forked from pytorch/pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
config.yml
9516 lines (9358 loc) · 349 KB
/
config.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# WARNING: DO NOT EDIT THIS FILE DIRECTLY!!!
# See the README.md in this directory.
# IMPORTANT: To update Docker image version, please follow
# the instructions at
# https://github.com/pytorch/pytorch/wiki/Docker-image-build-on-CircleCI
version: 2.1
parameters:
run_binary_tests:
type: boolean
default: false
run_build:
type: boolean
default: true
run_master_build:
type: boolean
default: false
run_slow_gradcheck_build:
type: boolean
default: false
executors:
windows-with-nvidia-gpu:
machine:
resource_class: windows.gpu.nvidia.medium
image: windows-server-2019-nvidia:previous
shell: bash.exe
windows-xlarge-cpu-with-nvidia-cuda:
machine:
resource_class: windows.xlarge
image: windows-server-2019-vs2019:stable
shell: bash.exe
windows-medium-cpu-with-nvidia-cuda:
machine:
resource_class: windows.medium
image: windows-server-2019-vs2019:stable
shell: bash.exe
commands:
calculate_docker_image_tag:
description: "Calculates the docker image tag"
steps:
- run:
name: "Calculate docker image hash"
command: |
DOCKER_TAG=$(git rev-parse HEAD:.circleci/docker)
echo "DOCKER_TAG=${DOCKER_TAG}" >> "${BASH_ENV}"
designate_upload_channel:
description: "inserts the correct upload channel into ${BASH_ENV}"
steps:
- run:
name: adding UPLOAD_CHANNEL to BASH_ENV
command: |
our_upload_channel=nightly
# On tags upload to test instead
if [[ -n "${CIRCLE_TAG}" ]]; then
our_upload_channel=test
fi
echo "export UPLOAD_CHANNEL=${our_upload_channel}" >> ${BASH_ENV}
# This system setup script is meant to run before the CI-related scripts, e.g.,
# installing Git client, checking out code, setting up CI env, and
# building/testing.
setup_linux_system_environment:
steps:
- run:
name: Set Up System Environment
no_output_timeout: "1h"
command: .circleci/scripts/setup_linux_system_environment.sh
setup_ci_environment:
steps:
- run:
name: Set Up CI Environment After attach_workspace
no_output_timeout: "1h"
command: .circleci/scripts/setup_ci_environment.sh
brew_update:
description: "Update Homebrew and install base formulae"
steps:
- run:
name: Update Homebrew
no_output_timeout: "10m"
command: |
set -ex
# Update repositories manually.
# Running `brew update` produces a comparison between the
# current checkout and the updated checkout, which takes a
# very long time because the existing checkout is 2y old.
for path in $(find /usr/local/Homebrew -type d -name .git)
do
cd $path/..
git fetch --depth=1 origin
git reset --hard origin/master
done
export HOMEBREW_NO_AUTO_UPDATE=1
# Install expect and moreutils so that we can call `unbuffer` and `ts`.
# moreutils installs a `parallel` executable by default, which conflicts
# with the executable from the GNU `parallel`, so we must unlink GNU
# `parallel` first, and relink it afterwards.
brew unlink parallel
brew install moreutils
brew link parallel --overwrite
brew install expect
brew_install:
description: "Install Homebrew formulae"
parameters:
formulae:
type: string
default: ""
steps:
- run:
name: Install << parameters.formulae >>
no_output_timeout: "10m"
command: |
set -ex
export HOMEBREW_NO_AUTO_UPDATE=1
brew install << parameters.formulae >>
run_brew_for_macos_build:
steps:
- brew_update
- brew_install:
formulae: libomp
run_brew_for_ios_build:
steps:
- brew_update
- brew_install:
formulae: libtool
optional_merge_target_branch:
steps:
- run:
name: (Optional) Merge target branch
no_output_timeout: "10m"
command: |
if [[ -n "$CIRCLE_PULL_REQUEST" && "$CIRCLE_BRANCH" != "nightly" ]]; then
PR_NUM=$(basename $CIRCLE_PULL_REQUEST)
CIRCLE_PR_BASE_BRANCH=$(curl -s https://api.github.com/repos/$CIRCLE_PROJECT_USERNAME/$CIRCLE_PROJECT_REPONAME/pulls/$PR_NUM | jq -r '.base.ref')
if [[ "${BUILD_ENVIRONMENT}" == *"xla"* || "${BUILD_ENVIRONMENT}" == *"gcc5"* ]] ; then
set -x
git config --global user.email "[email protected]"
git config --global user.name "CircleCI"
git config remote.origin.url https://github.com/pytorch/pytorch.git
git config --add remote.origin.fetch +refs/heads/master:refs/remotes/origin/master
git fetch --tags --progress https://github.com/pytorch/pytorch.git +refs/heads/master:refs/remotes/origin/master --depth=100 --quiet
# PRs generated from ghstack has format CIRCLE_PR_BASE_BRANCH=gh/xxx/1234/base
if [[ "${CIRCLE_PR_BASE_BRANCH}" == "gh/"* ]]; then
CIRCLE_PR_BASE_BRANCH=master
fi
export GIT_MERGE_TARGET=`git log -n 1 --pretty=format:"%H" origin/$CIRCLE_PR_BASE_BRANCH`
echo "GIT_MERGE_TARGET: " ${GIT_MERGE_TARGET}
export GIT_COMMIT=${CIRCLE_SHA1}
echo "GIT_COMMIT: " ${GIT_COMMIT}
git checkout -f ${GIT_COMMIT}
git reset --hard ${GIT_COMMIT}
git merge --allow-unrelated-histories --no-edit --no-ff ${GIT_MERGE_TARGET}
echo "Merged $CIRCLE_PR_BASE_BRANCH branch before building in environment $BUILD_ENVIRONMENT"
set +x
else
echo "No need to merge with $CIRCLE_PR_BASE_BRANCH, skipping..."
fi
else
echo "This is not a pull request, skipping..."
fi
upload_binary_size_for_android_build:
description: "Upload binary size data for Android build"
parameters:
build_type:
type: string
default: ""
artifacts:
type: string
default: ""
steps:
- run:
name: "Binary Size - Install Dependencies"
no_output_timeout: "5m"
command: |
retry () {
$* || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
}
retry pip3 install requests
- run:
name: "Binary Size - Untar Artifacts"
no_output_timeout: "5m"
command: |
# The artifact file is created inside docker container, which contains the result binaries.
# Now unpackage it into the project folder. The subsequent script will scan project folder
# to locate result binaries and report their sizes.
# If artifact file is not provided it assumes that the project folder has been mounted in
# the docker during build and already contains the result binaries, so this step can be skipped.
export ARTIFACTS="<< parameters.artifacts >>"
if [ -n "${ARTIFACTS}" ]; then
tar xf "${ARTIFACTS}" -C ~/project
fi
- run:
name: "Binary Size - Upload << parameters.build_type >>"
no_output_timeout: "5m"
command: |
cd ~/project
export ANDROID_BUILD_TYPE="<< parameters.build_type >>"
export COMMIT_TIME=$(git log --max-count=1 --format=%ct || echo 0)
python3 .circleci/scripts/upload_binary_size_to_scuba.py android
##############################################################################
# Binary build (nightlies nightly build) defaults
# The binary builds use the docker executor b/c at time of writing the machine
# executor is limited to only two cores and is painfully slow (4.5+ hours per
# GPU build). But the docker executor cannot be run with --runtime=nvidia, and
# so the binary test/upload jobs must run on a machine executor. The package
# built in the build job is persisted to the workspace, which the test jobs
# expect. The test jobs just run a few quick smoke tests (very similar to the
# second-round-user-facing smoke tests above) and then upload the binaries to
# their final locations. The upload part requires credentials that should only
# be available to org-members.
#
# binary_checkout MUST be run before other commands here. This is because the
# other commands are written in .circleci/scripts/*.sh , so the pytorch source
# code must be downloaded on the machine before they can be run. We cannot
# inline all the code into this file, since that would cause the yaml size to
# explode past 4 MB (all the code in the command section is just copy-pasted to
# everywhere in the .circleci/config.yml file where it appears).
##############################################################################
# Checks out the Pytorch and Builder repos (always both of them), and places
# them in the right place depending on what executor we're running on. We curl
# our .sh file from the interweb to avoid yaml size bloat. Note that many jobs
# do not need both the pytorch and builder repos, so this is a little wasteful
# (smoke tests and upload jobs do not need the pytorch repo).
binary_checkout: &binary_checkout
name: Checkout pytorch/builder repo
command: .circleci/scripts/binary_checkout.sh
# Parses circleci arguments in a consistent way, essentially routing to the
# correct pythonXgccXcudaXos build we want
binary_populate_env: &binary_populate_env
name: Set up binary env variables
command: .circleci/scripts/binary_populate_env.sh
binary_install_miniconda: &binary_install_miniconda
name: Install miniconda
no_output_timeout: "1h"
command: .circleci/scripts/binary_install_miniconda.sh
# This section is used in the binary_test and smoke_test jobs. It expects
# 'binary_populate_env' to have populated /home/circleci/project/env and it
# expects another section to populate /home/circleci/project/ci_test_script.sh
# with the code to run in the docker
binary_run_in_docker: &binary_run_in_docker
name: Run in docker
# This step only runs on circleci linux machine executors that themselves
# need to start docker images
command: .circleci/scripts/binary_run_in_docker.sh
##############################################################################
# Build parameters
##############################################################################
pytorch_params: &pytorch_params
parameters:
build_environment:
type: string
default: ""
docker_image:
type: string
default: ""
resource_class:
type: string
default: "large"
use_cuda_docker_runtime:
type: string
default: ""
build_only:
type: string
default: ""
environment:
BUILD_ENVIRONMENT: << parameters.build_environment >>
DOCKER_IMAGE: << parameters.docker_image >>
USE_CUDA_DOCKER_RUNTIME: << parameters.use_cuda_docker_runtime >>
BUILD_ONLY: << parameters.build_only >>
resource_class: << parameters.resource_class >>
pytorch_android_params: &pytorch_android_params
parameters:
build_environment:
type: string
default: ""
op_list:
type: string
default: ""
lite_interpreter:
type: string
default: "1"
environment:
BUILD_ENVIRONMENT: pytorch-linux-xenial-py3-clang5-android-ndk-r19c-gradle-custom-build-single
DOCKER_IMAGE: "308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-py3-clang5-android-ndk-r19c"
PYTHON_VERSION: "3.6"
SELECTED_OP_LIST: << parameters.op_list >>
BUILD_LITE_INTERPRETER: << parameters.lite_interpreter >>
pytorch_ios_params: &pytorch_ios_params
parameters:
build_environment:
type: string
default: ""
ios_arch:
type: string
default: ""
ios_platform:
type: string
default: ""
op_list:
type: string
default: ""
use_metal:
type: string
default: "0"
lite_interpreter:
type: string
default: "1"
environment:
BUILD_ENVIRONMENT: << parameters.build_environment >>
IOS_ARCH: << parameters.ios_arch >>
IOS_PLATFORM: << parameters.ios_platform >>
SELECTED_OP_LIST: << parameters.op_list >>
USE_PYTORCH_METAL: << parameters.use_metal >>
BUILD_LITE_INTERPRETER: << parameters.lite_interpreter >>
pytorch_windows_params: &pytorch_windows_params
parameters:
executor:
type: string
default: "windows-xlarge-cpu-with-nvidia-cuda"
build_environment:
type: string
default: ""
test_name:
type: string
default: ""
cuda_version:
type: string
default: "10.1"
python_version:
type: string
default: "3.8"
vc_version:
type: string
default: "14.16"
vc_year:
type: string
default: "2019"
vc_product:
type: string
default: "BuildTools"
use_cuda:
type: string
default: ""
environment:
BUILD_ENVIRONMENT: <<parameters.build_environment>>
SCCACHE_BUCKET: "ossci-compiler-cache"
CUDA_VERSION: <<parameters.cuda_version>>
PYTHON_VERSION: <<parameters.python_version>>
VC_VERSION: <<parameters.vc_version>>
VC_YEAR: <<parameters.vc_year>>
VC_PRODUCT: <<parameters.vc_product>>
USE_CUDA: <<parameters.use_cuda>>
TORCH_CUDA_ARCH_LIST: "5.2 7.5"
JOB_BASE_NAME: <<parameters.test_name>>
JOB_EXECUTOR: <<parameters.executor>>
binary_linux_build_params: &binary_linux_build_params
parameters:
build_environment:
type: string
default: ""
docker_image:
type: string
default: ""
libtorch_variant:
type: string
default: ""
resource_class:
type: string
default: "2xlarge+"
environment:
BUILD_ENVIRONMENT: << parameters.build_environment >>
LIBTORCH_VARIANT: << parameters.libtorch_variant >>
ANACONDA_USER: pytorch
resource_class: << parameters.resource_class >>
docker:
- image: << parameters.docker_image >>
binary_linux_test_upload_params: &binary_linux_test_upload_params
parameters:
build_environment:
type: string
default: ""
docker_image:
type: string
default: ""
libtorch_variant:
type: string
default: ""
resource_class:
type: string
default: "medium"
use_cuda_docker_runtime:
type: string
default: ""
environment:
BUILD_ENVIRONMENT: << parameters.build_environment >>
DOCKER_IMAGE: << parameters.docker_image >>
USE_CUDA_DOCKER_RUNTIME: << parameters.use_cuda_docker_runtime >>
LIBTORCH_VARIANT: << parameters.libtorch_variant >>
resource_class: << parameters.resource_class >>
binary_mac_params: &binary_mac_params
parameters:
build_environment:
type: string
default: ""
environment:
BUILD_ENVIRONMENT: << parameters.build_environment >>
binary_windows_params: &binary_windows_params
parameters:
build_environment:
type: string
default: ""
executor:
type: string
default: "windows-xlarge-cpu-with-nvidia-cuda"
environment:
BUILD_ENVIRONMENT: << parameters.build_environment >>
BUILD_FOR_SYSTEM: windows
JOB_EXECUTOR: <<parameters.executor>>
promote_common: &promote_common
docker:
- image: pytorch/release
parameters:
package_name:
description: "package name to promote"
type: string
default: ""
environment:
PACKAGE_NAME: << parameters.package_name >>
ANACONDA_API_TOKEN: ${CONDA_PYTORCHBOT_TOKEN}
AWS_ACCESS_KEY_ID: ${PYTORCH_BINARY_AWS_ACCESS_KEY_ID}
AWS_SECRET_ACCESS_KEY: ${PYTORCH_BINARY_AWS_SECRET_ACCESS_KEY}
##############################################################################
# Job specs
##############################################################################
jobs:
pytorch_linux_build:
<<: *pytorch_params
machine:
image: ubuntu-2004:202104-01
steps:
# See Note [Workspace for CircleCI scripts] in job-specs-setup.yml
- checkout
- calculate_docker_image_tag
- setup_linux_system_environment
- optional_merge_target_branch
- setup_ci_environment
- run:
name: Build
no_output_timeout: "1h"
command: |
set -e
if [[ ${BUILD_ENVIRONMENT} == *"pure_torch"* ]]; then
echo 'BUILD_CAFFE2=OFF' >> "${BASH_ENV}"
fi
if [[ ${BUILD_ENVIRONMENT} == *"paralleltbb"* ]]; then
echo 'ATEN_THREADING=TBB' >> "${BASH_ENV}"
echo 'USE_TBB=1' >> "${BASH_ENV}"
elif [[ ${BUILD_ENVIRONMENT} == *"parallelnative"* ]]; then
echo 'ATEN_THREADING=NATIVE' >> "${BASH_ENV}"
fi
echo "Parallel backend flags: "${PARALLEL_FLAGS}
# Pull Docker image and run build
echo "DOCKER_IMAGE: "${DOCKER_IMAGE}:${DOCKER_TAG}
time docker pull ${DOCKER_IMAGE}:${DOCKER_TAG} >/dev/null
export id=$(docker run --env-file "${BASH_ENV}" --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -t -d -w /var/lib/jenkins ${DOCKER_IMAGE}:${DOCKER_TAG})
git submodule sync && git submodule update -q --init --recursive --depth 1
docker cp /home/circleci/project/. $id:/var/lib/jenkins/workspace
export COMMAND='((echo "sudo chown -R jenkins workspace && export JOB_BASE_NAME="$CIRCLE_JOB" && cd workspace && .jenkins/pytorch/build.sh && find ${BUILD_ROOT} -type f -name "*.a" -or -name "*.o" -delete") | docker exec -u jenkins -i "$id" bash) 2>&1'
echo ${COMMAND} > ./command.sh && unbuffer bash ./command.sh | ts
# Copy dist folder back
docker cp $id:/var/lib/jenkins/workspace/dist /home/circleci/project/. || echo "Dist folder not found"
# Push intermediate Docker image for next phase to use
if [ -z "${BUILD_ONLY}" ]; then
# Note [Special build images]
# The xla build uses the same docker image as
# pytorch_linux_bionic_py3_6_clang9_build. In the push step, we have to
# distinguish between them so the test can pick up the correct image.
output_image=${DOCKER_IMAGE}:${DOCKER_TAG}-${CIRCLE_SHA1}
if [[ ${BUILD_ENVIRONMENT} == *"xla"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-xla
elif [[ ${BUILD_ENVIRONMENT} == *"libtorch"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-libtorch
elif [[ ${BUILD_ENVIRONMENT} == *"paralleltbb"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-paralleltbb
elif [[ ${BUILD_ENVIRONMENT} == *"parallelnative"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-parallelnative
elif [[ ${BUILD_ENVIRONMENT} == *"android-ndk-r19c-x86_64"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-android-x86_64
elif [[ ${BUILD_ENVIRONMENT} == *"android-ndk-r19c-arm-v7a"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-android-arm-v7a
elif [[ ${BUILD_ENVIRONMENT} == *"android-ndk-r19c-arm-v8a"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-android-arm-v8a
elif [[ ${BUILD_ENVIRONMENT} == *"android-ndk-r19c-x86_32"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-android-x86_32
elif [[ ${BUILD_ENVIRONMENT} == *"android-ndk-r19c-vulkan-x86_32"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-android-vulkan-x86_32
elif [[ ${BUILD_ENVIRONMENT} == *"vulkan-linux"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-vulkan
else
export COMMIT_DOCKER_IMAGE=$output_image
fi
docker commit "$id" ${COMMIT_DOCKER_IMAGE}
time docker push ${COMMIT_DOCKER_IMAGE}
fi
- run:
name: upload build & binary data
no_output_timeout: "5m"
command: |
cd /pytorch && export COMMIT_TIME=$(git log --max-count=1 --format=%ct || echo 0)
python3 -mpip install requests && \
SCRIBE_GRAPHQL_ACCESS_TOKEN=${SCRIBE_GRAPHQL_ACCESS_TOKEN} \
python3 .circleci/scripts/upload_binary_size_to_scuba.py || exit 0
- store_artifacts:
path: /home/circleci/project/dist
pytorch_linux_test:
<<: *pytorch_params
machine:
image: ubuntu-2004:202104-01
steps:
# See Note [Workspace for CircleCI scripts] in job-specs-setup.yml
- checkout
- calculate_docker_image_tag
- setup_linux_system_environment
- setup_ci_environment
- run:
name: Download Docker image
no_output_timeout: "90m"
command: |
set -e
export PYTHONUNBUFFERED=1
if [[ "${DOCKER_IMAGE}" == *rocm3.9* ]]; then
export DOCKER_TAG="f3d89a32912f62815e4feaeed47e564e887dffd6"
fi
# See Note [Special build images]
output_image=${DOCKER_IMAGE}:${DOCKER_TAG}-${CIRCLE_SHA1}
if [[ ${BUILD_ENVIRONMENT} == *"xla"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-xla
elif [[ ${BUILD_ENVIRONMENT} == *"libtorch"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-libtorch
elif [[ ${BUILD_ENVIRONMENT} == *"paralleltbb"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-paralleltbb
elif [[ ${BUILD_ENVIRONMENT} == *"parallelnative"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-parallelnative
elif [[ ${BUILD_ENVIRONMENT} == *"vulkan-linux"* ]]; then
export COMMIT_DOCKER_IMAGE=$output_image-vulkan
else
export COMMIT_DOCKER_IMAGE=$output_image
fi
echo "DOCKER_IMAGE: "${COMMIT_DOCKER_IMAGE}
if [[ ${BUILD_ENVIRONMENT} == *"paralleltbb"* ]]; then
echo 'ATEN_THREADING=TBB' >> "${BASH_ENV}"
echo 'USE_TBB=1' >> "${BASH_ENV}"
elif [[ ${BUILD_ENVIRONMENT} == *"parallelnative"* ]]; then
echo 'ATEN_THREADING=NATIVE' >> "${BASH_ENV}"
fi
echo "Parallel backend flags: "${PARALLEL_FLAGS}
time docker pull ${COMMIT_DOCKER_IMAGE} >/dev/null
# TODO: Make this less painful
if [ -n "${USE_CUDA_DOCKER_RUNTIME}" ]; then
export id=$(docker run --env-file "${BASH_ENV}" --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --gpus all --shm-size=2g -t -d -w /var/lib/jenkins ${COMMIT_DOCKER_IMAGE})
elif [[ ${BUILD_ENVIRONMENT} == *"rocm"* ]]; then
hostname
export id=$(docker run --env-file "${BASH_ENV}" --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --shm-size=8g --ipc=host --device /dev/kfd --device /dev/dri --group-add video -t -d -w /var/lib/jenkins ${COMMIT_DOCKER_IMAGE})
else
export id=$(docker run --env-file "${BASH_ENV}" --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --shm-size=1g --ipc=host -t -d -w /var/lib/jenkins ${COMMIT_DOCKER_IMAGE})
fi
echo "id=${id}" >> "${BASH_ENV}"
- run:
name: Check for no AVX instruction by default
no_output_timeout: "20m"
command: |
set -e
is_vanilla_build() {
if [ "${BUILD_ENVIRONMENT}" == "pytorch-linux-bionic-py3.6-clang9-test" ]; then
return 0
fi
if [ "${BUILD_ENVIRONMENT}" == "pytorch-linux-xenial-py3.6-gcc5.4-test" ]; then
return 0
fi
return 1
}
if is_vanilla_build; then
echo "apt-get update && apt-get install -y qemu-user gdb" | docker exec -u root -i "$id" bash
echo "cd workspace/build; qemu-x86_64 -g 2345 -cpu Broadwell -E ATEN_CPU_CAPABILITY=default ./bin/basic --gtest_filter=BasicTest.BasicTestCPU & gdb ./bin/basic -ex 'set pagination off' -ex 'target remote :2345' -ex 'continue' -ex 'bt' -ex='set confirm off' -ex 'quit \$_isvoid(\$_exitcode)'" | docker exec -u jenkins -i "$id" bash
else
echo "Skipping for ${BUILD_ENVIRONMENT}"
fi
- run:
name: Run tests
no_output_timeout: "90m"
command: |
set -e
cat >docker_commands.sh \<<EOL
# =================== The following code will be executed inside Docker container ===================
set -ex
export SCRIBE_GRAPHQL_ACCESS_TOKEN="${SCRIBE_GRAPHQL_ACCESS_TOKEN}"
export JOB_BASE_NAME="$CIRCLE_JOB"
${PARALLEL_FLAGS}
cd workspace
EOL
if [[ ${BUILD_ENVIRONMENT} == *"multigpu"* ]]; then
echo ".jenkins/pytorch/multigpu-test.sh" >> docker_commands.sh
elif [[ ${BUILD_ENVIRONMENT} == *onnx* ]]; then
echo "pip install click mock tabulate networkx==2.0" >> docker_commands.sh
echo "pip -q install --user \"file:///var/lib/jenkins/workspace/third_party/onnx#egg=onnx\"" >> docker_commands.sh
echo ".jenkins/caffe2/test.sh" >> docker_commands.sh
else
echo ".jenkins/pytorch/test.sh" >> docker_commands.sh
fi
echo "(cat docker_commands.sh | docker exec -u jenkins -i "$id" bash) 2>&1" > command.sh
unbuffer bash command.sh | ts
if [[ ${BUILD_ENVIRONMENT} == *"coverage"* ]]; then
echo "Retrieving C++ coverage report"
docker cp $id:/var/lib/jenkins/workspace/build/coverage.info ./test
fi
if [[ ${BUILD_ENVIRONMENT} == *"coverage"* || ${BUILD_ENVIRONMENT} == *"onnx"* ]]; then
echo "Retrieving Python coverage report"
docker cp $id:/var/lib/jenkins/workspace/test/.coverage ./test
docker cp $id:/var/lib/jenkins/workspace/test/coverage.xml ./test
python3 -mpip install codecov
python3 -mcodecov
fi
- run:
name: Report results
no_output_timeout: "5m"
command: |
set -e
# Retrieving test results should be done as very first step as command never fails
# But is always executed if previous step fails for some reason
echo "Retrieving test reports"
docker cp $id:/var/lib/jenkins/workspace/test/test-reports ./ || echo 'No test reports found!'
docker stats --all --no-stream
cat >docker_commands.sh \<<EOL
# =================== The following code will be executed inside Docker container ===================
set -ex
export BUILD_ENVIRONMENT=${BUILD_ENVIRONMENT}
export SCRIBE_GRAPHQL_ACCESS_TOKEN="${SCRIBE_GRAPHQL_ACCESS_TOKEN}"
export CIRCLE_TAG="${CIRCLE_TAG:-}"
export CIRCLE_SHA1="$CIRCLE_SHA1"
export CIRCLE_PR_NUMBER="${CIRCLE_PR_NUMBER:-}"
export CIRCLE_BRANCH="$CIRCLE_BRANCH"
export JOB_BASE_NAME="$CIRCLE_JOB"
export CIRCLE_WORKFLOW_ID="$CIRCLE_WORKFLOW_ID"
cd workspace
export PYTHONPATH="\${PWD}"
python tools/print_test_stats.py --upload-to-s3 --compare-with-s3 test
EOL
echo "(cat docker_commands.sh | docker exec -u jenkins -e LANG=C.UTF-8 -i "$id" bash) 2>&1" > command.sh
unbuffer bash command.sh | ts
when: always
- store_test_results:
path: test-reports
- store_artifacts:
path: test/.coverage
- store_artifacts:
path: test/coverage.xml
pytorch_windows_build:
<<: *pytorch_windows_params
parameters:
executor:
type: string
default: "windows-xlarge-cpu-with-nvidia-cuda"
build_environment:
type: string
default: ""
test_name:
type: string
default: ""
cuda_version:
type: string
default: "10.1"
python_version:
type: string
default: "3.8"
vc_version:
type: string
default: "14.16"
vc_year:
type: string
default: "2019"
vc_product:
type: string
default: "BuildTools"
use_cuda:
type: string
default: ""
executor: <<parameters.executor>>
steps:
- checkout
- run:
name: Install VS2019 toolchain
no_output_timeout: 10m
command: |
powershell .circleci/scripts/vs_install.ps1
- run:
name: Install Cuda
no_output_timeout: 30m
command: |
if [[ "${USE_CUDA}" == "1" ]]; then
.circleci/scripts/windows_cuda_install.sh
fi
- run:
name: Install Cudnn
command : |
if [[ "${USE_CUDA}" == "1" ]]; then
.circleci/scripts/windows_cudnn_install.sh
fi
- run:
name: Build
no_output_timeout: "90m"
command: |
set -e
set +x
export AWS_ACCESS_KEY_ID=${CIRCLECI_AWS_ACCESS_KEY_FOR_WIN_BUILD_V1}
export AWS_SECRET_ACCESS_KEY=${CIRCLECI_AWS_SECRET_KEY_FOR_WIN_BUILD_V1}
set -x
.jenkins/pytorch/win-build.sh
- persist_to_workspace:
root: "C:/w"
paths: build-results
- store_artifacts:
path: C:/w/build-results
pytorch_windows_test:
<<: *pytorch_windows_params
parameters:
executor:
type: string
default: "windows-medium-cpu-with-nvidia-cuda"
build_environment:
type: string
default: ""
test_name:
type: string
default: ""
cuda_version:
type: string
default: "10.1"
python_version:
type: string
default: "3.8"
vc_version:
type: string
default: "14.16"
vc_year:
type: string
default: "2019"
vc_product:
type: string
default: "BuildTools"
use_cuda:
type: string
default: ""
executor: <<parameters.executor>>
steps:
- checkout
- attach_workspace:
at: c:/users/circleci/workspace
- run:
name: Install VS2019 toolchain
no_output_timeout: 10m
command: |
powershell .circleci/scripts/vs_install.ps1
- run:
name: Install Cuda
no_output_timeout: 30m
command: |
if [[ "${CUDA_VERSION}" != "cpu" ]]; then
if [[ "${CUDA_VERSION}" != "10" || "${JOB_EXECUTOR}" != "windows-with-nvidia-gpu" ]]; then
.circleci/scripts/windows_cuda_install.sh
fi
fi
- run:
name: Install Cudnn
command : |
if [[ "${CUDA_VERSION}" != "cpu" ]]; then
.circleci/scripts/windows_cudnn_install.sh
fi
- run:
name: Test
no_output_timeout: "30m"
command: |
set -e
export IN_CI=1
set +x
export AWS_ACCESS_KEY_ID=${CIRCLECI_AWS_ACCESS_KEY_FOR_WIN_BUILD_V1}
export AWS_SECRET_ACCESS_KEY=${CIRCLECI_AWS_SECRET_KEY_FOR_WIN_BUILD_V1}
set -x
.jenkins/pytorch/win-test.sh
- run:
name: Report results
no_output_timeout: "5m"
command: |
set -ex
export AWS_ACCESS_KEY_ID=${CIRCLECI_AWS_ACCESS_KEY_FOR_WIN_BUILD_V1}
export AWS_SECRET_ACCESS_KEY=${CIRCLECI_AWS_SECRET_KEY_FOR_WIN_BUILD_V1}
export PYTHONPATH="$PWD"
pip install typing_extensions boto3
python tools/print_test_stats.py --upload-to-s3 --compare-with-s3 test
when: always
- store_test_results:
path: test/test-reports
- store_artifacts:
path: test/coverage.xml
binary_linux_build:
<<: *binary_linux_build_params
steps:
- checkout
- calculate_docker_image_tag
- run:
<<: *binary_checkout
- run:
<<: *binary_populate_env
- run:
name: Build
no_output_timeout: "1h"
command: |
source "/pytorch/.circleci/scripts/binary_linux_build.sh"
# Preserve build log
if [ -f /pytorch/build/.ninja_log ]; then
cp /pytorch/build/.ninja_log /final_pkgs
fi
- run:
name: Output binary sizes
no_output_timeout: "1m"
command: |
ls -lah /final_pkgs
- run:
name: upload build & binary data
no_output_timeout: "5m"
command: |
source /env
cd /pytorch && export COMMIT_TIME=$(git log --max-count=1 --format=%ct || echo 0)
python3 -mpip install requests && \
SCRIBE_GRAPHQL_ACCESS_TOKEN=${SCRIBE_GRAPHQL_ACCESS_TOKEN} \
python3 /pytorch/.circleci/scripts/upload_binary_size_to_scuba.py || exit 0
- persist_to_workspace:
root: /
paths: final_pkgs
- store_artifacts:
path: /final_pkgs
# This should really just be another step of the binary_linux_build job above.
# This isn't possible right now b/c the build job uses the docker executor
# (otherwise they'd be really really slow) but this one uses the macine
# executor (b/c we have to run the docker with --runtime=nvidia and we can't do
# that on the docker executor)
binary_linux_test:
<<: *binary_linux_test_upload_params
machine:
image: ubuntu-2004:202104-01
steps:
# See Note [Workspace for CircleCI scripts] in job-specs-setup.yml
- checkout
- attach_workspace:
at: /home/circleci/project
- setup_linux_system_environment
- setup_ci_environment
- run:
<<: *binary_checkout
- run:
<<: *binary_populate_env
- run:
name: Prepare test code
no_output_timeout: "1h"
command: .circleci/scripts/binary_linux_test.sh
- run:
<<: *binary_run_in_docker
binary_upload:
parameters:
package_type:
type: string
description: "What type of package we are uploading (eg. wheel, libtorch, conda)"
default: "wheel"
upload_subfolder:
type: string
description: "What subfolder to put our package into (eg. cpu, cudaX.Y, etc.)"
default: "cpu"
docker:
- image: continuumio/miniconda3
environment:
- DRY_RUN: disabled
- PACKAGE_TYPE: "<< parameters.package_type >>"
- UPLOAD_SUBFOLDER: "<< parameters.upload_subfolder >>"
steps:
- attach_workspace:
at: /tmp/workspace
- checkout
- designate_upload_channel
- run:
name: Install dependencies
no_output_timeout: "1h"
command: |
conda install -yq anaconda-client
pip install -q awscli
- run:
name: Do upload
no_output_timeout: "1h"
command: |
AWS_ACCESS_KEY_ID="${PYTORCH_BINARY_AWS_ACCESS_KEY_ID}" \
AWS_SECRET_ACCESS_KEY="${PYTORCH_BINARY_AWS_SECRET_ACCESS_KEY}" \
ANACONDA_API_TOKEN="${CONDA_PYTORCHBOT_TOKEN}" \
.circleci/scripts/binary_upload.sh
# Nighlty build smoke tests defaults
# These are the second-round smoke tests. These make sure that the binaries are
# correct from a user perspective, testing that they exist from the cloud are
# are runnable. Note that the pytorch repo is never cloned into these jobs
##############################################################################
smoke_linux_test:
<<: *binary_linux_test_upload_params
machine:
image: ubuntu-2004:202104-01
steps:
- checkout
- calculate_docker_image_tag
- setup_linux_system_environment
- setup_ci_environment
- run:
<<: *binary_checkout
- run:
<<: *binary_populate_env
- run:
name: Test
no_output_timeout: "1h"
command: |
set -ex
cat >/home/circleci/project/ci_test_script.sh \<<EOL
# The following code will be executed inside Docker container
set -eux -o pipefail
/builder/smoke_test.sh
# The above code will be executed inside Docker container
EOL
- run:
<<: *binary_run_in_docker
smoke_mac_test:
<<: *binary_linux_test_upload_params
macos:
xcode: "12.0"
steps:
- checkout
- run:
<<: *binary_checkout
- run:
<<: *binary_populate_env
- brew_update
- run:
<<: *binary_install_miniconda
- run:
name: Build
no_output_timeout: "1h"
command: |
set -ex