void ORDERED_PARTIAL_CONVOLVE_SIMD(int n, float * a, float const * b)
{
int i;
float ab0;
v4sf * RESTRICT va = (v4sf *)a;
v4sf const * RESTRICT vb = (v4sf const *)b;
assert(VALIGNED(a) && VALIGNED(b));
ab0 = a[0] * b[0];
for (i = 0; i < n / 4; i += 2) {
v4sf a1r = va[i+0], a1i = va[i+1];
v4sf b1r = vb[i+0], b1i = vb[i+1];
UNINTERLEAVE2(a1r, a1i, a1r, a1i);
UNINTERLEAVE2(b1r, b1i, b1r, b1i);
VCPLXMUL(a1r, a1i, b1r, b1i);
INTERLEAVE2(a1r, a1i, a1r, a1i);
va[i+0] = a1r, va[i+1] = a1i;
}
a[0] = ab0;
a[1] = b[n] * a[n] - b[n+1] * a[n+1];
}
void ORDERED_CONVOLVE_SIMD(int n, void * not_used, float * a, float const * b)
{
int i;
float ab0, ab1;
v4sf * RESTRICT va = (v4sf *)a;
v4sf const * RESTRICT vb = (v4sf const *)b;
assert(VALIGNED(a) && VALIGNED(b));
ab0 = a[0] * b[0], ab1 = a[1] * b[1];
for (i = 0; i < n / 4; i += 2) {
v4sf a1r = va[i+0], a1i = va[i+1];
v4sf b1r = vb[i+0], b1i = vb[i+1];
UNINTERLEAVE2(a1r, a1i, a1r, a1i);
UNINTERLEAVE2(b1r, b1i, b1r, b1i);
VCPLXMUL(a1r, a1i, b1r, b1i);
INTERLEAVE2(a1r, a1i, a1r, a1i);
va[i+0] = a1r, va[i+1] = a1i;
}
a[0] = ab0, a[1] = ab1;
(void)not_used;
}
/* ---------------------------------------------------------------- */
void
VL_XCAT3(_vl_imconvcol_v, SFX, _sse2)
(T* dst, int dst_stride,
T const* src,
int src_width, int src_height, int src_stride,
T const* filt, int filt_begin, int filt_end,
int step, unsigned int flags)
{
int x = 0 ;
int y ;
int dheight = (src_height - 1) / step + 1 ;
vl_bool use_simd = VALIGNED(src_stride) ;
vl_bool transp = flags & VL_TRANSPOSE ;
vl_bool zeropad = (flags & VL_PAD_MASK) == VL_PAD_BY_ZERO ;
double totcol = 0 ;
double simdcol = 0 ;
/* let filt point to the last sample of the filter */
filt += filt_end - filt_begin ;
while (x < 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 ;
int stop ;
if ((x + VSIZE < src_width) & VALIGNED(src + x) & use_simd)
{
/* ---------------------------------------------- Vectorized */
for (y = 0 ; y < src_height ; y += step) {
union {
VTYPE v ;
T x [VSIZE] ;
} acc ;
VTYPE v, c ;
T const *srci ;
acc.v = VSTZ () ;
v = VSTZ() ;
filti = filt ;
stop = filt_end - y ;
srci = src + x - stop * src_stride ;
if (stop > 0) {
if (zeropad) {
v = VSTZ () ;
} else {
v = * (VTYPE*) (src + x) ;
}
while (filti > filt - stop) {
c = VLD1 (filti--) ;
acc.v = VADD (acc.v, VMUL (v, c)) ;
srci += src_stride ;
}
}
stop = filt_end - VL_MAX(filt_begin, y - src_height + 1) + 1 ;
while (filti > filt - stop) {
v = * (VTYPE*) srci ;
c = VLD1 (filti--) ;
acc.v = VADD (acc.v, VMUL (v, c)) ;
srci += src_stride ;
}
if (zeropad) v = VSTZ () ;
stop = filt_end - filt_begin + 1;
while (filti > filt - stop) {
c = VLD1 (filti--) ;
acc.v = VADD (acc.v, VMUL (v, c)) ;
}
if (transp) {
*dst = acc.x[0] ;
dst += dst_stride ;
*dst = acc.x[1] ;
dst += dst_stride ;
#if(VSIZE == 4)
*dst = acc.x[2] ;
dst += dst_stride ;
*dst = acc.x[3] ;
dst += dst_stride ;
#endif
dst += 1 * 1 - VSIZE * dst_stride ;
} else {
*dst = acc.x[0] ;
dst += 1 ;
*dst = acc.x[1] ;
dst += 1 ;
#if(VSIZE == 4)
*dst = acc.x[2] ;
dst += 1 ;
*dst = acc.x[3] ;
dst += 1 ;
#endif
dst += 1 * dst_stride - VSIZE * 1 ;
}
} /* next y */
if (transp) {
dst += VSIZE * dst_stride - dheight * 1 ;
} else {
dst += VSIZE * 1 - dheight * dst_stride ;
}
x += VSIZE ;
simdcol += VSIZE ;
totcol += VSIZE ;
} else {
/* ------------------------------------------------- Vanilla */
for (y = 0 ; y < 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 - 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 ;
totcol += 1 ;
} /* next x */
}
}
