diff options
| author | Kevin O'Connor <kevin@koconnor.net> | 2019-01-18 20:05:55 -0500 |
|---|---|---|
| committer | Kevin O'Connor <kevin@koconnor.net> | 2019-01-28 20:05:50 -0500 |
| commit | c3e889a67cf5ac0ad2a04b8b5ed7fb4c7fb5bbcd (patch) | |
| tree | 09b7c8c304741930e2b4501795b623b8b8f18301 | |
| parent | 8cd83b4c2dcaeac1fe68f18eadd7f25ff42476c2 (diff) | |
| download | kutter-c3e889a67cf5ac0ad2a04b8b5ed7fb4c7fb5bbcd.tar.gz kutter-c3e889a67cf5ac0ad2a04b8b5ed7fb4c7fb5bbcd.tar.xz kutter-c3e889a67cf5ac0ad2a04b8b5ed7fb4c7fb5bbcd.zip | |
docs: Add performance results for SAMD51
Signed-off-by: Kevin O'Connor <kevin@koconnor.net>
| -rwxr-xr-x | docs/Debugging.md | 18 | ||||
| -rwxr-xr-x | docs/Features.md | 5 |
2 files changed, 21 insertions, 2 deletions
diff --git a/docs/Debugging.md b/docs/Debugging.md index a96538c5..bd637a4e 100755 --- a/docs/Debugging.md +++ b/docs/Debugging.md @@ -390,6 +390,23 @@ The test was last run on commit `b161a69e` with gcc version stepper result is `SET ticks 277`, the best dual stepper result is `SET ticks 410`, and the best three stepper result is `SET ticks 664`. +### SAMD51 step rate benchmark ### + +The following configuration sequence is used on the SAMD51: +``` +allocate_oids count=3 +config_stepper oid=0 step_pin=PA22 dir_pin=PA20 min_stop_interval=0 invert_step=0 +config_stepper oid=1 step_pin=PA22 dir_pin=PA21 min_stop_interval=0 invert_step=0 +config_stepper oid=2 step_pin=PA22 dir_pin=PA19 min_stop_interval=0 invert_step=0 +finalize_config crc=0 +``` + +The test was last run on commit `8cd83b4c` with gcc version +`arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0` on a SAMD51G19A +micro-controller. The best single stepper result is `SET ticks 114`, +the best dual stepper result is `SET ticks 114`, and the best three +stepper result is `SET ticks 119`. + ## Command dispatch benchmark ## The command dispatch benchmark tests how many "dummy" commands the @@ -419,6 +436,7 @@ commands per second is then `100000 * mcu_frequency / clock_diff`. | lpc1768 (USB) | 546K | b161a69e | arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0 | | sam4s8c (USB) | 579K | 8e0eb0d5 | arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0 | | lpc1769 (USB) | 619K | b161a69e | arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0 | +| samd51 (USB) | 620K | 8cd83b4c | arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0 | Host Benchmarks =============== diff --git a/docs/Features.md b/docs/Features.md index b0b43538..5e7f9f9e 100755 --- a/docs/Features.md +++ b/docs/Features.md @@ -137,11 +137,12 @@ represent total number of steps per second on the micro-controller. | SAM4S8C ARM | 455K | 455K | | Smoothieboard (ARM LPC1768) | 487K | 487K | | Smoothieboard (ARM LPC1769) | 584K | 584K | +| SAMD51 ARM | 630K | 630K | | SAM4E8E ARM | 638K | 638K | | Beaglebone PRU | 680K | 680K | On AVR platforms, the highest achievable step rate is with just one stepper stepping. On the STM32F103, Arduino Zero, and Due, the highest step rate is with two simultaneous steppers stepping. On the PRU, -SAM4S8C, SAM4E8E, and LPC176x the highest step rate is with three -simultaneous steppers. +SAMD51, SAM4S8C, SAM4E8E, and LPC176x the highest step rate is with +three simultaneous steppers. |