To view parent comment, click here.
To read all comments associated with this story, please click here.
adkilla,
"I wouldn't want the stagnation that is happening in the x86 platform to extend to ARM SoCs. If it weren't for AMD, we would all be stuck with a 32-bit ISA on x86, with an overly costly and less than optimal upgrade path to Itanium. Unfortunately we've lost the 3rd party chipset market on x86 due to having too few CPU players."
Haha, I was actually very disappointed with AMD when they told the world they were going to extend the life of x86 with a 64bit variant of it. I sincerely thought that we would be migrated to better architectures by now if AMD hadn't anchored us right back to the x86 platform (albeit with some improvements). The AMD64 ISA still suffers from a lack of GP registers compared to alternatives, which necessitates complex hacks like register renaming. The opcodes are still highly inconsistent, increasing the amount of logic needed to parse them. The whole architecture is shrouded in subtle legacy designs.
I guess we have to wait for a newcomer to replace x86-64, but now that x86 is 64bit that could take a while (x86-64 could conceivably last a few decades like the x86 did).
I don't think so - if you'd take AMD out of the equation, the world would just mostly continue buying x86-32 until really hitting that 4 GiB limit ...at which point MS would just save the day by forcing PAE in their then-new (and in that alternative reality) Vista/7, and that would be it (assuming Intel management wouldn't come to their senses prior to that)
Generally, over time everything collects & grows in legacies... And considering the most likely "better" alternatives, can you really say with a straight face that we would be better off without x86-64? (consumers in general - sorry, nobody cares about asm, OS, compiler devs
) Still, in a few years you might more or less get what you want(?) - the Loongson ~MIPS chips have hardware-assisted x86 emulation. Considering all the x86 licensing issues, it's of course unlikely to show up in "current" (in the future) ~Western products ...my guess: it's there (and being worked on) to be ready when P5, MMX, P6, SSE patents lapse in the coming decade (I think) - that subset of x86 should allow running virtually all really important(tm) legacy software, a perspective probably very appealing to the Chinese, in their supposed quest to technology independence.
So, you just have to move to PRC to experience it, or at least to the areas likely within their sphere of influence in the future ;p (that should be SE Asia and large parts of Latin America and Africa ...though who knows, maybe more ;p )
I guess MS would just save the day by forcing PAE in Vista/7, in that alternative reality (if Intel wouldn't wise up sooner) ...overall, probably not much of a difference to us.
And 3rd party chipsets were likely going out anyway, due to increasing integration of x86 platforms (so not exactly stagnation, and even similar in spirit to ARM SoCs). Anyway, if there would be more x86 chipsets thanks to there being more x86 CPU players ...those chipsets wouldn't really be 3rd party, wouldn't they :p (plus, while we might despair the loss of ULi or SiS, I won't miss VIA chipsets; but BTW SiS, x86, and SoCs... http://en.wikipedia.org/wiki/Vortex86 )
Edited 2012-09-16 14:23 UTC





Member since:
2005-07-07
I wouldn't want the stagnation that is happening in the x86 platform to extend to ARM SoCs. If it weren't for AMD, we would all be stuck with a 32-bit ISA on x86, with an overly costly and less than optimal upgrade path to Itanium. Unfortunately we've lost the 3rd party chipset market on x86 due to having too few CPU players.
I hope the ARM SoC market stays the way it is with even more competition and SoC options coming into it.