[Quant][PT2E] Enable weight scale optimization in QConv PT2E #105996
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
leslie-fang-intel
requested review from
jerryzh168,
salilsdesai,
kimishpatel,
digantdesai and
jianyuh
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/105996
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 430294f with merge base 97a291f ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Jul 26, 2023
Closed
Closed
Closed
leslie-fang-intel
added a commit
that referenced
this pull request
Jul 26, 2023
ghstack-source-id: 05dcbc7472ef4573dde8c06e4bd8d6b0c9ee76f7 Pull Request resolved: #105996
leslie-fang-intel
changed the title
[ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Jul 26, 2023
ghstack-source-id: 7455c3a56d6ef5cd25a5a03df06fd65467dbf689 Pull Request resolved: #105996
github-actions
bot
added
module: cpu
[ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Jul 26, 2023
ghstack-source-id: b60eea67f24668eb4269380fb1254e9d013f24e7 Pull Request resolved: #105996
cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 gujinghui PenghuiCheng jianyuh min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 23, 2023
…ndant QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 2 IDeep change as IDeep PR: intel/ideep#222 and intel/ideep#223 - For IDeep PR: intel/ideep#222 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. - For IDeep PR: intel/ideep#223 which includes AArch64 specific changes with the oneDNN 3.1.1 upgrade. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 23, 2023
…ht scale reciprocal calculation" **Summary** Upgrade IDeep which includes 2 IDeep change as IDeep PR: intel/ideep#222 and intel/ideep#223 - For IDeep PR: intel/ideep#222 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. - For IDeep PR: intel/ideep#223 which includes AArch64 specific changes with the oneDNN 3.1.1 upgrade. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
**Summary** After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR: - This QConv implementation expects to work functionally both with current IDeep version and the following IDeep upgrade in PR: #107565. - With the following IDeep upgrade in PR: #107565, the QConv has better performance since the redundant reciprocal calculation are removed. cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 gujinghui PenghuiCheng jianyuh min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
jerryzh168
approved these changes
Aug 23, 2023
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Aug 25, 2023
ghstack-source-id: 2e5ddcd8b1e64d459b1934ff16469e6cb8feb8a5 Pull Request resolved: pytorch#105996
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
…ndant QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
…ht scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
**Summary** After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR: - This QConv implementation expects to work functionally both with current IDeep version and the following IDeep upgrade in PR: #107565. - With the following IDeep upgrade in PR: #107565, the QConv has better performance since the redundant reciprocal calculation are removed. cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 gujinghui PenghuiCheng jianyuh min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Aug 25, 2023
ghstack-source-id: 6888c85b439a646fa3994a643162da995b82bb67 Pull Request resolved: pytorch#105996
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
…remove redundant QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
… QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
**Summary** After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR: - This QConv implementation expects to work functionally both with current IDeep version and the following IDeep upgrade in PR: #107565. - With the following IDeep upgrade in PR: #107565, the QConv has better performance since the redundant reciprocal calculation are removed. cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 gujinghui PenghuiCheng jianyuh min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
…remove redundant QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
… QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
**Summary** After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR: - This QConv implementation expects to work functionally both with current IDeep version and the following IDeep upgrade in PR: #107565. - With the following IDeep upgrade in PR: #107565, the QConv has better performance since the redundant reciprocal calculation are removed. cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 gujinghui PenghuiCheng jianyuh min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
…remove redundant QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
leslie-fang-intel
added a commit
that referenced
this pull request
Aug 25, 2023
… QConv weight scale reciprocal calculation" **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. cc gujinghui PenghuiCheng XiaobingSuper jianyuh jgong5 mingfeima sanchitintel ashokei jingxu10 min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
**Summary** After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR: - This QConv implementation expects to work functionally both with current IDeep version and the following IDeep upgrade in PR: #107565. - With the following IDeep upgrade in PR: #107565, the QConv has better performance since the redundant reciprocal calculation are removed. cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 gujinghui PenghuiCheng jianyuh min-jean-cho yanbing-j Guobing-Chen Xia-Weiwen [ghstack-poisoned]
|
@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 |
pytorchmergebot
pushed a commit
that referenced
this pull request
Aug 26, 2023
…ht scale reciprocal calculation (#107565) **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. Pull Request resolved: #107565 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: #104580, #104581, #104588, #104590, #105455, #105456, #105639, #105906, #105996
voznesenskym
pushed a commit
that referenced
this pull request
Aug 27, 2023
**Summary** After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR: - This QConv implementation expects to work functionally both with current IDeep version and the following IDeep upgrade in PR: #107565. - With the following IDeep upgrade in PR: #107565, the QConv has better performance since the redundant reciprocal calculation are removed. Pull Request resolved: #105996 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: #104580, #104581, #104588, #104590, #105455, #105456, #105639, #105906
voznesenskym
pushed a commit
that referenced
this pull request
Aug 27, 2023
…ht scale reciprocal calculation (#107565) **Summary** Upgrade IDeep which includes 1 IDeep change as IDeep PR: intel/ideep#226 - For IDeep PR: intel/ideep#226 which has done 2 things: - Remove the redundant QConv weight scale reciprocal calculation. - Pump IDEEP_VERSION_REVISION version from 0 to 1. So only QConv related calculation will be impacted and we already use IDeep version API in #105996 to make the corresponding change in PyTorch. Pull Request resolved: #107565 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: #104580, #104581, #104588, #104590, #105455, #105456, #105639, #105906, #105996
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Summary
After oneDNN 3.1 upgrade, we don't need to do the weight scale reciprocal calculation. So, remove the redundant reciprocal calculation to optimize QConv performance and using IDeep version API to implement it in this PR:
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10 @gujinghui @PenghuiCheng @jianyuh @min-jean-cho @yanbing-j @Guobing-Chen @Xia-Weiwen