I had heard of another thing recently, but can't seem to find it again. Basically there was some kind of code that was being implemented by nvidia boards that made amds perform worse on benchmarks.

Nvidia makes mobo chipsets still?

Somehow, I don't remember any new mobo or chipset from them. Ion doesn't count, if those are still popular (can't say I really follow those).

Huh, I thought you could OC on laptop cores. Not by much though but still.

Turbo boost will do it depending on the usage of cores... if it's a program utilizing any less than 4, it'll kick in.. depending on the program, the frequency will rise..

The Clarksfield-based 740QM in my laptop can go to just about 3ghz on single core usage... the temperature gets so high you can heat your fingers with the keyboard... that's why mainstream lappies won't let you OC.

It might not have been a board, but some kind of coding, tesselation or some such. I really don't remember. It was just something to do with benchmarks. Anyway, whatever the case may be, there was nvidia or intel coding (can't remember which) that would cause amds to perform worse than they should be.

Here's a quote I found:

"However, the Intel CPU dispatcher does not only check which instruction set is supported by the CPU, it also checks the vendor ID string," Fog details, "If the vendor string says 'GenuineIntel' then it uses the optimal code path. If the CPU is not from Intel then, in most cases, it will run the slowest possible version of the code, even if the CPU is fully compatible with a better version."

It turns out that while this is known behaviour, few users of the Intel compiler actually seem to know about it. Intel does not advertise the compiler as being Intel-specific, so the company has no excuse for deliberately crippling performance on non-Intel machines.

"Many software developers think that the compiler is compatible with AMD processors, and in fact it is, but unbeknownst to the programmer it puts in a biased CPU dispatcher that chooses an inferior code path whenever it is running on a non-Intel processor," Fog writes, "If programmers knew this fact they would probably use another compiler. Who wants to sell a piece of software that doesn't work well on AMD processors?"

In fact, Fog points out that even benchmarking programs are affected by this, up to a point where benchmark results can differ greatly depending on how a processor identifies itself. Ars found out that by changing the CPUID of a VIA Nano processor to AuthenticAMD you could increase performance in PCMark 2005's memory subsystem test by 10% - changing it to GenuineIntel yields a 47.4% performance improvement! There's more on that here [print version - the regular one won't load for me].

In other words, this is a very serious problem."

Intel, not Nvidia, is indeed rumored (or known?) of doing this kind of thing. Notice who your quote talks about (yeah, I bet this was a simple mixup, but still).

There's a lot of discussions on the net regarding the Intel Compiler and its bias.

Yeah I just couldn't remember which company it was. I treat Nvidia and Intel like they're one unit. Both are pieces of shit imo. (I have an nvidia board fyi). Nvidias been caught dozens of times over the years of falsifying their benchmarks, through things like built in code for scanning for 3dmark

Most laptops have overclocked features locked in the bios (Dells, HP, Lenovos...) 

If you have one of those "gamer" oriented laptops you may be able to overclock a little bit, but this is at the cost of battery life and heat. 

Otherwise, laptops have tutbo cores just like desktops which kick in when utilized, but I don't consider this an overclocks. I consider laptops downclocking themselves when not in turbo mode, rather than overclocking...

Pemalite said: Solid-Stark said: Well that's a devious practice. Also, on a tangent, isn't Broadwell planned to be embedded-only in all boards? I've heard nothing but negative feedback from this. Anyone think AMD can take advantage of Intel's bad rap? Nah. "Broadwell-D" is planned for socket 1150. (The same socket as Haswell.) Broadwell-H, Broadwell-U and Broadwell-Y (ITX, Ultrabook and Tablets) will drop any and all sockets. Broadwell-M will use a PGA socket for higher-end Laptops. That's been the plan from Intel anyway and follows it's tic-toc strategy, however "rumours" (Aka, stuff you shouldn't take as gospel/truth) point towards a Haswell Refresh for 2014 instead of Broadwell with Skylake still on track for 2015.

Interesting. I looked it up and I did find confirmation (from Intel) that 2014 will be a Haswell refresh at least for Desktops. Broadwell will be mobile only (all fronts) if it's out next year (and Broadwell will be available for higher end only at some point); Skylake will be out sometime after Broadwell, perhaps in 2015, and will be the replacement for Haswell refresh for Desktops + all other.

At least that's how I understood it :p I wonder why Intel has yet top clarify their roadmaps (AMD too).

Hopefully AMD can capitalize on this mistake with their new Steamroller CPUs... *fingers crossed for Steamroller to be good*