Bugfix - RPP BitwiseAND BitwiseOR #465
Open
+72
−72
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
Member
r-abishek
commented
Oct 30, 2024
r-abishek
commented
- Fix mismatches in output between FP16 and other bit depths due to precision differences.
- Use rounding off operation instead of truncation.
Fix output mismatches between FP16 and other bit depths
rrawther
reviewed
Nov 18, 2024
| dst_f8->f1[5] = (float)((uchar)(src1_f8->f1[5]) & (uchar)(src2_f8->f1[5])); | ||
| dst_f8->f1[6] = (float)((uchar)(src1_f8->f1[6]) & (uchar)(src2_f8->f1[6])); | ||
| dst_f8->f1[7] = (float)((uchar)(src1_f8->f1[7]) & (uchar)(src2_f8->f1[7])); | ||
| dst_f8->f1[0] = (float)((uchar)(std::nearbyintf)(src1_f8->f1[0]) & (uchar)(std::nearbyintf)(src2_f8->f1[0])); |
There was a problem hiding this comment.
This is wrong as it will change the float value before doing AND. Please do reinterpret_cast instead
There was a problem hiding this comment.
- The logical operations (XOR, Bitwise And etc) support is provided for images only. Images can be stored in the following formats and carry the following values for the formats : U8 (0 to 255), I8 (-128 to 127), Float (0 to 1)
- In case of float image, we rescale the images to 0 to 255 range before we perform the logical operations. While rescaling, some of the values are close to the ceil value (Eg - 224.99267578125 in case of representing 225) and to account for the same rounding operation is done here. Usage of reinterpret cast and performing the operation leads to output mismatches in this case. Thanks
There was a problem hiding this comment.
What is the purpose of these operators? Is this supposed to do logical or arithmetical operation?
rrawther
requested changes
Nov 18, 2024
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.