[x265] [PATCH] arm: Implement planecopy_cp NEON

[ramya at multicorewareinc.com]

# HG changeset patch
# User Ramya Sriraman<ramya at multicorewareinc.com>
# Date 1456985538 -19800
#      Thu Mar 03 11:42:18 2016 +0530
# Node ID dbccf88be30776f12c7f8c52b9da67d4607abcab
# Parent  9cc9920bf82be1b43efd2a3628e28a3a78ab3b2f
arm: Implement planecopy_cp NEON

diff -r 9cc9920bf82b -r dbccf88be307 source/common/arm/asm-primitives.cpp
--- a/source/common/arm/asm-primitives.cpp	Wed Mar 02 17:26:11 2016 +0530
+++ b/source/common/arm/asm-primitives.cpp	Thu Mar 03 11:42:18 2016 +0530
@@ -142,6 +142,9 @@
         p.pu[LUMA_64x48].copy_pp = PFX(blockcopy_pp_64x48_neon);
         p.pu[LUMA_64x64].copy_pp = PFX(blockcopy_pp_64x64_neon);
 
+        // planecopy
+        p.planecopy_cp = PFX(pixel_planecopy_cp_neon);
+
         // sad
         p.pu[LUMA_8x4].sad    = PFX(pixel_sad_8x4_neon);
         p.pu[LUMA_8x8].sad    = PFX(pixel_sad_8x8_neon);
diff -r 9cc9920bf82b -r dbccf88be307 source/common/arm/pixel-util.S
--- a/source/common/arm/pixel-util.S	Wed Mar 02 17:26:11 2016 +0530
+++ b/source/common/arm/pixel-util.S	Thu Mar 03 11:42:18 2016 +0530
@@ -626,3 +626,56 @@
     pop             {r4, r5}
     bx              lr
 endfunc
+
+function x265_pixel_planecopy_cp_neon
+    push            {r4, r5, r6}
+    ldr             r4, [sp, #12]
+    ldr             r5, [sp, #16]
+    ldr             r12, [sp, #20]
+    vdup.8          q2, r12
+    sub             r5, #1
+
+.loop_h:
+    eor             r6, r6
+    eor             r12, r12
+.loop_w:
+    add             r12, r0, r6
+    vld1.u8         {q0}, [r12]
+    vshl.u8         q0, q0, q2
+    add             r12, r2, r6
+    vst1.u8         {q0}, [r12]
+
+    add             r6, #16
+    cmp             r6, r4
+    blt             .loop_w
+
+    add             r0, r1
+    add             r2, r3
+
+    subs             r5, #1
+    bgt             .loop_h
+
+// handle last row
+    mov             r5, r4
+    lsr             r5, #3
+
+.loopW8:
+    vld1.u8         d0, [r0]!
+    vshl.u8         d0, d0, d4
+    vst1.u8         d0, [r2]!
+    subs            r4, r4, #8
+    subs            r5, #1
+    bgt             .loopW8
+
+    mov             r5,#8
+    sub             r5, r4
+    sub             r0, r5
+    sub             r2, r5
+    vld1.u8         d0, [r0]
+    vshl.u8         d0, d0, d4
+    vst1.u8         d0, [r2]
+
+    pop             {r4, r5, r6}
+    bx              lr
+endfunc
+
diff -r 9cc9920bf82b -r dbccf88be307 source/common/arm/pixel.h
--- a/source/common/arm/pixel.h	Wed Mar 02 17:26:11 2016 +0530
+++ b/source/common/arm/pixel.h	Thu Mar 03 11:42:18 2016 +0530
@@ -163,4 +163,6 @@
 void x265_pixel_add_ps_16x16_neon(pixel* a, intptr_t dstride, const pixel* b0, const int16_t* b1, intptr_t sstride0, intptr_t sstride1);
 void x265_pixel_add_ps_32x32_neon(pixel* a, intptr_t dstride, const pixel* b0, const int16_t* b1, intptr_t sstride0, intptr_t sstride1);
 void x265_pixel_add_ps_64x64_neon(pixel* a, intptr_t dstride, const pixel* b0, const int16_t* b1, intptr_t sstride0, intptr_t sstride1);
+
+void x265_pixel_planecopy_cp_neon(const uint8_t* src, intptr_t srcStride, pixel* dst, intptr_t dstStride, int width, int height, int shift);
 #endif // ifndef X265_I386_PIXEL_ARM_H