This is with STM32F100 CM3 @48MHz (Teensy compatible I think):
timer = millis;
for (i=0;i<400;i++) {
sinres[i]=sinf((float)i);
}
timer = millis - timer;
printf("\rElapsed time float sin 400x into array: %u millis\n", timer);
timer = millis;
for (i=0;i<400;i++) {
sinresd[i]=sinl((long double)i);
}
timer = millis - timer;
printf("\rElapsed time double sin 400x into array: %u millis\n", timer);
Elapsed time float sin 400x into array: 8 millis
Elapsed time double sin 400x into array: 19 millis