Monday, July 27th 2020

Intel to Clock "Rocket Lake-S" High, Evidence of an ES with 5.00 GHz Boost

Intel's 11th Generation Core "Rocket Lake-S" desktop processors in the LGA1200 package could come with clock speeds that are of the norm these days. Intel appears unwilling to dial down clock speeds in the wake of increased IPC with the new generation "Cypress Cove" CPU cores that drive these processors. Twitter handle "leakbench," which tracks interesting Geekbench results, fished out a database listing for a "Rocket Lake-S" engineering sample with clock speeds of 3.40 GHz base, and 5.00 GHz boost.

The listing has all the telltale signs of "Cypress Cove," such as 48 KB L1D cache, 512 KB per core L2 cache, and 16 MB shared L3 cache for this 8-core/16-thread chip. "Cypress Cove" is rumored to be to be a back-port of Intel's "Willow Cove" CPU core design from its original 10 nm+ node to the 14 nm++. VideoCardz compared this "Rocket Lake-S" ES benchmark result to that of a retail Core i7-10700K, and found its single-threaded performance to be roughly 6.35 percent higher despite a 200 MHz clock-speed deficit, although for some reason, its multi-threaded performance is trailing by over 15 percent.
Sources: Geekbench Database, Leakbench, VideoCardz, HardwareLeaks
Add your own comment

33 Comments on Intel to Clock "Rocket Lake-S" High, Evidence of an ES with 5.00 GHz Boost

#26
Steevo
So IPC improvement with more cache, that also generates heat, so the multicore speed is slower and suffers. Well paint me suprised.....
Posted on Reply
#27
R0H1T
tabascosauzNot sure where you're getting this 10% number. Willow Cove offers a generational (10-15%) improvement over Sunny Cove, which is well known to have met or exceeded Intel's stated IPC improvement over Coffee Lake (can't remember if 14 or 18%). The only reason Ice Lake didn't show it was because maximum attainable clocks on 10+ were abysmal and negated most of those improvements.

Please don't tell me that "10%" came from Moore's Law is Dead.

That said, Willow Cove is supposed to feature more/updated L3 as its headlining feature. All the leaks around Cypress Cove show that the 8-core ES has exactly the same amount of L3 as existing 8-core SKUs from Coffee 8-core and Comet 10-core dies. Intel did say it was a "reworked cache structure"...
Not sure where you're getting this from, the vast majority of gains on Sunny Cove have come due to AVX512 & while its successor may offer double digit gains I'm struggling to see where they'll pull this from ~ perhaps some exotic instructions that'll become mainstream a decade after Intel introduced them?

Citation needed :rolleyes:
Posted on Reply
#28
FlanK3r
It is sad...SIngle thread seems not bad (similar like i9-10900K on Turbo 5.2-5.3 GHz), but multithread is nothing special...
On both sides are some results a little worse or a little better (9900K stock and 3700X database of stocks setting)


stock Ryzen 7 3700X vs Rocket Lake


stock i9-9900K vs Rocket Lake


Posted on Reply
#29
Tomgang
Wow 5 Ghz, wait haven't we seen that before. Oh yeah the last 2 or 3 gen cpu 14 nm off cause:kookoo:

Yeah if you can't tell, I'm not impressed by Intel lately.
Posted on Reply
#30
tabascosauz
R0H1TNot sure where you're getting this from, the vast majority of gains on Sunny Cove have come due to AVX512 & while its successor may offer double digit gains I'm struggling to see where they'll pull this from ~ perhaps some exotic instructions that'll become mainstream a decade after Intel introduced them?

Citation needed :rolleyes:
Go read any of AT's articles including the Surface Book Picasso vs Ice Lake comparison / Ice Lake Preview / Ice Lake Review / 3700X and 3900X review. SPEC2017 uses AVX2 on AMD and Intel, not AVX512. AMD vs AMD comparisons on 2017 are also in line with AMD's IPC claims. The only clickbait IPC claims are the hype "leaks" that pegged Ice Lake at 48%+ gains due to AVX512.

The controversy at the time was that Intel was pushing the whole "benchmarks don't matter" narrative; without benchmarks, where do you get IPC tests from? AVX512 wins are blatantly obvious, because the margins are obvious.

Call it for what it is - cheating with AVX512 Ice Lake wasn't. Ice Lake was a promising new uarch stuck on a dung pile of a process that hit a voltage wall long before 4GHz, resulting in a barely competitive, equally warm mobile chip as its predecessors. Sunny and Willow are bigger cores than Skylake, just don't expect 5.3GHz TVB and 10 cores.
Posted on Reply
#31
Dave65
RaendorDoesn’t look from the numbers like anything much to offer compared to existing lineup. I was hoping for more from a new arch even despite backport.
Some here will think it is the best thing since cheesecake...
Posted on Reply
#32
efikkan
tabascosauzWillow Cove offers a generational (10-15%) improvement over Sunny Cove, which is well known to have met or exceeded Intel's stated IPC improvement over Coffee Lake (can't remember if 14 or 18%). The only reason Ice Lake didn't show it was because maximum attainable clocks on 10+ were abysmal and negated most of those improvements.
I'm not saying you're wrong here, but do you have a source for the IPC gains for Willow Cove?
(Sunny Cove was 18% BTW)
tabascosauzThat said, Willow Cove is supposed to feature more/updated L3 as its headlining feature. All the leaks around Cypress Cove show that the 8-core ES has exactly the same amount of L3 as existing 8-core SKUs from Coffee 8-core and Comet 10-core dies. Intel did say it was a "reworked cache structure"...
The main feature of Willow Cove is more L2 and L3 cache.
Here look at this table, which one does Rocket Lake most closely resemble?


Skylake (client)Ice Lake / Sunny Cove (client)Tiger Lake /Willow CoveRocket Lake
L1 Instruction32 kB32 kB32 kB32 kB
L1 data32 kB48 kB48 kB48 kB
L2256 kB512 kB1.25 MB512 kB
L32 MB2 MB3 MB2 MB
Posted on Reply
#33
InVasMani
Benchmark how well it works as food dehydrator.
Posted on Reply
Add your own comment
Jun 12th, 2024 20:14 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts