Fast GPIO access

KarlL · 13 March 2018 15:25

Hi all,

When accessing the GPIO through SoapySDR, it seems to be taking around 250µs for a call like writeGPIODir or writeGPIO.

Is this normal and should a different approach be used if one wants to react faster?

Is anyone using the GPIO at faster speeds somehow?

andrewback · 14 March 2018 09:39

You could try using Lime Suite directly.

github.com

myriadrf/LimeSuite/blob/master/src/examples/gpio_example.cpp

/**
    @file   gpio_example.cpp
    @author Lime Microsystems (www.limemicro.com)
    @brief  GPIO example
 */
#include <lime/LimeSuite.h>
#include <iostream>
#include <chrono>
#include <thread>

//Device structure, should be initialize to NULL
lms_device_t* device = NULL;

int error()
{
    if (device != NULL)
        LMS_Close(device);
    exit(-1);
}

This file has been truncated. show original

KarlL · 15 March 2018 03:02

Thanks Andrew for the advice. I’m not seeing much difference though. At least it means there’s no noticeable overhead when using the SoapySDR API.

I guess I’ll try to use some Arduino or Raspberry Pi to control the GPIO, to see if I can drive it faster.

andrewback · 15 March 2018 06:41

So this thread is about transferring samples, but I wonder if there is anything in here which might point to a potential solution:

E.g. some protocol buffering that could be shrunk to reduce latency.

KarlL · 16 March 2018 00:33

That’s interesting thanks, maybe not directly related to the GPIO but it might be useful indeed to bring down latency when receiving samples.