Enable Intel ScalableVectorSearch support #4548
+3,003
−2
There are no files selected for viewing
This file contains hidden or 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 file contains hidden or 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 file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,138 @@ | ||
| /* | ||
| * Copyright (c) Meta Platforms, Inc. and affiliates. | ||
| * | ||
| * This source code is licensed under the MIT license found in the | ||
| * LICENSE file in the root directory of this source tree. | ||
| */ | ||
|
|
||
| #include <faiss/IndexSVSFlat.h> | ||
|
|
||
| #include <faiss/impl/FaissAssert.h> | ||
| #include <svs/core/data.h> | ||
| #include <svs/core/query_result.h> | ||
|
|
||
| #include <svs/orchestrators/exhaustive.h> | ||
|
|
||
| namespace faiss { | ||
|
|
||
| IndexSVSFlat::IndexSVSFlat(idx_t d, MetricType metric) : Index(d, metric) {} | ||
|
|
||
| void IndexSVSFlat::add(idx_t n, const float* x) { | ||
| if (!impl) { | ||
| init_impl(n, x); | ||
| return; | ||
| } | ||
|
|
||
| FAISS_THROW_MSG( | ||
| "IndexSVSFlat does not support adding points after initialization"); | ||
| } | ||
|
|
||
| void IndexSVSFlat::reset() { | ||
| if (impl) { | ||
| delete impl; | ||
| impl = nullptr; | ||
| } | ||
| ntotal = 0; | ||
| } | ||
|
|
||
| IndexSVSFlat::~IndexSVSFlat() {} | ||
|
|
||
| void IndexSVSFlat::search( | ||
| idx_t n, | ||
| const float* x, | ||
| idx_t k, | ||
| float* distances, | ||
| idx_t* labels, | ||
| const SearchParameters* params) const { | ||
| FAISS_THROW_IF_NOT(impl); | ||
| FAISS_THROW_IF_NOT(k > 0); | ||
|
|
||
| auto queries = svs::data::ConstSimpleDataView<float>(x, n, d); | ||
|
|
||
| auto results = | ||
| svs::QueryResult<size_t>{queries.size(), static_cast<size_t>(k)}; | ||
| // TODO: Tuable Flat parameters | ||
| impl->search(results.view(), queries, {}); | ||
|
|
||
| svs::threads::parallel_for( | ||
| impl->get_threadpool_handle(), | ||
| svs::threads::StaticPartition(n), | ||
| [&](auto is, auto SVS_UNUSED(tid)) { | ||
| for (auto i : is) { | ||
| for (idx_t j = 0; j < k; ++j) { | ||
| labels[j + i * k] = results.index(i, j); | ||
| distances[j + i * k] = results.distance(i, j); | ||
| } | ||
| } | ||
| }); | ||
| } | ||
|
|
||
| void IndexSVSFlat::init_impl(idx_t n, const float* x) { | ||
| auto data = svs::data::SimpleData<float>(n, d); | ||
| auto threadpool = svs::threads::ThreadPoolHandle( | ||
| svs::threads::OMPThreadPool(omp_get_max_threads())); | ||
| ntotal = n; | ||
|
|
||
| svs::threads::parallel_for( | ||
| threadpool, | ||
| svs::threads::StaticPartition(n), | ||
| [&](auto is, auto SVS_UNUSED(tid)) { | ||
| for (auto i : is) { | ||
| data.set_datum(i, std::span<const float>(x + i * d, d)); | ||
| } | ||
| }); | ||
|
|
||
| switch (metric_type) { | ||
| case METRIC_INNER_PRODUCT: | ||
| impl = new svs::Flat(svs::Flat::assemble<float>( | ||
| std::move(data), svs::DistanceIP(), std::move(threadpool))); | ||
| break; | ||
| case METRIC_L2: | ||
| impl = new svs::Flat(svs::Flat::assemble<float>( | ||
| std::move(data), svs::DistanceL2(), std::move(threadpool))); | ||
| break; | ||
| default: | ||
| FAISS_ASSERT(!"not supported SVS distance"); | ||
| } | ||
| } | ||
|
|
||
| void IndexSVSFlat::serialize_impl(std::ostream& out) const { | ||
| FAISS_THROW_IF_NOT_MSG( | ||
| impl, "Cannot serialize: SVS index not initialized."); | ||
|
|
||
| // Write index to temporary files and concatenate the contents | ||
| svs_io::SVSTempDirectory tmp; | ||
| impl->save(tmp.data); | ||
| tmp.write_files_to_stream(out); | ||
| } | ||
|
|
||
| void IndexSVSFlat::deserialize_impl(std::istream& in) { | ||
| FAISS_THROW_IF_MSG( | ||
| impl, "Cannot deserialize: SVS index already initialized."); | ||
|
|
||
| // Write stream to files that can be read by Flat::assemble() | ||
| svs_io::SVSTempDirectory tmp; | ||
| tmp.write_stream_to_files(in); | ||
|
|
||
| auto threadpool = svs::threads::ThreadPoolHandle( | ||
| svs::threads::OMPThreadPool(omp_get_max_threads())); | ||
|
|
||
| switch (metric_type) { | ||
| case METRIC_INNER_PRODUCT: | ||
| impl = new svs::Flat(svs::Flat::assemble<float>( | ||
| svs::VectorDataLoader<float>(tmp.data.string()), | ||
| svs::DistanceIP(), | ||
| std::move(threadpool))); | ||
| break; | ||
| case METRIC_L2: | ||
| impl = new svs::Flat(svs::Flat::assemble<float>( | ||
| svs::VectorDataLoader<float>(tmp.data.string()), | ||
| svs::DistanceL2(), | ||
| std::move(threadpool))); | ||
| break; | ||
| default: | ||
| FAISS_ASSERT(!"not supported SVS distance"); | ||
| } | ||
| } | ||
|
|
||
| } // namespace faiss |
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,55 @@ | ||
| /* | ||
| * Copyright (c) Meta Platforms, Inc. and affiliates. | ||
| * | ||
| * This source code is licensed under the MIT license found in the | ||
| * LICENSE file in the root directory of this source tree. | ||
| */ | ||
|
|
||
| #pragma once | ||
|
|
||
| #include <iostream> | ||
|
|
||
| #include <svs/core/distance.h> | ||
|
|
||
| #include <faiss/Index.h> | ||
| #include <faiss/impl/svs_io.h> | ||
|
|
||
| namespace svs { | ||
| class Flat; | ||
| } | ||
|
|
||
| namespace faiss { | ||
|
|
||
| struct IndexSVSFlat : Index { | ||
| // sequential labels | ||
| size_t nlabels{0}; | ||
|
|
||
| IndexSVSFlat() = default; | ||
| IndexSVSFlat(idx_t d, MetricType metric = METRIC_L2); | ||
|
|
||
| ~IndexSVSFlat(); | ||
|
|
||
| void add(idx_t n, const float* x) override; | ||
|
|
||
| void search( | ||
| idx_t n, | ||
| const float* x, | ||
| idx_t k, | ||
| float* distances, | ||
| idx_t* labels, | ||
| const SearchParameters* params = nullptr) const override; | ||
|
|
||
| void reset() override; | ||
|
|
||
| /* The actual SVS implementation */ | ||
| svs::Flat* impl{nullptr}; | ||
|
|
||
| /* Initializes the implementation, using the provided data */ | ||
| virtual void init_impl(idx_t n, const float* x); | ||
|
|
||
| /* Serialization */ | ||
| void serialize_impl(std::ostream& out) const; | ||
| void deserialize_impl(std::istream& in); | ||
| }; | ||
|
|
||
| } // namespace faiss |
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is the build failure due to this by default being
ON?Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
by default do we want to keep it
ONor we want o keep itOFF? (concern stems from whether we are confident that SVS works on all platforms that we care to support, with the expected performance levels)There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeah after discussion, we plan to set OFF by default, and we will create a new CI which will enable it. If it does not break other platforms, eventually we can set ON by default, but that can be a separate PR.