Use float64x2 for _mm_stream_pd temporal store

JishinMaster / simd_utils

A header only library implementing common mathematical functions using SIMD intrinsics

BSD 2-Clause "Simplified" License

93 stars 21 forks source link

Use float64x2 for _mm_stream_pd temporal store #2

Closed jerinphilip closed 2 years ago

jerinphilip commented 2 years ago

Replace previously used float32x4 which leads to compilation error when using clang++.

Fixes: #1

JishinMaster commented 2 years ago

Thank you for your interest in this project, you help is deeply appreciated! I am merging this pull request but the problem comes from the sse2neon project (https://github.com/DLTcollab/sse2neon/blob/master/sse2neon.h) which I am using for a smoother code for ARM (since most of the project is writtent using X86 intrinsics). You could try to also open a pull request there.