Question
H7 OCTOSPI HyperRAM data throughput changing with compilation
Heyho,
I'm using the H733 (custom board) / H735 (eval kit) with Infineon's HyperRAM S70KL1281 / S70KL1282 at 100 MHz for some time now, all working great, except for one thing that is very annoying:
- the data throughput from / to HyperRAM seems to depend on compilation, even though the OCTOSPI peripheral was not changed
- after some compilations it's about 178 Mbyte / s, after another only 54 MB/s.
- data throughput is constant for one compilation, no matter if I call the test function at MCU power up or while operating with all other peripherals running
- no caching anywhere
I'm pretty sure that it's not "faulty" timing measurements, using the cycle counter and disabling all interrupt calls around the for loops.
- Is there something wrong in my test function?
- Is it maybe "only" how the for loop / iteration is compiled?
- right now I can't get it back to the high speed, so no map / list file
- my scope here is too old and slow to check the signal lines
Here's the test function, first writing to HyperRAM, then reading:
/* +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ */
/* OCTOSPI HyperRAM test
*/
#define HYPER_TEST_UART 1
uint32_t OspiHypRamTest(uint8_t u8CountDown)
{
uint32_t i = 0;
uint32_t u32Val = 0xFFFFFFFF;
uint32_t u32MaxLen = (uint32_t)((uint32_t)OSPI_HYPERRAM_END_ADDR / 4);
uint32_t u32Errors = 0;
uint32_t u32Data = 0;
uint32_t u32CycStart = 0;
uint32_t u32Cycles = 0;
float flClockMHz = (float)HAL_RCC_GetSysClockFreq() / 1E6;
float flVal = 0.0f;
uint32_t *pu32MemAddr = NULL;
if( OCTOSPI1 == pOspiHypRam ) pu32MemAddr = (uint32_t *)OCTOSPI1_BASE;
else if( OCTOSPI2 == pOspiHypRam ) pu32MemAddr = (uint32_t *)OCTOSPI2_BASE;
#if HYPER_TEST_UART
uart_printf("\n\r+++++++++++++++++++++++++++++++++++++++++++++++++\n\r");
uart_printf("OCTOSPI HyperRAM test, memory mapped, IRQs OFF\n\rcounting ");
if( 0 == u8CountDown ) uart_printf("UP, start with 0\n\r\n\r");
else uart_printf("DOWN, start with %08lX\n\r\n\r", u32Val);
uart_printf("writing bytes: %lu\n\r", (uint32_t)OSPI_HYPERRAM_END_ADDR);
#endif
__DSB();
__disable_irq();
/* write complete HyperRAM */
/* UP - should be faster */
if( 0 == u8CountDown )
{
u32CycStart = DWT->CYCCNT;
for( i = 0; i < u32MaxLen; i++ )
{
pu32MemAddr[i] = i;
}
__DMB();
__DSB();
u32Cycles = DWT->CYCCNT;
}
/* DOWN */
else
{
u32Val = 0xFFFFFFFF;
u32CycStart = DWT->CYCCNT;
for( i = 0; i < u32MaxLen; i++ )
{
pu32MemAddr[i] = u32Val;
u32Val--;
}
__DMB();
__DSB();
u32Cycles = DWT->CYCCNT;
}
__enable_irq();
__DSB();
u32Cycles -= u32CycStart;
flVal = (float)u32Cycles / flClockMHz;
flOspiRamSpeedMBpsMmWr = (float)OSPI_HYPERRAM_END_ADDR / flVal;
flOspiRamSpeedMBpsMmWr *= (float)MEGA_CORRECTION;
#if HYPER_TEST_UART
uart_printf("%lu CPU cycles = %.1f ms\n\r", u32Cycles, (flVal / 1000.0f));
uart_printf("\n\r-> %.2f MB/s (%.0f Mbit/s) WRITE\n\r\n\r", flOspiRamSpeedMBpsMmWr, (8.0f * flOspiRamSpeedMBpsMmWr));
uart_printf("reading & comparing bytes: %lu\n\r", (uint32_t)OSPI_HYPERRAM_END_ADDR);
#endif
__DSB();
if( OCTOSPI1 == pOspiHypRam ) pu32MemAddr = (uint32_t *)OCTOSPI1_BASE;
else if( OCTOSPI2 == pOspiHypRam ) pu32MemAddr = (uint32_t *)OCTOSPI2_BASE;
__disable_irq();
__DSB();
/* read complete HyperRAM and compare */
/* UP - should be faster */
if( 0 == u8CountDown )
{
u32CycStart = DWT->CYCCNT;
for( i = 0; i < u32MaxLen; i++ )
{
u32Data = pu32MemAddr[i];
if( u32Data != i ) u32Errors++;
}
__DMB();
__DSB();
u32Cycles = DWT->CYCCNT;
}
/* DOWN */
else
{
u32Val = 0xFFFFFFFF;
u32CycStart = DWT->CYCCNT;
for( i = 0; i < u32MaxLen; i++ )
{
u32Data = pu32MemAddr[i];
if( u32Data != (u32Val - i) ) u32Errors++;
}
__DMB();
__DSB();
u32Cycles = DWT->CYCCNT;
}
__enable_irq();
u32Cycles -= u32CycStart;
flVal = (float)u32Cycles / flClockMHz;
flOspiRamSpeedMBpsMmRd = (float)OSPI_HYPERRAM_END_ADDR / flVal;
flOspiRamSpeedMBpsMmRd *= (float)MEGA_CORRECTION;
#if HYPER_TEST_UART
uart_printf("%lu CPU cycles = %.1f ms\n\r", u32Cycles, (flVal / 1000.0f));
uart_printf("\n\r-> %.2f MB/s (%.0f Mbit/s) READ\n\r", flOspiRamSpeedMBpsMmRd, (8.0f * flOspiRamSpeedMBpsMmRd));
if( 0 == u32Errors ) uart_printf("\n\rNULL errors\n\r");
else uart_printf("\n\r# ERR: u32Errors = %lu\n\r", u32Errors);
uart_printf("-------------------------------------------------\n\r");
#endif
return u32Errors;
}Anybody any ideas?
Thanks in advance!