Intel accused of inflating CPU benchmark results
Intel accused of inflating CPU benchmark results
SPEC says Intel's Xeon processors were using a compiler that artificially inflated the results of its industrial benchmark by as much as 9%.
Intel accused of inflating CPU benchmark results::SPEC says Intel's Xeon processors were using a compiler that artificially inflated the results of its industrial benchmark by as much as 9%.
Oh, I thought that was assumed, because Intel always does that. At least I noticed it very clearly already back in the 90's.
What CPU did you notice that on in the 90's and how did you notice it?
I remember specifically P4 was vastly overrated by Intel, where Athlon was actually generally faster at math, Intel used specially compiled code to show P4 was faster.
But there were several examples where Intel cheated, because Athlon was way better than P4.
I even went so far as to make my own test program, to see what the actual speeds were. I was an IT consultant, and was frustrated that customers were convinced Intel P4 was better than Athlon. And they also claimed Intel was more compatible, which was so annoying, since Athlon was actually more backwards compatible than P4.
Everyone does it, it's basically expected at this point that any manufacturer will announce that their new chip will run an infinite loop in fewer microseconds than the neighbouring one would.
Ah yes, the Snake oil merchants tried to sell snake oil....again
Again?
But I suppose it's not that different to when they rigged an industrial phase-change cooler onto one of their CPUs, then pretended it could perform like an AMD CPU lol
Well, it could*!
*with an industrial cooling system
Wait, people trust corporate benchmarks?
Most of humanity is pretty clueless about IT in general and are just used to trusting who they buy from with zero critical thought or research.
Again?!
i will only care if they ever see consequences for it.
If a chip has instructions to make certain tasks go faster, I'd say it's fair to recompile the benchmark to use them. We didn't stop adding new things after the 486.
Are amd, nvidia and Intel not accused of this every generation?
It’s dieselgate for processors.
Very mixed on this. If the compiler is for example using stuff like constexpr in C++ to do major calculations at compile time instead of at runtime then yeah its cheating.
But on the other hand if its doing some Microarchitecture specific optmizations like reordering instructions or replacing certain instructions with others - as long as these are available to the public its fair game i.m.o..
The article states that the compilation was tailored for this specific task, which means it doesn't represent how the CPU would normally perform it. So it's definitely cheating.
A benchmark is not supposed to be a compiler optimization competition. If they showed both, and revealed it was optimized, it would be another matter.Even if the compiler was available to the public most software doesn't use it, so the benchmark is still not representative of real world performance.