Repository navigation
Implement more intrinsics. - #7
Merged
OmniBlade merged 2 commits intoSep 11, 2026
Merged
Conversation
Okladnoj
added a commit
to Okladnoj/GeneralsGameCode
that referenced
this pull request
Sep 7, 2026
Pins GameMath at OmniBlade/gamemath @ ea3c18bd, the head of TheAssemblyArmada/GameMath#7, and remeasures the bench matrix against it in both orders. The control, 47be83a, was remeasured in the same sitting, so the two are comparable; the committed numbers from the earlier session are not, since nothing in them records the revision they were taken on. The bits do not move. All six math-win-* dumps come back identical to the ones taken on 47be83a, so the SSE fabs returns what the software path returned. Being unchanged, they are not part of this commit. fabs is the row the pin adds. On x64 the double path falls from 6.5 ns per call to 1.6. On x86, the architecture the game builds, it rises instead, from 8.1 ns to 10.8 - the same to within a couple of tenths across all four x86 configurations and both measurement orders. The float path is unchanged everywhere except x64, where it rises from 1.4 to 1.6. sqrt is the same code on both pins and moved by 0 to 7 per cent, which is the noise floor here and is what makes the fabs figures readable. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
OmniBlade
force-pushed
the
feature/fabsintrin
branch
from
September 8, 2026 08:29
ea3c18b to
5c6d0ae
Compare
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implements ARM intrinsics for sqrt and SSE intrinsics for fabs.