Without even counting on the TSMC 6nm full node advantage. That's even worst than what I expectedDouble the power of the nvidia chips they compared to being 15% faster? Probably won't even be faster when third party tests come out.
Without even counting on the TSMC 6nm full node advantage. That's even worst than what I expectedDouble the power of the nvidia chips they compared to being 15% faster? Probably won't even be faster when third party tests come out.
Full node? N6 is "7nm class" just like every other "7nm" processWithout even counting on the TSMC 6nm full node advantage. That's even worst than what I expected
Which makes it a full node ahead of the 10nm class 8lpp that ampere is fabbed on.Full node? N6 is "7nm class" just like every other "7nm" process
I was comparing to Ampere, which is what intel is referring to in their official competitive slide deckFull node? N6 is "7nm class" just like every other "7nm" process
Which makes the performance a little more embarrassing when you also consider that RTX 3060 mobile it's being compared against is only full-fat GA106, with 13.25 billion transistors and a 276mm2 on the much less dense Samsung process.Which makes it a full node ahead of the 10nm class 8lpp that ampere is fabbed on.
Furthermore, Intel finally adds the promised 3DMark optimizations toggle. In case you don’t remember, Intel launched its discrete GPU architecture with special architecture optimizations that boosted synthetic performance in software such as 3DMark. This is why we are seeing great results from Arc GPUs in this software, yet these cards perform much worse in games. Nevertheless, such benchmark-specific optimizations are against UL 3DMark rules, which is why all former Arc GPU tests were annotated as ‘not approved’.
Intel promised to provide a toggle in its Arc Control software that would disable said optimizations and allow Arc GPUs to perform a valid benchmark test. This was supposed to launch in April, but it took Intel another 2 months to finally enable this toggle.
Is there a specific reason to run them at resolutions none are even remotely comfortable with? The differences might be quite a bit different.I had test with chameleonrt use a 2.88M polygons hairball model:
View attachment 6655
No, the only reason is the aspect ratio of my monitor is 16:10.Is there a specific reason to run them at resolutions none are even remotely comfortable with? The differences might be quite a bit different.
Try running something like 1280x800 or even lower to give the cards a chanceNo, the only reason is the aspect ratio of my monitor is 16:10.
Don't we see the gap between AMD and NVidia widen with increased resolution?Why would lower resolutions help slower cards catch up? Higher resolution may actually help improve BVH cache hit rates and increase coherence in ray packets benefiting architectures that don’t handle divergence well.
Try running something like 1280x800 or even lower to give the cards a chance
Why would lower resolutions help slower cards catch up? Higher resolution may actually help improve BVH cache hit rates and increase coherence in ray packets benefiting architectures that don’t handle divergence well.
Who said it would help slower cards catch up? None of the cards is comfortable at that resolution based on performance, it doesn't mean the gaps would be smaller, bigger or even same at resolutions they're comfortable with. Whichever it is depends on several factors, obviously.Don't we see the gap between AMD and NVidia widen with increased resolution?
Who said it would help slower cards catch up? None of the cards is comfortable at that resolution based on performance, it doesn't mean the gaps would be smaller, bigger or even same at resolutions they're comfortable with. Whichever it is depends on several factors, obviously.
Don't we see the gap between AMD and NVidia widen with increased resolution?
I disagree, we have a whole thread dedicated to showing the contrary...In RT specifically? Not sure as there isn’t a lot of data on pure RT benchmarks at different resolutions.
I disagree, we have a whole thread dedicated to showing the contrary...