Conroe & Merom,the war between 4Mb Cache,who is winner?!

[maratus]

I really thaught Conroe was going to get much higher performance due to the higher FSB, but it seems like I was wrong. Maybe it's a different scene in multimedia/decoding/encoding.

I really appreciate your work Coolaler, we know much more about these processors now!
I know it's a bit much to ask about but could you compare Merom and Conroe in:
*Winrar -packing and unpacking
*Mp3/wma/divx etc.

And maybe a Firefox benchmark? Does anybody know where to get that benchmark?

Oh yes, there are lots of debates about Conroe/Merom performance in
WinRar....

[iboomalot]

will be nice this summer when more overclocking features are avil and we can see how far these CPUs can OC and keep the Bus speed within reason.


If Conroe or merom can hit 3.5 on water I might even switch for a yr or two.

[Direwolf]

All the processors based on conroe should oc a good 50% give or take dont you guys believe if heat is not an issue. Im interested in the 6600 model

[ORCBEAST]

Coolaler

Freaking amazing comparison's, I was shocked how close those two really are! Imagine laptops with Merom ^__^

I think with new boards and new steppings coming out on both the differences will change all the time. Conroe will still be cheaper I reckon and will be released before Merom.

[Mesce]

Like someone said earlier it seems that the biggest difference between conroe and merom will be the motherboard. With the desktop motherboards offering more performance compared to the sckt 479 merom motherboards.

[nn_step]

If I remember correctly Memron is just a lower volt version of Conroe.. and the test practically show that...

[iterations]

Conroe/Merom performance comparison summary:

SuperPI_1m
Conroe: 17.125
Merom: 17.344

CPUmark99
Conroe: 418
Merom:413

SiSoft Sandra Dhrystone/Whetstone/Integer/FP/MemInt/MemFloat
Conroe: 27395/18882/163122/88312/7367/5871
Merom: 27515/18720/163693/88016/5478/5481

SiSoft Sanrda Memory Latency Linear/Random/Cache
Conroe: 60ns/14ns/31390
Merom: 78ns/12ns/28816

CineBench 2003 32-bit 1CPU/xCPU
Conroe: 509/941
Merom: 509/940

TMPGenc
Conroe: 15:34
Merom: 16:39

SuperPi_32M
Conroe: 16:36.797
Merom: 18:04.672

3DMark06CPU
Conroe: 2523
Merom: 2574

[EZClock]

Conroe does 1 minute and 30 seconds better in 32mb, incredible. Just imagine the 3.33XE on a decent OCing board .

[elmor]

I think that the most differences depends on the ram running different speeds and timings. Imo not a fair comparison when the rams aren't equal.

Though nice comparison coolaler, and previews like this are priceless.

[StyM]

how about some sciencemark results??

[DriveEuro]

Can CPUZ not properly read the Merom? Is it REALLY running at 1.37ghz? Can't be.

[iterations]

Can CPUZ not properly read the Merom? Is it REALLY running at 1.37ghz? Can't be.

That is just EIST (speedstep) kicking in, the processor was idle at the time of the screenshot. It was running at 2.96GHz during the benchmark.

[Mowgli]

COnroe in July, Merom in September, am i right?

Looks like the battle between these two...the scores are pretty close...

[DriveEuro]

That is just EIST (speedstep) kicking in, the processor was idle at the time of the screenshot. It was running at 2.96GHz during the benchmark.

Oh yeah... Duh. Forgot about that.

[iterations]

Correct: Woodcrest in June, Conroe in July, Merom in September.

I would expect Conroe and Merom to be very similar clock-for-clock since they are the same microarchitecture, just different voltage bins.

[iterations]

Yeah I think everyone knows that. There are many differences between the systems, FBS speed, memory ammount and timings, harddrives, video cards, etc...

It is still very interesting data though.

[Thorburn]

Not fair to compare anything besides CPU only tests as FSB/RAM speed difers, lol

your comparing apples to oranges in those super pi runs

That I believe is the point.
The major difference between these two machines is the front side bus and memory bandwidth, hence it gives an insight into how reliant the Core Microarchitecture is on its memory subsystem and how different setups will affect its performance.

At a silicon level these chips are as different as Yonah and Sossaman, I wouldn't be surprised if a wafer could pass as either.

[freecableguy]

CONROE = MEROM

You are all seeing a FSB difference. They ARE the same architecture.

[boblemagnifique]

CONROE = MEROM

You are all seeing a FSB difference. They ARE the same architecture.

+1 i think

[Lastviking]

1Gb vs 2Gb why not run both with 1gb or 2gb??i dont think its a fair test to run one on 2gb..

[don_vercetti]

1Gb vs 2Gb why not run both with 1gb or 2gb??i dont think its a fair test to run one on 2gb..

I thought that as well...but i read the top..

Merom T7400 Platform

M/B ?AOpen i975Xa-YDG
MEM ?G.SKILL DDRII HZ 1024x2 Dual Channel
HDD ?WD3200KS SATAII 16Mb Cache
VGA CARD ?ATI X1900 CF
POWER: ?? 520W
OS ?WIN XP SP2
CPU COOLER?Tower 120
CPU ?INTEL Core Mobile T7400 ES

Conroe Platform

M/B ?MSI 975X Platinum
MEM ?G.SKILL 2GB DDRII 1000 HZ 1024X2 Dual Channel
HDD ?Maxtor 300g SATAII 16Mb Cache
VGA CARD ?NV 7900GTX
POWER: Enhance 650W
OS ?WIN XP SP2
CPU COOLER?Tower 120
CPU ?Intel Core 2 Duo E6400 : 2.13G (266x08)/FSB 1066/L2 4MB

I think it is a reporting error....although coolaler can confirm or deny.

[SMa]

isn't it logical that the Conroe is faster if you run the tests with different ram frequencys and timings?
463.6MHz 4-3-2-4 vs. 380.3MHz 4-4-3-8

[GoldenTiger]

Oh yes, there are lots of debates about Conroe/Merom performance in
WinRar....

Yeah, I know man, that's my favorite benchie! It uses the hard disk so much, it is fun to watch the orange light stay almost solid and flicker... I always watch it intently wondering when it will flicker next!! It's so exciting!!

ROFL!

[PkG.1337]

They are the same in terms of performance
I think the only thing that matters to me now is overclockablilty

[pik-ard v1.1]

hmm, so basicly what's best for air overclockers is whatever has the right multi to have maximized ram speed at 3-3.2ghz... doesn't matter if it's conroe or merom. hmm...