VL_EXPORT COMPARISONFUNCTION_TYPE
VL_XCAT(vl_get_vector_comparison_function_, SFX)(VlVectorComparisonType type)
{
COMPARISONFUNCTION_TYPE function = 0 ;
switch (type) {
case VlDistanceL2 : function = VL_XCAT(_vl_distance_l2_, SFX) ; break ;
case VlDistanceL1 : function = VL_XCAT(_vl_distance_l1_, SFX) ; break ;
case VlDistanceChi2 : function = VL_XCAT(_vl_distance_chi2_, SFX) ; break ;
case VlDistanceHellinger : function = VL_XCAT(_vl_distance_hellinger_, SFX) ; break ;
case VlDistanceJS : function = VL_XCAT(_vl_distance_js_, SFX) ; break ;
case VlKernelL2 : function = VL_XCAT(_vl_kernel_l2_, SFX) ; break ;
case VlKernelL1 : function = VL_XCAT(_vl_kernel_l1_, SFX) ; break ;
case VlKernelChi2 : function = VL_XCAT(_vl_kernel_chi2_, SFX) ; break ;
case VlKernelHellinger : function = VL_XCAT(_vl_kernel_hellinger_, SFX) ; break ;
case VlKernelJS : function = VL_XCAT(_vl_kernel_js_, SFX) ; break ;
default: abort() ;
}
#ifndef VL_DISABLE_SSE2
/* if a SSE2 implementation is available, use it */
if (vl_cpu_has_sse2() && vl_get_simd_enabled()) {
switch (type) {
case VlDistanceL2 : function = VL_XCAT(_vl_distance_l2_sse2_, SFX) ; break ;
case VlDistanceL1 : function = VL_XCAT(_vl_distance_l1_sse2_, SFX) ; break ;
case VlDistanceChi2 : function = VL_XCAT(_vl_distance_chi2_sse2_, SFX) ; break ;
case VlKernelL2 : function = VL_XCAT(_vl_kernel_l2_sse2_, SFX) ; break ;
case VlKernelL1 : function = VL_XCAT(_vl_kernel_l1_sse2_, SFX) ; break ;
case VlKernelChi2 : function = VL_XCAT(_vl_kernel_chi2_sse2_, SFX) ; break ;
default: break ;
}
}
#endif
return function ;
}
VL_EXPORT COMPARISONFUNCTION3_TYPE
VL_XCAT(vl_get_vector_3_comparison_function_, SFX)(VlVectorComparisonType type)
{
COMPARISONFUNCTION3_TYPE function = 0 ;
switch (type) {
case VlDistanceMahalanobis : function = VL_XCAT(_vl_distance_mahalanobis_sq_, SFX) ; break ;
default: abort() ;
}
#ifndef VL_DISABLE_SSE2
/* if a SSE2 implementation is available, use it */
if (vl_cpu_has_sse2() && vl_get_simd_enabled()) {
switch (type) {
case VlDistanceMahalanobis : function = VL_XCAT(_vl_distance_mahalanobis_sq_sse2_, SFX) ; break ;
default: break ;
}
}
#endif
#ifndef VL_DISABLE_AVX
/* if an AVX implementation is available, use it */
if (vl_cpu_has_avx() && vl_get_simd_enabled()) {
switch (type) {
case VlDistanceMahalanobis : function = VL_XCAT(_vl_distance_mahalanobis_sq_avx_, SFX) ; break ;
default: break ;
}
}
#endif
return function ;
}
VL_EXPORT void
VL_XCAT(vl_imconvcol_v, SFX)
(T* dst, vl_size dst_stride,
T const* src,
vl_size src_width, vl_size src_height, vl_size src_stride,
T const* filt, vl_index filt_begin, vl_index filt_end,
int step, unsigned int flags)
{
vl_index x = 0 ;
vl_index y ;
vl_index dheight = (src_height - 1) / step + 1 ;
vl_bool transp = flags & VL_TRANSPOSE ;
vl_bool zeropad = (flags & VL_PAD_MASK) == VL_PAD_BY_ZERO ;
/* dispatch to accelerated version */
#ifndef VL_DISABLE_SSE2
if (vl_cpu_has_sse2() && vl_get_simd_enabled()) {
VL_XCAT3(_vl_imconvcol_v,SFX,_sse2)
(dst,dst_stride,
src,src_width,src_height,src_stride,
filt,filt_begin,filt_end,
step,flags) ;
return ;
}
#endif
/* let filt point to the last sample of the filter */
filt += filt_end - filt_begin ;
while (x < (signed)src_width) {
/* Calculate dest[x,y] = sum_p image[x,p] filt[y - p]
* where supp(filt) = [filt_begin, filt_end] = [fb,fe].
*
* CHUNK_A: y - fe <= p < 0
* completes VL_MAX(fe - y, 0) samples
* CHUNK_B: VL_MAX(y - fe, 0) <= p < VL_MIN(y - fb, height - 1)
* completes fe - VL_MAX(fb, height - y) + 1 samples
* CHUNK_C: completes all samples
*/
T const *filti ;
vl_index stop ;
for (y = 0 ; y < (signed)src_height ; y += step) {
T acc = 0 ;
T v = 0, c ;
T const* srci ;
filti = filt ;
stop = filt_end - y ;
srci = src + x - stop * src_stride ;
if (stop > 0) {
if (zeropad) {
v = 0 ;
} else {
v = *(src + x) ;
}
while (filti > filt - stop) {
c = *filti-- ;
acc += v * c ;
srci += src_stride ;
}
}
stop = filt_end - VL_MAX(filt_begin, y - (signed)src_height + 1) + 1 ;
while (filti > filt - stop) {
v = *srci ;
c = *filti-- ;
acc += v * c ;
srci += src_stride ;
}
if (zeropad) v = 0 ;
stop = filt_end - filt_begin + 1 ;
while (filti > filt - stop) {
c = *filti-- ;
acc += v * c ;
}
if (transp) {
*dst = acc ; dst += 1 ;
} else {
*dst = acc ; dst += dst_stride ;
}
} /* next y */
if (transp) {
dst += 1 * dst_stride - dheight * 1 ;
} else {
dst += 1 * 1 - dheight * dst_stride ;
}
x += 1 ;
} /* next x */
}
