[FFmpeg-cvslog] x86/intreadwrite: add SSE2 optimized AV_COPY128U

[James Almer]

ffmpeg | branch: master | James Almer <jamrial at gmail.com> | Thu Jul 25 13:20:07 2024 -0300| [9e7a93c6fd1706644c775a608b12a84960940d61] | committer: James Almer

x86/intreadwrite: add SSE2 optimized AV_COPY128U

Signed-off-by: James Almer <jamrial at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=9e7a93c6fd1706644c775a608b12a84960940d61
---

 libavutil/x86/intreadwrite.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/libavutil/x86/intreadwrite.h b/libavutil/x86/intreadwrite.h
index 65cc6b39a1..c92b75ed12 100644
--- a/libavutil/x86/intreadwrite.h
+++ b/libavutil/x86/intreadwrite.h
@@ -37,6 +37,13 @@ static av_always_inline void AV_COPY128(void *d, const void *s)
     _mm_store_si128((__m128i *)d, tmp);
 }
 
+#define AV_COPY128U AV_COPY128U
+static av_always_inline void AV_COPY128U(void *d, const void *s)
+{
+    __m128i tmp = _mm_loadu_si128((const __m128i *)s);
+    _mm_storeu_si128((__m128i *)d, tmp);
+}
+
 #define AV_ZERO128 AV_ZERO128
 static av_always_inline void AV_ZERO128(void *d)
 {