niconiconi @niconiconi@mk.absturztau.be
Public

Optimizing IRQ latency on the STM32H743 @ 480 MHz, perhaps for NES ROM emulation... Best result so far: 100 nanoseconds input-to-output latency when the vector table and the IRQ handler are relocated to Tightly-Coupled Memory without making HAL calls. Not bad, but the GPIO controller (several buses away) looks like the real performance killer here.

STM32 development board with a STM32H743VI microcontroller.Oscilloscope trace of a rising edge trigger and the STM32's GPIO pulse (25 ns), the latency is 97.60 ns./* Define output sections */ SECTIONS { /* The startup code goes into ITCM (relocated from FLASH) */ .isr_vector : { . = ALIGN(4); __isr_vector_start = .; KEEP(*(.isr_vector)) /* Startup code */ . = ALIGN(4); __isr_vector_end = .; } >ITCMRAM AT> FLASH .itcm_text : { . = ALIGN(4); __itcm_text_start = .; *(.itcm_text) *(.itcm_text*) . = ALIGN(4); __itcm_text_end = .; } > ITCMRAM AT> FLASH /* used by the startup to initialize data */ _si_isr_vector = LOADADDR(.isr_vector); _si_itcm_text = LOADADDR(".itcm_text");# Basic compiler flags CFLAGS = -O2 -flto -Wall -Wextra -std=c99 -pedantic CFLAGS += -DSTM32H743xx -DUSE_HAL_DRIVER # debug symbols? #CFLAGS += -g -ggdb # If this macro is set, system_stm32h7xx.c overwrites the interrupt # vector table address (VTOR register) to a custom address. CFLAGS += -DUSER_VECT_TAB_ADDRESS=0x00000000void relocate_to_itcm(void) { extern volatile char _si_isr_vector; extern volatile char __isr_vector_start, __isr_vector_end; volatile char *flash_isr_vector_start = &_si_isr_vector; volatile char *ram_isr_vector_start = &__isr_vector_start; volatile char *ram_isr_vector_end = &__isr_vector_end; size_t len = ram_isr_vector_end - ram_isr_vector_start; for (size_t i = 0; i < len; i++) { ram_isr_vector_start[i] = flash_isr_vector_start[i]; } #ifdef SEMIHOSTING printf("relocate %p-%p to %p, %d bytes\n", flash_isr_vector_start, flash_isr_vector_start + len, ram_isr_vector_start, len); #endif extern volatile char _si_itcm_text; extern volatile char __itcm_text_start, __itcm_text_end; volatile char *flash_itcm_text_start = &_si_itcm_text; volatile char *ram_itcm_text_start = &__itcm_text_start; volatile char *ram_itcm_text_end = &__itcm_text_end; len = ram_itcm_text_end - ram_itcm_text_start; for (size_t i = 0; i < len; i++) { ram_itcm_text_start[i] = flash_itcm_text_start[i]; } #ifdef SEMIHOSTING printf("relocate %p-%p to %p, %d bytes\n", flash_itcm_text_start, flash_itcm_text_start + len, ram_itcm_text_start, len); #endif }__attribute__((section (".itcm_text"))) void HAL_GPIO_EXTI_Callback(uint16_t GPIO_Pin) { if (GPIO_Pin != GPIO_PIN_0) return; GPIOA->BSRR = (uint32_t) GPIO_PIN_2; GPIOA->BSRR = (uint32_t) GPIO_PIN_2 << 16U; }__attribute__((section (".itcm_text"))) void SysTick_Handler(void) { HAL_IncTick(); } /******************************************************************************/ /* STM32H7xx Peripherals Interrupt Handlers */ /* Add here the Interrupt Handler for the used peripheral(s) (PPP), for the */ /* available peripheral interrupt handler's name please refer to the startup */ /* file (startup_stm32h7xx.s). */ /******************************************************************************/ __attribute__((section (".itcm_text"))) void EXTI0_IRQHandler(void) { HAL_GPIO_EXTI_Callback(GPIO_PIN_0); // Still make a dummy HAL call to ACK the IRQ // TODO: ACK it manually HAL_GPIO_EXTI_IRQHandler(0xFFFF); }
0
0
0

If you have a fediverse account, you can quote this note from your own instance. Search https://mk.absturztau.be/notes/ajv8mjcw305b017a on your instance and quote it. (Note that quoting is not supported in Mastodon.)