On Wed, 27 Jul 2022, Swinney, Jonathan wrote:
- added a test for yuv2plane1 - fixed test for yuv2planeX for aarch64 which was previously not working at all - updated the test for yuv2planeX to check exact results or approximated resultsSigned-off-by: Jonathan Swinney <jswin...@amazon.com> --- libswscale/x86/swscale.c | 8 +- tests/checkasm/sw_scale.c | 189 ++++++++++++++++++++++++++++++-------- 2 files changed, 155 insertions(+), 42 deletions(-) diff --git a/libswscale/x86/swscale.c b/libswscale/x86/swscale.c index 628f12137c..32d441245d 100644 --- a/libswscale/x86/swscale.c +++ b/libswscale/x86/swscale.c @@ -534,7 +534,8 @@ switch(c->dstBpc){ \ ASSIGN_SSE_SCALE_FUNC(c->hcScale, c->hChrFilterSize, sse2, sse2); ASSIGN_VSCALEX_FUNC(c->yuv2planeX, sse2, , HAVE_ALIGNED_STACK || ARCH_X86_64); - ASSIGN_VSCALE_FUNC(c->yuv2plane1, sse2); + if (!(c->flags & SWS_ACCURATE_RND)) + ASSIGN_VSCALE_FUNC(c->yuv2plane1, sse2); switch (c->srcFormat) { case AV_PIX_FMT_YA8: @@ -583,14 +584,15 @@ switch(c->dstBpc){ \ ASSIGN_VSCALEX_FUNC(c->yuv2planeX, sse4, if (!isBE(c->dstFormat)) c->yuv2planeX = ff_yuv2planeX_16_sse4, HAVE_ALIGNED_STACK || ARCH_X86_64); - if (c->dstBpc == 16 && !isBE(c->dstFormat)) + if (c->dstBpc == 16 && !isBE(c->dstFormat) && !(c->flags & SWS_ACCURATE_RND)) c->yuv2plane1 = ff_yuv2plane1_16_sse4; } if (EXTERNAL_AVX(cpu_flags)) { ASSIGN_VSCALEX_FUNC(c->yuv2planeX, avx, , HAVE_ALIGNED_STACK || ARCH_X86_64); - ASSIGN_VSCALE_FUNC(c->yuv2plane1, avx); + if (!(c->flags & SWS_ACCURATE_RND)) + ASSIGN_VSCALE_FUNC(c->yuv2plane1, avx); switch (c->srcFormat) { case AV_PIX_FMT_YUYV422:
I think it would be good to have someone who's more familiar with swscale (or just someone else overall) acknowledge these changes too.
diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c index b643a47c30..b01fc31fd9 100644 --- a/tests/checkasm/sw_scale.c +++ b/tests/checkasm/sw_scale.c @@ -18,6 +18,7 @@ */ #include <string.h> +#include <stdbool.h>
We don't generally use stdbool in ffmpeg, even if it's C99 - just use a plain int and 0/1.
Other than that, the checkasm changes look fine (I coauthored part of them - and your cleanup of my WIP patch looks good!).
// Martin _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
