Please run one script and report runtime numbers for performance comparison

Hi,

at least some people reading this forum should have access to a MKR1000 board.

Please run the sketch attached to this thread http://forum.arduino.cc/index.php?topic=391511.0

and report the numbers (for -Os size optimized default and -O3 optimized, you can change in Arduino IDE platform.txt) in this thread http://forum.arduino.cc/index.php?topic=397480.msg2740647#msg2740647

for comparison of >16MHz Arduino models (and ESP8266-12E) pure integer computing performance on a single sample. I have determined the numbers for Arduino Due and ESP8266-12E already.

Thanks for your support,

Hermann.

Can somebody please run the sketch on Arduino MKR1000?

nathancamp provided both Arduino 101 numbers here.

This is the updated table while waiting for MKR1000 and Arduino Zero numbers:

| model | | -Os | | -O3 | | speed | | processor | | Wifi | | - | - | - | - | - | - | - | - | - | - | - | | 101 | | 846 | | 791 | | 32MHz | | Intel® Curie | | - | | Due | | 548 | | 494 | | 84MHz | | ATSAM3X8E | | - | | MKR1000 | | | | | | 48MHz | | SAMD21 Cortex-M0+ | | yes | | Zero | | | | | | 48MHz | | ATSAMD21G18 | | - | | ESP8266-12E | | 612 | | 304 | | 80MHz | | Tensilica Xtensa LX106 | | yes |

Hermann.

sensorsiot provided the numbers for MKR1000 (1038, 825), summary in this posting:

Hermann.

Its not optimised for the MKR as it does not have the while serial statement.

No need for that, because the time measurement is done via t0 and t1 timestamps, and there is not a single Serial statement between them. So only for statements and integer comparison/computation get measured with microsecond precision.

Hermann.