Skip to content

add patches to fix PyTorch 1.10.0 build on POWER #15904

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

Merged
akesandgren merged 3 commits into from
Nov 30, 2022
+417 −74
Merged

add patches to fix PyTorch 1.10.0 build on POWER #15904

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c282fb2
Fix PyTorch 1.10.0 build on PPC
Flamefire Jul 25, 2022
642d33b
Fix FP16 quantization (fixes test_quantization)
Flamefire Sep 9, 2022
c1f6e50
Add PyTorch-1.10.0_fix-kineto-crash.patch
Flamefire Sep 22, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 40 additions & 19 deletions easybuild/easyconfigs/p/PyTorch/PyTorch-1.10.0-foss-2021a-CUDA-11.3.1.eb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,34 +8,37 @@ PyTorch is a deep learning framework that puts Python first."""

toolchain = {'name': 'foss', 'version': '2021a'}

sources = [{
'filename': '%(name)s-%(version)s.tar.gz',
'git_config': {
'url': 'https://github.com/pytorch',
'repo_name': 'pytorch',
'tag': 'v%(version)s',
'recursive': True,
},
}]
source_urls = [GITHUB_RELEASE]
sources = ['%(namelower)s-v%(version)s.tar.gz']

patches = [
'PyTorch-1.7.0_avoid-nan-in-test-torch.patch',
'PyTorch-1.7.0_disable-dev-shm-test.patch',
'PyTorch-1.7.1_correctly-pass-jit_opt_level.patch',
'PyTorch-1.8.1_dont-use-gpu-ccc-in-test.patch',
'PyTorch-1.8.1_increase-distributed-test-timeout.patch',
'PyTorch-1.9.0_limit-world-size-for-zero-redundancy-opt-test.patch',
'PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch',
'PyTorch-1.10.0_add-dummy-bfloat16-for-ppc.patch',
'PyTorch-1.10.0_fix-alias-violation-in-bitwise-ops.patch',
'PyTorch-1.10.0_fix-faulty-asserts-and-skip-test.patch',
'PyTorch-1.10.0_fix-faulty-asserts.patch',
'PyTorch-1.10.0_fix-fp16-quantization-without-fbgemm.patch',
'PyTorch-1.10.0_fix-kineto-crash.patch',
'PyTorch-1.10.0_fix-missing-VSX-dispatch.patch',
'PyTorch-1.10.0_fix-test-cond-cpu.patch',
'PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch',
'PyTorch-1.10.0_fix-test-model_dump.patch',
'PyTorch-1.10.0_fix-vnni-detection.patch',
'PyTorch-1.10.0_fix-vsx-vector-functions.patch',
'PyTorch-1.10.0_fix-XNNPACK-tests.patch',
'PyTorch-1.10.0_increase_zero_optimizer_test_tolerance.patch',
'PyTorch-1.10.0_remove-vec-dump-functions.patch',
'PyTorch-1.10.0_skip_cmake_rpath.patch',
'PyTorch-1.10.0_skip_failing_ops_tests.patch',
'PyTorch-1.10.0_skip_nan_tests_openblas.patch',
'PyTorch-1.10.0_skip_cmake_rpath.patch',
'PyTorch-1.10.0_skip-nnapi-test-without-qnnpack.patch',
]
checksums = [
None, # can't add proper SHA256 checksum, because source tarball is created locally after recursive 'git clone'
'1970225700d1f9791eb553855ad3c22e7c9fd69cff2765d532506b33e449831e', # pytorch-v1.10.0.tar.gz
'b899aa94d9e60f11ee75a706563312ccefa9cf432756c470caa8e623991c8f18', # PyTorch-1.7.0_avoid-nan-in-test-torch.patch
'622cb1eaeadc06e13128a862d9946bcc1f1edd3d02b259c56a9aecc4d5406b8a', # PyTorch-1.7.0_disable-dev-shm-test.patch
# PyTorch-1.7.1_correctly-pass-jit_opt_level.patch
Expand All @@ -45,24 +48,42 @@ checksums = [
'7a6e512274f0b8673f4f207a5bc53387d88be7e79833f42d20365668b2118071',
# PyTorch-1.9.0_limit-world-size-for-zero-redundancy-opt-test.patch
'ff573660913ce055e24cfd194ce747ba5685091c631cfd443eae2a99d56b57ea',
# PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch
'313dca681f45ce3bc7c4557fdcdcbe0b77216d2c708fa30a2ec0e22c44876707',
# PyTorch-1.10.0_add-dummy-bfloat16-for-ppc.patch
'0c8bf4b284c5c2cb4d175645d44bed674cca5218de741a8ea698cef2884a86da',
# PyTorch-1.10.0_fix-alias-violation-in-bitwise-ops.patch
'426c9ead1a74b656748d4c8bf8afd4303d8b9f2394ad22b21a845d07c8ca1d12',
# PyTorch-1.10.0_fix-faulty-asserts-and-skip-test.patch
'67152215e4530a9b1d7349fb20864445fd815288f04ab9e96e45c73b2d87827a',
# PyTorch-1.10.0_fix-faulty-asserts.patch
'44d2bb998ec3b3b65659f3327894745888a58f957a191cb524b4003018db51a2',
# PyTorch-1.10.0_fix-fp16-quantization-without-fbgemm.patch
'dfc09c2e787e757191a0ebf68ace46e2a90d71263ba84e2ee764b596d2ee6769',
# PyTorch-1.10.0_fix-kineto-crash.patch
'dc467333b28162149af8f675929d8c6bf219f23230bfc0d39af02ba4f6f882eb',
# PyTorch-1.10.0_fix-missing-VSX-dispatch.patch
'29368e69e98cb16659a2043b7a0df0411c99bc57a70405f8b5300f68c25f3ee9',
# PyTorch-1.10.0_fix-test-cond-cpu.patch
'51f83f5d5ef69656ef35b73f17e0671e70113798421be11ea4c7b56ffcc4da03',
# PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch
'313dca681f45ce3bc7c4557fdcdcbe0b77216d2c708fa30a2ec0e22c44876707',
# PyTorch-1.10.0_fix-test-model_dump.patch
'339148ae1a028cda6e750ac93fa38a599f66c7abe26586c9219f1a206ea14557',
# PyTorch-1.10.0_fix-vnni-detection.patch
'1f3664c0febfa2a3fc4c0cd3bae185f289716ac0b6c3d7e8fa1cee19ba62b7cc',
# PyTorch-1.10.0_fix-vsx-vector-functions.patch
'7bef5f96cb83b2d655d2f76dd7468a171d446f0b3e06da2232ec7f886484d312',
# PyTorch-1.10.0_fix-XNNPACK-tests.patch
'd3e749a2a42efce463e3b8a1aebb21f0edf2256682c4417297d9a44a6210e5f8',
# PyTorch-1.10.0_increase_zero_optimizer_test_tolerance.patch
'e65afb01786f7f030ccb5faada1eb474bb0c418bcadcf1baaa71a4fa2f3f4240',
# PyTorch-1.10.0_remove-vec-dump-functions.patch
'5e796c83f74e77aa193fef2720a7a41e3e0eb39df726a6f0a2a1c55d37d8fcc8',
# PyTorch-1.10.0_skip_cmake_rpath.patch
'ac05943bb205623f91ef140aa00869efc5fe844184bd666bebf5405808610448',
# PyTorch-1.10.0_skip_failing_ops_tests.patch
'399af94ffcef4a6db5226552c46f11e9b0f0f371b2d7924b9e5764d2281581ab',
# PyTorch-1.10.0_skip_nan_tests_openblas.patch
'7d3f83e3056d9e47a460790313238f28708beb596cafaa7ae55e374d368bbedf',
# PyTorch-1.10.0_skip_cmake_rpath.patch
'ac05943bb205623f91ef140aa00869efc5fe844184bd666bebf5405808610448',
# PyTorch-1.10.0_skip-nnapi-test-without-qnnpack.patch
'34ba476a7bcddec323bf9eca083cb4623d0f569d081aa3add3769c24f22849d2',
]

osdependencies = [OS_PKG_IBVERBS_DEV]
Expand Down
53 changes: 37 additions & 16 deletions easybuild/easyconfigs/p/PyTorch/PyTorch-1.10.0-foss-2021a.eb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,32 +7,35 @@ PyTorch is a deep learning framework that puts Python first."""

toolchain = {'name': 'foss', 'version': '2021a'}

sources = [{
'filename': '%(name)s-%(version)s.tar.gz',
'git_config': {
'url': 'https://github.com/pytorch',
'repo_name': 'pytorch',
'tag': 'v%(version)s',
'recursive': True,
},
}]
source_urls = [GITHUB_RELEASE]
sources = ['%(namelower)s-v%(version)s.tar.gz']

patches = [
'PyTorch-1.7.0_avoid-nan-in-test-torch.patch',
'PyTorch-1.7.0_disable-dev-shm-test.patch',
'PyTorch-1.7.1_correctly-pass-jit_opt_level.patch',
'PyTorch-1.8.1_increase-distributed-test-timeout.patch',
'PyTorch-1.9.0_limit-world-size-for-zero-redundancy-opt-test.patch',
'PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch',
'PyTorch-1.10.0_add-dummy-bfloat16-for-ppc.patch',
'PyTorch-1.10.0_fix-alias-violation-in-bitwise-ops.patch',
'PyTorch-1.10.0_fix-faulty-asserts-and-skip-test.patch',
'PyTorch-1.10.0_fix-faulty-asserts.patch',
'PyTorch-1.10.0_fix-fp16-quantization-without-fbgemm.patch',
'PyTorch-1.10.0_fix-kineto-crash.patch',
'PyTorch-1.10.0_fix-missing-VSX-dispatch.patch',
'PyTorch-1.10.0_fix-test-cond-cpu.patch',
'PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch',
'PyTorch-1.10.0_fix-test-model_dump.patch',
'PyTorch-1.10.0_fix-vnni-detection.patch',
'PyTorch-1.10.0_fix-vsx-vector-functions.patch',
'PyTorch-1.10.0_fix-XNNPACK-tests.patch',
'PyTorch-1.10.0_increase_zero_optimizer_test_tolerance.patch',
'PyTorch-1.10.0_remove-vec-dump-functions.patch',
'PyTorch-1.10.0_skip_failing_ops_tests.patch',
'PyTorch-1.10.0_skip_nan_tests_openblas.patch',
'PyTorch-1.10.0_skip-nnapi-test-without-qnnpack.patch',
]
checksums = [
None, # can't add proper SHA256 checksum, because source tarball is created locally after recursive 'git clone'
'1970225700d1f9791eb553855ad3c22e7c9fd69cff2765d532506b33e449831e', # pytorch-v1.10.0.tar.gz
'b899aa94d9e60f11ee75a706563312ccefa9cf432756c470caa8e623991c8f18', # PyTorch-1.7.0_avoid-nan-in-test-torch.patch
'622cb1eaeadc06e13128a862d9946bcc1f1edd3d02b259c56a9aecc4d5406b8a', # PyTorch-1.7.0_disable-dev-shm-test.patch
# PyTorch-1.7.1_correctly-pass-jit_opt_level.patch
Expand All @@ -41,22 +44,40 @@ checksums = [
'7a6e512274f0b8673f4f207a5bc53387d88be7e79833f42d20365668b2118071',
# PyTorch-1.9.0_limit-world-size-for-zero-redundancy-opt-test.patch
'ff573660913ce055e24cfd194ce747ba5685091c631cfd443eae2a99d56b57ea',
# PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch
'313dca681f45ce3bc7c4557fdcdcbe0b77216d2c708fa30a2ec0e22c44876707',
# PyTorch-1.10.0_add-dummy-bfloat16-for-ppc.patch
'0c8bf4b284c5c2cb4d175645d44bed674cca5218de741a8ea698cef2884a86da',
# PyTorch-1.10.0_fix-alias-violation-in-bitwise-ops.patch
'426c9ead1a74b656748d4c8bf8afd4303d8b9f2394ad22b21a845d07c8ca1d12',
# PyTorch-1.10.0_fix-faulty-asserts-and-skip-test.patch
'67152215e4530a9b1d7349fb20864445fd815288f04ab9e96e45c73b2d87827a',
# PyTorch-1.10.0_fix-faulty-asserts.patch
'44d2bb998ec3b3b65659f3327894745888a58f957a191cb524b4003018db51a2',
# PyTorch-1.10.0_fix-fp16-quantization-without-fbgemm.patch
'dfc09c2e787e757191a0ebf68ace46e2a90d71263ba84e2ee764b596d2ee6769',
# PyTorch-1.10.0_fix-kineto-crash.patch
'dc467333b28162149af8f675929d8c6bf219f23230bfc0d39af02ba4f6f882eb',
# PyTorch-1.10.0_fix-missing-VSX-dispatch.patch
'29368e69e98cb16659a2043b7a0df0411c99bc57a70405f8b5300f68c25f3ee9',
# PyTorch-1.10.0_fix-test-cond-cpu.patch
'51f83f5d5ef69656ef35b73f17e0671e70113798421be11ea4c7b56ffcc4da03',
# PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch
'313dca681f45ce3bc7c4557fdcdcbe0b77216d2c708fa30a2ec0e22c44876707',
# PyTorch-1.10.0_fix-test-model_dump.patch
'339148ae1a028cda6e750ac93fa38a599f66c7abe26586c9219f1a206ea14557',
# PyTorch-1.10.0_fix-vnni-detection.patch
'1f3664c0febfa2a3fc4c0cd3bae185f289716ac0b6c3d7e8fa1cee19ba62b7cc',
# PyTorch-1.10.0_fix-vsx-vector-functions.patch
'7bef5f96cb83b2d655d2f76dd7468a171d446f0b3e06da2232ec7f886484d312',
# PyTorch-1.10.0_fix-XNNPACK-tests.patch
'd3e749a2a42efce463e3b8a1aebb21f0edf2256682c4417297d9a44a6210e5f8',
# PyTorch-1.10.0_increase_zero_optimizer_test_tolerance.patch
'e65afb01786f7f030ccb5faada1eb474bb0c418bcadcf1baaa71a4fa2f3f4240',
# PyTorch-1.10.0_remove-vec-dump-functions.patch
'5e796c83f74e77aa193fef2720a7a41e3e0eb39df726a6f0a2a1c55d37d8fcc8',
# PyTorch-1.10.0_skip_failing_ops_tests.patch
'399af94ffcef4a6db5226552c46f11e9b0f0f371b2d7924b9e5764d2281581ab',
# PyTorch-1.10.0_skip_nan_tests_openblas.patch
'7d3f83e3056d9e47a460790313238f28708beb596cafaa7ae55e374d368bbedf',
# PyTorch-1.10.0_skip-nnapi-test-without-qnnpack.patch
'34ba476a7bcddec323bf9eca083cb4623d0f569d081aa3add3769c24f22849d2',
]

osdependencies = [OS_PKG_IBVERBS_DEV]
Expand Down
59 changes: 40 additions & 19 deletions easybuild/easyconfigs/p/PyTorch/PyTorch-1.10.0-fosscuda-2020b.eb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,34 +7,37 @@ PyTorch is a deep learning framework that puts Python first."""

toolchain = {'name': 'fosscuda', 'version': '2020b'}

sources = [{
'filename': '%(name)s-%(version)s.tar.gz',
'git_config': {
'url': 'https://github.com/pytorch',
'repo_name': 'pytorch',
'tag': 'v%(version)s',
'recursive': True,
},
}]
source_urls = [GITHUB_RELEASE]
sources = ['%(namelower)s-v%(version)s.tar.gz']

patches = [
'PyTorch-1.7.0_avoid-nan-in-test-torch.patch',
'PyTorch-1.7.0_disable-dev-shm-test.patch',
'PyTorch-1.7.1_correctly-pass-jit_opt_level.patch',
'PyTorch-1.8.1_dont-use-gpu-ccc-in-test.patch',
'PyTorch-1.8.1_increase-distributed-test-timeout.patch',
'PyTorch-1.9.0_limit-world-size-for-zero-redundancy-opt-test.patch',
'PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch',
'PyTorch-1.10.0_add-dummy-bfloat16-for-ppc.patch',
'PyTorch-1.10.0_fix-alias-violation-in-bitwise-ops.patch',
'PyTorch-1.10.0_fix-faulty-asserts-and-skip-test.patch',
'PyTorch-1.10.0_fix-faulty-asserts.patch',
'PyTorch-1.10.0_fix-fp16-quantization-without-fbgemm.patch',
'PyTorch-1.10.0_fix-kineto-crash.patch',
'PyTorch-1.10.0_fix-missing-VSX-dispatch.patch',
'PyTorch-1.10.0_fix-test-cond-cpu.patch',
'PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch',
'PyTorch-1.10.0_fix-test-model_dump.patch',
'PyTorch-1.10.0_fix-vnni-detection.patch',
'PyTorch-1.10.0_fix-vsx-vector-functions.patch',
'PyTorch-1.10.0_fix-XNNPACK-tests.patch',
'PyTorch-1.10.0_increase_zero_optimizer_test_tolerance.patch',
'PyTorch-1.10.0_remove-vec-dump-functions.patch',
'PyTorch-1.10.0_skip_cmake_rpath.patch',
'PyTorch-1.10.0_skip_failing_ops_tests.patch',
'PyTorch-1.10.0_skip_nan_tests_openblas.patch',
'PyTorch-1.10.0_skip_cmake_rpath.patch',
'PyTorch-1.10.0_skip-nnapi-test-without-qnnpack.patch',
]
checksums = [
None, # can't add proper SHA256 checksum, because source tarball is created locally after recursive 'git clone'
'1970225700d1f9791eb553855ad3c22e7c9fd69cff2765d532506b33e449831e', # pytorch-v1.10.0.tar.gz
'b899aa94d9e60f11ee75a706563312ccefa9cf432756c470caa8e623991c8f18', # PyTorch-1.7.0_avoid-nan-in-test-torch.patch
'622cb1eaeadc06e13128a862d9946bcc1f1edd3d02b259c56a9aecc4d5406b8a', # PyTorch-1.7.0_disable-dev-shm-test.patch
# PyTorch-1.7.1_correctly-pass-jit_opt_level.patch
Expand All @@ -44,24 +47,42 @@ checksums = [
'7a6e512274f0b8673f4f207a5bc53387d88be7e79833f42d20365668b2118071',
# PyTorch-1.9.0_limit-world-size-for-zero-redundancy-opt-test.patch
'ff573660913ce055e24cfd194ce747ba5685091c631cfd443eae2a99d56b57ea',
# PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch
'313dca681f45ce3bc7c4557fdcdcbe0b77216d2c708fa30a2ec0e22c44876707',
# PyTorch-1.10.0_add-dummy-bfloat16-for-ppc.patch
'0c8bf4b284c5c2cb4d175645d44bed674cca5218de741a8ea698cef2884a86da',
# PyTorch-1.10.0_fix-alias-violation-in-bitwise-ops.patch
'426c9ead1a74b656748d4c8bf8afd4303d8b9f2394ad22b21a845d07c8ca1d12',
# PyTorch-1.10.0_fix-faulty-asserts-and-skip-test.patch
'67152215e4530a9b1d7349fb20864445fd815288f04ab9e96e45c73b2d87827a',
# PyTorch-1.10.0_fix-faulty-asserts.patch
'44d2bb998ec3b3b65659f3327894745888a58f957a191cb524b4003018db51a2',
# PyTorch-1.10.0_fix-fp16-quantization-without-fbgemm.patch
'dfc09c2e787e757191a0ebf68ace46e2a90d71263ba84e2ee764b596d2ee6769',
# PyTorch-1.10.0_fix-kineto-crash.patch
'dc467333b28162149af8f675929d8c6bf219f23230bfc0d39af02ba4f6f882eb',
# PyTorch-1.10.0_fix-missing-VSX-dispatch.patch
'29368e69e98cb16659a2043b7a0df0411c99bc57a70405f8b5300f68c25f3ee9',
# PyTorch-1.10.0_fix-test-cond-cpu.patch
'51f83f5d5ef69656ef35b73f17e0671e70113798421be11ea4c7b56ffcc4da03',
# PyTorch-1.10.0_fix-test-dataloader-fixed-affinity.patch
'313dca681f45ce3bc7c4557fdcdcbe0b77216d2c708fa30a2ec0e22c44876707',
# PyTorch-1.10.0_fix-test-model_dump.patch
'339148ae1a028cda6e750ac93fa38a599f66c7abe26586c9219f1a206ea14557',
# PyTorch-1.10.0_fix-vnni-detection.patch
'1f3664c0febfa2a3fc4c0cd3bae185f289716ac0b6c3d7e8fa1cee19ba62b7cc',
# PyTorch-1.10.0_fix-vsx-vector-functions.patch
'7bef5f96cb83b2d655d2f76dd7468a171d446f0b3e06da2232ec7f886484d312',
# PyTorch-1.10.0_fix-XNNPACK-tests.patch
'd3e749a2a42efce463e3b8a1aebb21f0edf2256682c4417297d9a44a6210e5f8',
# PyTorch-1.10.0_increase_zero_optimizer_test_tolerance.patch
'e65afb01786f7f030ccb5faada1eb474bb0c418bcadcf1baaa71a4fa2f3f4240',
# PyTorch-1.10.0_remove-vec-dump-functions.patch
'5e796c83f74e77aa193fef2720a7a41e3e0eb39df726a6f0a2a1c55d37d8fcc8',
# PyTorch-1.10.0_skip_cmake_rpath.patch
'ac05943bb205623f91ef140aa00869efc5fe844184bd666bebf5405808610448',
# PyTorch-1.10.0_skip_failing_ops_tests.patch
'399af94ffcef4a6db5226552c46f11e9b0f0f371b2d7924b9e5764d2281581ab',
# PyTorch-1.10.0_skip_nan_tests_openblas.patch
'7d3f83e3056d9e47a460790313238f28708beb596cafaa7ae55e374d368bbedf',
# PyTorch-1.10.0_skip_cmake_rpath.patch
'ac05943bb205623f91ef140aa00869efc5fe844184bd666bebf5405808610448',
# PyTorch-1.10.0_skip-nnapi-test-without-qnnpack.patch
'34ba476a7bcddec323bf9eca083cb4623d0f569d081aa3add3769c24f22849d2',
]

osdependencies = [OS_PKG_IBVERBS_DEV]
Expand Down
Loading