3diy
/
klipper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs: Update benchmarks 

Signed-off-by: Kevin O'Connor <kevin@koconnor.net>
This commit is contained in:
Kevin O'Connor 2018-11-16 18:59:55 -05:00
parent b161a69e98
commit 52fa91fb9a
2 changed files with 19 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
docs/Debugging.md
View File

@ -264,12 +264,13 @@ config_stepper oid=2 step_pin=ar23 dir_pin=ar22 min_stop_interval=0 invert_step=
finalize_config crc=0 finalize_config crc=0
``` ```
The test was last run on commit `f886212b` with gcc version `avr-gcc The test was last run on commit `b161a69e` with gcc version `avr-gcc
(GCC) 4.8.1`. Both the 16Mhz and 20Mhz tests were run using simulavr (GCC) 4.8.1`. Both the 16Mhz and 20Mhz tests were run using simulavr
configured for an atmega644p (previous tests have confirmed simulavr configured for an atmega644p (previous tests have confirmed simulavr
results match tests on both a 16Mhz at90usb and a 16Mhz atmega2560). results match tests on both a 16Mhz at90usb and a 16Mhz atmega2560).
On both 16Mhz and 20Mhz the best single stepper result is `SET ticks On both 16Mhz and 20Mhz the best single stepper result is `SET ticks
106` and the best three stepper result is `SET ticks 481`. 106`, the best dual stepper result is `SET ticks 276`, and the best
three stepper result is `SET ticks 481`.
### Arduino Due step rate benchmark ### ### Arduino Due step rate benchmark ###
@ -282,9 +283,9 @@ config_stepper oid=2 step_pin=PA21 dir_pin=PC30 min_stop_interval=0 invert_step=
finalize_config crc=0 finalize_config crc=0
``` ```
The test was last run on commit `67278a6d` with gcc version The test was last run on commit `b161a69e` with gcc version
`arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. The best single `arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. The best single
stepper result is `SET ticks 250`, the best dual stepper result is stepper result is `SET ticks 207`, the best dual stepper result is
`SET ticks 205`, and the best three stepper result is `SET ticks 317`. `SET ticks 205`, and the best three stepper result is `SET ticks 317`.
### Duet Wifi step rate benchmark ### ### Duet Wifi step rate benchmark ###
@ -316,9 +317,10 @@ config_stepper oid=2 step_pin=P8_19 dir_pin=P8_18 min_stop_interval=0 invert_ste
finalize_config crc=0 finalize_config crc=0
``` ```
The test was last run on commit `0adea120`. The best single stepper The test was last run on commit `b161a69e` with gcc version `pru-gcc
result is `SET ticks 909`, the best dual stepper result is `SET ticks (GCC) 8.0.0 20170530 (experimental)`. The best single stepper result
859`, and the best three stepper result is `SET ticks 871`. is `SET ticks 861`, the best dual stepper result is `SET ticks 853`,
and the best three stepper result is `SET ticks 883`.
### STM32F103 step rate benchmark ### ### STM32F103 step rate benchmark ###
@ -331,10 +333,10 @@ config_stepper oid=2 step_pin=PA4 dir_pin=PB7 min_stop_interval=0 invert_step=0
finalize_config crc=0 finalize_config crc=0
``` ```
The test was last run on commit `7cbc44b8` with gcc version The test was last run on commit `b161a69e` with gcc version
`arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. The best single `arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. The best single
stepper result is `SET ticks 44`, the best dual stepper result is `SET stepper result is `SET ticks 41`, the best dual stepper result is `SET
ticks 44`, and the best three stepper result is `SET ticks 74`. ticks 48`, and the best three stepper result is `SET ticks 80`.
### LPC176x step rate benchmark ### ### LPC176x step rate benchmark ###
@ -347,13 +349,13 @@ config_stepper oid=2 step_pin=P1.23 dir_pin=P1.18 min_stop_interval=0 invert_ste
finalize_config crc=0 finalize_config crc=0
``` ```
The test was last run on commit `8fca9084` with gcc version The test was last run on commit `b161a69e` with gcc version
`arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. For the 100Mhz `arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. For the 100Mhz
LPC1768, the best single stepper result is `SET ticks 128`, the best LPC1768, the best single stepper result is `SET ticks 119`, the best
dual stepper result is `SET ticks 118`, and the best three stepper dual stepper result is `SET ticks 118`, and the best three stepper
result is `SET ticks 154`. The 120Mhz LPC1769 results were obtained by result is `SET ticks 154`. The 120Mhz LPC1769 results were obtained by
overclocking an LPC1768 to 120Mhz - the best single stepper result is overclocking an LPC1768 to 120Mhz - the best single stepper result is
`SET ticks 148`, the best dual stepper result is `SET ticks 137`, and `SET ticks 140`, the best dual stepper result is `SET ticks 137`, and
the best three stepper result is `SET ticks 154`. the best three stepper result is `SET ticks 154`.
### SAMD21 step rate benchmark ### ### SAMD21 step rate benchmark ###
@ -367,9 +369,9 @@ config_stepper oid=2 step_pin=PA17 dir_pin=PA21 min_stop_interval=0 invert_step=
finalize_config crc=0 finalize_config crc=0
``` ```
The test was last run on commit `cf2393ef` with gcc version The test was last run on commit `b161a69e` with gcc version
`arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. The best single `arm-none-eabi-gcc (Fedora 7.1.0-5.fc27) 7.1.0`. The best single
stepper result is `SET ticks 323`, the best dual stepper result is 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`. `SET ticks 410`, and the best three stepper result is `SET ticks 664`.
Host Benchmarks Host Benchmarks

4
docs/Features.md
View File

@ -132,12 +132,12 @@ represent total number of steps per second on the micro-controller.
| 16Mhz AVR | 151K | 100K | | 16Mhz AVR | 151K | 100K |
| 20Mhz AVR | 189K | 125K | | 20Mhz AVR | 189K | 125K |
| Arduino Zero (ARM SAMD21) | 234K | 217K | | Arduino Zero (ARM SAMD21) | 234K | 217K |
| STM32F103 | 364K | 324K | | STM32F103 | 333K | 300K |
| Arduino Due (ARM SAM3X8E) | 410K | 397K | | Arduino Due (ARM SAM3X8E) | 410K | 397K |
| Smoothieboard (ARM LPC1768) | 487K | 487K | | Smoothieboard (ARM LPC1768) | 487K | 487K |
| Smoothieboard (ARM LPC1769) | 584K | 584K | | Smoothieboard (ARM LPC1769) | 584K | 584K |
| SAM4E8E ARM | 638K | 638K | | SAM4E8E ARM | 638K | 638K |
| Beaglebone PRU | 689K | 689K | | Beaglebone PRU | 680K | 680K |
On AVR platforms, the highest achievable step rate is with just one On AVR platforms, the highest achievable step rate is with just one
stepper stepping. On the STM32F103, Arduino Zero, and Due, the highest stepper stepping. On the STM32F103, Arduino Zero, and Due, the highest