From bd394012e8e2df4d204668134b76723f0ad41536 Mon Sep 17 00:00:00 2001
From: Andrey Kamaev <no@email>
Date: Tue, 3 Jul 2012 11:30:17 +0000
Subject: [PATCH] Eliminated discrepancy between SSE and non-SSE versions of
 bilinear resize

---
 modules/imgproc/src/imgwarp.cpp | 45 +++++++++++++++++++++++++--------
 1 file changed, 34 insertions(+), 11 deletions(-)

diff --git a/modules/imgproc/src/imgwarp.cpp b/modules/imgproc/src/imgwarp.cpp
index bc5477fd7..a311d5be6 100644
--- a/modules/imgproc/src/imgwarp.cpp
+++ b/modules/imgproc/src/imgwarp.cpp
@@ -782,19 +782,8 @@ struct VResizeCubicVec_32f
     }
 };
 
-typedef HResizeNoVec HResizeLinearVec_8u32s;
-typedef HResizeNoVec HResizeLinearVec_16u32f;
-typedef HResizeNoVec HResizeLinearVec_16s32f;
-typedef HResizeNoVec HResizeLinearVec_32f;
-typedef HResizeNoVec HResizeLinearVec_64f;
-
 #else
 
-typedef HResizeNoVec HResizeLinearVec_8u32s;
-typedef HResizeNoVec HResizeLinearVec_16u32f;
-typedef HResizeNoVec HResizeLinearVec_16s32f;
-typedef HResizeNoVec HResizeLinearVec_32f;
-
 typedef VResizeNoVec VResizeLinearVec_32s8u;
 typedef VResizeNoVec VResizeLinearVec_32f16u;
 typedef VResizeNoVec VResizeLinearVec_32f16s;
@@ -807,6 +796,12 @@ typedef VResizeNoVec VResizeCubicVec_32f;
 
 #endif
 
+typedef HResizeNoVec HResizeLinearVec_8u32s;
+typedef HResizeNoVec HResizeLinearVec_16u32f;
+typedef HResizeNoVec HResizeLinearVec_16s32f;
+typedef HResizeNoVec HResizeLinearVec_32f;
+typedef HResizeNoVec HResizeLinearVec_64f;
+
 
 template<typename T, typename WT, typename AT, int ONE, class VecOp>
 struct HResizeLinear
@@ -894,6 +889,34 @@ struct VResizeLinear
     }
 };
 
+template<>
+struct VResizeLinear<uchar, int, short, FixedPtCast<int, uchar, INTER_RESIZE_COEF_BITS*2>, VResizeLinearVec_32s8u>
+{
+    typedef uchar value_type;
+    typedef int buf_type;
+    typedef short alpha_type;
+
+    void operator()(const buf_type** src, value_type* dst, const alpha_type* beta, int width ) const
+    {
+        alpha_type b0 = beta[0], b1 = beta[1];
+        const buf_type *S0 = src[0], *S1 = src[1];
+        VResizeLinearVec_32s8u vecOp;
+
+        int x = vecOp((const uchar**)src, (uchar*)dst, (const uchar*)beta, width);
+        #if CV_ENABLE_UNROLLED
+        for( ; x <= width - 4; x += 4 )
+        {
+            dst[x+0] = uchar(( ((b0 * (S0[x+0] >> 4)) >> 16) + ((b1 * (S1[x+0] >> 4)) >> 16) + 2)>>2);
+            dst[x+1] = uchar(( ((b0 * (S0[x+1] >> 4)) >> 16) + ((b1 * (S1[x+1] >> 4)) >> 16) + 2)>>2);
+            dst[x+2] = uchar(( ((b0 * (S0[x+2] >> 4)) >> 16) + ((b1 * (S1[x+2] >> 4)) >> 16) + 2)>>2);
+            dst[x+3] = uchar(( ((b0 * (S0[x+3] >> 4)) >> 16) + ((b1 * (S1[x+3] >> 4)) >> 16) + 2)>>2);
+        }
+        #endif
+        for( ; x < width; x++ )
+            dst[x] = uchar(( ((b0 * (S0[x] >> 4)) >> 16) + ((b1 * (S1[x] >> 4)) >> 16) + 2)>>2);
+    }
+};
+
 
 template<typename T, typename WT, typename AT>
 struct HResizeCubic