Inline below. On Dec 15, 2011, at 2:31 AM, Juan Vuletich <j...@jvuletich.org> wrote:
> frank wrote: >> On 12/15/2011 08:02 AM, Casey Ransberger wrote: >> >>> Hypothesis: Mainstream software slows down at a rate slightly less than >>> mainstream hardware speeds up. >>> >> >> Hmmm, seems like a more optimistic Version of Wirth's law (yes, Niklaus): >> "Software is getting slower more rapidly than hardware becomes faster." >> >> Frank >> > > There's also Nathan Myhrvold's four Laws of Software: ( > http://www.codinghorror.com/blog/2006/09/software-its-a-gas.html , > http://blogs.msdn.com/b/larryosterman/archive/2005/06/17/430215.aspx ). > 1) Software is a gas: Software always expands to fit whatever container it is > stored in. Good metaphor. Melikes. > 2) Software grows until it becomes limited by Moore's Law: The initial growth > of software is rapid, like gas expanding, but is inevitably limited by the > rate of increase in hardware speed. Too true! > 3) Software growth makes Moore's Law possible: People buy new hardware > because the software requires it. Funny, but I think Moore's Law happens because around every 18 months, a large enough contingent of people want to buy a computer that's orders of magnitude faster / has orders of magnitude more storage/memory and faster network more pixels etc blah, blah, blah than what they've been getting on with for a number of years. > 4) Software is only limited by human ambition and expectation: We'll always > find new algorithms, new applications, and new users. It kind of seems like this one should actually help. I think what's really happening is: every programmer rediscovers the same algorithm and codes it up, not knowing that it's already in the standard library, because the standard library is so big that no one wants to read it. > These are interesting for several reasons. One is that Nathan doesn't only > describe the phenomena, but also a possible explanation for it. Which makes his arguments fun! > Besides, now that it seems Moore's Law doesn't hold anymore, what will happen? I'm not buying it. The economy just sucks. Give it a couple of holiday seasons, ARM and Intel will find a way again to sell me a computer that's twice as fast as the one I bought a year and a half ago;) > Will software bloat end? Will we focus again in efficiency and simplicity? > Will this make projects like FONC and Cuis relevant to mainstream? One thing that's clear: people are really into little portable gadgets right now. So the shift happened: it's not about how many volts you can push through some silicon without melting it right now, it's about how much you can get done with as little electricity as possible. FWIW, I think this shift is why we aren't seeing performance-doubling. I think we're seeing market focus on battery-life-doubling instead. When I really think about it, these are two sides of the same coin. Which is why I still doubt that Moore was wrong... > WRT law 3), we already see the change. Some years ago, computers were > advertised only in terms of speed. Now they make people want new, slower > computers (iPads and such). Regular PCs, even if much faster, are not "fancy" > anymore. Depends on market segment. I want a cheap slow (you know, fast, like my old Mac, not slow like that fast AMD thing and Windows, that's just too slow) computer that has a battery that lasts for days but still lets me program like I could on my desktop (nope, Android, this isn't you. Don't want language hurdles. Just let me compile what I want.) "Devil's Advocate" but I'm mostly with ya:) > Cheers, > Juan Vuletich > > _______________________________________________ > fonc mailing list > fonc@vpri.org > http://vpri.org/mailman/listinfo/fonc _______________________________________________ fonc mailing list fonc@vpri.org http://vpri.org/mailman/listinfo/fonc
