Slashdot Mirror
Why Doesn't the Itanium Get the Respect It's Due?
happycorp wonders: "As in recent years the Itanium does well, easily beating x86 processors even at its low clockspeed (1.4Ghz). The supercomputer people are serious about benchmarking (no easily tricked microbenchmarks or reliance on closed-source
commercial apps), so the discrepancy between the performance and perception of this chip is serious.
With a single-CPU Itanium2 system at
around $2000 their price is already reasonable, and the price would come down
(and software would be ported) if the Itanium ever became a mass market chip. Having an affordable chip one step above a Xeon or Opteron in floating-point performance would not be such a bad thing for gaming enthusiasts (or 3D artists). So, the recent
article
on the
Top 500 supercomputers list brings up a question I've been meaning to ask:
Why do we see so many disparaging opinions of the Itanium processor (all those 'Itanic' jokes, etc.)?"
"It seems computing enthusiasts' sentiment is set against this processor, and its likely that it's going to be abandoned sooner or later. We'll be paying for x86 compatibility indefinitely (recall the Xeon has roughly
three times the number of transistors of the ppc970 for example; but we hardly get three times the performance).
These are a couple scores from the top 20, with the total gigaflops divided by the number of processors to obtain a per-processor speed:
rank processor ghz (gflops / #procs) speed #5 ppc970 2.2 (27910 / 4800) 5.81 #7 itanium2 1.4 (19940 / 4096) 4.86 #10 opteron 2.0 (15250 / 5000) 3.05 #20 xeon 3.06 (9819 / 2500) 3.92
Given this, consider what a 2 or 3 Ghz Itanium could do.
(fine print: I am not affiliated with the Itanium or the top500 list in any way)."
These are a couple scores from the top 20, with the total gigaflops divided by the number of processors to obtain a per-processor speed:
rank processor ghz (gflops / #procs) speed #5 ppc970 2.2 (27910 / 4800) 5.81 #7 itanium2 1.4 (19940 / 4096) 4.86 #10 opteron 2.0 (15250 / 5000) 3.05 #20 xeon 3.06 (9819 / 2500) 3.92
Given this, consider what a 2 or 3 Ghz Itanium could do.
(fine print: I am not affiliated with the Itanium or the top500 list in any way)."
Because it's cool to hate Intel.
I love Intel. I wouldn't use another chip because I've had bad experiences with them, and never a single (notable) one with Intel. But for some reason, people love to bash Intel, simply because it's the big behemoth.
Less costly doesn't necessarily imply better - I'm an avid hater of Microsoft, definitely, but it's not solely because they're huge.
AccountKiller
Oh well, I love AMD for their work, but I really think they barked up the wrong tree. I would have supported whole heartedly an implementation of PPC 64-bit or even some grounded up archetecture just as much as I supported Itanium, but they decided to go the cheapest route, faking it for the sake of performance.
Secondly, the Itanium's really not a consumer chip, as much as Intel wants it to be. The Itanium's a hella fast server chip, and that's where it'll stay for the rest of its diminuative mitigated life. I liken it to the POWER chips.
Now, if Intel got off their asses, they'd realize they could have it both ways if they wanted. Release a chip that's got a true x86-32 bit core and a true 64-bit Itanium core, run them in parallel and when code comes for a 32 bit processor, let it run on the x86 core. The earlier P6 cores would suffice, hell, even a Pentium M with a smaller cache and a lower clock speed would work. But that's a very complicated solution, and it's really playing to the masses.
Lastly, I don't want to sound too harsh on AMD, they really are doing their best to get back marketshare, but I really feel they've headed in a bad direction. While it seems like a good business move, it's terribly prolonging x86's life. On top of that, it's causing a huge stir in the market, especially where it concerns the hundred billion dollar giant Intel and the even worse, Microsoft. While both are bloated monopolies, they both have enough money and enough power to shut AMD up permanantly, and where would we be left, Transmeta??? Please. AMD needs to play their cards right and not be so infuriated; their gains are there, for the first time their server hardware is there, they just need to get their reputation running for them. It's really such a complex issue that I don't know where I stand with AMD anymore. I hate them for x86-64, but I love them for their speed. I hate them for keeping Itaniums out of my reach, but I love them for gaming. So complex an issue.
"Victory means exit strategy, and it's important for the President to explain to us what the exit strategy is." G.W.Bush
Yes, clearly making compilers work hard and have complex optimization code to generate high performance output is asking too much of them.
You must be a fan of gcc.
The format of this site sucks.. Lemme re-phrase. AMD and Linux are the greatest thing since Costa Rican Poontang ! Understood ?