LOL at the wishful thinking that AMD will be able to magically get 15-20% higher IPC from a slightly tweaked architecture on the same process node.
Its called science :whistle
Intel seems to be happy with a mere 3% increase in IPC, while Trinity IPC is looking great in Engineering Sample benchmarks. We will see May 15th!
I don't think I've seen so many doctored results and made up math on the interwebs since last week!
Obviously we should trust this guy instead of the well-documented and thorough reviews by legitimate websites!
Obviously you can't comprehend the concept that performance does not directly scale with clock speed.Unless you have an FX 8150 that overclocks to 4.9 Ghz and a 6990 that overclocks to 990/1500 you are not qualified to judge whether my results are "made up". Any one with an FX 8150, or with common sense (36.1% clock scaled up from reviews at stock on CPU) can confirm my results within error.
Unless you have an FX 8150 that overclocks to 4.9 Ghz and a 6990 that overclocks to 990/1500 you are not qualified to judge whether my results are "made up". Any one with an FX 8150, or with common sense (36.1% clock scaled up from reviews at stock on CPU) can confirm my results within error.
Translation:
I am right, everyone else is wrong, nobody else can prove me wrong because nobody else was stupid enough to pair such a high power GPU with such a lousy CPU.
As they should, since the FX-8150 is a cheaper less expensive part compared to those other CPU. Thuban die size is larger than 8150. Intel CPU are on a smaller more advanced process.
Fact remains, it goes from being 48% behind at single threaded to DEAD even in the multithreaded test, compared to 2500k. If you are going to call that "bad scaling", than what is wrong with Intel's scaling such that they lose so much ground when going to the multicore test?
IMO this thread is potential evidence that AMD is paying people to post this nonsense on the forums. The OP has posted this same thread across just about every tech site out there.
Obviously you can't comprehend the concept that performance does not directly scale with clock speed.
Anyone with common sense can tell your results are BS.
have you done any 4-thread testing on Bulldozer, so we can see "without module contention, bulldozer is this much faster per clock than Ph2"?
have you done any 4-thread testing on Bulldozer, so we can see "without module contention, bulldozer is this much faster per clock than Ph2"?
We're talking about GPU performance and CPU scaling. Hence the title/topic of the thread.At least for the CPU part , perfs scaling with frequency is almost perfect
with a BD , so who s spreading BS ??...:biggrin:
have you done any 4-thread testing on Bulldozer, so we can see "without module contention, bulldozer is this much faster per clock than Ph2"?
I don't think I've seen so many doctored results and made up math on the interwebs since last week!
Obviously we should trust this guy instead of the well-documented and thorough reviews by legitimate websites!