[PyTorch] Don't hardcode 4 * Vec::size() in vectorized_reduction#138014
[PyTorch] Don't hardcode 4 * Vec::size() in vectorized_reduction#138014swolchok wants to merge 3 commits intogh/swolchok/668/basefrom
Conversation
This will break once we support 128-bit vectors, and there's no reason to do it. Differential Revision: [D64421982](https://our.internmc.facebook.com/intern/diff/D64421982/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/138014
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit ef84551 with merge base 0786b37 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D64421982 |
malfet
left a comment
There was a problem hiding this comment.
LGTM, just wanted to confirm that Vec::size() is constexpr, perhaps adding an explicit constexpr would be a nice touch
…ed_reduction" This will break once we support 128-bit vectors, and there's no reason to do it. Differential Revision: [D64421982](https://our.internmc.facebook.com/intern/diff/D64421982/) cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D64421982 |
…] Don't hardcode 4 * Vec::size() in vectorized_reduction" This will break once we support 128-bit vectors, and there's no reason to do it. Differential Revision: [D64421982](https://our.internmc.facebook.com/intern/diff/D64421982/) cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D64421982 |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
|
This pull request was exported from Phabricator. Differential Revision: D64421982 |
The ifdef as written just checks if the macOS 15.0-capable SDK is being used. You also need a runtime gate to make sure macOS 15 is in use. Differential Revision: [D64429453](https://our.internmc.facebook.com/intern/diff/D64429453/) Pull Request resolved: #138022 Approved by: https://github.com/Skylion007, https://github.com/malfet ghstack dependencies: #137722, #138014
Stack from ghstack (oldest at bottom):
defined(__aarch64__) && !defined(CPU_CAPABILITY_SVE256)instead ofdefined(CPU_CAPABILITY_NEON)#137722This will break once we support 128-bit vectors, and there's no reason to do it.
Differential Revision: D64421982
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10