GCC Cortex-M3 Timing Benchmarks

ti.platforms.tiva:LM4F232H5QD:1 (compiler version: 4.7.3)

Benchmark Cycles (1)
Interrupt Latency 93 (2)
Hwi_restore() 2
Hwi_disable() 3
Hwi dispatcher prolog 170
Hwi dispatcher epilog 273
Hwi dispatcher() 431
Hardware Interrupt to Blocked Task 855
Hardware Interrupt to Software Interrupt 527
Swi_enable() 88
Swi_disable() 18
Post Software Interrupt Again 35
Post Software Interrupt without Context Switch 116
Post Software Interrupt with Context Switch 279
Create a New Task without Context Switch 2914
Set a Task Priority without a Context Switch 213
Task_yield 354
Post Semaphore, No Waiting Task 60
Post Semaphore No Task Switch 338
Post Semaphore with Task Switch 481
Pend on Semaphore, No Context Switch 60
Pend on Semaphore with Task Switch 494
Clock_getTicks 11

(1) The benchmark application was built using BIOS.LibType_Custom with the following BIOS.customCCOpts settings:

"-mcpu=cortex-m3 -mthumb -mabi=aapcs -O3 -Wunused -Wunknown-pragmas -ffunction-sections -fdata-sections -Dti_sysbios_Build_useHwiMacros -Dfar= -D__DYNAMIC_REENT__".

Timings were obtained using the Tiva Launchpad TM4C123GH6PM board running at 40MHz.

(2) The M3 target also supports zero latency interrupts. See ti.sysbios.family.arm.m3.Hwi cdocs for details.