Paul Masurel
Paul Masurel
Hi @wuranbo. For several reason I think, Log analytics could be a great use case for tantivy. Analytics is a use case of search where the super low-level performance really...
Good point :) Let's fix it. I suspect you know what I meant there, but just in case : tantivy's "fast field" = lucene's docvalues.
The optimized path of decompressoin with delta require the `sse3` instruction set (it uses `_mm_lddqu_si128` ). On Xeon, it was added quite late. I suspect the problem you are experiencing...
On my CPU (Ryzen 7 4750U) I get the following ``` Benchmarking BitPacker4x/decompress-2: Warmin Benchmarking BitPacker4x/decompress-2: Collecting 100 samples in estimated 5.0007 s (32M i Benchmarking BitPacker4x/decompress-2: Analyz BitPacker4x/decompress-2 time:...
If you are on linux, can you run the following command? `lscpu | grep pni` (SSE3 is weirdly named pni on linux)
It might be interesting to investigate: - can you double-check that the code path is the one using SIMD If it is not the case, it coudl be a problem...
This is not doing what it is advertising. The compiler does not do as expected.
Thanks for creating the issue.
Recording the tutorial as a [ascii cinema](https://asciinema.org/) animation and add it to the README.
Thank you @o0Ignition0o ! We changed our dependency. It works fine. The publication of quickwit to cargo is blocked for another reason but that should eventually happen.