Skip to content

SIMD vector math overhaul#4

Merged
Mcgode merged 50 commits into
mainfrom
simd-fix
Apr 23, 2026
Merged

SIMD vector math overhaul#4
Mcgode merged 50 commits into
mainfrom
simd-fix

Conversation

@Mcgode

@Mcgode Mcgode commented Apr 11, 2026

Copy link
Copy Markdown
Owner

Previous implementation added code complexity and edge cases.

Performance gain was negligible to negative. It also added code complexity and edge cases.
@Mcgode Mcgode self-assigned this Apr 11, 2026
Mcgode added 27 commits April 11, 2026 23:01
…from Matrix33Base

Simplified the Matrix33Base template by removing `SimdOptimal` parameter and all SIMD-related code. Updated related function templates, typedefs, and unit tests to reflect these changes.
…coverage

Removed duplicate and unnecessary test cases involving basic matrix addition, subtraction, multiplication, and transposition operations in `Matrix33_UnitTests.cpp` to streamline and align with the simplified `Matrix33Base` implementation.
Implemented 2x2 and 4x4 SIMD matrix inversion functions, including support for SSE2. Added `_mm_swizzle` and `_mm_swizzle4` macros to the SIMD utility header.
Mcgode added 22 commits April 21, 2026 15:59
@Mcgode Mcgode marked this pull request as ready for review April 23, 2026 16:44
@Mcgode Mcgode merged commit 79e2465 into main Apr 23, 2026
9 checks passed
@Mcgode Mcgode deleted the simd-fix branch April 23, 2026 16:44
@Mcgode Mcgode linked an issue Apr 23, 2026 that may be closed by this pull request
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Fix SIMD support for vector math

1 participant