If PowerMacs become G6, it should follow that iMacs, Powerbooks and current PowerMac G4's will be G5. For eMacs and iBooks pump up the G4's but don't loose too much sleep. They are low end, after all.
Problem is it's easy to confirm or kill this rumor by doing sysctl -a in 10.4 and seeing if it turns up two values, specifically the number of physical and logical processors.ddtlm said:Sun Baked:
I think this all goes to show that the rumor mill cranks out random crap all the time. Who knows if the next chip is a Power5-lite, or a 970-dual, or something else. Clearly not the rumormongers, they just spew constantly and everyone seems to forget that the story was different last week.
I actually find the dual-core G5 very easy to believe because it would be easy for IBM to design, easy to Apple to use, and sort of easy to produce (though it would be getting a tad large at 90nm). Lots of companies are talking about dual core versions of chips they already have (AMD, Intel, Sun, HP...).
Oh that is interesting. Then perhaps this dual-core 970 thing is nonsense, cause Apple's not gona get both. Neither IBM nor Apple are into throwing away their money.Problem is it's easy to confirm or kill this rumor by doing sysctl -a in 10.4 and seeing if it turns up two values, specifically the number of physical and logical processors.
Ahhh a real fighting machine. I myself would prefer a dual dual G5.AoWolf said:Cool imagine a duel duel g5![]()
Actually 2 dual core processors would require the 4 way smp code.iris_failsafe said:I would like to draw attention to the 4 way smp that Apple has committed to. A 4 processor multi-core machine.
Earth Simulator here we come![]()
fluidinclusion said:A PowerMac 970 seems so much more powerful because of the "970" >> "5" or "6". Marketing 101.
ddtlm said:Hector:
Totally incorrect. You can't look at mhz and conclude that its fast enough, any more than you can look at processor clock speeds. It's latency is not low enough. Sure it can stream a lot of data (bandwidth) but that main RAM has a huge round-trip time (latency). The G4's L3 had lower bandwidth but much lower latency as well.
Lemme give you a secret to estimating the feasibility of a rumor relating to a large R&D investment: you need to establish that the people spending on R&D are going to recoup that cost. For years now I've used that simple rule to correctly predict the non-arrival of crasy things that everyone else seemed to swallow hook, line and sinker. Apply that rule to the idea of there being both a 970-dual and a Power5-lite. When I apply it, I see that the two chips aim at the same market, harming profit. Note, neither chip is aimed at the market that will be increasingly held by the 970fx, so I see no conflict there.Tiger is enhanced to support SMP systems better. Whether that comes from SMT enabled CPU or dual core is irrelevant.
Mmm, on-die memory controllers. Drool. But anyway Sun, at least, had it before AMD did... for example on the crappy US2i chips.And that is exactly why IBM needs to steal an idea from AMD and put the memory controller on chip.
Actually Hyperthreading ("SMT") is not the same thing as dual cores. SMT is one processor pretending to be more than one, dual cores is two genuine processors jammed into one package.I think this dual core technology is the new trend. Intel is using it already (what they call HyperThreading) and I just read an article in Dr Dobbs (August) explaining that Intel is struggling with the old Pentium arch to win Mhz and the only think that saves them is the dual core tech they have.
It is possible that a G5-dual could occupy the market for a year or more before being replaced by a Power5-lite. There are some questions there, I'd wonder if going from true dual core to SMT would be a step backwards, and also I wonder why Apple would be designing for SMT already.
ddtlm said:Actually Hyperthreading ("SMT") is not the same thing as dual cores. SMT is one processor pretending to be more than one, dual cores is two genuine processors jammed into one package.
Intel has spoken about dual-core Prescotts... dual SMT cores, kinda like a Power5 in that regard.
musicpyrite said:1 MB L2 cache per processor sounds good to me.
Does anybody know if it will have 2 MB L3 cache per probessor?
The P-M is something of an enhanced P-3 that is designed for laptops.Another question: what is the pentium M exaclty? because they have lower frequency than P4, I think they are closer to the G4 than the old P4
When AMD went to 64-bit they took the time to fix some of x86's problems and so they gained performance, however since PPC didn't have those issues, there really isn't an automatic gain. Some PPC programs can benefit if redesigned for 64-bit but generally its not a real big deal.In the DDJ article I mentioned earlier, they said current apps run faster on 64 bits processor, I don't see why but that's good news for you lucky G5 owners
musicpyrite said:1 MB L2 cache per processor sounds good to me.
~Shard~ said:Even if Apple implements this chip "sometime in 2005" I doubt they will brand it as a G6. The G5 hasn't been out for that long relatively, even when next year rolls around, and I don't think a processor change like this would really warrant a name change like that. Save the "G6" moniker for something truly big - maybe "The G6 in '06"...![]()
mac_head101 said:But if apple doesn't ever design macs for gaming they can only realistically gain 30 to 40 percent market share, as 70%of PCs are sold for GAMING