AMD Alleges Intel Compilers Create Slower AMD Code

[HDTVMan]

Originally posted by: 100proof

Originally posted by: HDTVMan
A while ago there was an guy who did programming in a binary level. As I recall he removed the check for Genuine Intel and AMD got a big performance boost. I for one thought he was full of crap but apparently it must be legit.

All hell is going to break loose.

If Intel deliberately caused instability for Genuine AMD there is going to be hell to pay.

Companies and Consumers could file suits against Intel. Tough to prove but I would imagine AMD has some binary programmers under microscope with this one.

What Applications and what else has been degraded or worse made unstable.

http://www.swallowtail.org/naughty-intel.html

huh I posted that link on the first page?

 

[100proof]

Originally posted by: HDTVMan

Originally posted by: 100proof

http://www.swallowtail.org/naughty-intel.html

huh I posted that link on the first page?

Haven't been reading the entire thread, just skimming and had seen that link posted elsewhere.. :laugh:

About the entire argument being made, yeah it's somewhat unethical of Intel to take part in this practice.. However, if Intel didn't advertise this product to simply compile code, and instead specifically advertised that this product was intended for use with Intel CPU's then I'd imagine it's hard for Intel to be guilty of anything except careful wording.. Customers may have bought the product assuming that Intel would have made their product unrestricted for all cpus from all manufacturers, when Intel might have stated on the packaging for use with Intel cpus, etc.. The question is what is the specific language on the packaging and were Intel's Compilers advertised specifically for Intel products, or just products in general..

 

[HDTVMan]

Originally posted by: 100proof

Originally posted by: HDTVMan

Originally posted by: 100proof

http://www.swallowtail.org/naughty-intel.html

huh I posted that link on the first page?

Haven't been reading the entire thread, just skimming and had seen that link posted elsewhere.. :laugh:

About the entire argument being made, yeah it's somewhat unethical of Intel to take part in this practice.. However, if Intel didn't advertise this product to simply compile code, and instead specifically advertised that this product was intended for use with Intel CPU's then I'd imagine it's hard for Intel to be guilty of anything except careful wording.. Customers may have bought the product assuming that Intel would have made their product unrestricted for all cpus from all manufacturers, when Intel might have stated on the packaging for use with Intel cpus, etc.. The question is were Intel's Compilers advertised specifically for Intel products, or just products in general..

Then the source should never check for Genuine Intel. Since it does it becomes unethical. The program should not care what CPU is in the machine. It should compile all code as if it were Intel and not have to care about any other CPU. Since it checks for Genuine Intel and if it doesnt pass the program should prompt and stop and tell the use the compiler is for Intel only machines. Instead it puts junk code into the compile.

Very bad move to be caught red handed doing.

 

[p3r2y]

Originally posted by: ariafrost
If that isn't unethical, I don't know black from white.

I just bought parts for my college SFF rig... AMD proc, ATI mobo, nVidia graphics card, reusing a Philips soundcard... no Creative or Intel for me!

whats wrong with creative? i like my audigy 2 zs

 

[100proof]

Originally posted by: HDTVMan

Originally posted by: 100proof

Originally posted by: HDTVMan

Originally posted by: 100proof

http://www.swallowtail.org/naughty-intel.html

huh I posted that link on the first page?

Haven't been reading the entire thread, just skimming and had seen that link posted elsewhere.. :laugh:

About the entire argument being made, yeah it's somewhat unethical of Intel to take part in this practice.. However, if Intel didn't advertise this product to simply compile code, and instead specifically advertised that this product was intended for use with Intel CPU's then I'd imagine it's hard for Intel to be guilty of anything except careful wording.. Customers may have bought the product assuming that Intel would have made their product unrestricted for all cpus from all manufacturers, when Intel might have stated on the packaging for use with Intel cpus, etc.. The question is were Intel's Compilers advertised specifically for Intel products, or just products in general..

Then the source should never check for Genuine Intel. Since it does it becomes unethical. The program should not care what CPU is in the machine. It should compile all code as if it were Intel and not have to care about any other CPU. Since it checks for Genuine Intel and if it doesnt pass the program should prompt and stop and tell the use the compiler is for Intel only machines. Instead it puts junk code into the compile.


Very bad move to be caught red handed doing.

Sure it's a bad move, it's bad form, and I doubt many businesses will stand for purchasing a product offering from Intel that deliberately cripples its compiler(s) when it doesn't detect an Intel processor. After all who wants to buy a semi-crippled product? I doubt Intel will be found guilty of misrepresentation in a court of law if the wording on the package states that it's for use with Intel Processors.. Usually the liability rests with the language on the packaging as that's what influences a consumer's purchase. If these products state on the packaging "for use with Intel CPUs" then Intel isn't guilty of anything..

Oh by the way, my next cpu will be an AMD processor.. :laugh:

 

[Lithan]

Originally posted by: crimson117

Originally posted by: Lithan
Let's not forget they don't give their compiler away. They are selling it and PURPOSELY making it disfunctional. That is more than illegal. That is throw your ass in jail for fraud kind of illegal.

I was chatting about this on slashdot, and came to thinking that for this allegation, Intel didn't do anything illegal.

They only claim that their compiler produces code optimized for Intel processors. By optimized, they mean it uses standard optimized instruction sets like MMX and SSE when it detects Intel processors, and forces old-fashioned slow byte-by-byte operations for non-Intel processors. Sure it's a lousy way to write a compiler, and it only makes sense for developers who are compiling code that will only ever be run on Intel processors, but there's nothing actually illegal about it.

From http://www.intel.com/cd/software/products/asmo-na/eng/compilers/219754.htm
Achieve outstanding application performance on Intel® processors using Intel® C++ Compiler for Windows*.

See? They say it'll give great performance on Intel processors. Any wise developer should think, before using this compiler, "Well what does it do on non-Intel processors?", then ask the question, and if they find out it write crappy code for non-Intel processors, they should use another compiler.

You'd be right IF it claimed to be SSE-whatever enabled on INTEL procs. It claimed to be SSE-whatever enabled on all procs that supported it and then INTENTIONALLY disabled it on Non-intel Procs. That is fraud.

 

[Icopoli]

For those that just don't get it:

If you had an IBM cpu with SSE, SSE2 or SSE3, it would still compile like crap because it's not an Intel processor. It's not AMD vs Intel here, it's Intel vs anyone who would consider making a SSE instruction set enabled CPU. There's no other side to this arguement, Intel fu*ked up, and now they're paying for it.

I don't know how people are so blind or ignorant.

 

[100proof]

Originally posted by: Icopoli
For those that just don't get it:

If you had an IBM cpu with SSE, SSE2 or SSE3, it would still compile like crap because it's not an Intel processor. It's not AMD vs Intel here, it's Intel vs anyone who would consider making a SSE instruction set enabled CPU. There's no other side to this arguement, Intel fu*ked up, and now they're paying for it.

I don't know how people are so blind or ignorant.

:laugh: People understand the argument that's being made.. You're missing the liability aspect.. Sure this looks rather damaging to Intel's credibility. Now business individuals with purchasing decisions that were unaware of this crippling behavior by Intel's Compiler may consider alternative compilers... This information can also bolster AMD's case that Intel wishes to intentionally surpress its competitors products.. However, if Intel specifically stated on the packaging of the product that it is "for use with Intel Processors" then Intel isn't guilty of anything except careful wording...

 

[miketheidiot]

Originally posted by: JDCentral
We should all just use gcc...



What about the other x86 processors?

Is VIA going to sue for Intel not optimizing it's compilers for the x86-Eden CPUs?

I am a partial AMD fanboy... but I think that AMD will lose this particular argument.

If it really wants full optimization, AMD should write their own compilers...

Which would increase the price of their chips, making them closer to intel's priceline.

*thinking out loud*

You're missing the part where the made the compilier more complex in order to deactivate extensions in amd processors. Could this be why amd showed no improvement due to sse3?

 

[MDme]

does this mean that AMD processors may actually be faster than intel CPUs in media encoding as well??? maybe that's why the venice (with sse3) didn't seem any faster than the non ss3 enabled A64's.

maybe AMD should just issue a patch for the intel compiler which bypasses the geniune-intel CPU check. that way intel R&D benefits AMD CPUs too

 

[ryanv12]

Yeah, guys...this isn't about optimization. Intel's processors aren't gaining any performance with this code. It's about crippling their competition so they look better in comparison. There's a fine line between monopolistic and mere compeition. I definitely agree this crosses that line.

 

[miketheidiot]

Originally posted by: MDme
does this mean that AMD processors may actually be faster than intel CPUs in media encoding as well??? maybe that's why the venice (with sse3) didn't seem any faster than the non ss3 enabled A64's.

maybe AMD should just issue a patch for the intel compiler which bypasses the geniune-intel CPU check. that way intel R&D benefits AMD CPUs too

i'm sure that sun has some decent programmers working for them, perhaps they would be up to the job as well

 

[Fox5]

Originally posted by: MDme
does this mean that AMD processors may actually be faster than intel CPUs in media encoding as well??? maybe that's why the venice (with sse3) didn't seem any faster than the non ss3 enabled A64's.

maybe AMD should just issue a patch for the intel compiler which bypasses the geniune-intel CPU check. that way intel R&D benefits AMD CPUs too

AMD will generally win the smaller media encoding benchmarks, but the big programs have always seemed heavily geared towards Intel. I don't know if SSE support alone would make the difference...though 5% or 10% is often all the athlon 64 processors would need to match or beat Intel.

 

[100proof]

Originally posted by: miketheidiot

Originally posted by: JDCentral
We should all just use gcc...



What about the other x86 processors?

Is VIA going to sue for Intel not optimizing it's compilers for the x86-Eden CPUs?

I am a partial AMD fanboy... but I think that AMD will lose this particular argument.

If it really wants full optimization, AMD should write their own compilers...

Which would increase the price of their chips, making them closer to intel's priceline.

*thinking out loud*

You're missing the part where the made the compilier more complex in order to deactivate extensions in amd processors. Could this be why amd showed no improvement due to sse3?

With the present information available and Intel's credibility gap, I'd like to see some testing done to verify..

 

[Pabster]

Some of you are REALLY short sighted.

Another "allegation" to the heap.

Let us think about this. Code compiled with Intel C++ runs better on Intel chips? IMAGINE THAT!

 

[RoosterKooster]

Originally posted by: christoph83

Originally posted by: Duvie
AMD and Untel have a cross-licensing agreement with SSE and SSE2, right??? then by having their cpu flags not enable SSE and SSE2 on the compiler even though AMD has them seems a violation of that...

I wouldn't argue with it if AMD needed something added above Intel to run more optimized. i wouldn't expect Intel to optimize or tweak for their competitor but this isn't about this...this is about a very specific cpu flag that sole purpose is to look for intel trademark cpus..Once it was removed the compiler would use the SSE and SSE2 functions and perform 10% faster on the opteron...that is just plain crookedness...If you can justify this I would question why you are...

Maybe that's something to check out. But AFAIK the liscence is just to let amd use those SSE,SSE2 instructions in their chips. Since when does intel have to optimize their own compiler to enhance AMD's chips?

It's not as simple as the compiler NOT optimizing the AMD code, they are explicitly avoiding the optimization if it is an AMD chip. They should be compiling based SOLELY on the CPU's capabilities and not on whether it is an Intel CPU and its capabilities or if the CPU is an AMD cpu and then IGNORE the capabilities and compile with legacy optimizations but not the new, faster SSE2 & SSE3.

Intel is going down!!!

 

[Fox5]

Originally posted by: Pabster
Some of you are REALLY short sighted.

Another "allegation" to the heap.

Let us think about this. Code compiled with Intel C++ runs better on Intel chips? IMAGINE THAT!

That's not the problem, the problem is that the code compiled on the Intel compiler for Intel chips runs better on AMD cpus than the code compiled on the Intel compiler for AMD cpus.

 

[Keysplayr]

Originally posted by: coomar

Originally posted by: Bona Fide
Hm...AMD sure seems to be busting out all these allegations out of nowhere...I'm sure someone thinks that these are starting to lose their legitimacy. Even if AMD is right, they are gonna get some disrespect from the consumer community because of all this all-out warfare with Intel.

you can be counter-sued quite easily for slander, it would be dumb on the part of amd to take many of their legitimate beefs and stick them in with some weak ones, intel would counter-sue and amd would lose a lot of steam

a backlash from customers? the lawsuit alleges that intel is trying to create a monopoly, that it has consistently acted like someone out of the soprano's rather than an clean-cut corporation, that it has driven up costs (amd cpu's are cheaper so by limiting the amount of them on the market, intel is effectively increasing the cost to the customer), that is has sabotoged software (there is a huge difference between sabotage and optimization), the list goes on and on, I can in no way imagine this case going to a jury trial, the back-lash to intel would be immense

No.............such.............thing. Not even Disney.