interrupt for NNDescent #3432
Closed
interrupt for NNDescent #3432
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
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
568a47b
to
d14e700
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
d14e700
to
cb53b35
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
cb53b35
to
08267f8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
08267f8
to
1e8b0f1
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
1e8b0f1
to
b8b1a57
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
b8b1a57
to
06b39df
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
06b39df
to
399388e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
399388e
to
583db16
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
583db16
to
9443e8e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
force-pushed
the
export-D57300514
branch
from
ac2521b
to
6ca732e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
6ca732e
to
56b9aa9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
56b9aa9
to
c6ef289
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
c6ef289
to
28244cc
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
force-pushed
the
export-D57300514
branch
from
28244cc
to
84e1a28
Compare
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
84e1a28
to
8711090
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
mengdilin
added a commit
to mengdilin/faiss
that referenced
this pull request
May 14, 2024
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
8711090
to
d2c7a11
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
Summary: Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514
mengdilin
force-pushed
the
export-D57300514
branch
from
d2c7a11
to
55e3266
Compare
|
This pull request was exported from Phabricator. Differential Revision: D57300514 |
|
This pull request has been merged in 558a7c3. |
abhinavdangeti
pushed a commit
to blevesearch/faiss
that referenced
this pull request
Jul 12, 2024
Summary: Pull Request resolved: facebookresearch#3432 Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514 fbshipit-source-id: d343e0a292c35027ffdb8cbd0131e945b9881d63
aalekhpatel07
pushed a commit
to aalekhpatel07/faiss
that referenced
this pull request
Oct 17, 2024
Summary: Pull Request resolved: facebookresearch#3432 Addresses the issue in facebookresearch#3173 for `IndexNNDescent`, I see that there is already interrupt implemented for it's [search](https://fburl.com/code/iwn3tqic) API, so I looked into it's `add` API. For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from [nndescent](https://fburl.com/code/5rdb1p5o). For every iteration of `nndescent` takes around ~12 seconds, ~70-80% of the time is spent on `join` method (~10 seconds per iteration) and ~20-30% spent on `update` (~2 second per iteration). Adding the interrupt on the `join` should suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise) Reviewed By: junjieqi, mdouze Differential Revision: D57300514 fbshipit-source-id: d343e0a292c35027ffdb8cbd0131e945b9881d63
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.
Summary:
Addresses the issue in #3173
for
IndexNNDescent, I see that there is already interrupt implemented for it's search API, so I looked into it'saddAPI.For a given dataset nb = 10 mil, iter = 10, K = 32, d = 32 on a CPU only machine reveals that bulk of the cost comes from nndescent. For every iteration of
nndescenttakes around ~12 seconds, ~70-80% of the time is spent onjoinmethod (~10 seconds per iteration) and ~20-30% spent onupdate(~2 second per iteration). Adding the interrupt on thejoinshould suffice on quickly terminating the program when users hit ctrl+C (happy to move the interrupt elsewhere if we think otherwise)Reviewed By: mdouze
Differential Revision: D57300514