Slashdot Mirror
Pentium 4 6XX Sequence and New EE P4s Launched
Mojo-Dog writes "Today Intel took the wraps off their new
Pentium 4 Processors with EM64T extensions for 64-bit computing. The
Pentium 4 6XX Sequence and Pentium 4 3.73GHz are based on Prescott 2M cores with
a full 2MB of on-chip L2 cache as well.
HotHardware.com has a full review with benchmarks posted of these new P4s,
many of which also offer Intel's SpeedStep technology for power savings and
improved thermals, which has been available in Pentium Mobile CPUs for some time
now."
"older" P4 will have a price drop,which will be good for People saving 50$ on a new System.
... of this new CPU is how little power it uses compared to older Prescotts:
. htm
- 600/index.x?pg=16
http://www.hardcoreware.net/reviews/review-263-11
http://www.techreport.com/reviews/2005q1/pentium4
Load temperatures are the same levels as idle temps on the old prescotts!
"If you spend a significant amount of time waiting for that sort of thing to complete then it could well be worth it, especially if you're rendering more complex models." If I did that, I'd be better off with an Intel Xeon processor or two, not this.
Item 2 isn't a "design error", it's a trade-off at any moment in time whether you support 64-bit addressing, doing so means a lot more transistors, and if (as with Intel) most of your customers are buying mid-range desktop machines that's a bad trade in 1992, in fact it was still a bad trade as recently as 5 years ago.
Item 3 is an improvement, but you mis-described NX, it doesn't "prevent buffer overflows" at all. It's a _marginal_ defense again deliberate stack smash attacks in which executable code is written during a buffer overflow. Buffer overflows have been used by Black Hats quite happily on Alpha, MIPS etc all these years despite non-executable stacks. It remains to be seen whether the development cost for this feature pays for itself in terms of raising the bar for black hats.
Item 1 is a trade-off again, but one that Intel should have made years ago, perhaps when they designed the 386. 128 registers means a lot more silicon, yet many inner loops will never use more than a dozen or so registers, meaning you either make price/performance worse, or you sacrifice something else (maybe vector instructions) to keep costs down. Every designer makes their own decisions here, and they're validated in the market. Eight wasn't enough, Sixteen is definitely closer to the sweet spot.
AMD made good trade offs with x86-64, they were rewarded in the marketplace and Intel are jumping on the same bandwagon now with EM64T.
RISC processors always have more cache than CISC processors, it's part of the design tradeoff. RISC takes less silicon to implement the core than CISC, which leaves more room to dedicate to the cache. Also the same complex operation requires more instructions on a RISC than a CISC, thus you need more L2 to keep the same amount of functional code in cache.
11*43+456^2
If I'm not totally incorrect we may see 64-bit GPUs in the next few years (2007?). IIRC, there was some remark from some ATI/nVidia guy somehere. Perhaps it was relating to the upcoming Unreal 3 technology, I really don't remember. Or, was it 128-bit colours? Hrrrmmm...
Actually, most computing activity isn't CPU bound. I've got a mobile Athlon 64, for example, and with obvious exceptions like games or media encoding, the CPU usually runs in the slowest mode, with low utilisation. On the other hand, with all the stuff I run (ssh sessions, email client, web browsers, media players) it's relatively rare for the CPU to be doing nothing at all.
Among other things, running the CPU in the slowest mode saves power because it reduces cooling pressure, so the fans and whatnot can run at lower speeds. This is on a laptop, but my desktop has ACPI-managed fans too.
8 more general purpose registers will do well to most code.
SSE3 in Prescott was an addition with very little real usage so far. The 64-bit x86-based ISA is a prime example of what you'll hate yourself for not having in a few years from now. So, now you have to wait some more time before you can get an affordable 64-bit CPU. If you're currently in love with the positive points of SMP, you will even have to wait for an affordable dual-core 64-bit chip. Good luck....
Oh dear, I certainly hope not.
I've never had driver problems with Linux built in 64 bit mode. I have a production server running with it and still going. amd64 root # uptime 22:08:59 up 170 days, 10:13, 1 user, load average: 0.00, 0.00, 0.00 amd64 root # uname -m x86_64
Servers are irrelevant; Windows XP is an OS for desktops and laptops, not servers. To me, an operating system is ready when it runs on a broad range of hardware systems in the target category, taking full advantage of their features. On the various laptop and desktop systems I've used, Windows XP 64-bit (RC version) has mediocre hardware support, but Linux and BSD are even worse. For small servers, any of Windows (Server 2003, not XP), Linux or BSD is fine, but BSD doesn't scale to larger systems, leaving only Windows and Linux (ideally 2.6, since 2.4 can't keep up with Windows in terms of scalability).
In the laptop market, I wouldn't even consider Linux/x86 to be 'ready'. Its laptop hardware support is very poor compared to Windows XP, especially in terms of power management. Very often, even though it can use the hardware in some fashion, it can't make use of all its capabilities. For most desktop systems Linux is fine.
If running a kernel on the chip were all that mattered, Windows (or, more precisely, the NT kernel) would have been 'ready' since before the AMD64 shipped, since Microsoft had it running on prototypes from AMD, and Microsoft's main kernel developer had been working with AMD on the chip design for years.
From the article...
"This is a very interesting test because it shows you the balanced smoothness of Intel's Hyper-Threading technology in action."
What the heck are these crakeheads talking about.
Don't forget that Intel does a lot more than X86 CPUs too. They just retook the NOR flash sales title (admittedly after losing it, through another stupid business decision), and Hector Ruiz may now be mulling the sale of Spansion because of the intense competition. On one hand they are up against the wall WRT being forced to use band-aid solutions for the current P4 CPUs as a result of their bull-headed run for MHz, as well as the limited acceptance of Itanium. On the other hand, however, they are dominating the mobile sector with P-M and are expanding that platform; they also have their hands in things like WiMax and other emerging technologies; and don't forget they have enough money in the bank to probably buy AMD.
With Otellini now being fairly frank about the competitive landscape, I think it's possible that the company has reached a turning point.
Your own post is pretty misleading.
The Itanium didn't offer drastically improved performance for the price, and AMD processors don't sacrifice much performance for x86 compatibility.
<blockquote>As in the past, backward compatibility won out over superior technology, and AMD has been winning market share from Intel.</blockquote>
Not true at all. Price/Performance won out. In this case, the better performer for the price, just happens to have better backwards compatibility as well.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant