How does Xeon E 5645 2.4 GHz compare to i-7 2600K 3.4 GHz ?

[dan99t]

I bought Dell workstation T-7500 with Xeon E 5645 2.4 GHz with other configuration like RAM, HDD, Win-7, etc same as Dell XPS 8300 desktop with i-7 2600K 3.4 GHz

But I am finding that workstation seems slower than desktop.

So is it the processor that is slow or something else ?

Percentage wise How much slower it should be ?

They want extra $ 500.00 to upgrade to Xeon X5650, 2.66 GHz. Would that be as good as i-7 2600K 3.4 GHz or better?

 

[Aquinus]

I bought Dell workstation T-7500 with Xeon E 5645 2.4 GHz with other configuration like RAM, HDD, Win-7, etc same as Dell XPS 8300 desktop with i-7 2600K 3.4 GHz

But I am finding that workstation seems slower than desktop.

So is it the processor that is slow or something else ?

Percentage wise How much slower it should be ?

What do you mean it runs slower? At what points does it slow down and is the HDD configuration (and hardware being used,) the same as the 2600 system? Clock-for-clock they're about the same (3.4ghz with 4 cores vs 2.4ghz on 6 cores.) With the speed of the platform, I doubt the CPU is what is making your workstation go slow. Maybe more information about both of the rigs would be helpful.

They want extra $ 500.00 to upgrade to Xeon X5650, 2.66 GHz. Would that be as good as i-7 2600K 3.4 GHz or better?

Upgrade the CPU yourself? That CPU costs only about 300 USD more if you buy the CPU by itself which puts their price at 200 USD over retail.

 

[Red_Machine]

Second result on google.

http://www.cpubenchmark.net/cpu.php?cpu=Intel+Xeon+E5645+@+2.40GHz

The Xeon is about 30-40% slower than the i7.

 

[Aquinus]

Second result on google.

http://www.cpubenchmark.net/cpu.php?cpu=Intel+Xeon+E5645+@+2.40GHz

The Xeon is about 30-40% slower than the i7.

At work I've run WPrime on a server with dual Xeon E5520 and my overclocked 3820 @ 4.75ghz runs faster than this dual-processor platform at stocks speeds it would be close, but we're talking about Nehelem vs Sandy Bridge which sports IPC improvements as well. I wouldn't go with a higher clocked CPU unless you need it. A multi-threaded benchmark would show where Xeon's shine.

(Xeons also support buffered and ECC memory, which adds to memory latencies.)

 

[Red_Machine]

I'm thinking his Xeon is Nehalem-based, considering the difference in speed. So what I said still stands, it feels slower because it IS slower.

 

[Aquinus]

I'm thinking his Xeon is Nehalem-based, considering the difference in speed. So what I said still stands, it feels slower because it IS slower.

You wouldn't feel that kind of difference between those two CPUs though. I think it's disk I/O and that the drive on the 2600k system is most likely faster. Honestly, just booting into Windows and using basic applications (internet browser, video, etc,) (excluding the fact that I now use SSDs,) but the 3820 launches applications off of my raid just as fast as my Phenom II 940 did. I would not be surprised one bit if this 100% an I/O issue and not a CPU issue. 2.4ghz 6-core isn't slow (plus there is a small turbo there iirc.)

 

[dan99t]

Both have WD 500 GB 7200 RPM ( No SSD, but would SSD make a huge difference ? )

Both have 12 GB RAM except Workstation has ECC. Does that slow it down ?

Xeon is Westmere

 

[Anusha]

Both have WD 500 GB 7200 RPM ( No SSD, but would SSD make a huge difference ? )

Both have 12 GB RAM except Workstation has ECC. Does that slow it down ?

Xeon is Westmere

SSD would make a BIG difference. nuf said.

 

[ShiBDiB]

SSD would make a BIG difference. nuf said.

No they wouldnt, just in load times. Thats about it.

 

[Anusha]

No they wouldnt, just in load times. Thats about it.

says someone who's not using one.

 

[ShiBDiB]

says someone who's not using one.

Ya but I can read, research and come to educated conclusions. The logic of, you dont own it so you dont know, is absolutely fucking retarded.

 

[Anusha]

Ya but I can read, research and come to educated conclusions. The logic of, you dont own it so you dont know, is absolutely fucking retarded.

but in this case, it is true.

even at the same sequential speed, SSDs feel much faster. reviews don't necessarily reveal that aspect. ask anyone who's using a SSD, can they go back to a regular HDD and use that PC for few minutes. you'll get your answer.

 

[ShiBDiB]

but in this case, it is true.

even at the same sequential speed, SSDs feel much faster. reviews don't necessarily reveal that aspect. ask anyone who's using a SSD, can they go back to a regular HDD and use that PC for few minutes. you'll get your answer.

All an ssd does is increase read and write times.. thus all it effects is load times. (In simple terms).

You have some screwy logic, if I go from a ferrari to a cadillac then ya its gonna seem slow. But it still performs the task of driving at a perfectly acceptable rate.

 

[Anusha]

All an ssd does is increase read and write times.. thus all it effects is load times. (In simple terms).

that's the most retarded thing i've heard whole year!

 

[Inceptor]

that's the most retarded thing i've heard whole year!

He's right, SSDs have increased read/write, across all r/w block sizes. This is where your 'feel' comes in; mechanical HDDs have decent sustained r/w but the r/w speed on small blocks of data is extremely slow compared to SSDs. The faster small block r/w on an SSD creates your faster 'feel'.

Why argue about something you obviously don't know enough about?

 

[Bo$$]

SSD lower access times vs HDD, speed has little relevence in realworld speed

 

[theeldest]

hey Dan,

I know exactly what you mean. I have my i5-2500k (4.6Ghz) at home and a T5500 with an x5660 (6-cores at 2.8Ghz) here at the office. The i5 feels a lot more snappy. Now, when I start loading up the VMs and such the more cores are a pretty big advantage.

Does that T7500 have just a single E5645 or two?

What does it have as far as graphics are concerned? Dual cards?

How long have you had it?

 

[theeldest]

Both have WD 500 GB 7200 RPM ( No SSD, but would SSD make a huge difference ? )

Both have 12 GB RAM except Workstation has ECC. Does that slow it down ?

Xeon is Westmere

Sorry for the two quick posts.

The ECC memory is a percent or two slower than non-ecc so you're not going to feel that difference.

Upgrading the hard drive would definitely help make it feel quicker. When I first booted up this T5500 it was running on a single 500GB drive just like yours. Played with it a bit before I realized the other 3 drives weren't being used.

Now it's set up in a 4-drive RAID10 and it definitely made a noticeable performance difference. Going SSD would help though.

Point of Interest: All OCZ drives are on sale on NewEgg and have an additional 15% discount via discount code. A 120GB drive ends up under $100 after all discounts & $30 rebate.

 

[theeldest]

SSD lower access times vs HDD, speed has little relevence in realworld speed

I swear, last post. (3 in a row is ridiculous).

Here's a great article on Storage Review: http://www.storagereview.com/articles/200003/20000318Conclude.html

It's from way back in they day when they first started using IOMeter. They discuss how Access Time has a huge impact on hard drive performance.

Let's examine a few examples from the theoretical side:

Drive A has a 13 millisecond access time and a 20 MB/sec transfer rate. Drive B has a 13 millisecond access time and a 30 MB/sec transfer rate. In all other cases, the two units are identical. Just how much faster is drive B than A? Let's take an easy example, SR's IOMeter Database Access Pattern. In this particular case (which isn't far off from typical workstation usage), Drive A's average I/O operation will take 13 milliseconds + (8k block / 20,000k transfer rate) = 13.4 milliseconds. Drive B, with its superior transfer rate, would take 13.26 milliseconds to complete the transaction. Not nearly as significant as we initially thought, is it?

Let's take the example one step further with a look at STR in an asymptotic nature. That's right, assume drive B possesses an infinitely fast transfer rate. In this case, Drive B bests drive A by a 13ms vs. 13.4 ms margin. That's right, a 3% margin.

As BO$$ said, speed is of little concern. The difference in random access time is immense (well over an order of magnitude difference). Anytime you do something in a program that hasn't been loaded from memory it's pulling from the hard drive. Most times these are small transfers that may be fragmented or just separate in nature.

If you can access these files immediately the transfer rate is secondary and and everything will feel more responsive because it *is* more responsive.

 

[Anusha]

He's right, SSDs have increased read/write, across all r/w block sizes. This is where your 'feel' comes in; mechanical HDDs have decent sustained r/w but the r/w speed on small blocks of data is extremely slow compared to SSDs. The faster small block r/w on an SSD creates your faster 'feel'.

Why argue about something you obviously don't know enough about?

he said increased TIMES, when it is increased SPEED. seriously? you are exactly saying what i am saying and still you take his side?

besides, the faster feeling is not in your head, it is really there. whole system it way snappier with an SSD. not everything is measurable by a suite of tests.

 

[eidairaman1]

ya Know to insult someone is not Nice at all Anusha. So grow the piss up


Btw SSDs do have advantage of no moving parts they however rely on a Clock Tick and latencies to determine performance so Some SSDs are faster than Other SSDs. Thing is the Xeon Based Platform, Im assuming is still 1366 vs 1155 and plus the Xeon being ran at 2.4 GHz vs a 2600K at 3.4 GHz. My only thinking is the Server Parts come at a slower tick rate so they can be sold at a certain TDP level so they can be put in cluster/blade servers where core density means more than clock speed which in turn true multi thread environments (Server Market) the Xeon Shines. If You could bump the Xeon clock rate up and then compare you might get your answer.

Hear this too, TPU test rig is still 1366 based and hasnt changed because the numbers are way too similar to justify an "Upgrade/sidegrade" to 1155

 

[Anusha]

ya Know to insult someone is not Nice at all Anusha. So grow the piss up

i apologize. i guess my crossfire woes are making me miserable.

but i still am holding my grounds. an SSD would make your PC experience so much better. besides, why downgrade the CPU *paying more $$$* for more performance when he can simply put in an SSD?

 

[eidairaman1]

Ok only thing I can think of is that Read and Write times to SSDs are faster, IDK by how much though because the other factor is Consumer Level SSDs are running off SATA bus and not directly off the Pci Express bus

 

[Anusha]

Ok only thing I can think of is that Read and Write times to SSDs are faster, IDK by how much though because the other factor is Consumer Level SSDs are running off SATA bus and not directly off the Pci Express bus

i believe it only affect RAID systems?

 

[Aquinus]

Ok only thing I can think of is that Read and Write times to SSDs are faster, IDK by how much though because the other factor is Consumer Level SSDs are running off SATA bus and not directly off the Pci Express bus

There is also practically no "seek time" since all an SSD has to do is select a segment of memory where a hard drive has to physically move the head across a rotating platter, where you then have to wait for the part of the media move under the head to where the stored data is. This makes SSDs able to perform more (vastly more) I/O operations per second, so assuming a regular HDD could hit the same read speeds as an SSD (which they don't), the SSD would benefit with smaller files where HDDs would benefit larger files. HDDs still benefit larger files because of the capacity and price per amount of storage, but for booting and running applications, SSDs fly and benefit you with the things you use on a regular basis. Honestly, it was like night and day going from just my RAID-5 with 3x 1tb drives to RAID-0 with two Force GTs on SATA 6gb for a boot device.