Phenom IIs, Core I7-920 Win Out In Value Analysis

An anonymous reader writes "We've all seen processor benchmarks, but how do today's enthusiast CPUs look when you account for performance per dollar? Using a smorgasbord of charts, scatter plots, and performance tests, The Tech Report attempted to single out the highest-value offerings out of 16 popular Intel and AMD processors. The results might surprise you: AMD's 45nm Phenom IIs (both triple- and quad-core) prove to be strikingly competitive with Intel's Core 2 Quads. And, on the high end, Intel's $266 Core i7-920 turns out to be a compelling step up despite the higher costs of Core i7 platforms in general."

Comments

Suprise?

[AnonGCB]

Really, who doesn't know that AMD is higher performance per dollar.

Re:Suprise?

[nicolas.kassis]

Dollars are meaningless GIVE ME RAW SPEED!!!!

Re:Suprise?

[geekoid]

She cares because the Intel chips run cooler, and therefore the box will be quieter.

Re:Suprise?

[etymxris]

That's why you should stick to Core 2 Duos, which run at 65W, and are performance competitive with the latest AMD chips in 99% of use cases (quad core only has real value to "power" users that do things like transcoding, ray tracing, run multiple VMs, or run server apps).

The i7 performance advantages just don't seem to be worth the doubling (or more) of TDP. The Phenom IIs don't fare much better.

Re:Suprise?

[Anonymous Coward]

Dollars are meaningless? And this is rated +5 Insightful? I knew the economy was bad, but I didn't knew it was THAT bad! (That or /. is some kind of billionaire's club.)

Mistake in TFS

[Evanisincontrol]

And, on the high end, Intel's $266 Core i7-920 turns out to be a compelling step up despite the higher costs of Core i7 platforms in general.

TFA says that the Core i7-920 is $284; the chip below it (The Core 2 Quad Q9550) is $266. It's still up there on the performance/price scale, though.

Bottom LIne

[cybrthng]

Its about your investment.. For me Phenom II was a no brainer because of AM2+ compatibility. Once newegg put those suckers at 200 bucks i jumped. Its like i have an entire new PC and that was upgrading from the 9600 quad core.

Oddly enough i didn't have complaints about the performance of the 9600.. i just figured encoding times and processing times would be reduced enough that it would accelerate my work and well, for 200 bucks its done so and more so than i expected.

i7 is a nice platform but i'm penny pinching right now and looking for better ROI vs bragging rights.

Re:Bottom LIne

[gad_zuki!]

>i7 is a nice platform but i'm penny pinching right now and looking for better ROI vs bragging rights.

I wonder if penny-pinching will be more common with the economic downturn. If AMD can price itself lower then ROI will be very tempting, even if the Intel product is faster.

Re:Bottom LIne

[__aatmkh9910]

I agree, me(and most other consumers) will buy whichever chip gives them the most GHz for their buck, it doesn't matter who makes it.

Re:Bottom LIne

[Anonymous Coward]

I have an AMD 3800 X2 processor machine. I *never* had a problem with the processor's speed being my limiting factor in term of work getting done. *Never*.

Vast majority of consumers (including businesses) of computers are no longer limited by processor speed. It is not 1990s anymore. Any cheap processor will run your shit adequately provided you have 4GB RAM or more.

No Brainer

[XPeter]

It's been like this for the past few years. If your on a budget, go with AMD. If you have a little more dough to spend, go with Intel.

AMD price : performance linear

[jbeaupre]

What stood out to me is that AMD seems to have a fairly consistent price:performance ratio. Is this policy?

Most of their offerings fall pretty close to a line (not quite a zero crossing, but close). If this holds true for all their current and future offerings, you don't have to have test metrics for every processor. You can use price as a reasonable estimate of performance. i.e. Double the price gets you twice the performance.

Intel on the other hand, you can't trust price to indicate performance. A lot more research is involved. OR else you have to assume there's a high likelihood that the AMD offering for the same price will be better.

Re:AMD price : performance linear

[giverson]

It's because Intel dominates the high end. AMD can't sell a processor with a premium pricetag because its performance would compete with Intel's midrange which is priced pretty reasonably.

AMD is the loveable underdog, but don't forget how expensive their X2s were when they were dominant. AMD isn't cheap because they're doing us a favor, they're cheap because they have to be.

Re:AMD price : performance linear

[Bill Dog]

Indeed. Something that stood out to me (from that scatter graph) is:
* If you don't want to spend more than $100 on a CPU, AMD wins.
* If you don't want to spend more than $150 on a CPU, AMD wins.
* If you don't want to spend more than $200 on a CPU, AMD wins.
* If you don't want to spend more than $250 on a CPU, AMD wins.
* If you don't want to spend more than $300 on a CPU, Intel's (cheapest) i7 wins by far.

Re:AMD price : performance linear

[fnj]

Now run your comparisons based on 64 bit code instead of 32 bit. Intel shits the bed running in 64 bit mode.

Re:Price is all-important

[644bd346996]

Buying a faster chip is a lot cheaper and faster than rewriting something to be multithreaded.

Re:Price is all-important

[bami]

But buying a faster multi-core (as in, 3 or more cores) chip isn't going to do you any good if your application only runs on one or two threads.

Re:Price is all-important

[ArcherB]

But buying a faster multi-core (as in, 3 or more cores) chip isn't going to do you any good if your application only runs on one or two threads.

Very true if your system only runs that single application. However, everyone I know runs multiple applications just by booting their OS.

Re:Only one benchmark?

[Anonymous Coward]

Try reading the whole article!
Page 2: http://techreport.com/articles.x/16570/2

They are Multimedia Centric but not just 1 benchmark...
"We used the following versions of our test applications:

        * WorldBench 6 beta 2
        * Half-Life 2: Episode Two
        * Crysis Warhead
        * Far Cry 2
        * Unreal Tournament 3 1.3
        * Valve VRAD map build benchmark
        * Valve Source Engine particle simulation benchmark
        * Cinebench R10 64-bit Edition
        * POV-Ray for Windows 3.7 beta 29 64-bit
        * notfred's Folding benchmark CD 9/28/08 revision
        * The Panorama Factory 5.2 x64 Edition
        * Windows Media Encoder 9 x64 Edition
        * x264 HD benchmark 2.0 with x264 version 0.59.819
        * LAME MT 3.97a 64-bit
"

Re:Price is all-important

[SuperAndy]

Which is even more the case if you virtualise an operating system.

Re:Price is all-important

[geekoid]

multithreading is not that difficult, and there are ways to multithread an app without rewriting. Granted it's hackish, but then so is almost all of software.

Re:Let's stop making reviews for gamers

[fnj]

I'm curious what you think of the Atom processors

The Atom is an efficiency crap fest. It's garbage. I'd rather have an Arm chip any day. Let's get away from this absurd undead i386 architecture garbage. Linux runs on any architecture.

Re:Let's stop making reviews for gamers

[geekoid]

What real difference do you get from over clocking.
Don't get me wrong, I don't have anything against overclocking, and did it back when perfomance gains was going from Doom as a slide show to a smooth running game.
I also understand overclocking for the sake of overclocking. But is getting 15% increase in MHz really noticeable without testing?

And does it still ahve the same direct relationships now that a lot of work is being removed from the CPU, and the CPU's are tasking across several cores?

Re:Up front costs are a fraction of total costs

[yoshi_mon]

...running at 200 watts 24x7...

Unless your running SETI or some other setup then it's doubtful that your CPU is pegged at 200W 24x7. But lets for the sake of argument say that for whatever reason that some setup has it's CPU pegged at max/near-max all the time. What then is the value of the productivity?

Now that's a huge question and something I'm not even going to being to answer but just wanted to point out that putting out a lot of big numbers without context is pretty silly.