1/*
2 * Copyright (C) 2011 University of Szeged
3 * Copyright (C) 2011 Zoltan Herczeg
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 *
14 * THIS SOFTWARE IS PROVIDED BY UNIVERSITY OF SZEGED ``AS IS'' AND ANY
15 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
17 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL UNIVERSITY OF SZEGED OR
18 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
19 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
20 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
21 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
22 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25 */
26
27#ifndef FEGaussianBlurNEON_h
28#define FEGaussianBlurNEON_h
29
30#if HAVE(ARM_NEON_INTRINSICS)
31
32#include "platform/graphics/cpu/arm/filters/NEONHelpers.h"
33#include "platform/graphics/filters/FEGaussianBlur.h"
34
35namespace blink {
36
37inline void boxBlurNEON(Uint8ClampedArray* srcPixelArray, Uint8ClampedArray* dstPixelArray,
38                        unsigned dx, int dxLeft, int dxRight, int stride, int strideLine, int effectWidth, int effectHeight)
39{
40    uint32_t* sourcePixel = reinterpret_cast<uint32_t*>(srcPixelArray->data());
41    uint32_t* destinationPixel = reinterpret_cast<uint32_t*>(dstPixelArray->data());
42
43    float32x4_t deltaX = vdupq_n_f32(1.0 / dx);
44    int pixelLine = strideLine / 4;
45    int pixelStride = stride / 4;
46
47    for (int y = 0; y < effectHeight; ++y) {
48        int line = y * pixelLine;
49        float32x4_t sum = vdupq_n_f32(0);
50        // Fill the kernel
51        int maxKernelSize = std::min(dxRight, effectWidth);
52        for (int i = 0; i < maxKernelSize; ++i) {
53            float32x4_t sourcePixelAsFloat = loadRGBA8AsFloat(sourcePixel + line + i * pixelStride);
54            sum = vaddq_f32(sum, sourcePixelAsFloat);
55        }
56
57        // Blurring
58        for (int x = 0; x < effectWidth; ++x) {
59            int pixelOffset = line + x * pixelStride;
60            float32x4_t result = vmulq_f32(sum, deltaX);
61            storeFloatAsRGBA8(result, destinationPixel + pixelOffset);
62            if (x >= dxLeft) {
63                float32x4_t sourcePixelAsFloat = loadRGBA8AsFloat(sourcePixel + pixelOffset - dxLeft * pixelStride);
64                sum = vsubq_f32(sum, sourcePixelAsFloat);
65            }
66            if (x + dxRight < effectWidth) {
67                float32x4_t sourcePixelAsFloat = loadRGBA8AsFloat(sourcePixel + pixelOffset + dxRight * pixelStride);
68                sum = vaddq_f32(sum, sourcePixelAsFloat);
69            }
70        }
71    }
72}
73
74} // namespace blink
75
76#endif // HAVE(ARM_NEON_INTRINSICS)
77
78#endif // FEGaussianBlurNEON_h
79