Core2 Duo E4300 vs Pentium D 945 (which is better) ?

The street price for these two (OEM) are exactly the same ($233 CDN):

Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Dual-Core / Presler

Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe /

I'm thinking that the D will run hotter. It's also got twice the
cache as the Core.

The core supposedly has better performance per clock, but the ratio of
3.4:1.8 is about 1.9 (is the core *that much* faster per clock?).

So which one would you get?

Would this:

Core 2 Duo E6300 1.86GHz / 2MB Cache / 1066MHz FSB

beat the 945 D, even if it's $20 more?

Intel Guy <> wrote:

> The street price for these two (OEM) are exactly the same ($233 CDN):
>
> Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Dual-Core / Presler
>
> Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe /
>
> I'm thinking that the D will run hotter. It's also got twice the
> cache as the Core.
>
> The core supposedly has better performance per clock, but the ratio of
> 3.4:1.8 is about 1.9 (is the core *that much* faster per clock?).
>
> So which one would you get?
>
> Would this:
>
> Core 2 Duo E6300 1.86GHz / 2MB Cache / 1066MHz FSB
>
> beat the 945 D, even if it's $20 more?

Go for the Core2 in any case. You dont want to be stuck with a 32-bit
processor like the P945D in two years.

Plus, the FSB is so fast that the cache sizes don't matter much.

--
regards , Peter B. P. - http://titancity.com/blog , http://macplanet.dk

If guns kill, do pencils cause spelling errors?

Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler

vs

Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe

"Peter B. P." wrote:

> > So which one would you get?
>
> Go for the Core2 in any case. You dont want to be stuck with
> a 32-bit processor like the P945D in two years.

Aren't both of them 64-bit (Intel EM64T) ?

Intel Guy wrote:

> Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
>
> vs
>
> Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe
>
> Aren't both of them 64-bit (Intel EM64T) ?

So I take it then that the 945 is the better buy because it will
outperform the E4300.

Intel Guy <> wrote:

> Intel Guy wrote:
>
> > Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
> >
> > vs
> >
> > Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe
> >
> > Aren't both of them 64-bit (Intel EM64T) ?
>
> So I take it then that the 945 is the better buy because it will
> outperform the E4300.

Sorry, have been busy.

Yse, they are both 64-bit, you're right.

I haven't seen benchmarks, but my money is on the Core CPU.

--
regards , Peter B. P. - http://titancity.com/blog , http://macplanet.dk

If guns kill, do pencils cause spelling errors?

"Peter B. P." wrote:

> Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
>
> vs
>
> Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe


> Yes, they are both 64-bit, you're right.
>
> I haven't seen benchmarks, but my money is on the Core CPU.

Just looking at the ratio of the clock's of those two, the core would
have to be 1.89 times more effective or efficient on a clock-per-clock
(or ghz per ghz) basis compared to the D just to reach performance
parity with the D. And then you have the fact that the D's cache is
twice the size of the Core.

Wasn't there some sort of rule of thumb that you multiply the core's
clock by 1.x to compare it to the D? If so, what is x ?

On Tue, 27 Feb 2007 09:17:44 -0500, Intel Guy wrote:

> "Peter B. P." wrote:
>
> > Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
> >
> > vs
> >
> > Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe
>
>
>> Yes, they are both 64-bit, you're right.
>>
>> I haven't seen benchmarks, but my money is on the Core CPU.
>
> Just looking at the ratio of the clock's of those two, the core would
> have to be 1.89 times more effective or efficient on a clock-per-clock
> (or ghz per ghz) basis compared to the D just to reach performance
> parity with the D. And then you have the fact that the D's cache is
> twice the size of the Core.
>
> Wasn't there some sort of rule of thumb that you multiply the core's
> clock by 1.x to compare it to the D? If so, what is x ?

The P4 architecture is pretty dreadful. My benchmarks show that the Core2
ranges between 2.2 and 3.75X faster on a clock for clock basis. My Core2
is an E6700 2.66GHz with a 4M cache. My P4 is a dual Xeon, 2.66GHz with
..5M caches. The much bigger cache on the Pentium D should help a lot so
the ratio between the Pentium D and a Core2 won't be as high. However one
thing to take into account is that the Core2 is very overclockable, the
Pentium D is running close to it's limits. I'm running my Core2 at 3GHz
with stock Intel cooling and it's been completely stable. I probably could
run it faster but Lmsensors doesn't work on my motherboard, Abit AB9 Pro,
so I don't know what the CPU temperatures are and I wouldn't want to push
the CPU any further without being able to measure that.

"Intel Guy" <> wrote in message
news:...
> "Peter B. P." wrote:
>
> > Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
> >
> > vs
> >
> > Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe
>
>
>> Yes, they are both 64-bit, you're right.
>>
>> I haven't seen benchmarks, but my money is on the Core CPU.
>
> Just looking at the ratio of the clock's of those two, the core would
> have to be 1.89 times more effective or efficient on a clock-per-clock
> (or ghz per ghz) basis compared to the D just to reach performance
> parity with the D. And then you have the fact that the D's cache is
> twice the size of the Core.
>
> Wasn't there some sort of rule of thumb that you multiply the core's
> clock by 1.x to compare it to the D? If so, what is x ?

Toms Hardware had benchmarks and the Core 2 Duo was faster... even at 1.8
and 2 MB Cache. It's IPC is just that much higher. You would have to have
a perfect storm of an application having amazing cache hits at 2-4 MB for
the 945 to be better. Like someone said though, you can overclock that 1.8
to 2.6 or even 3 GHz and blow the 945 completely out of the water. You
would have to be crazy to buy a 945 or any 800/900 level Pentium unless they
were dirt cheap.

Intel Guy <> wrote:
> "Peter B. P." wrote:
> > Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
> >
> > vs
> >
> > Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe
>
> Wasn't there some sort of rule of thumb that you multiply the core's
> clock by 1.x to compare it to the D? If so, what is x ?

Not formally; it depends on workload. But depending on how much you believe
the hype, it's somewhere between 1.5x-2x. It also depends on what; GCC runs
much faster on my 2ghz (T7200) laptop than on my ~3.4ghz (overclocked P-D
940) desktop, despite slower ram (single channel 667mhz vs dual channel
800mhz) in the laptop. Video encoding goes *slightly* faster on the
desktop.

--
Nate Edel http://www.cubiclehermit.com/

"What's the use of yearning for Elysian Fields when you know you can't get
'em, and would only let 'em out on building leases if you had 'em?" (WSG)

Intel Guy wrote:
> "Peter B. P." wrote:
>
> > Pentium D 945 3.4GHz / 4MB Cache / 800MHz FSB / Presler
> >
> > vs
> >
> > Core2 Duo E4300 1.80GHz / 2MB Cache / 800MHz FSB / Conroe
>
>
>> Yes, they are both 64-bit, you're right.
>>
>> I haven't seen benchmarks, but my money is on the Core CPU.
>
> Just looking at the ratio of the clock's of those two, the core would
> have to be 1.89 times more effective or efficient on a clock-per-clock
> (or ghz per ghz) basis compared to the D just to reach performance
> parity with the D. And then you have the fact that the D's cache is
> twice the size of the Core.

Based on compiling the Linux kernel as a benchmark,the core should be
about 1.5 times faster than the 945, while for float it should be faster
than that, quite a bit if you have a compiler which can take advantage.

The core will overclock with the original heatsink, the 945 is unlikely
to do so. Not impossible, but... more likely to have a much higher o/c
limit with the core.
>
> Wasn't there some sort of rule of thumb that you multiply the core's
> clock by 1.x to compare it to the D? If so, what is x ?


--
Bill Davidsen
He was a full-time professional cat, not some moonlighting
ferret or weasel. He knew about these things.