Cycle counter on ARM Cortex M4 (or M3)?

Question

I\'m trying to profile a C function (which is called from an interrupt, but I can extract it and profile it elsewhere) on a Cortex M4.

What are the possibilities to

Answer 1

Expanding previous answers with a DWT_CYCCNT example (STM32) in main (similar to my other post).

Note: I added a delay method as well. You can verify stopwatch_delay by calling STOPWATCH_START, run stopwatch_delay(ticks), then call STOPWATCH_STOP and verify with CalcNanosecondsFromStopwatch(m_nStart, m_nStop). Adjust ticks as needed.

uint32_t m_nStart;               //DEBUG Stopwatch start cycle counter value
uint32_t m_nStop;                //DEBUG Stopwatch stop cycle counter value

#define DEMCR_TRCENA    0x01000000

/* Core Debug registers */
#define DEMCR           (*((volatile uint32_t *)0xE000EDFC))
#define DWT_CTRL        (*(volatile uint32_t *)0xe0001000)
#define CYCCNTENA       (1<<0)
#define DWT_CYCCNT      ((volatile uint32_t *)0xE0001004)
#define CPU_CYCLES      *DWT_CYCCNT
#define CLK_SPEED         168000000 // EXAMPLE for CortexM4, EDIT as needed

#define STOPWATCH_START { m_nStart = *((volatile unsigned int *)0xE0001004);}
#define STOPWATCH_STOP  { m_nStop = *((volatile unsigned int *)0xE0001004);}


static inline void stopwatch_reset(void)
{
    /* Enable DWT */
    DEMCR |= DEMCR_TRCENA; 
    *DWT_CYCCNT = 0;             
    /* Enable CPU cycle counter */
    DWT_CTRL |= CYCCNTENA;
}

static inline uint32_t stopwatch_getticks()
{
    return CPU_CYCLES;
}

static inline void stopwatch_delay(uint32_t ticks)
{
    uint32_t end_ticks = ticks + stopwatch_getticks();
    while(1)
    {
            if (stopwatch_getticks() >= end_ticks)
                    break;
    }
}

uint32_t CalcNanosecondsFromStopwatch(uint32_t nStart, uint32_t nStop)
{
    uint32_t nDiffTicks;
    uint32_t nSystemCoreTicksPerMicrosec;

    // Convert (clk speed per sec) to (clk speed per microsec)
    nSystemCoreTicksPerMicrosec = CLK_SPEED / 1000000;

    // Elapsed ticks
    nDiffTicks = nStop - nStart;

    // Elapsed nanosec = 1000 * (ticks-elapsed / clock-ticks in a microsec)
    return 1000 * nDiffTicks / nSystemCoreTicksPerMicrosec;
} 

void main(void)
{
    int timeDiff = 0;
    stopwatch_reset();

    // =============================================
    // Example: use a delay, and measure how long it took
    STOPWATCH_START;
    stopwatch_delay(168000); // 168k ticks is 1ms for 168MHz core
    STOPWATCH_STOP;

    timeDiff = CalcNanosecondsFromStopwatch(m_nStart, m_nStop);
    printf("My delay measured to be %d nanoseconds\n", timeDiff);

    // =============================================
    // Example: measure function duration in nanosec
    STOPWATCH_START;
    // run_my_function() => do something here
    STOPWATCH_STOP;

    timeDiff = CalcNanosecondsFromStopwatch(m_nStart, m_nStop);
    printf("My function took %d nanoseconds\n", timeDiff);
}