Originally Posted by jinu117
Wow, I do take offesne to such comment. If you happen to be a programmer, please only use machine language from now on in name of optimization. Your program will run twice faster if not more on many instances. And also, for loop instructions, optimize it per each cpu that it will be used since that will be most time consuming of processor utilization.
:stick:
I hate those people who think programmers programming should be an artist. It could be but in all practical senses, it has become art of production not art itself...
I get the feeling someone is still living under rock.
***warning... following can be very long and extremely boring***
Here is an example of why such technology can benefit.
Typical business setting. Business application that handles multiple things at same time. It can use optimization greatly to maybe improve performance by 60%. Software is used by 100 employees that actively uses it 4 hours a day. Let's say realized improvement is 20%. Realized revenue increase from improvement is 10% (this is very high number for those of you who have worked in IT... 5% is considered incredible).
Avg salary 50k is assumption here. Programmer salary avg let's say 100k (counting in the people who actually can do this multicore optimization... this is considered pretty high end).
Also, this application gets renewed every year in many facet in functionality, etc
Now let's boil down hard numbers: With optimization say we see 60% improvement in software.
Optimization cost for current application at least usually is 200k or so in such type of codes. Benefit from such code optimization first year. about (half a day) 10% of total employee salary of 100is 250k. So total gain first year is 50k.
Subsequent maintenance improvement based on schedule probably will cost 100k more than otherwise thanks to complexity of changing such optimized code. Subsequential gain of such endeavour is 150k each year. Life of such program usually is 5 years until some high lvl changes and wants brand new system that works with "the new goal of company"
so during life span of such program, benefit is 650k. Not a small number.
Now, without optimization but with optimized software let's say we see 40% improvement in software. Realized gain 13%. Revenue improvement 6.67%
Cost is none up front. First year gain in proportion would be 6.7% of total salary. 167k per year. benefit over 5 year span... 667k.
changing the number around a little to larger company of 200. We will have bit better return. 1850k for optimization, 1670k for non optimization...
Now, this didn't taken into account of downtime for entire company, etc for upgrading suite of software that goes with such major endeavour (basically H/W and software upgarde need to be closely matched etc which usually do add time to upgrade). Most of companies of non financial nature does expect 1-2 days delay of no system in such scenario (financial ones tend to do more qa and through line up of what should happen and backup procedure planning which adds huge amount of money on developmental/deployment cost).
So.... for all the trouble, how much gain is there? Really, how much gain? Programmers don't get paid to make art. They get paid to do the job that will benefit company...
I think I went a bit far off.. not saying optimization is futile, it isn't. For new applications, etc... it probably is more than worth it to invest time & money in. But disregarding technology that immediate benefit possible and cost saving to most companies especially small to medium sized ones... is... bit careless to say the least.
