x86: move horizontal add macros to x86util

Also port relevant AVX2/XOP optimizations from x264 with permission
to relicense to LGPL from the corresponding authors

Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

libavcodec/x86/h264_intrapred_10bit.asm

@@ -171,22 +171,6 @@ PRED4x4_HD
 ;-----------------------------------------------------------------------------
 ; void ff_pred4x4_dc(pixel *src, const pixel *topright, int stride)
 ;-----------------------------------------------------------------------------
-%macro HADDD 2 ; sum junk
-%if mmsize == 16
-    movhlps %2, %1
-    paddd   %1, %2
-    pshuflw %2, %1, 0xE
-    paddd   %1, %2
-%else
-    pshufw  %2, %1, 0xE
-    paddd   %1, %2
-%endif
-%endmacro
-
-%macro HADDW 2
-    pmaddwd %1, [pw_1]
-    HADDD   %1, %2
-%endmacro
 
 INIT_MMX mmxext
 cglobal pred4x4_dc_10, 3, 3

libavutil/x86/x86util.asm

@@ -273,6 +273,39 @@
 %endif
 %endmacro
 
+%macro HADDD 2 ; sum junk
+%if sizeof%1 == 32
+%define %2 xmm%2
+    vextracti128 %2, %1, 1
+%define %1 xmm%1
+    paddd   %1, %2
+%endif
+%if mmsize >= 16
+%if cpuflag(xop) && sizeof%1 == 16
+    vphadddq %1, %1
+%endif
+    movhlps %2, %1
+    paddd   %1, %2
+%endif
+%if notcpuflag(xop) || sizeof%1 != 16
+    PSHUFLW %2, %1, q0032
+    paddd   %1, %2
+%endif
+%undef %1
+%undef %2
+%endmacro
+
+%macro HADDW 2 ; reg, tmp
+%if cpuflag(xop) && sizeof%1 == 16
+    vphaddwq  %1, %1
+    movhlps   %2, %1
+    paddd     %1, %2
+%else
+    pmaddwd %1, [pw_1]
+    HADDD   %1, %2
+%endif
+%endmacro
+
 %macro PALIGNR 4-5
 %if cpuflag(ssse3)
 %if %0==5