Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

consistent_squeeze_stack_stateful_kernel_with_cache_test #7289

Merged
merged 79 commits into from
Mar 24, 2022
Merged

consistent_squeeze_stack_stateful_kernel_with_cache_test #7289

merged 79 commits into from
Mar 24, 2022

Conversation

clackhan
Copy link
Contributor

添加squeeze、stack和stateful_kernel_with_cache consistent测试

hjchen2 and others added 30 commits January 5, 2022 18:42
@hjchen2
add doc for pybind type
1743bf0
@hjchen2
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow
b1ff4b2
@hjchen2
eager consistent autotest
31359f1
@hjchen2
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow into …
93aaed9 
…dev_eager_consistent_auto_test
@hjchen2
align placement repr and api
68534be
@hjchen2
export necessary apis to pickle object
4fc1196
@hjchen2
broadcast rank 0 to other rank if consistent test
d191ce6
@hjchen2
update consistent add unittest
4077b86
@hjchen2
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow into …
af19043 
…dev_eager_consistent_auto_test
@hjchen2
refine
3c30177
@hjchen2
Merge branch 'master' of https://github.com/Oneflow-Inc/oneflow into …
ce63e4f 
…dev_eager_consistent_auto_test
@hjchen2
Merge branch 'master' into dev_eager_consistent_auto_test
355e251
@hjchen2
add concat tests
3fc646f
@hjchen2
Merge branch 'dev_eager_consistent_auto_test' of https://github.com/O…
198368c 
…neflow-Inc/oneflow into dev_eager_consistent_auto_test
@hjchen2
Merge branch 'master' into dev_eager_consistent_auto_test
93f7bb7
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
23220f3
@hjchen2
Merge branch 'master' into dev_eager_consistent_auto_test
dfa286d
@hjchen2
refine
4fe7c9e
@hjchen2
Merge branch 'dev_eager_consistent_auto_test' of https://github.com/O…
84e7f00 
…neflow-Inc/oneflow into dev_eager_consistent_auto_test
@hjchen2
Merge branch 'master' into dev_eager_consistent_auto_test
d4e686c
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
7c57e20
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
9fcbd8c
@hjchen2
refine
3a2b9d0
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
d9b2e37
@hjchen2
use larger dim size
a89d133
@hjchen2
Merge branch 'dev_eager_consistent_auto_test' of https://github.com/O…
d9b82de 
…neflow-Inc/oneflow into dev_eager_consistent_auto_test
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
a02b954
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
aaa457c
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
97eb854
@oneflow-ci-bot
Merge branch 'master' into dev_eager_consistent_auto_test
9aac591
@clackhan clackhan requested review from oneflow-ci-bot and removed request for oneflow-ci-bot March 22, 2022 22:50
@github-actions
Copy link
Contributor

Speed stats: 
GPU Name: GeForce GTX 1080 

✔️ OneFlow resnet50 time: 128.4ms (= 12836.5ms / 100, input_shape=[16, 3, 224, 224])
PyTorch resnet50 time: 141.7ms (= 14170.9ms / 100, input_shape=[16, 3, 224, 224])
✔️ Relative speed: 1.10 (= 141.7ms / 128.4ms)

✔️ OneFlow resnet50 time: 78.4ms (= 7840.9ms / 100, input_shape=[8, 3, 224, 224])
PyTorch resnet50 time: 83.9ms (= 8387.9ms / 100, input_shape=[8, 3, 224, 224])
✔️ Relative speed: 1.07 (= 83.9ms / 78.4ms)

OneFlow resnet50 time: 51.4ms (= 10280.6ms / 200, input_shape=[4, 3, 224, 224])
PyTorch resnet50 time: 58.6ms (= 11720.2ms / 200, input_shape=[4, 3, 224, 224])
✔️ Relative speed: 1.14 (= 58.6ms / 51.4ms)

OneFlow resnet50 time: 43.1ms (= 8617.3ms / 200, input_shape=[2, 3, 224, 224])
PyTorch resnet50 time: 43.6ms (= 8716.0ms / 200, input_shape=[2, 3, 224, 224])
✔️ Relative speed: 1.01 (= 43.6ms / 43.1ms)

OneFlow resnet50 time: 39.5ms (= 7908.8ms / 200, input_shape=[1, 3, 224, 224])
PyTorch resnet50 time: 39.3ms (= 7857.0ms / 200, input_shape=[1, 3, 224, 224])
✔️ Relative speed: 0.99 (= 39.3ms / 39.5ms)

md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
build_dataset >>>>>> ImageFolder
build_dataset >>>>>> ImageFolder
✔️ Relative speed: 0.99 (= 50.5s / 50.0s)

md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
build_dataset >>>>>> ImageFolder
build_dataset >>>>>> ImageFolder
✔️ Relative speed: 1.02 (= 13.2s / 13.6s)

md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
build_dataset >>>>>> ImageFolder
build_dataset >>>>>> ImageFolder
✔️ Relative speed: 0.96 (= 7.6s / 7.3s)

✔️ OneFlow resnet50 time: 135.7ms (= 13573.2ms / 100, input_shape=[16, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 156.6ms (= 15661.2ms / 100, input_shape=[16, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.15 (= 156.6ms / 135.7ms)

OneFlow resnet50 time: 88.2ms (= 8820.0ms / 100, input_shape=[8, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 100.7ms (= 10070.6ms / 100, input_shape=[8, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.14 (= 100.7ms / 88.2ms)

OneFlow resnet50 time: 62.9ms (= 12578.2ms / 200, input_shape=[4, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 85.3ms (= 17056.6ms / 200, input_shape=[4, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.36 (= 85.3ms / 62.9ms)

OneFlow resnet50 time: 54.1ms (= 10824.0ms / 200, input_shape=[2, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 66.4ms (= 13275.6ms / 200, input_shape=[2, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.23 (= 66.4ms / 54.1ms)

OneFlow resnet50 time: 48.9ms (= 9772.6ms / 200, input_shape=[1, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 61.8ms (= 12358.6ms / 200, input_shape=[1, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.26 (= 61.8ms / 48.9ms)

@github-actions
Copy link
Contributor

CI failed when running job: cuda-module. PR label automerge has been removed

@clackhan clackhan requested review from oneflow-ci-bot and removed request for oneflow-ci-bot March 23, 2022 08:37
@clackhan clackhan added the need-highest-priority Only add this when you really need it!!! Will block all other PRs. label Mar 23, 2022
@clackhan clackhan requested review from oneflow-ci-bot and removed request for oneflow-ci-bot March 23, 2022 22:50
@clackhan clackhan removed the need-highest-priority Only add this when you really need it!!! Will block all other PRs. label Mar 23, 2022
@github-actions
Copy link
Contributor

Speed stats: 
GPU Name: GeForce GTX 1080 

✔️ OneFlow resnet50 time: 128.3ms (= 12829.5ms / 100, input_shape=[16, 3, 224, 224])
PyTorch resnet50 time: 141.2ms (= 14117.6ms / 100, input_shape=[16, 3, 224, 224])
✔️ Relative speed: 1.10 (= 141.2ms / 128.3ms)

✔️ OneFlow resnet50 time: 77.3ms (= 7728.0ms / 100, input_shape=[8, 3, 224, 224])
PyTorch resnet50 time: 84.1ms (= 8407.1ms / 100, input_shape=[8, 3, 224, 224])
✔️ Relative speed: 1.09 (= 84.1ms / 77.3ms)

OneFlow resnet50 time: 52.8ms (= 10557.1ms / 200, input_shape=[4, 3, 224, 224])
PyTorch resnet50 time: 58.1ms (= 11623.5ms / 200, input_shape=[4, 3, 224, 224])
✔️ Relative speed: 1.10 (= 58.1ms / 52.8ms)

OneFlow resnet50 time: 41.0ms (= 8203.8ms / 200, input_shape=[2, 3, 224, 224])
PyTorch resnet50 time: 46.2ms (= 9232.9ms / 200, input_shape=[2, 3, 224, 224])
✔️ Relative speed: 1.13 (= 46.2ms / 41.0ms)

OneFlow resnet50 time: 39.1ms (= 7818.0ms / 200, input_shape=[1, 3, 224, 224])
PyTorch resnet50 time: 42.9ms (= 8574.8ms / 200, input_shape=[1, 3, 224, 224])
✔️ Relative speed: 1.10 (= 42.9ms / 39.1ms)

md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
build_dataset >>>>>> ImageFolder
build_dataset >>>>>> ImageFolder
✔️ Relative speed: 1.00 (= 50.8s / 50.6s)

md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
build_dataset >>>>>> ImageFolder
build_dataset >>>>>> ImageFolder
✔️ Relative speed: 0.95 (= 13.7s / 13.1s)

md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
md5 /home/ci-user/ci-cache/test_cache/onerec_test/nanodataset.zip 7f5cde8b5a6c411107517ac9b00f29db
build_dataset >>>>>> ImageFolder
build_dataset >>>>>> ImageFolder
✔️ Relative speed: 0.99 (= 7.5s / 7.4s)

✔️ OneFlow resnet50 time: 136.0ms (= 13604.7ms / 100, input_shape=[16, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 157.9ms (= 15791.5ms / 100, input_shape=[16, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.16 (= 157.9ms / 136.0ms)

OneFlow resnet50 time: 88.2ms (= 8819.0ms / 100, input_shape=[8, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 100.1ms (= 10012.4ms / 100, input_shape=[8, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.14 (= 100.1ms / 88.2ms)

OneFlow resnet50 time: 61.1ms (= 12225.8ms / 200, input_shape=[4, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 80.8ms (= 16164.1ms / 200, input_shape=[4, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.32 (= 80.8ms / 61.1ms)

OneFlow resnet50 time: 52.4ms (= 10472.1ms / 200, input_shape=[2, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 77.4ms (= 15477.1ms / 200, input_shape=[2, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.48 (= 77.4ms / 52.4ms)

OneFlow resnet50 time: 48.9ms (= 9775.6ms / 200, input_shape=[1, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 61.6ms (= 12326.7ms / 200, input_shape=[1, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.26 (= 61.6ms / 48.9ms)

@mergify mergify bot merged commit a8ae124 into master Mar 24, 2022
@mergify mergify bot deleted the consistent_squeeze_stack_stateful_kernel_with_cache_test branch March 24, 2022 04:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@hjchen2 hjchen2 hjchen2 approved these changes

@wyg1997 wyg1997 wyg1997 approved these changes

@oneflow-ci-bot oneflow-ci-bot Awaiting requested review from oneflow-ci-bot

Assignees
No one assigned
Labels
automerge enhancement system test
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@clackhan @hjchen2 @wyg1997 @oneflow-ci-bot