[FFmpeg-devel] [PATCH] swscale/x86/rgb2rgb: replace shuffle_bytes_2103_mmxext with an SSE2 version

[James Almer]

shuffle_bytes_2103_c: 46.5
shuffle_bytes_2103_mmxext: 29.3
shuffle_bytes_2103_sse2: 12.5

Signed-off-by: James Almer <jamrial at gmail.com>
---
 libswscale/x86/rgb2rgb.c     |  6 ++----
 libswscale/x86/rgb_2_rgb.asm | 30 +++++++++++-------------------
 2 files changed, 13 insertions(+), 23 deletions(-)

diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c
index 21ccfafe51..912fe431b3 100644
--- a/libswscale/x86/rgb2rgb.c
+++ b/libswscale/x86/rgb2rgb.c
@@ -116,7 +116,7 @@ DECLARE_ALIGNED(8, extern const uint64_t, ff_bgr2UVOffset);
 
 #endif /* HAVE_INLINE_ASM */
 
-void ff_shuffle_bytes_2103_mmxext(const uint8_t *src, uint8_t *dst, int src_size);
+void ff_shuffle_bytes_2103_sse2(const uint8_t *src, uint8_t *dst, int src_size);
 void ff_shuffle_bytes_2103_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
 void ff_shuffle_bytes_0321_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
 void ff_shuffle_bytes_1230_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
@@ -154,10 +154,8 @@ av_cold void rgb2rgb_init_x86(void)
         rgb2rgb_init_avx();
 #endif /* HAVE_INLINE_ASM */
 
-    if (EXTERNAL_MMXEXT(cpu_flags)) {
-        shuffle_bytes_2103 = ff_shuffle_bytes_2103_mmxext;
-    }
     if (EXTERNAL_SSE2(cpu_flags)) {
+        shuffle_bytes_2103 = ff_shuffle_bytes_2103_sse2;
 #if ARCH_X86_64
         uyvytoyuv422 = ff_uyvytoyuv422_sse2;
 #endif
diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm
index 0bf1278718..2d2ac778b7 100644
--- a/libswscale/x86/rgb_2_rgb.asm
+++ b/libswscale/x86/rgb_2_rgb.asm
@@ -25,7 +25,7 @@
 
 SECTION_RODATA
 
-pb_mask_shuffle2103_mmx times 8 dw 255
+pb_mask_shuffle2103 times 8 dw 255
 pb_shuffle2103: db 2, 1, 0, 3, 6, 5, 4, 7, 10, 9, 8, 11, 14, 13, 12, 15
 pb_shuffle0321: db 0, 3, 2, 1, 4, 7, 6, 5, 8, 11, 10, 9, 12, 15, 14, 13
 pb_shuffle1230: db 1, 2, 3, 0, 5, 6, 7, 4, 9, 10, 11, 8, 13, 14, 15, 12
@@ -50,11 +50,10 @@ SECTION .text
 ;------------------------------------------------------------------------------
 ; shuffle_bytes_2103_mmext (const uint8_t *src, uint8_t *dst, int src_size)
 ;------------------------------------------------------------------------------
-INIT_MMX mmxext
-cglobal shuffle_bytes_2103, 3, 5, 8, src, dst, w, tmp, x
-    mova   m6, [pb_mask_shuffle2103_mmx]
-    mova   m7, m6
-    psllq  m7, 8
+INIT_XMM sse2
+cglobal shuffle_bytes_2103, 3, 5, 4, src, dst, w, tmp, x
+    mova   m2, [pb_mask_shuffle2103]
+    psllq  m3, m2, 8
 
     movsxdifnidn wq, wd
     mov xq, wq
@@ -86,28 +85,21 @@ jge .end
 
 .loop_simd:
     movu     m0, [srcq+wq]
-    movu     m1, [srcq+wq+8]
-
-    pshufw   m3, m0, 177
-    pshufw   m5, m1, 177
 
-    pand     m0, m7
-    pand     m3, m6
+    pshuflw   m1, m0, 0xb1
+    pshufhw   m1, m1, 0xb1
 
-    pand     m1, m7
-    pand     m5, m6
+    pand     m0, m3
+    pand     m1, m2
 
-    por      m0, m3
-    por      m1, m5
+    por      m0, m1
 
     movu      [dstq+wq], m0
-    movu  [dstq+wq + 8], m1
 
-    add              wq, mmsize*2
+    add              wq, mmsize
     jl .loop_simd
 
 .end:
-    emms
     RET
 
 ;------------------------------------------------------------------------------
-- 
2.45.1