• State Not Answered
  • Locked Locked
  • Replies 15 replies
  • Subscribers 21 subscribers
  • Views 2621 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

How to "optimize" self-defined 32bit shift-left routine ?

Jimmy liao

Dear all,
I encountered one problem about "executing self-defined 32bit shift-left routine too long"...

That is, I built my own routine to execute 32-bit shift left operation and found it takes too long(Due to some reason 32bit shift left is NOT allowed in my project currently...)

[code body]

UINT32 ShiftLeft32Bits(UINT32 Operand, UINT8 ShiftValue){
        bit     Carry;
        OperandDW = Operand;
        while(ShiftValue>0){
                Carry=0;
                if(OperandDWLo&0x8000)
                        Carry=1;
                OperandDWLo<<=1;
                OperandDWHi = (OperandDWHi<<1) | Carry;
                ShiftValue-=1;
        }
        return OperandDW;
}

[Statistics]
if "Operand = ShiftLeft32Bits(x1, 31);"
=> cost 60us ( where Operand,x1 are 4-byte xdata variables)

My question is: is it possible to "optimize" above code segments(favor speed) ? Thanks in advance...

p.s I am implementing sha256 calculation...

Parents
  • 0 in reply to Jimmy liao

    Thus I think in some special cases self-defined routine is better than that in ?C?LIB_CODE even we consider it in early design...<p>

    That's probably due to doing byte-wise shifts first.

    This, of course, results in slightly larger code _and_ slightly more cycles in certain cases, but if the shift_value is evenly distributed, the optimization lowers the average cycle count.

Reply
  • 0 in reply to Jimmy liao

    Thus I think in some special cases self-defined routine is better than that in ?C?LIB_CODE even we consider it in early design...<p>

    That's probably due to doing byte-wise shifts first.

    This, of course, results in slightly larger code _and_ slightly more cycles in certain cases, but if the shift_value is evenly distributed, the optimization lowers the average cycle count.

Children
No data