Intel's claims Penryn 40% faster in games!

[wickedmonster]

http://www.techreport.com/onearticle.x/12272

Wow! A 3.33 GHZ Penryn is 40% faster than a 2.93 GHZ QX6800 in games! Barcelona is going to get creamed if this is true.

More benchmark data:

http://techgage.com/viewimg/?img=/articles/intel/beijing_idf_07/idf_beijing_01.jpg&desc=Intel%20Penryn

Penryn is going to be a monster!

 

[BaronMatrix]

http://www.techreport.com/onearticle.x/12272

Wow! A 3.33 GHZ Penryn is 40% faster than a 2.93 GHZ QX6800 in games! Barcelona is going to get creamed if this is true.

We'll have to wait until we actually see Agena FX. If the perf holds up to the specs I'd say a similarly clocked Agena will be at 80% faster than K8 in games due to the higher RAM speed (supports 1066), faster HT3 bus and dual loads/stores.

I personally will be glad to see an actual benchmark, though I don't doubt AMDs "word." Penryn will be formidable but it seems to me like Intel maybe making too many intros too close together.

Everyone also thought the P4s high clocks would do in K8.

 

[RichPLS]

http://www.techreport.com/onearticle.x/12272

Wow! A 3.33 GHZ Penryn is 40% faster than a 2.93 GHZ QX6800 in games! Barcelona is going to get creamed if this is true.

We'll have to wait until we actually see Agena FX. If the perf holds up to the specs I'd say a similarly clocked Agena will be at 80% faster than K8 in games due to the higher RAM speed (supports 1066), faster HT3 bus and dual loads/stores.
Benches...Links...

I personally will be glad to see an actual benchmark, though I don't doubt AMDs "word."

Ain't that the TRUTH!!!

Penryn will be formidable but it seems to me like Intel maybe making too many intros too close together.

Which is following their plan as expected... :roll:

Everyone also thought the P4s high clocks would do in K8.

They did reach right up there, eventually matching and even besting quite a few once stock speeds got up to 3.6 and 3.8GHz... and then you could still overclock them further...

 

[nightscope]

http://www.techreport.com/onearticle.x/12272

Wow! A 3.33 GHZ Penryn is 40% faster than a 2.93 GHZ QX6800 in games! Barcelona is going to get creamed if this is true.

Well, you don't know how Barcelona performs. You might be just as surprised when they release their K10 benchies on April 23rd (according to a post somewhere on here).

 

[RichPLS]

But in 6 months, how many revisions and releases will intel have out improving thier performance that these unseen benchmark claims are beating current production C2D's?
So if AMD is indeed 80% faster, will intel be 120% faster?

 

[boduke]

http://www.techreport.com/onearticle.x/12272

Wow! A 3.33 GHZ Penryn is 40% faster than a 2.93 GHZ QX6800 in games! Barcelona is going to get creamed if this is true.

Well, you don't know how Barcelona performs. You might be just as surprised when they release their K10 benchies on April 23rd (according to a post somewhere on here).

Here's the issue with this - "they" are going to be AMD releasing benchmarks - not third party - AMD. They should have had ES's in peoples hands by now - they should be doing far more than they are. They're not. So even AFTER the 23rd until Toms, Anand, [H], whoever as long as it's NOT AMD, gets their hands on these parts and releases independent benchmarks then I'll take it all with a with a large grain of salt.

And before any of you AMD fans spout nonsense I feel exactly the same regarding Intel's statements in terms of their upcoming parts....

 

[nightscope]

But in 6 months, how many revisions and releases will intel have out improving thier performance that these unseen benchmark claims are beating current production C2D's?
So if AMD is indeed 80% faster, will intel be 120% faster?

Well, if Penryn is released before K10 (which is very likely), then AMD will have the advantage of examining a processor so they can base theirs to have higher performance. Oh well, we can't really say anything until we see some benchies! (Wonder how long we've been saying that).

 

[ajfink]

But in 6 months, how many revisions and releases will intel have out improving thier performance that these unseen benchmark claims are beating current production C2D's?
So if AMD is indeed 80% faster, will intel be 120% faster?

Well, if Penryn is released before K10 (which is very likely), then AMD will have the advantage of examining a processor so they can base theirs to have higher performance. Oh well, we can't really say anything until we see some benchies! (Wonder how long we've been saying that).

I hate when people make statements like this. For crying out loud....

This is quite a hefty claim for Intel to make. Perhaps they mean running Doom 3 at the lowest possible settings on integrated graphics. Who knows.

 

[nightscope]

But in 6 months, how many revisions and releases will intel have out improving thier performance that these unseen benchmark claims are beating current production C2D's?
So if AMD is indeed 80% faster, will intel be 120% faster?

Well, if Penryn is released before K10 (which is very likely), then AMD will have the advantage of examining a processor so they can base theirs to have higher performance. Oh well, we can't really say anything until we see some benchies! (Wonder how long we've been saying that).

I hate when people make statements like this. For crying out loud....

This is quite a hefty claim for Intel to make. Perhaps they mean running Doom 3 at the lowest possible settings on integrated graphics. Who knows.

Exactly! We can't really say anything until we see some benchmarks!

 

[Major_Spittle]

Here's the issue with this - "they" are going to be AMD releasing benchmarks - not third party - AMD. They should have had ES's in peoples hands by now - they should be doing far more than they are. They're not. So even AFTER the 23rd until Toms, Anand, [H], whoever as long as it's NOT AMD, gets their hands on these parts and releases independent benchmarks then I'll take it all with a with a large grain of salt.

And before any of you AMD fans spout nonsense I feel exactly the same regarding Intel's statements in terms of their upcoming parts....

Lets keep in mind that AMD is releasing a Server chip. Of course there won't really be any previews of it other than AMD sabre rattling. This is normal for server chips because bussinesses don't run out and buy new server chips because of some review 2 months before the release.

Now as far as the K10 desktop processor benchmarks. There is no release date for K10 desktop chips yet. Hell, if K10 Server chips are in high demand and the desktop market looks bleak for K10 due to price/performance/competition, a K10 desktop processor could still be being tweaked before it will be released. So why would AMD benchmark something they haven't even finalized for market yet???

 

[Opterondo]

http://www.techreport.com/onearticle.x/12272

Wow! A 3.33 GHZ Penryn is 40% faster than a 2.93 GHZ QX6800 in games! Barcelona is going to get creamed if this is true.

We'll have to wait until we actually see Agena FX. If the perf holds up to the specs I'd say a similarly clocked Agena will be at 80% faster than K8 in games due to the higher RAM speed (supports 1066), faster HT3 bus and dual loads/stores.

I personally will be glad to see an actual benchmark, though I don't doubt AMDs "word." Penryn will be formidable but it seems to me like Intel maybe making too many intros too close together.

Everyone also thought the P4s high clocks would do in K8.
Sadly not, AMD has stated that K10 has 80% higher FPU performance (roughly 25% faster in games) than K8-Opt. per core. This is good enough to best the C2D but AMD has skipped a generation so they need to set their sights higher; second place isn't going to cut it. And not everyone is going to want to run 8 core AgenaFX to keep up with the 4 core Penryn.

There is one thing I don't like about, "Penryn is 40% faster .. in games!". What was the resolution 640x480? Was there any eyecandy turned on? Is this determined my measuring useless MAX FPS or by measuring useful MIN FPS (the chunk test)?

 

[ajfink]

But in 6 months, how many revisions and releases will intel have out improving thier performance that these unseen benchmark claims are beating current production C2D's?
So if AMD is indeed 80% faster, will intel be 120% faster?

Well, if Penryn is released before K10 (which is very likely), then AMD will have the advantage of examining a processor so they can base theirs to have higher performance. Oh well, we can't really say anything until we see some benchies! (Wonder how long we've been saying that).

I hate when people make statements like this. For crying out loud....

This is quite a hefty claim for Intel to make. Perhaps they mean running Doom 3 at the lowest possible settings on integrated graphics. Who knows.

To bench a CPU on running game code, this is the only way to do it ... otherwise you are not benching the CPU you are benching the GPU.

This is true.

I'm not much of a PC gamer (360 all the way), I'm more interested in video / audio encoding power and other tasks. So, in my mind, getting 120fps instead of 110 seems like a bit of a moot point to me. I don't mean to sound like Baron, though.

 

[chiefwonk]

no more talk clamining % increase we want the benchmarks....................... lets see who got higher performance

 

[the_vorlon]

Perhaps more important from an AMD point of view is that Intel will FINALLY (my god it is f&*king time) get rid of the Netburst based chips for 4 sockets and up.

The 8xxx series Opterons are AMD's best cash cow, they still go for well over $1000 a pop, because the combination of Hypertransport and the fact that netburst utterly sucks means that in 4s/8 cores and up, Intel is currently getting destroyed.

4 Woodcrest/Clovertowns on a 4 socket/4 FSB board + 64 meg snoop filter, while certainly in no danger whatsoever of winning a beauty prize for technical elegance, will at least be back in the game, perhaps even marginally ahead, performance wise.

~~~~~

Due in Q3 of this year is also Intel’s Caneland platform with Tigerton dual- and quad-core processors. The CPUs will replace the aging Xeon MP 7100 series and will not only complement Intel’s 65 nm Core architecture deployment, but also allow Intel to regain market shares it has lost to AMD in the lucrative MP server segment.

By the end of the year, Intel will also be offering a dual-socket consumer PC platform. Depending on your view, this could either be seen as a reaction to AMD’s dual-socket QuadFX (4x4) platform or as a logical step to offer what some enthusiasts have been doing for some time - to take a Xeon server board and use Woodcrest or Clovertown processors to build a system with two dual- or quad-core processors. Intel calls this project “Skulltrail,” which will support two Core processors with up to eight cores. The platform will also run up to four graphics cards.

 

[dragonsprayer]

lol!

40% faster - 40% faster in which game, a which resolution????


wow this just happens to match the statement by amd that their new processors are 40% faster then c2d!

Get it - its bs!

 

[razortonguekiss]

damn mayn, I'm here waitin to purchase parts for somethin new and all this ill ass stuff is jus waitin to be introduced to the market...

decisions decisions

 

[3Ball]

It would appear that a ~14% faster clock speed penryn (3.33ghz vs 2.93ghz) is 40% faster in whatever game they claim. So this makes it ~26% faster clock for clock than the current intel core 2 quad cores am I correct? Will this be enough to best barcelona from the information we have recieved that is, which looks better so far...I havent had much time to look over the situation! Any thoughts?

Best,

3Ball

 

[Sharikook]

AMD has claimed Barcelona will be 40% faster on one FP benchmark. Yes, the same one that Henri Richard stood around complaining that was too old to use.

Is everyone else sick of AMD's puerile whining about "open and fair compeition" and how Intel only shows benchmarks that favour their products when AMD does exactly the same thing?! AMD could save some cash by firing Henri Richard for sure!

 

[r0x0r]

There is one thing I don't like about, "Penryn is 40% faster .. in games!". What was the resolution 640x480? Was there any eyecandy turned on? Is this determined my measuring useless MAX FPS or by measuring useful MIN FPS (the chunk test)?

Couldn't agree more.

 

[wickedmonster]

http://www.theinquirer.net/default.aspx?article=38977

For SSE4 optimized programs, Penryn is 61% faster than Conroe in video encoding. 18 secs vs 29 secs.

 

[epsilon84]

The keypoint being - how long until applications start to take advantage of SSE4?

 

[wickedmonster]

http://techgage.com/viewimg/?img=/articles/intel/beijing_idf_07/idf_beijing_01.jpg&desc=Intel%20Penryn

Wow! Penryn is going to rock!

 

[qcmadness]

http://techgage.com/viewimg/?img=/articles/intel/beijing_idf_07/idf_beijing_01.jpg&desc=Intel%20Penryn

Wow! Penryn is going to rock!

1st, Penryn has about 10% frequency advantage.
2nd, the "211%" percent faster is based on optimized codes which should not be treated as other benches. I will need a SSE-3 optimized encoding application to confirm the SSE code performance.

 

[gOJDO]

Sadly not, AMD has stated that K10 has 80% higher FPU performance (roughly 25% faster in games) than K8-Opt. per core.

FP performance has nothing to do with GAMES performance!
Games CPU performance depends of its AL and its SSE performance(90% of the instructions).
K10 will perform faster in games for sure, but not faster than Core2, clock for clock.

 

[impreza]

and tell me why I need it when I have yet to find a game that can use more than half my 4200x2?
to use that you will need a r600+