News Intel: Alder Lake Sampling, Sapphire Rapids Samples in Q4

[Admin]

Intel's Alder Lake client CPUs shipped to PC makers, Sapphire Rapids samples in Q4.

Intel: Alder Lake Sampling, Sapphire Rapids Samples in Q4 : Read more

 

[Geef]

Who wants to bet their Q4 timeframe will be 'pushed back' and they will tide everyone over with a 14++++++++++++++ chip?

 

[InvalidError]

Who wants to bet their Q4 timeframe will be 'pushed back' and they will tide everyone over with a 14++++++++++++++ chip?

I doubt Intel can afford any further delays when it looks like Zen 3 will pass Intel on per-core performance.

 

[JayNor]

Intel's Rocket Lake-S should take care of the zen3 desktop challenge.

Intel also has pcie4 on their new laptop chips.
I read an article for Samsung 980 Pro pcie4 m.2 format drive today. Looks like pcie4 is a good feature to have.

https://www.phoronix.com/scan.php?page=article&item=samsung-980-pro&num=1

 

[Jimbojan]

Intel really should go directly to 5nm, that is to skip 7nm all together, if it can to catch up with and surpass TSMC

 

[InvalidError]

Intel really should go directly to 5nm, that is to skip 7nm all together, if it can to catch up with and surpass TSMC

The "nm" figures are little more than marketing. Intel's 14nm process is about as dense as others' 10nm, its 10nm process is about as dense as others' 7-8nm and its 7nm process is expected to be about as dense as TSMC's 5nm.

Also, even if Intel wanted to skip steps, it wouldn't be able to simply due to the limited supply of next-gen EUV equipment, so it would still need to deploy 7nm in the meantime just to keep up with demand that 10-14nm cannot keep up with.

 

[Kamen Rider Blade]

RocketLake is based off the same MicroArchitecture as TigerLake, and after seeing it go up against Renoir, I'm not impressed.

AlderLake is where Intel has a real chance to catch up.

 

[watzupken]

So now Intel is going to call their 10nm+++ "enhanced SuperFin". I am not sure if they are going to regret going down this naming convention because 7nm is still a number of years away. So 10nm ++++ is going to be "very enhanced SuperFin". Whatever SuperFin they have, I don't feel its enough to turn the tide for them at this point. Especially so when they are unable to produce enough of 10nm chips.

 

[watzupken]

RocketLake is based off the same MicroArchitecture as TigerLake, and after seeing it go up against Renoir, I'm not impressed.

AlderLake is where Intel has a real chance to catch up.

Alder Lake may do well in the mobile space where the small cores will help. On the desktop space, its fairly pointless considering the rumored specs includes Alder Lake for desktop that does not come with any small cores at all. But if one is looking for performance, the lack of faster cores may limit their attractiveness. 8 fast and 8 slow cores for example will not bring them near the multicore performance of a proper 16 core Zen 3 CPU.

 

[JayNor]

8 fast and 8 slow cores for example will not bring them near the multicore performance of a proper 16 core Zen 3 CPU.

-

Intel's Gracemont doesn't have to match high performance cores ... just the AMD cores that have only avx2 and no dlboost. If they match AMD's zen3 cores doing SIMD and exceed AMD's zen3 doing simd AI operations with an atom core that is 1/3 the size and half the power of Intel's Golden Cove cores, then Intel can claim a win in many benchmarks, just as they demonstrated in the Tiger Lake launch.

 

[evilpaul]

Maybe they'll be really good in Sysmark, too? Are most people really running AI workloads and whatever software actually uses AVX512 on their laptops? The HPC laptop market?

And PCIe 4.0 in laptops? Sounds amazing for battery life. Are there benchmarks of it making a difference outside of CrystalDiskMark' sequential QD32 tests?

 

[JayNor]

Sapphire Rapids status was stated as "broadly sampling" at sc20.

It is on the 10ESF process ... same as the Xe-HP. It includes pcie5/CXL, DDR5, AMX tiled matrix processing of bfloat16, support for a new Optane version.

Xe-HP is also sampling.