Repository navigation
Improve SSE intrinsic support. - #6
Merged
Merged
Conversation
This leads to software fallback for 64bit returns on 32bit platforms.
Okladnoj
added a commit
to Okladnoj/GeneralsGameCode
that referenced
this pull request
Sep 3, 2026
TheAssemblyArmada/GameMath#6 adds an SSE path to sqrt and corrects the lrint family, and OmniBlade asked for it to be checked against the software path ARM uses. The cast matrix answers that, but only if the build fetches his branch, so the pin moves here for the duration of the run and goes back to the TheSuperHackers tag afterwards. The macOS half is already in: the dump built against this branch is byte identical to the one on 59f7ccd, so the -ffp-contract=off he added for clang moves nothing on ARM and math-mac-arm64-clang.txt stands as the software reference. Nothing else could change there - the new sqrt sits behind USE_SSE, which is x86 and x64 only, which is exactly why the Windows half is the half that answers the question.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Corrects intrinsic use for lrint family to return correctly sized integer in all cases. This causes 32bit code to fall back to software conversion for 64bit returns as there is no intrinsic available.
Also adds intrinsic use for sqrt which according to the standard should give the same results as the software implementation.