int sobel_argb32_3x3_partial(vbx_uword_t *sobel_out, vbx_uword_t *argb_in, const short image_width,
const short image_height, const short image_pitch, const short renorm)
{
VBX::Prefetcher<vbx_uword_t> input(1,image_width,argb_in,argb_in+image_height*image_pitch,image_pitch);
VBX::Vector<vbx_uword_t> output(image_width);
VBX::Vector<vbx_uhalf_t>* luma[3];
luma[0]=new VBX::Vector<vbx_uhalf_t>(image_width);
luma[1]=new VBX::Vector<vbx_uhalf_t>(image_width);
luma[2]=new VBX::Vector<vbx_uhalf_t>(image_width);
VBX::Vector<vbx_uhalf_t> gradient_x(image_width);
VBX::Vector<vbx_uhalf_t> gradient_y(image_width);
VBX::Vector<vbx_uhalf_t>* sobel_rows[3];
sobel_rows[0]=new VBX::Vector<vbx_uhalf_t>(image_width);
sobel_rows[1]=new VBX::Vector<vbx_uhalf_t>(image_width);
sobel_rows[2]=new VBX::Vector<vbx_uhalf_t>(image_width);
input.fetch();
int rowmod3=0;
for(int row=0;row<image_height;row++){
input.fetch();
VBX::Vector<vbx_uhalf_t>& sobel_top= *sobel_rows[rowmod3];
VBX::Vector<vbx_uhalf_t>& sobel_bot= *sobel_rows[mod3(rowmod3+2)];
VBX::Vector<vbx_uhalf_t>& luma_top= *luma[rowmod3];
VBX::Vector<vbx_uhalf_t>& luma_mid= *luma[mod3(rowmod3+1)];
VBX::Vector<vbx_uhalf_t>& luma_bot= *luma[mod3(rowmod3+2)];
rowmod3=mod3(rowmod3+1);
argb_to_luma8(luma_bot,input[0]);
sobel_row( sobel_bot ,luma_bot);
if(row<2){
continue;
}
gradient_y=absdiff(sobel_top,sobel_bot);
gradient_x=luma_top +luma_bot + luma_mid*2;
gradient_x[1 upto image_width-1]=absdiff(gradient_x[0 upto image_width-2],gradient_x[2 upto image_width]);
output=((gradient_x + gradient_y) >> renorm);
output.cond_move(output>0xFF,0xFF);
output*=0x010101;
//write to output buffer, skipping first and last elements
output[1 upto (image_width -1)].dma_write(sobel_out+(row-1)*image_pitch +1);
}
output=0;
output.dma_write(sobel_out);
output.dma_write(sobel_out+ (image_height-1)*image_pitch);
delete luma[0];
delete luma[1];
delete luma[2];
delete sobel_rows[0];
delete sobel_rows[1];
delete sobel_rows[2];
return 0;
}
void argb_to_luma8(vbx_ubyte_t* output,vbx_uword_t* input,int rows,int cols)
{
VBX::Prefetcher<vbx_uword_t> v_in(1,cols,input,input+rows*cols,cols);
VBX::Vector<vbx_uhalf_t> v_luma_calc(cols);
VBX::Vector<vbx_ubyte_t> v_luma_byte(cols);
v_in.fetch();
for(int i=0; i<rows; i++) {
v_in.fetch();
argb_to_luma8(v_luma_calc,v_in[0]);
v_luma_byte=v_luma_calc;
v_luma_byte.dma_write(output+i*cols);
}
}
