Nios II Classic Software Developer’s Handbook

ID 683282
Date 5/14/2015
Public
Document Table of Contents

8.1.3. Latency and Response Time

Exception (interrupt) latency, as defined in the previous section, is the time required for the hardware to respond to an exception. Response time, in contrast, is the time required to begin executing code specific to the exception cause, such as a particular ISR. Response time includes latency plus the time required for the HAL to carry out some or all of the following overhead tasks:
  • Context save—Saving registers on the stack
  • RTOS context switch—Calling context-switch function(s) if an RTOS is implemented
  • Dispatch handler—Determining the cause of the exception, and transferring control to a specific handler or ISR

If you are concerned with system performance, response time is the more important than latency, because it reflects the time elapsed between the physical event and the system’s specific response to that event.