• Locked Locked
  • Replies 8 replies
  • Subscribers 119 subscribers
  • Views 4553 views
  • Users 0 members are here
2025 survey

We are running a survey to help us improve the experience for all of our members. If you see the survey appear, please take the time to tell us about your experience if you can.

Options
Related
How was your experience today?
This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Cortex-R4 : does "dual-issued pairs" really improve performance ?

Christophe Beausoleil
Note: This was originally posted on 1st August 2011 at http://forums.arm.com

Hello,

Could someone help me to explain that behavior :
I use a sequence of 4096 instructions (target is TMS570/Cortex-R4F) :
movs r0,#1
str r0, [r8~#0]
movs r1,#2
str r1, [r8~#4]
movs r2,#3
str r3, [r8~#8]
...

When "dual-issue" mode is enabled (bits 28-31 of Auxiliary Control  Register and bits 18-20 of Secondary Auxiliary Control Register are  reset), this code (plus a few instructions bordering it) executes in 5162 clock cycles.
When "dual-issue" mode is disabled (same bits are set), this code executes in 4146 clock cycles !!!

I observe this phenomenon for both ARM and Thumb2 modes.

So when "dual-issue" mode is enabled, it seems that one pipeline stage  is "sometimes" (once out of 4) waiting for dual words (thus introducing  extra wait states) in order to process them by pairs, but I can't find  any description of it.

Could someone help me to understand, please ? This is quite important for me,  because I have to produce highly deterministic real-time software, and  this kind of feature is hard to model...

Thanks for any help.

Best regards

Christophe
Parents
  • Arm Employee Badge
    Note: This was originally posted on 21st January 2012 at http://forums.arm.com

    With larger 'real' code we know that dual issue is usefully faster but this looks like a particular test case for memory accesses and I'm guessing the LSU is doing all the work and finding it harder for some reason. Let me consult with some colleagues next week. In case its a characteristic of the memory system can you describe the hardware please? Also, how are you measuring it?
Reply
  • Arm Employee Badge
    Note: This was originally posted on 21st January 2012 at http://forums.arm.com

    With larger 'real' code we know that dual issue is usefully faster but this looks like a particular test case for memory accesses and I'm guessing the LSU is doing all the work and finding it harder for some reason. Let me consult with some colleagues next week. In case its a characteristic of the memory system can you describe the hardware please? Also, how are you measuring it?
Children
No data