surak / gist:7ba1f5db0b5bac2150585eaf73954f83
Created January 17, 2022 18:41
SciPy-Stack deep for Jens
== 2022-01-17 18:34:46,183 easyblock.py:287 INFO This is EasyBuild 4.4.1 (framework: 4.4.1, easyblocks: 4.4.1) on host deepv.
== 2022-01-17 18:34:46,183 easyblock.py:293 INFO This is easyblock Bundle from module easybuild.easyblocks.generic.bundle (/usr/local/software/skylake/Stages/2020/software/EasyBuild/4.4.1/lib/python2.7/site-packages/easybuild/easyblocks/generic/bundle.py)
== 2022-01-17 18:34:46,183 easyblock.py:933 INFO Build dir set to /dev/shm/swmanage/deep/SciPyStack/2021/gcccoremkl-10.3.0-2021.2.0-Python-3.8.5
== 2022-01-17 18:34:46,183 easyblock.py:993 INFO Software install dir set to /usr/local/software/skylake/stages/2020/software/SciPy-Stack/2021-gcccoremkl-10.3.0-2021.2.0-Python-3.8.5
== 2022-01-17 18:34:46,184 easyblock.py:998 INFO Module install dir set to /usr/local/software/skylake/stages/2020/modules/all
== 2022-01-17 18:34:46,184 easyblock.py:272 INFO Init completed for application name SciPy-Stack version 2021
== 2022-01-17 18:34:46,184 easyblock.py:3658 INFO Obtained application instan
@surak
surak / gist:8231ae5e92c4fbb56c60803a7b616e14
Created January 17, 2022 18:17
PyTorch 1.10.1 gcc11, `toolchainopts = {'openmp': False, 'pic': True}`
This file has been truncated, but you can view the full file.
== 2022-01-17 17:50:05,327 easyblock.py:303 INFO This is EasyBuild 4.5.1 (framework: 4.5.1, easyblocks: 4.5.1) on host jwlogin23.juwels.
== 2022-01-17 17:50:05,327 easyblock.py:309 INFO This is easyblock EB_PyTorch from module easybuild.easyblocks.pytorch (/p/software/juwelsbooster/stages/2022/software/EasyBuild/4.5.1/lib/python3.6/site-packages/easybuild/easyblocks/p/pytorch.py)
== 2022-01-17 17:50:05,327 easyblock.py:947 INFO Build dir set to /dev/shm/strube1/juwelsbooster/PyTorch/1.10.1/gcccoremkl-11.2.0-2021.4.0-CUDA-11.5
== 2022-01-17 17:50:05,327 easyblock.py:1004 INFO Software install dir set to /p/project/ccstao/cstao05/easybuild/juwelsbooster/software/PyTorch/1.10.1-gcccoremkl-11.2.0-2021.4.0-CUDA-11.5
== 2022-01-17 17:50:05,327 easyblock.py:1009 INFO Module install dir set to /p/project/ccstao/cstao05/easybuild/juwelsbooster/modules/all
== 2022-01-17 17:50:05,327 easyblock.py:278 INFO Init completed for application name PyTorch version 1.10.1
== 2022-01-17 17:50:05,327 pythonpackage.py:306 INFO Usin
@surak
surak / easybuild-PyTorch-1.11-20220117.175255.HXhVt.log
Created January 17, 2022 17:54
libtorch_cpu.so: undefined symbol: __kmpc_global_thread_num (this has CFLAGS=-fopenmp)
This file has been truncated, but you can view the full file.
== 2022-01-17 17:52:55,287 easyblock.py:303 INFO This is EasyBuild 4.5.1 (framework: 4.5.1, easyblocks: 4.5.1) on host jwlogin24.juwels.
== 2022-01-17 17:52:55,288 easyblock.py:309 INFO This is easyblock EB_PyTorch from module easybuild.easyblocks.pytorch (/p/software/juwelsbooster/stages/2022/software/EasyBuild/4.5.1/lib/python3.6/site-packages/easybuild/easyblocks/p/pytorch.py)
== 2022-01-17 17:52:55,288 easyblock.py:947 INFO Build dir set to /dev/shm/strube1/juwelsbooster/PyTorch/1.11/gcccoremkl-11.2.0-2021.4.0-CUDA-11.5
== 2022-01-17 17:52:55,288 easyblock.py:1004 INFO Software install dir set to /p/project/ccstao/cstao05/easybuild/juwelsbooster/software/PyTorch/1.11-gcccoremkl-11.2.0-2021.4.0-CUDA-11.5
== 2022-01-17 17:52:55,288 easyblock.py:1009 INFO Module install dir set to /p/project/ccstao/cstao05/easybuild/juwelsbooster/modules/all
== 2022-01-17 17:52:55,288 easyblock.py:278 INFO Init completed for application name PyTorch version 1.11
== 2022-01-17 17:52:55,289 pythonpackage.py:306 INFO Using defa
[5448/6571] Building CXX object test_cpp_c10d/CMakeFiles/FileStoreTest.dir/FileStoreTest.cpp.o
[5449/6571] Building CXX object caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/BinaryOpsKernel.cpp.AVX512.cpp.o
[5450/6571] Linking CXX shared library lib/libtorch_cpu.so
[5451/6571] Linking CXX executable bin/TCPStoreTest
[5452/6571] Linking CXX executable bin/FileStoreTest
[5453/6571] Linking CXX executable bin/HashStoreTest
[5454/6571] Building NVCC (Device) object caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/torch_cuda_generated_SegmentReduce.cu.o
FAILED: caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/torch_cuda_generated_SegmentReduce.cu.o /dev/shm/strube1/juwels/PyTorch/1.10.0/g
cccoremkl-11.2.0-2021.4.0-CUDA-11.5/pytorch/build/caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/torch_cuda_generated_SegmentReduce.cu.
o
@surak
surak / gist:bfdf681deebeeb625cfdc91e1ea2abb8
Created December 1, 2021 17:17
Pytorch 1.10 on easybuild
[2752/6571] Building CXX object third_party/ideep/mkl-dnn/src/common/CMakeFiles/dnnl_common.dir/primitive_cache.cpp.o
FAILED: third_party/ideep/mkl-dnn/src/common/CMakeFiles/dnnl_common.dir/primitive_cache.cpp.o
/p/software/juwels/stages/2022/software/GCCcore/11.2.0/bin/g++ -DDNNL_ENABLE_CONCURRENT_EXEC -DDNNL_ENABLE_CPU_ISA_HINTS -DDNNL_ENABLE_ITT_TASKS -DDNNL_ENABLE_MAX_CPU_ISA -DDNNL_X64=1 -DIDEEP_USE_MKL -DMAGMA_V2 -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx_torch -DTH_BLAS_MKL -D__STDC_CONSTANT_MACROS -D__STDC_LIMIT_MACROS -I/dev/shm/strube1/juwels/PyTorch/1.10.0/gcccoremkl-11.2.0-2021.4.0-CUDA-11.5/pytorch/cmake/../third_party/benchmark/include -I/dev/shm/strube1/juwels/PyTorch/1.10.0/gcccoremkl-11.2.0-2021.4.0-CUDA-11.5/pytorch/cmake/../third_party/cudnn_frontend/include -I/dev/shm/strube1/juwels/PyTorch/1.10.0/gcccoremkl-11.2.0-2021.4.0-CUDA-11.5/pytorch/build/caffe2/contrib/aten -I/dev/shm/strube1/juwels/PyTorch/1.10.0/gcccoremkl-11.2.0-2021.4.0-CUDA-11.5/pytorch/third_party/onnx -I/de
#
# Current EasyBuild configuration
# (C: command line argument, D: default value, E: environment variable, F: configuration file)
#
allow-loaded-modules (E) = EasyBuild
buildpath (E) = /dev/shm/strube1/juwels
containerpath (E) = /p/project/ccstao/cstao05/easybuild/juwels/containers
cuda-compute-capabilities (E) = 6.0, 7.0
detect-loaded-modules (E) = error
experimental (E) = True
== 2021-11-30 16:34:36,211 build_log.py:227 INFO This is EasyBuild 4.5.0 (framework: 4.5.0, easyblocks: 4.5.0) on host jwlogin05.juwels.
== 2021-11-30 16:34:36,256 build_log.py:230 INFO Command line: --allow-loaded-modules='EasyBuild' --buildpath='/dev/shm/strube1/juwels' --containerpath='/p/project/ccstao/cstao05/easybuild/juwels/containers' --cuda-compute-capabilities='6.0,7.0' --detect-loaded-modules='error' --experimental --hide-deps='ACTC,ANTLR,APR,APR-util,AT-SPI2-ATK,AT-SPI2-core,ATK,Autoconf,Automake,Bison,CUSP,Coreutils,CubeWriter,DB,DBus,DocBook-XML,Dyninst,ETSF_IO,Exiv2,FFmpeg,FLTK,FTGL,FoX,GCCcore,GEGL,GL2PS,GLEW,GLM,GLPK,GLib,GObject-Introspection,GPC,GTI,GTK+,GTS,Gdk-Pixbuf,Ghostscript,GraphicsMagick,GtkSourceView,HarfBuzz,ICU,JSON-C,JSON-GLib,JUnit,JasPer,JsonCpp,JupyterKernel-Bash,JupyterKernel-Cling,JupyterKernel-JavaScript,JupyterKernel-Julia,JupyterKernel-Octave,JupyterKernel-PyDeepLearning,JupyterKernel-PyParaView,JupyterKernel-PyQuantum,JupyterKernel-R,JupyterKernel-Ruby,JupyterProxy-Matl
== 2021-08-23 02:50:27,894 tensorflow.py:963 INFO Starting cpu test
== 2021-08-23 02:50:27,894 run.py:172 INFO Auto-enabling streaming output of 'bazel --output_user_root=/p/scratch/hai_consultantfzj/strube1/TensorFlow/2.5.0/gcccoremkl-10.3.0-2021.2.0-Python-3.8.5/tmp3dcfr05a-bazel-tf --host_jvm_args=-Xms512m --host_jvm_args=-Xmx4096m test --config=noaws --config=nogcp --config=nohdfs --compilation_mode=opt --config=opt --subcommands --verbose_failures --jobs=40 --copt="-fPIC" --action_env=CPATH='/p/software/juwels/stages/Devel-2020/software/cURL/7.71.1
-GCCcore-10.3.0/include:/p/software/juwels/stages/Devel-2020/software/double-conversion/3.1.5-GCCcore-10.3.0/include:/p/software/juwels/stages/Devel-2020/software/flatbuffers/2.0.0-GCCcore-10.3.0/include:/p/software/juwels/stages/Devel-2020/software/giflib/5.2.1-GCCcore-10.3.0/include:/p/software/juwels/stages/Devel-2020/software/hwloc/2.4.1-GCCcore-10.3.0/include:/p/software/juwels/stages/Devel-2020/software/ICU/67.1-GCCcore-10.3.0/include:/p/software/juwels/