[DUG] Int64 or floating point faster?

[Leigh Wanstead]

Hi Jolyon,

Sorry for the confusion.

I mean add each operand of the assembler code corresponding to certain
value of cpu cycles together to get a rough idea.

Div is far more dear than plus for sure :-)

Of course take care of condition jump/jump as this will multiple the
figures depends on how many jump it will be.

Regards
Leigh


On 18 August 2014 09:11, Jolyon Smith <jsmith at deltics.co.nz> wrote:

> Leigh, I'm not sure that this would be a reliable indicator of
> performance.  Surely some opcodes are more "expensive" than others ?  The
> relationship between opcodes and CPU cycles is not 1:1 afaik.
>
>
> On 18 August 2014 08:51, Leigh Wanstead <leigh.wanstead at gmail.com> wrote:
>
>> Just one suggestion, why not look at assembler code in delphi to count
>> the lines and add up the operands to get the cpu cycle total number? :-)
>>
>> My 2 nz cents
>>
>> Leigh
>>
>> _______________________________________________
>> NZ Borland Developers Group - Delphi mailing list
>> Post: delphi at listserver.123.net.nz
>> Admin: http://delphi.org.nz/mailman/listinfo/delphi
>> Unsubscribe: send an email to delphi-request at listserver.123.net.nz with
>> Subject: unsubscribe
>>
>
>
> _______________________________________________
> NZ Borland Developers Group - Delphi mailing list
> Post: delphi at listserver.123.net.nz
> Admin: http://delphi.org.nz/mailman/listinfo/delphi
> Unsubscribe: send an email to delphi-request at listserver.123.net.nz with
> Subject: unsubscribe
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://listserver.123.net.nz/pipermail/delphi/attachments/20140818/4f2a29b8/attachment-0001.html