IVF Index Support in SVS #156
Conversation
standard 1 level clustering or faster two level hierarchical clustering. Clustering algorithm uses AMX on supported Intel (R) Xeon (R) systems. Also, added support for BF16 datatype.
ibhati
requested review from
aguerreb,
napetrov,
mihaic,
homksei,
yuejiaointel,
ethanglaser,
ahuber21,
dian-lun-lin and
Alexsandruss
as code owners
| } | ||
|
|
||
| struct CreateDenseCluster { | ||
| using This = CreateDenseCluster; |
There was a problem hiding this comment.
These are used in the extensions of compressed datasets (LVQ/Leanvec)
| , distance_{std::move(distance_function)} | ||
| , threadpool_{threads::as_threadpool(std::move(threadpool_proto))} | ||
| , n_inner_threads_{n_inner_threads} { | ||
| // Initialize threadpools for intra-query parallelism |
There was a problem hiding this comment.
We need to be careful about nested parallelism. From this constructor, it's not obvious that the threadpool_ and n_inner_threads will be nested (i.e., two-level parallelism). Could we maybe have better naming? Also, how do we handle custom threadpool in this case?
|
|
||
| Clustering clustering(std::move(centroids), std::move(clusters)); | ||
| auto build_time = svs::lib::time_difference(tic); | ||
| fmt::print("IVF build time: {} seconds\n", build_time); |
There was a problem hiding this comment.
This print should be moved to logger
There was a problem hiding this comment.
Thanks for pointing that out, I will move all these prints in the logger with appropriate verbosity levels
| final_assignments_time.finish(); | ||
| kmeans_timer.finish(); | ||
| svs::logging::debug("{}", timer); | ||
| fmt::print("kmeans clustering time: {}\n", lib::as_seconds(timer.elapsed())); |
There was a problem hiding this comment.
This print should be moved to logger
|
|
||
| // On GCC, we need to add this attribute so that BFloat16 members can appear inside | ||
| // packed structs. | ||
| class __attribute__((packed)) BFloat16 { |
There was a problem hiding this comment.
What's the different between Float16 and BFloat16?
There was a problem hiding this comment.
Here is a short write-up explaining these formats and the differences: https://nhigham.com/2018/12/03/half-precision-arithmetic-fp16-versus-bfloat16/
This update introduces IVF (Inverted File) index support in SVS, allowing for index construction using either standard one-level clustering or a faster two-level hierarchical clustering approach. The clustering algorithm is optimized to utilize AMX (Advanced Matrix Extensions) on supported Intel® Xeon® systems, enhancing performance on compatible hardware. Additionally, support for the BF16 (bfloat16) data type has been introduced, broadening the range of data formats that can be efficiently processed.
Tasks