Try to use avx_hs() - slow and requires alignment 4096 bits < (l.size*l.siz...

AlexeyAB

2018-08-08 a284a7da8d1facbf984a22302665a2a50295a687

 src/cost_layer.c

@@ -31,7 +31,7 @@

cost_layer make_cost_layer(int batch, int inputs, COST_TYPE cost_type, float scale)
{
    fprintf(stderr, "Cost Layer: %d inputs\n", inputs);
    fprintf(stderr, "cost                                           %4d\n",  inputs);
    cost_layer l = {0};
    l.type = COST;