Slashdot Mirror
AMD Athlon XP 3200+ Released
SpinnerBait writes "AMD took the wraps off their next speed bump with the Barton core, the Athlon
XP 3200+. This CPU runs with a 400MHz Front Side Bus at 2.2GHz and is
targeted at competing toe to toe with Intel's latest P4. The
benchmarks and review over at HotHardware, look pretty good but Intel's
3GHz/800MHz FSB P4 variant seems to squeak past it here and there. Regardless, more of that "yin" to compete with Intel's "yang" was released today by AMD and consumers will benefit again from the competition."
There are plenty of uses for fast cpu's that don't involve bloated software, hardware synthesis (ask Xylinx about it), media encoding and creation (software music synths are cpu hogs), high detail 3D visualization, genetic algorthims, etc. These are all apps I have used either professionally or recreationally (or both) and they all will have no problem scaling to any cpu based on moving electrons.
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
They use the marketing to show that their chips perform similar to Intel ones even though they're at a lower clock speed. Intel's P4 is designed to clock high and need to be clocked high as it can't do as much per cycle as the AMD.
Imagine the situation where car buyers only looked at the CC of the engine to determine how fast it would go, the AMD car would be a 2 litre but the Intel car would be 2.8 or something. So buyers would choose the Intel. Except the Intel engine has 4 cylinders and the AMD has 6 etc...
well if you want comparisons....
we just bought some Dell 2.2ghz P-4 laptops here to replace some aging and damaged laptops.. what they are replacing are P-III 800 laptops.
All of them run W2K and the users are NOT feeling a speed difference. Yes some of the processor intensive apps are fast. the winstone tests show it's faster.. but word processing and internet does not get a speed increase.
So in conclusion of my findings I also reccomend to EVERYONE to not upgrade their computer unless they absolutely have to. If you own a P-III that is 800mhz or higher, you will not see any difference unless you are a power user or a gamer.
It's just silly to spend money for the sake of spending it. as soon as we get a magnitude of speed change that will be very noticable (read that as SCSI like hard drive speeds... IDE is too damn slow) it is a waste of time and money to upgrade like we did 2 years ago and earlier. there are no real performance and quality changes (except for downgrade in quality)
Do not look at laser with remaining good eye.
Well, say intel used a performance rating to compare the P4 to a PIII, and took the 1GHz PIII as the baseline. Since the Pentium 4 does a lot less per clock cycle than the PIII, they'd probably have to call their P IV 3.0GHz a "P IV 2300+" or something.
Stick Men
Of course, they don't have to, since they've got the fastest chip on the block.
Yep, they have. But I find it interesting that if both chips were running the same true clockspeed, the AMD would be faster. It leads me to believe that Intel rely far more on being able to ramp up their clockspeed than they do on creating a better chip. For that reason alone I prefer AMD.
Considering the tech sector was the hardest hit? And tech people without jobs are more likely to spend time on Slashdot?
What's this Submit thingy do?
why they don't use MIPS/bogomips for chip benchmarks???
while (1) { if (rand() % 2) foo(); else bar(); }
How do you branch-predict that? Beyond simple for-loops (predict correctly N times in a row, predict wrong exactly once at the end of the loop) it gets very difficult.
But branch-prediction is only one part of the total pipeline performance, and you are arguing the wrong way anyway. Overall, it is the slower clock speed processors where pipelining is more important. In these processors you need to make sure the pipeline is full to get more operations per clock, to compensate for the slower clock speed. At 3GHz, it doesn't matter much if your code doesn't pipeline very well. At 500MHz, it is critical. That is why pentiums are such good general purpose processors, and why Itanium sucks.
I agree with you that they now play the thug to stay on top (burying alpha, doing a huge con job with Itanium etc etc).
...at least get it right!
MHz = operational speed, aka RPM. Not CC
Since Intel's P4 is does less work per cycle, it's like a small displacement engine working at high rpm. AMD's Barton is like a large engine working at lazier, lower revs.
>special interests have corrupted
>mainstream benchmarks to make them an
> unusuable guide.
This is true, to a certain extent!
People used to benchmark with, say,
Office scripts or other "office" jobs.
Most modern benchmarks are almost
100% multimedia (Internet content
creation, Divx, MP3 photoshop etc
come to mind). This is very convenient
for Intel because P4 is a multimedia
design (long pipes, high MHz, small
cache, fast FSB, SSE2) designed for
serial operations (small loops, no
branches) with huge data sets (fast
memory is good here).
The Athlon is a completely different
design and it cannot compete. I am
really wondering how it performs e.g.
with kernel compiles or other
system scripts.
Anyway, this reminds me of the situation
with K5 and Quake. Until the era of
Quake (and Pentium Classic) all
competing processors (AMD K5, K6,
Cyrix) had very very slow FPUs.
Quake was the first widespread game
to use FPUs (it relied on the FPU to
compute 1/z with fdiv) and even though
the K5/K6 were VERY fast with integer
code the Pentium Classic had vastly
superior performance under Quake
(popular benchmark at the time!).
Anyway, this whole situation is not
necessarily the fault of the benchmark
designers. Frankly, even though the
AMD may be faster at e.g. Excel I don't
intend to use huge multi-megabyte
spreadsheets (most of us don't) but
I do intend to use MP3/MPEG2 etc
algorithms for which (like Internet
Content Creation) the P4 may be
a better choice for those that can
afford it.
Actually I do own an Athlon 2200+
and I am very pleased with its
performance mostly (and most
importantly) because it is CHEAP.
(AMD always has better MIPS/FLOPS
per $, that's why I buy AMD)