Penryn 40% faster on games, video...

[terrace215]

http://biz.yahoo.com/bw/070417/20070416006532.html?.v=1

Gelsinger provided performance indicators for Intel's upcoming Penryn family of processors. For desktop PCs, he said to expect increases of about 15 percent for imaging-related applications; 25 percent for 3-D rendering; more than 40 percent for gaming; and more than 40 percent faster video encoding with Intel SSE4 optimized video encoders. The indicators were based on pre-production 45nm Hi-k Intel® quad core processor running at 3.33 Gigahertz (GHz) with a 1333 Megahertz (MHz) front side bus (FSB) and 12MB cache versus an Intel® Core(TM) 2 Extreme processor QX6800 introduced last week at 2.93 GHz with 1066 FSB and 8MB cache.

For high-performance computing (HPC) and workstation systems, Gelsinger said to expect gains up to an estimated 45 percent for bandwidth intensive applications; and a 25 percent increase for servers using Java(1). These indicators were derived from pre-production 45nm Hi-k Intel® Xeon® processors with 1600 MHz front side bus for workstation and HPC, and a 1333 MHz front side bus for servers versus today's quad-core Intel® Xeon® X5355 processors.

So much for Barcelona...

[serialk11r]

Some other chart said Barcelona was going to be 40% faster than Kentsfield/Clovertown... Now penryn... I think its going to be an intense battle.

[OmegaMerc]

40%? That sounds like a huge gap. Is it 40% with an IGP card or 40% with an enthusiast card or both? I'll believe it when I see it.

[m0da]

ditto. won't believe the extent of the gap until solid proof rolls out

[Vapor]

Good news is they have 3.33GHz 1333FSB chips up and running already

Let's face it...most of us would be happy with identical clock-for-clock performance with only higher clocks...but we're getting both, even if it is only a small gain in some applications.

[nn_step]

umm, who is doing their math?

[Movieman]

[QUOTE=Vapor;2134339]Good news is they have 3.33GHz 1333FSB chips up and running already
QUOTE]

At my house!

[theteamaqua]

they claim P35 was going to be 15% faster for core 2 duo ... how did that turn out ...

[nn_step]

they claim P35 was going to be 15% faster for core 2 duo ... how did that turn out ...

with matching Ram, about Zero

[Shintai]

This time we got actual benchmarks. More than we ever got on Barcelona.

[theteamaqua]

with matching Ram, about Zero

bingo ... and how will this turn out??

i am not syaing there wont be any ... but the performance gain will definitely not be 40% ... much less than that

but again ill get Q6600 for $266 in Q3, then get K10 when it drops price sometime next year .. or not

[nn_step]

This time we got actual benchmarks. More than we ever got on Barcelona.

Please take the lead and use that link to FIND A SINGLE IMPARTIAL (NON-INTEL designed) benchmark.

bingo ... and how will this turn out??

i am not syaing there wont be any ... but the performance gain will definitely not be 40% ... much less than that

Actually it wouldn't actually have any improvement until quality DDR3 starting hitting the masses, then 15% is possible

[theteamaqua]

the problem with AMD is taht its OCing headroom ... if it OCs well , then it will definitely be a killer for kentsfield.. say it can easily do 3.5Ghz on air for 24/7 then it will bne most ideal

[flopper]

300 more mhz and 4mb cache add that to todays cpu and the results would then be a little more acurate.

I wished they gave the cpu to someone like Joe who then would run a benchmark before and after on a clogged machine to see the benefit

[Vapor]

Good news is they have 3.33GHz 1333FSB chips up and running already

At my house!

Yeah, but yours aren't 45nm

[nn_step]

300 more mhz and 4mb cache add that to todays cpu and the results would then be a little more acurate.

I wished they gave the cpu to someone like Joe who then would run a benchmark before and after on a clogged machine to see the benefit

lets be honest that isn't a real fair trial. Since I can get a better 3Dmark score on a K6 and a lean system; than a 4Ghz Penryn set up by a retard who just happens to download alot of spam and viruses

[Revv23]

^whats to say a 45nm penryn doesnt do 4ghz with ease?

no point speculating until we see some hard evidence or specs, otherwise romurs mean pretty much nothing for either chip.

[nn_step]

^whats to say a 45nm penryn doesnt do 4ghz with ease?

no point speculating until we see some hard evidence or specs, otherwise romurs mean pretty much nothing for either chip.

well we all know how useful the jump from 130nm to 90nm was for netburst in terms of max overclock
for all we know, it might overclock WORSE, since perhaps the cache is more likely to lower the max clock speed.

[-Acid-]

Yeah, but yours aren't 45nm

not yet !!!!

fb 800 ram is what dave needs tho

[Movieman]

Yeah, but yours aren't 45nm

I could put them in a vise and give it a 20nm squeeze!

[-Acid-]

I wish it was that simple lol

[Shintai]

Please take the lead and use that link to FIND A SINGLE IMPARTIAL (NON-INTEL designed) benchmark.

But we believe AMDs numbers out of the box. You are funny nn_step.

[Shintai]

well we all know how useful the jump from 130nm to 90nm was for netburst in terms of max overclock
for all we know, it might overclock WORSE, since perhaps the cache is more likely to lower the max clock speed.

Ye sure, you need serious help. Did you also miss the current 3.33Ghz bin?

[Revv23]

well we all know how useful the jump from 130nm to 90nm was for netburst in terms of max overclock
for all we know, it might overclock WORSE, since perhaps the cache is more likely to lower the max clock speed.

hmm well do you remember 180>130? or maybe 90>65?

anyways, thats not my point. My point was that you can't compare unreleased hardware, especially not to another piece of unreleased hardware.

[nn_step]

I could put them in a vise and give it a 20nm squeeze!

now that is Xtreme

I wish it was that simple lol

Amen to that, then I'd be running 5nm sandies

But we believe AMDs numbers out of the box. You are funny nn_step.

nope, I believe AMD has yet to release official benchmarks for K10.