Floating Point Square Root Module with Variable Odd Mantissa and No Rounding #188
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
Add a base class for floating point square root. Implement a basic floating point square root module. Mantissa is variable, but limited to odd numbers from 1 to 51. No rounding implemented. Implement a fixed point square root for values with three integral bits and up to 51 fractional bits. Add a fixed point square root method. Add tests for fixed-point and floating-point square root. Implements intel#171 Co-authored-by: James Farwell <james.c.farwell@intel.com> Co-authored-by: Curtis Anderson <curtis.anderson@intel.com> Signed-off-by: Stephen Weeks <stephen.weeks@intel.com> Signed-off-by: James Farwell <james.c.farwell@intel.com> Signed-off-by: Curtis Anderson <curtis.anderson@intel.com>
desmonddak
reviewed
Mar 8, 2025
desmonddak
reviewed
Mar 8, 2025
desmonddak
reviewed
Mar 8, 2025
desmonddak
reviewed
Mar 8, 2025
desmonddak
reviewed
Mar 8, 2025
desmonddak
reviewed
Mar 8, 2025
mkorbel1
reviewed
Mar 8, 2025
Rename 'width' member variable Add exception if signed numbers are attempted. Updated tests Reworked test cases into a single function to loop over all input values Aligned authors' names Remove unneedded library import
mkorbel1
reviewed
Mar 13, 2025
About to push more changes from Stephen, just need to run markdown lint first. |
Adding docs that pipelining is for future plumbing work Fixing sqrt output to be more sensical Removing magic number from random number test Fixing error signal for floating point sqrt logic Alligning names for floating_point_sqrt.dart Catching and properly reporting error on DeNorm Updating docs to mention we do not support DeNorms fixing fixed sqrt test
lucasphillips
force-pushed
the
issue-171
branch
from
d4fcc35 to
0216f02
Compare
|
Alright, I have pushed changes from Stephen which address all of the current comments except the second one from @desmonddak (about avoiding injecting newlines in strings). |
mkorbel1
reviewed
Mar 17, 2025
Remove newlines and tabs (\n, \t)
mkorbel1
approved these changes
Mar 19, 2025
desmonddak
approved these changes
Mar 20, 2025
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.
Description & Motivation
Sometimes we want to be able to do square root for floating points.
This is especially true for ML hardware.
This PR addresses that by adding a Floating Point Square Root module and extending
Fixed Point to have multiplication
Related Issue(s)
#171
Testing
Test cases were created for the Fixed Point Square Root and Floating Point.
Fixed Square Root tested:
Floating Point Tested:
Backwards-compatibility
No.
Documentation
Yes. This required changes to the Floating Point and Fixed Point docs within the HCL library. They are included within this change