• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

11900K is 88% faster then last gen & 35% faster then Ryzen 9 5900X

lol..
:eek:

May be the reason is at least you have a full FAT cpu with Intel unlike AMD's only half 8 core chip .

:D

He has an 8 core Zen 2 APU. Its a Laptop, a very nice Laptop but it doesn't have a full fat CPU. :p

Anyway, my CPU has the second CCD, it actually does, CRT 2 is detecting it, its just sleeping...
 
While the simple 'no' responses are correct, I'm sure there's some very specific contorted task where those figures are true.
There only problem is that those contorted task are meaningless.

AVX512. You know the most important SIMD since the sliced cheese butter hotdog cycle ;)
 
AVX512. You know the most important SIMD since the sliced cheese butter hotdog cycle ;)
There was a few posters on AT who always went on about AVX512 all the time before it came out, but they seemed to have gone quiet now.
Never mind that it's a power hog, not every problem can be parallelised as AVX512 requires. Plus, a super fast decoder still needs to read and write to memory.
AVX512 was basically Intel trying to show how x86 can compete with GPUs.
Then there's the crazy segmentation. Yes, we can understand why Intel's beancounters baulked at the die size increase AVX512 would require for lower end stuff, but then the also fused it off on perfectly good parts to play segmentation games and then wonder why it has so poor adaption rates.
 
There was a few posters on AT who always went on about AVX512 all the time before it came out, but they seemed to have gone quiet now.
Never mind that it's a power hog, not every problem can be parallelised as AVX512 requires. Plus, a super fast decoder still needs to read and write to memory.
AVX512 was basically Intel trying to show how x86 can compete with GPUs.
Then there's the crazy segmentation. Yes, we can understand why Intel's beancounters baulked at the die size increase AVX512 would require for lower end stuff, but then the also fused it off on perfectly good parts to play segmentation games and then wonder why it has so poor adaption rates.

Indeed, if Intel used their brains when deploying AVX512, I think SIMD would have been in better state.
 

For video encoding it has new encoders which speeds up certain types of encoding.

It isn't indicative of how fast the CPUs really are in 95% of use cases.

The improvement is mainly via the integrated gpu which hardly anyone uses anyway.

All Intel are claiming on average is 'double digit' IPC improvements. Which is probably going to be optimistic going by Intel's history.
 
About 20% IPC gain on Rocket Lake over Comet Lake I believe is the figure that most people might care about. Who buys a Core i9 and uses integrated graphics?! I buy the versions without any GPU - cheaper too.


I know right, silly Intel could have put 2 extra cores on Rocket lake if they leave off the igpu, as long as you don't mine the 400w power draw that is
 
Back
Top Bottom