Intel Launches New 2 Billion Transistor Itanium

Status
Not open for further replies.

nachochease

Distinguished
Oct 3, 2009
6
0
18,510
I get that this is for businesses, but only in quantities of 1000?! I have to think retailers are going to buy these and then resell them on an individual basis. How many businesses would need 1000 high end CPU's at once?
 

endorphines

Distinguished
Mar 11, 2008
68
0
18,640
@ nachochease, quoting in quantities of 1000 is the industry standard. if you look on intel's site even e5200's are quoted in quantities of 1000
 

necronic

Distinguished
May 22, 2009
109
0
18,680
[citation][nom]ben850[/nom]"Don't expect this to be something that you'd have at home to run Crysis, "there you go guys.. don't even ask![/citation]

Dumb question in this case anyways. Here's a good one:

But can it play Dwarf Fortress?
 

belardo

Splendid
Nov 23, 2008
3,540
2
22,795
Back when AMD came out with the 64bit Opteron CPUS (intel didn't have any 64bit other than Itanium), they started gobbling up server market share. One of these things that made Opteron sucessful was that it was far cheaper than Itanium and faster too. Also, programmers who know x86 didn't have to deal with the complex issues of IA64.

So how do these $4000 CPUs compare to Opterons and Xeons?
 
G

Guest

Guest
i thought that the itanium program was for the most part a done deal.
 
[citation][nom]Belardo[/nom]Back when AMD came out with the 64bit Opteron CPUS (intel didn't have any 64bit other than Itanium), they started gobbling up server market share. One of these things that made Opteron sucessful was that it was far cheaper than Itanium and faster too. Also, programmers who know x86 didn't have to deal with the complex issues of IA64.So how do these $4000 CPUs compare to Opterons and Xeons?[/citation]

Not entirely. IA64 was made for 64bit and in pure 64bit is faster. x86-64 was cheaper in the solution that it ran x86 in a pure form while Itanium only runs x86 in a emulated mode and thus its x86 is slower.

But if you need a true 64bit super server, Itanium is the way to go hence why it has been around since its release in 2001.
 
[citation][nom]ronch79[/nom]I don't see why companies would use Itanium when they can, for the same price, get a system with several Xeons or Opterons with similar performance but easier programmability.[/citation]
Because they already have programs optimized for the IA64 (and IA64 != x86-64).
 

agnickolov

Distinguished
Aug 10, 2006
520
0
18,980
I really don't get where the myth about being easier to program for x86 comes from. Even in the lowest level code (OS and drivers), only a small fraction of the code is actually written in assembly language. Everything else is written in C and higher level languages (personally I'm a C++ developer). The effects of the underlying machine architecture are hidden from the programmer by the language compiler (and I won't even mention interpreted languages...).
 

one-shot

Distinguished
Jan 13, 2006
1,369
0
19,310
Power 7>Tukwila

Tukwila is good, but Power 7 seems to be ahead of the game. Power 7 has up to 8 cores and 4 threads/core up to 32 total threads. Tukwila has up to 4 cores and 2 threads per core. Where is the Power 7 article?
 

nottheking

Distinguished
Jan 5, 2006
1,456
0
19,310
[citation][nom]one-shot[/nom]Power 7 has up to 8 cores and 4 threads/core up to 32 total threads.[/citation]
That doesn't tell the whole story; that's like saying that the PS3's Cell Broadband Engine has 1 core, and the Xbox 360's Xenon has 3, hence the latter is superior.

Like that, Itanium and POWER7 can't really be compared... Even less so, since they're entirely different architectures. (Itanium being IA-64, vs. IBM-POWER for the CBE, Xenon, and POWER7)

Itanium tends to have fewer cores, but a lot more complexity per core, allowing each core to process WAY more per clock cycle than any other architecture; hence, it's considered a unique design; while the POWER architecture is entirely 'RISC,' (Reduced Instruction Set) Itanium goes well beyond the x86-standard 'CISC' (Complex Instruction Set) and is in fact perhaps the world's only 'EPIC' (Explicitly Parallel Instruction Computing) architecture.

Rather than making the CPU figure out how to order the instructions, EPIC/Itanium includes structuring at the compiler level to control branching, allowing for little confusion or delay for the CPU handling complex, branching instructions. All this works out to EACH thread being capable of handling 6 instructions per clock cycle.

That means that while the upcoming POWER7 may have more threads at 32 to 8, Tukwila handles more instructions per clock cycle, at 48 to 32... Couple that with the fact that POWER7 has to cut its instruction complexity to achieve so many threads, and Tukwila almost certainly will provide far more capability at handling complicated instruction trees.

So it's all a matter of design; POWER7 will likely win in the FLoPS ring, due to outright having more cores, (and a whopping 4 floating-point units per core) while Tukwila will certainly be better at the Instructions/second race.
 
Status
Not open for further replies.