diff options
| author | Kevin O'Connor <kevin@koconnor.net> | 2024-10-28 13:48:07 -0400 |
|---|---|---|
| committer | Kevin O'Connor <kevin@koconnor.net> | 2024-11-14 11:35:23 -0500 |
| commit | a46dba08e2c1946c0460b8b485dd96046842c448 (patch) | |
| tree | dc6e27031006472c52f1943344e10df239057b24 | |
| parent | f6718291b78488c46de97888ff5764ed2895a9c6 (diff) | |
| download | kutter-a46dba08e2c1946c0460b8b485dd96046842c448.tar.gz kutter-a46dba08e2c1946c0460b8b485dd96046842c448.tar.xz kutter-a46dba08e2c1946c0460b8b485dd96046842c448.zip | |
docs: Add rp2350 to benchmarks
Signed-off-by: Kevin O'Connor <kevin@koconnor.net>
| -rw-r--r-- | docs/Benchmarks.md | 26 | ||||
| -rw-r--r-- | docs/Features.md | 1 |
2 files changed, 20 insertions, 7 deletions
diff --git a/docs/Benchmarks.md b/docs/Benchmarks.md index abe7d741..47ee77d4 100644 --- a/docs/Benchmarks.md +++ b/docs/Benchmarks.md @@ -395,9 +395,9 @@ micro-controller. | 1 stepper | 85 | | 3 stepper | 359 | -### RP2040 step rate benchmark +### RPxxxx step rate benchmark -The following configuration sequence is used on the RP2040: +The following configuration sequence is used on the RP2040 and RP2350: ``` allocate_oids count=3 @@ -407,15 +407,26 @@ config_stepper oid=2 step_pin=gpio27 dir_pin=gpio5 invert_step=-1 step_pulse_tic finalize_config crc=0 ``` -The test was last run on commit `59314d99` with gcc version -`arm-none-eabi-gcc (Fedora 10.2.0-4.fc34) 10.2.0` on a Raspberry Pi -Pico board. +The test was last run on commit `f6718291` with gcc version +`arm-none-eabi-gcc (Fedora 14.1.0-1.fc40) 14.1.0` on Raspberry Pi +Pico and Pico 2 boards. -| rp2040 | ticks | +| rp2040 (*) | ticks | | -------------------- | ----- | | 1 stepper | 5 | | 3 stepper | 22 | +| rp2350 | ticks | +| -------------------- | ----- | +| 1 stepper | 36 | +| 3 stepper | 169 | + +(*) Note that the reported rp2040 ticks are relative to a 12Mhz +scheduling timer and do not correspond to its 125Mhz internal ARM +processing rate. It is expected that 5 scheduling ticks corresponds to +~47 ARM core cycles and 22 scheduling ticks corresponds to ~224 ARM +core cycles. + ### Linux MCU step rate benchmark The following configuration sequence is used on a Raspberry Pi: @@ -476,7 +487,8 @@ hub. | sam4s8c (USB) | 650K | 8d4a5c16 | arm-none-eabi-gcc (Fedora 7.4.0-1.fc30) 7.4.0 | | samd51 (USB) | 864K | 01d2183f | arm-none-eabi-gcc (Fedora 7.4.0-1.fc30) 7.4.0 | | stm32f446 (USB) | 870K | 01d2183f | arm-none-eabi-gcc (Fedora 7.4.0-1.fc30) 7.4.0 | -| rp2040 (USB) | 873K | c5667193 | arm-none-eabi-gcc (Fedora 10.2.0-4.fc34) 10.2.0 | +| rp2040 (USB) | 885K | f6718291 | arm-none-eabi-gcc (Fedora 14.1.0-1.fc40) 14.1.0 | +| rp2350 (USB) | 885K | f6718291 | arm-none-eabi-gcc (Fedora 14.1.0-1.fc40) 14.1.0 | ## Host Benchmarks diff --git a/docs/Features.md b/docs/Features.md index fa430789..229cbef8 100644 --- a/docs/Features.md +++ b/docs/Features.md @@ -190,6 +190,7 @@ represent total number of steps per second on the micro-controller. | AR100 | 3529K | 2507K | | STM32F407 | 3652K | 2459K | | STM32F446 | 3913K | 2634K | +| RP2350 | 4167K | 2663K | | SAME70 | 6667K | 4737K | | STM32H743 | 9091K | 6061K | |