From 2e7b9a2c0f3f920caad5d2fc17713c6cc0f579b2 Mon Sep 17 00:00:00 2001 From: orestis Date: Fri, 19 Dec 2014 22:15:37 +0200 Subject: [PATCH] SymmRowSmallVec_8u32s 1x3 asymmetric NEON speedup: 1.95x Auto-vect speedup: 1.17x Test kernel: [-2, 0, 2] --- modules/imgproc/src/filter.cpp | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/modules/imgproc/src/filter.cpp b/modules/imgproc/src/filter.cpp index e810bf59b4..55cde48742 100644 --- a/modules/imgproc/src/filter.cpp +++ b/modules/imgproc/src/filter.cpp @@ -2370,9 +2370,32 @@ struct SymmRowSmallVec_8u32s vst1q_s32((int32_t *)(dst + i), vmovl_s16(vget_low_s16(y0))); vst1q_s32((int32_t *)(dst + i + 4), vmovl_s16(vget_high_s16(y0))); } + } else { - return 0; + int32x4_t k32 = vdupq_n_s32(0); + k32 = vld1q_lane_s32(kx + 1, k32, 1); + + int16x4_t k = vqmovn_s32(k32); + + uint8x8_t z = vdup_n_u8(0); + + for( ; i <= width - 8; i += 8, src += 8 ) + { + uint8x8_t x0, x1; + x0 = vld1_u8( (uint8_t *) (src - cn) ); + x1 = vld1_u8( (uint8_t *) (src + cn) ); + + int16x8_t y0; + int32x4_t y1, y2; + y0 = vsubq_s16(vreinterpretq_s16_u16(vaddl_u8(x1, z)), + vreinterpretq_s16_u16(vaddl_u8(x0, z))); + y1 = vmull_lane_s16(vget_low_s16(y0), k, 1); + y2 = vmull_lane_s16(vget_high_s16(y0), k, 1); + + vst1q_s32((int32_t *)(dst + i), y1); + vst1q_s32((int32_t *)(dst + i + 4), y2); + } } } else if( _ksize == 5 )