TR Forums

Hello everyone!
I was thinking the other day that why is it so that the 4-core Core i5 series from Intel out-performs (or atleast performs almost the same as) the 8 and 6-core AMD processors, in current applications?
Is it due to (i) applications are being developed with Intel architecture in mind? OR (ii) current applications / games aren't utilizing 6 or 8 cores, yet? OR is there some other reason?
Thanks in advance!

Long story short, the Intels can work through a thread faster than the AMDs. So if the AMD took say 12 clock cycles to do X, and the Intel took 7 cycles, the Intel wins. This is called Instructions Per Clock (IPC). So AMD adds more cores and higher clock frequencies to make up for this.

EDIT: I tried to make this as simple to understand as possible.

It's also important to note that aside from an arguably superior CPU architecture, Intel is making CPUs at a smaller process (22nm instead of 32nm or 28nm). In general, Intel can fit more transistors in a given space and also run them more efficiently (which means they can go faster before running into thermal limits).

Also one has to be careful on the way AMD markets cpu's. Their 8 core FX is closer to a 4 core with good hyper-threading vs. a true 8 core.

More cores doesn't do anything for you if the software you're using isn't coded to effectively take advantage of them...That and Intel CPUs have a higher IPC as others have mentioned.

Most mainstream applications are still sensitive to single-thread performance, and this is where Intel dominates today. The extra cores on the AMD 6- and 8-core CPUs won't help you in those situations.

For applications that scale well to lots of cores, the AMD FX CPUs can still be a cost effective option. Power consumption will generally be a bit higher than an equivalently performing Intel system though.

anotherengineer wrote:

Also one has to be careful on the way AMD markets cpu's. Their 8 core FX is closer to a 4 core with good hyper-threading vs. a true 8 core.

Depends on the workload. For applications that are mostly integer code you get pretty close to a full 8 cores since it is the FPUs that are shared. On FPU-heavy code, yeah you take a bit of a performance hit.

Option number 2.

Just a FYI, applications compiled with Intel's compiler... Will favor Intel's CPU to a varying degree.

Such as Waterfox (64-bit version of Firefox, compiled with Intel's compiler. I do believe regular Firefox and Palemoon use Microsoft's compiler instead.)

UnfriendlyFire wrote:

Just a FYI, applications compiled with Intel's compiler... Will favor Intel's CPU to a varying degree.

It'll take a lot of degrees to get to AMD's usual TDP.

Yes, I'll be here all week.

Zaeem wrote:

Hello everyone!
I was thinking the other day that why is it so that the 4-core Core i5 series from Intel out-performs (or atleast performs almost the same as) the 8 and 6-core AMD processors, in current applications?
Is it due to (i) applications are being developed with Intel architecture in mind? OR (ii) current applications / games aren't utilizing 6 or 8 cores, yet? OR is there some other reason?
Thanks in advance!

For floating point workloads, it's because AMD halved FP-parts of its "cores" that handle FP workloads. To quote Anandtech: "As a comparison point, one core in Haswell has the same floating point performance per cycle as two modules (or four cores) in Steamroller."

Intel's Haswell and Ivy Bridge cores are roughly 50% faster while running at significantly lower clocks than AMD's Piledriver cores (I say Piledriver since we're talking about 8-core models). So, to illustrate, let's say a single Piledriver core found in the FX-8350 which is running at 4.0GHz produces 8 billion results per second, and an Ivy Bridge core found in the Core i7-3770K and running at 3.5GHz can manage 12 billion results per second. Note that this is for illustrative purposes only and there's no way a particular core design will always perform similarly relative to another core design with all types of code mixes. If you use all the cores in each processor, the FX-8350 may actually beat the Core i7 if we assume that the app can really scale well across many cores and not just throw a few light threads at some of the cores or some other factor related to multi-threading is limiting performance (you might want to read up a bit on Amdahl's Law). If the apps you use can well utilize as many cores as there are available, going the FX route may be a sensible choice as long as you don't mind AMD's lower energy efficiency/higher power consumption. To make their FX chips more compelling, AMD prices them very competitively and boards for FX processors generally offer more value for money. If, however, your apps generally use only a few cores then obviously most of the cores in the 8-core AMD chips are just going to sit idle while the apps run on just a few cores which can only produce 8 billion results each (again, this figure is just our example to illustrate my point). In this case, you're better off with a Core i5 or, if you're willing to spend, a Core i7. Inversely, boards for Intel processors also tend to be more expensive than similarly specced boards for AMD FX processors.

Here's the theoretical math:

If you use all available cores,

Intel = 4 x 12 = 48 billion results
AMD = 8 x 8 = 64 billion results

If you use only 4 cores,

Intel = 4 x 12 = 48 billion results
AMD = 4 x 8 = 32 billion results

Let's say your app uses 7 cores,

Intel = 4 x 12 = 48 billion results
AMD = 7 x 8 = 56 billion results

As for the common belief that 8-core FX chips only have 4 FPUs, this is simply wrong. Each dual-core module in the FX contains two 128-bit floating point engines that are accessible to both cores and both can work independently of each other. However, both 128-bit FP engines can be ganged together to work on bigger chunks of data and this feature is available to both integer cores within a dual-core module. AMD calls this FlexFP. Obviously, if both FPUs are being used by a particular integer core, the other integer core within the module in question will have to wait its turn.

I like your last answer Ronch. N00b friendly paraphrasing:

"You have to fully use at least six cores of an AMD 8-core before their extra cores make up for the poor performance of each core"

Why thank you, Chrispy! Did you know I typed all that on my Nexus 7 tablet?

(Actually, I'm typing this on my Samsung Galaxy tab right now.)

I dropped mine in the snow up an Alp and I've been relegated to a temporary Blackberry running BBOS 7.

I'm using the Surface RT when I'm not in the office (free gift, I'm not *that* stupid) but I'm not sure if I'd be better off trying to use the blackberry;

My gorilla-pawed C-to-F# piano-key handspan means that on-screen keyboard typing from me looks an awful lot like the output of a narcoleptic facerolling their keyboard.