Cycle accurate simulation/emulation for Cortex - M4 Processor based board

Hi all,

I am  a master student in germany and doing my thesis currently. I wanted to measure CPU cycles using emulation/simulation for some code that is running on a cortex m4F processor based board. I had QEMU in mind at initial but it turns out it doesn't have support for my board and neither it is cycle accurate plus FP is not supported. Now I am searching for any freely available simulator or emulator that I can use for accurate cycle accurate measurement and do support FP and DSP instructions.

I am still not sure how accurate is QEMU for Cortex-M4 in terms of cycle accuracy? anyone with some experience?

I also saw this thread: https://community.arm.com/tools/f/discussions/5212/cycle-accurate-instruction-set-simulator-for-cortex-m

where there is said something about CPAKS for cortex M4 that is cycle accurate. But is it freely available? (for students etc).

Some quick replies will be appreciated.  Thank you in advance.

P.S: I am looking for a pure software based solution. I am also aware of keil/IAR simulators. any suggestions apart from these are welcomed :) 

Best Regards,

Fahad Masood