From 805e56008f822136031d28fa1c09c914cd98bfcf Mon Sep 17 00:00:00 2001 From: Kevin O'Connor Date: Mon, 11 Feb 2019 16:32:19 -0500 Subject: [PATCH] docs: Note command dispatch benchmark needs desktop class machine Signed-off-by: Kevin O'Connor --- docs/Debugging.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/docs/Debugging.md b/docs/Debugging.md index b171d4fe..a678a2be 100755 --- a/docs/Debugging.md +++ b/docs/Debugging.md @@ -420,7 +420,7 @@ communication mechanism. The test is run using the console.py tool (described above). The following is cut-and-paste into the console.py terminal window: ``` -DELAY {clock+freq} get_uptime +DELAY {clock + 2*freq} get_uptime FLOOD 100000 0.0 end_group get_uptime ``` @@ -429,6 +429,10 @@ When the test completes, determine the difference between the clocks reported in the two "uptime" response messages. The total number of commands per second is then `100000 * mcu_frequency / clock_diff`. +Note that this test may saturate the USB/CPU capacity of a Raspberry +Pi. The benchmarks below are with console.py running on a desktop +class machine. + | MCU | Rate | Build | Build compiler | | ------------------- | ---- | -------- | ------------------- | | pru (shared memory) | 5K | b161a69e | pru-gcc (GCC) 8.0.0 20170530 (experimental) |