Intel is infamous for this thing their love with HP Libs why do you think Raptor lake clocks 6Ghz they freaking relaxed the CPP from 54nm to 60nm for Golden Cove/Raptor Cove to hit 5+ GHz.Why did they even chose It?
HP allows this performance increase that is why it's HP B580 Is 72 MTr/mm2 for whole die vs 92 for N5 logic I guess the media engine is taking quite the space.I found this.
49% difference in density. I highly doubt HP allows the same increase in frequency. Actually, B580 clocks as a RTX4060.
But I must say that despite using HP libraries B580 is pretty efficient.
We are talking about GPUs here, not CPUs.Intel is infamous for this thing their love with HP Libs why do you think Raptor lake clocks 6Ghz they freaking relaxed the CPP from 54nm to 60nm for Golden Cove/Raptor Cove to hit 5+ GHz.
What performance increase, be more specific? Without HP It would clock at only 2GHz or what do you mean exactly?HP allows this performance increase that is why it's HP B580 Is 72 MTr/mm2 for whole die vs 92 for N5 logic I guess the media engine is taking quite the space.
We are also talking about Intel here 🤣We are talking about GPUs here, not CPUs.
In case of GPUs you can pretty easily widen them for more performance unlike CPU, diminishing returns are not a real issue, If you don't go ridiculously wide.
I Meant using more metal layers and taller cells you can gain more performance out of a circuit.What performance increase, be more specific? Without HP It would clock at only 2GHz or what do you mean exactly?
There is and there is no doublt about itB580 has 72 MTr/mm2 density
AD106 has 120.5 MTr/mm2 density
AD107 has 129.5 MTr/mm2 density
Nvidia has 67-80% higher density, that's simply a huge difference.
I don't how much clock speed hit they would have taken but it could have been smaller definitely.I believe Intel could have dropped clocks to just ~2GHz(-30%) and put 50% more units inside instead and be smaller and have better efficiency while performing the same by using HD libraries, but this is only my belief.
You presume the right hand talks to the left in these big orgs they can be hiring right up until the day the whole business unit gets shut down by executive decision.
Arc is not cancelled I guess 🙂
Yeah it can happen but after the reorg with arc and also the fact that they have been working on G31 for quite some time(since December) it would be ready to launch in 4-5 monthsYou presume the right hand talks to the left in these big orgs they can be hiring right up until the day the whole business unit gets shut down by executive decision.
I am a former employee of Raja at both AMD and Intel. Koduri is absolutely catastrophic.Promises features that never exist. Makes shit up the night before he's talking to the public. Creates wildly toxic and in-fighting organizations. Forces employees to go advocate for his half-baked shit. The cringe Radeon rebellion marketing was enthusiastically Raja. The bait and switch of the Arc "Odyssey" events -- creating hype for a high-end GPU that would never exist. He fancies himself a big thinker and an artist and mettles in every little piece of the product and launch, even down to selecting exactly which hot sauces need to be on the menu for a press event.I promise you, I PROMISE you, everything Raja touches turns to garbage. Every cringe Radeon launch, every bungled Arc launch, Raja legitimately owns all of it. He's a terrible leader.
Confirmation bias maybe but that is exactly how I imagined it would be. Out of experience but just in a different industry.
Or the previous employees know the writing is on the wall, many left for greener pastures but until it is final that dgpus get axed, the positions need to be filled again.
Arc is not cancelled I guess 🙂