Intel Launches New 2 Billion Transistor Itanium
It's the Intel processor for critical missions.
Running a mission-critical… mission? Intel this week introduced the Itanium processor 9300 series, previously codenamed "Tukwila," which delivers more than double the performance of its predecessor.
Helping boost performance in this two-billion transistor Itanium processor 9300 series is that it has twice as many cores as its predecessor (four versus two), eight threads per processor (through enhanced Hyper-Threading Technology), more cache, up to 800 percent the interconnect bandwidth, up to 500 percent the memory bandwidth, and up to 700 percent the memory capacity using-industry standard DDR3 components.
The processor's advanced machine-check architecture coordinates error handling across the hardware, firmware and operating system, and improves system availability by enabling recovery from otherwise fatal errors.
The Itanium 9300 processor employs the second generation of Intel Virtualization Technology to improve performance and robustness. Its Intel 7500 chipset can directly assign I/O devices to virtual machines, further boosting efficiency.
"Intel is committed to delivering a new era of mission-critical computing, and we are delighted 80 percent of Global 100 companies have chosen Itanium-based servers for their most demanding workloads," said Kirk Skaugen, vice president Intel Architecture Group and general manager Data Center Group. "Intel is continuing to drive the economics of Moore's Law into mission-critical computing with today's Itanium 9300 processor announcement, more than doubling performance for our customers once again."
Don't expect this to be something that you'd have at home to run Crysis, however, as the Itanium processor 9300 series ranges in price from $946 to $3,838 in quantities of 1,000.
- Steam Gamers Upgrading to 64-bit Win 7 Quickly
- Student's Robot Becomes Intel's Processor Demo
- Logitech Desktop Can Keep Rolling for 3 Years
- Microsoft Hotfixes Windows 7 Memory Leak
- (Update) StarCraft II Multiplayer Beta This Month!
- EA: Star Wars Old Republic MMO Beyond Q2'11
- City of Heroes Gets Visual Upgrade
- ATI Radeon HD 5570 is for Bang-for-Buck Gamers
- EA Ditching Plans for PC Version of Dead Space 2
- Bill Gates: The iPad Isn't All That
- Lastest Windows XP Update Causes BSOD Loop
- Dell's 27-Inch LCD Does 2560 x 1440 But No LEDs
- VOTW: Dungeons & Dragons on Microsoft Surface
- Microsoft, Apple Both Targeted in Patent Lawsuit
- WD's 1TB SATA 6.0 Gbps HDD Out in Japan
- Postage Stamp-Sized SSDs On The Horizon
- Lian Li's T1 Pitstop PC Case Looks Like a Spider
- Firefox 3.7 Alpha 1 Arrives for Preview
Cool beans. Now if I can just convince my boss that we need to build a supercomputer for our pid controller.
"Don't expect this to be something that you'd have at home to run Crysis, "
there you go guys.. don't even ask!
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?
So, a decade later, Intel still hopes to raise the Itanic.
http://www.pcmag.com/article2/0,2817,2339629,00.asp
I drinking water because I'm so firsty.
"But does it run Crysis?" LOLLLLLLLLLLLLLL
@ 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
"Don't expect this to be something that you'd have at home to run Crysis, "there you go guys.. don't even ask!
Dumb question in this case anyways. Here's a good one:
But can it play Dwarf Fortress?
I'm surprised they are still pushing Itanium which would compete in the same space as their Xeon Processors.
The numbers are beyond my imagination.
can this play runescape?
Hmmmm I wonder how these handle CAD as well Arc Map9?
I Didn't know this architecture was still alive.
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?
i thought that the itanium program was for the most part a done deal.
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?
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.
Hmm.... 1,000 processors for $4,000....
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.
Because they already have programs optimized for the IA64 (and IA64 != x86-64).
Can I have it for free.......? ^^
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...).
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?
I was looking at a Gulftown for my next build... wonder what would happen with one of these...
Gulftown? Ignored!
My next build will definitely be Sandybridge as I just got my new PC a while ago.
Power 7 has up to 8 cores and 4 threads/core up to 32 total threads.
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.
Can it pla...??
that's one serious processor. glad to be moving forward. now let's see what the competition has to offer?
Hmm.... 1,000 processors for $4,000....
Please don't tell us you actually think they're $4 each... >_
Please don't tell us you actually think they're $4 each... >_
they need to lower the price to $4 each,
I am tired of maya taking like 16 hours to render something on a quad core.
intel needs to sell these CPU's for $4 each so I can build a few systems that can use those CPU's and act as render slaves.
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.
There are a lot of people who don't really understand the Itanium at all. First of all, it's not in the same league as anything with the Nehalem. Comparisons between the two will tend to show the superiority of the Nehalem without the context of why.
For one, this is two nodes behind the newest Nehalems, and is made on 65nm. More to the point, the transistors are more reliable and less susceptible to soft errors. This requires more size and is generally slower, but, when you need things to be right, you can't run them on a toy that runs fast.
However, the assertion that the Itanium shows better IPC is just not consistent with benchmarks. The idea of an in order processor that instead relies on the compiler to do accurate scheduling sounded good, except such a compiler is impossible to create. We don't have benchmarks for the Tukwila yet, but previous versions did not show better IPC on integer workloads, than even the dreadful x86 processors like Core 2, and particularly Nehalem. This and the fact they can't clock nearly as high (which should give them an advantage on IPC, since caches can be clocked much faster vis-a-vis the core) should make it clear these things are not the IPC beasts they were envisioned to be.
POWER 7 looks to be a superior product by almost all measures. But, that's not an indictment against the IA-64 instruction set. They're on a 65nm node, on a very old architecture that hasn't been upgraded nearly as extensively as IBM has with POWER.
The next version of Itanium, Poulson, looks to be more of a "ground up" effort, and could change everything we think we know about the Itanium. The Tukwila is a nice improvement, but the core isn't changed a whole lot, although the much better system interface is going to help quite a bit.
Also, the Itanium core is NOT more complex than x86. It's actually quite small and simple. That's kind of the point. Move the complexity to the compiler, and get parallelism from it. The problem is, so far, it hasn't worked.
the question people should really be answering is........ CAN IT RUN A SERVER OF CRYSIS ONLINE WHERE EVERY SINGLE LAYER IS PLAYING WITH AT LEAST HIGH TO VERY HIGH SETTINGS AND AT LEAST 2X AA...... ON A SERVER WITH 30FPS AVG.....
beat that MAXED OUT
ahh....who guessed my parents P4 at home can play crysis...beat that, with a 9500gt
Theres a difference between playing, and going back in time..