[x265] [PATCH Review Only] filterHorizontal_p_p_4, for 4x4 block

[praveen at multicorewareinc.com]

# HG changeset patch
# User praveen Tiwari
# Date 1380890893 -19800
# Node ID f1b84f51c6ca4bff034f8a6422ac66dc31b7825c
# Parent  bf14f75b8cf99806c75cdc1a50b28b6cf265e3bd
filterHorizontal_p_p_4, for 4x4 block

diff -r bf14f75b8cf9 -r f1b84f51c6ca source/common/x86/ipfilter8.asm
--- a/source/common/x86/ipfilter8.asm	Fri Oct 04 01:39:22 2013 -0500
+++ b/source/common/x86/ipfilter8.asm	Fri Oct 04 18:18:13 2013 +0530
@@ -26,107 +26,58 @@
 %include "x86inc.asm"
 %include "x86util.asm"
 
-%if ARCH_X86_64 == 0
-
 SECTION_RODATA 32
-tab_leftmask:   db -1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0, 0, 0
-
 tab_Tm:     db 0, 1, 2, 3, 1, 2, 3, 4, 2, 3, 4, 5, 3, 4, 5, 6
-            db 4, 5, 6, 7, 5, 6, 7, 8, 6, 7, 8, 9, 7, 8, 9, 10
 
 tab_c_512:  times 8 dw 512
 
 SECTION .text
 
-%macro FILTER_H4 3
-    movu        %1, [src + col - 1]
-    pshufb      %2, %1, Tm4
+%macro FILTER_H4_w4 3
+    movu        %1, [srcq - 1]
+    pshufb      %2, %1, Tm0
     pmaddubsw   %2, coef2
-    pshufb      %1, %1, Tm5
-    pmaddubsw   %1, coef2
     phaddw      %2, %1
     pmulhrsw    %2, %3
     packuswb    %2, %2
 %endmacro
 
+%macro FILTER_H4_w4_CALL 0
+    FILTER_H4_w4   x0, x1, x2
+
+    movd        [dstq],      x1
+
+    add         srcq,        srcstrideq
+    add         dstq,        dststrideq
+%endmacro
+
 ;-----------------------------------------------------------------------------
 ; void filterHorizontal_p_p_4(pixel *src, intptr_t srcStride, pixel *dst, intptr_t dstStride, int width, int height, short const *coeff)
 ;-----------------------------------------------------------------------------
 INIT_XMM sse4
-cglobal filterHorizontal_p_p_4, 0, 7, 8
-%define src         r0
-%define dst         r1
-%define row         r2
-%define col         r3
-%define width       r4
-%define widthleft   r5
-%define mask_offset r6
-%define coef2       m7
-%define x3          m6
-%define Tm5         m5
-%define Tm4         m4
-%define x2          m3
-%define x1          m2
-%define x0          m1
-%define leftmask    m0
-%define tmp         r0
-%define tmp1        r1
- 
-    mov         tmp,        r6m
-    movu        coef2,      [tmp]
+cglobal filterHorizontal_p_p_4, 4, 5, 5, src, srcstride, dst, dststride
+%define coef2       m4
+%define Tm0         m3
+%define x2          m2
+%define x1          m1
+%define x0          m0
+
+    mov         r4,         r6m
+    movu        coef2,      [r4]
     packsswb    coef2,      coef2
     pshufd      coef2,      coef2,      0
 
-    mova        x3,         [tab_c_512]
+    mova        x2,         [tab_c_512]
 
-    mov         width,      r4m
-    mov         widthleft,  width
-    and         width,      ~7
-    and         widthleft,  7
-    mov         mask_offset,  widthleft
-    neg         mask_offset
+    mova        Tm0,        [tab_Tm]
 
-    movq        leftmask,   [tab_leftmask + (7 + mask_offset)]
-    mova        Tm4,        [tab_Tm]
-    mova        Tm5,        [tab_Tm + 16]
+%rep 3
+FILTER_H4_w4_CALL
+%endrep
 
-    mov         src,        r0m
-    mov         dst,        r2m
-    mov         row,        r5m
-
-_loop_row:
-    xor         col,        col
- 
-_loop_col:
-    FILTER_H4   x0, x1, x3
-    movh        [dst + col], x1
-
-    add         col,         8
- 
-    cmp         col,        width
-    jl         _loop_col
-
-_end_col:
-    test        widthleft,  widthleft
-    jz          _next_row
-
-    movq        x2, [dst + col]
-    FILTER_H4   x0, x1, x3
-    pblendvb    x2, x2, x1, leftmask
-    movh        [dst + col], x2
-
-_next_row:
-    add         src,        r1m
-    add         dst,        r3m
-    dec         row
-
-    test        row,        row
-    jz          _end_row
-
-    jmp         _loop_row
+    FILTER_H4_w4   x0, x1, x2
+    movd        [dstq],    x1
 
 _end_row:
 
     RET
-
-%endif  ; ARCH_X86_64 == 0