Skip to content

Commit d76528e

Browse files
authored
Update remaining Xeon processor mentions in Readme (#155)
1 parent 4447aba commit d76528e

File tree

1 file changed

+6
-4
lines changed

1 file changed

+6
-4
lines changed

README.md

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@ SVS provides vector similarity search:
2828
* and **state-of-the-art speed**,
2929
* while enabling the use of **less memory** than its alternatives.
3030

31-
This enables application and framework developers using similarity search to unleash its performance on Intel ® Xeon CPUs (2nd generation and newer).
31+
This enables application and framework developers using similarity search to unleash its performance on Intel(R) Xeon(R) CPUs (2nd generation and newer).
3232

3333
SVS offers a fully-featured and yet simple Python API, compatible with most standard libraries.
3434
SVS is written in C++ to facilitate its integration into performance-critical applications.
@@ -51,8 +51,8 @@ different configurations of SVS yield significantly increased performance (measu
5151
SVS is primarily optimized for large-scale similarity search but it still offers [state-of-the-art performance
5252
at million-scale](https://intel.github.io/ScalableVectorSearch/benchs/static/previous/small_scale_benchs.html).
5353

54-
Best performance is obtained with Xeon 6 processors (Granite Rapids), by making use of Intel(R) AVX-512 instructions,
55-
with excellent results also with 2nd through 5th gen Intel ® Xeon ® processors (Cascade Lake,
54+
Best performance is obtained with Intel(R) Xeon(R) 6 processors (Granite Rapids), by making use of Intel(R) AVX-512 instructions,
55+
with excellent results also with 2nd through 5th gen Intel(R) Xeon(R) processors (Cascade Lake,
5656
Ice Lake, Sapphire Rapids, and Emerald Rapids).
5757

5858
Performance will be degraded if Intel(R) AVX-512 instructions are not available.
@@ -65,10 +65,12 @@ SVS supports:
6565
* Similarity functions: Euclidean distance, inner product, cosine similarity.
6666
* Vectors with individual values encoded as: float32, float16, uint8, int8.
6767
* Vector compression (including Locally-adaptive Vector Quantization [[ABHT23]](#1))
68-
* Optimizations for Intel ® Xeon ® processors:
68+
* Optimizations for Intel(R) Xeon(R) processors:
6969
- 2nd generation (Cascade Lake)
7070
- 3rd generation (Ice Lake)
7171
- 4th generation (Sapphire Rapids)
72+
- 5th generation (Emerald Rapids)
73+
- 6th generation (Granite Rapids)
7274

7375
See [Roadmap](https://intel.github.io/ScalableVectorSearch/roadmap.html) for upcoming features.
7476

0 commit comments

Comments
 (0)