Implement UINT8 vector type - [MOD-8230, MOD-8408] #584
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
GuyAv46
changed the title
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #584 +/- ##
==========================================
+ Coverage 97.09% 97.19% +0.10%
==========================================
Files 104 106 +2
Lines 5503 5713 +210
==========================================
+ Hits 5343 5553 +210
Misses 160 160 ☔ View full report in Codecov by Sentry. |
alonre24
reviewed
Jan 1, 2025
Comment on lines
+301
to
+305
| // For uint8 vectors with cosine distance, the extra float for the norm shifts alignment to | ||
| // `(dim + sizeof(float)) % 32`. | ||
| // Vectors satisfying this have a residual, causing offset loads during calculation. | ||
| // To avoid complexity, we skip alignment here, assuming the performance impact is | ||
| // negligible. |
There was a problem hiding this comment.
I need to better understand the considerations here (I see it follows INT8 as well)
There was a problem hiding this comment.
👍🏼. I also thought about it and if we put the norm at the beginning of the vector we will be able to use alignment
There was a problem hiding this comment.
As discussed - let's open a (small) spike to try that
alonre24
reviewed
Jan 2, 2025
Comment on lines
+71
to
+81
| // The type should be able to hold `dimension * MAX_VAL(int_elem_t) * MAX_VAL(int_elem_t)`. | ||
| // To support dimension up to 2^16, we need the difference between the type and int_elem_t to be at | ||
| // least 2 bytes. We assert that in the implementation. | ||
| template <typename int_elem_t> | ||
| using ret_t = std::conditional_t<sizeof(int_elem_t) == 1, int, long long>; | ||
|
|
||
| template <typename int_elem_t> | ||
| static inline ret_t<int_elem_t> | ||
| INTEGER_InnerProductImp(const int_elem_t *pVect1, const int_elem_t *pVect2, size_t dimension) { | ||
| static_assert(sizeof(ret_t<int_elem_t>) - sizeof(int_elem_t) * 2 >= sizeof(uint16_t)); | ||
| ret_t<int_elem_t> res = 0; |
There was a problem hiding this comment.
This generic introduced for possible future integer types larger than 1 byte?
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.
Implement support for new type
UINT8This PR follows the implementation of the
INT8type and implements all the functionality required for theUINT8type.Mark if applicable