News Intel 10th Gen Comet Lake Mobile CPU Early Benchmark: Look out, AMD Ryzen 4000

shiitaki

Distinguished
Aug 20, 2011
44
0
18,540
Yes, something from Intel. The article is actually bad news for Intel because it doesn't mention Geekbench scores don't reflect the sustained performance since the very short tests run during the short term TDP power limit. The energy efficiency of the AMD chips is such that in anything runs for more than a minute will significantly go in AMDs favor. Another words AMD is going to run circles around Intel in making money. If all you want is some web browser, the new Intel is going to be great!! But then, do you need 16 threads?

This is terrible news for Intel because it means no IPC improvement and thus AMD Zen 2 gen is going to slay Intel mobile where it really hurts, power efficiency.

Nothing from Intel would be better, this just Intel proving to the world they have nothing. What is more alarming is the spin Toms is doing with this article, it's subtle but I would have expected more nuance and objectively, not such a superficial and simplistic article. The title is unjustified.
 
Sep 13, 2019
71
4
35
5ghz on a laptop? yeah right maybe during boot time lmao.

also 5.27ghz on a 45W rated chip? this bitch will throttle like mad, imagine manufacturers actually adding a 45W worth of cooling hardware, enjoy your campfire of a laptop.
 
  • Like
Reactions: PaulAlcorn
5ghz on a laptop? yeah right maybe during boot time lmao.

also 5.27ghz on a 45W rated chip? this bitch will throttle like mad, imagine manufacturers actually adding a 45W worth of cooling hardware, enjoy your campfire of a laptop.

I think Intel's single core boost clock is now just for marketing. Their desktop processors have trouble getting over 5.1ghz with 125watt tdp. How are we to expect a 45w chip to get to 5.27ghz? Doesn't make any sense.
 

Chung Leong

Reputable
Dec 6, 2019
494
193
4,860
Yes, something from Intel. The article is actually bad news for Intel because it doesn't mention Geekbench scores don't reflect the sustained performance since the very short tests run during the short term TDP power limit.

Sustain performance is not something that people worry about. It only comes into question on tasks requiring no human intervention. You won't have a job in such a case, let alone a high-end laptop.
 
Good luck achieving and maintaining 5.27Ghz in a laptop. Last time I have seen here in forums that many 9980K users were never hitting 5Ghz, most were capped at 4Ghz due to thermal throttling. Looks like AMD is winning in the mobile segment too with their Ryzen 4900H.
 

Anicolson

Distinguished
Jun 25, 2008
1
0
18,510
actually it depends on the user and his application.. some people like me actually DO think about it.
Example: I write my own code to do mapping. The idea is to show geopolitical events over time by updating a displayed map of an area (think world and migration of language or the Roman conquests of Europe, Asia or Africa). A typical map may have 16 M triangles to form areas on the earth. The projection to be used is user selectable. The orientation of the projection is user selectable and can change in real time. The globe can rotate at real time based on either user interaction or the passing of world time (one year per second).
A simulation consists of updating projected area, text, color of a rotating projection at 60 frames a second. A frame may contain maybe 16 M floating (double and divides ) calcs, packaging for OpenGL, and a redenering by the graphic engine. Hstorically, bandwidth is the issue. There is nothing gained by 6 vs 8 cores because memory BW is slow and the cache is too small. But while I watch or do the simulation , I can interact with it. The load is dynamically spread across the pools of cores based on the cycle times o each core on the last frame.

When I run it, the fans are high and florida power has to kick in another nuclear reactor.
I know I might be better off with a desktop, but I am among the poor and stupid that will do this crap from a 44ft sailboat, RV, my boycave or back lania at minutes at a time.

Not EVERYONE is the same. But I'm weird, retired and have no life.
 

joeblowsmynose

Distinguished
Good luck achieving and maintaining 5.27Ghz in a laptop. Last time I have seen here in forums that many 9980K users were never hitting 5Ghz, most were capped at 4Ghz due to thermal throttling. Looks like AMD is winning in the mobile segment too with their Ryzen 4900H.

If true, it'll probably be something like, one core boost for 0.2 seconds. Methinks Intel is stealing AMDs "boost" feature of high clocks for extremely short intervals.

While this feature will let users like Chung up there, open a browser in 0.001 seconds instead of 0.0015 seconds, (thank you Intel - we've been waiting for this!), unfortunately people will need to run sustained workloads on these processors, else why on earth would you need an 8 core in a laptop if one has no intention of doing anything but very light tasks? Just to brag about how many cores you have? Whatever, Bulldozer ...
 
  • Like
Reactions: Zizo007

PaulAlcorn

Managing Editor: News and Emerging Technology
Editor
Feb 24, 2015
876
394
19,360
So Intel is using likely using its TVB, Thermal Boost Velocity, in these 10th gen chips. This feature debuted with the tail-end of the 9th gen chips. So, you have normal Turbo Boost 2.0 that operates within certain voltage/temp constraints, but TVB kicks in ONLY if the processor is below 60C, and the second the proc goes above 60C (as in any meaningful sustained workload in a laptop, regardless of threading) you drop back to 2.0 speeds. The bad part? Intel just advertises TVB under the normal TB 2.0, even on ARK. As a result, 99.99% of customers will never know that's probably a millisecond of advantage here and there, and not meaningful. I'd love to get my hands on a laptop with a TVB'd chip so I could give it hell. My instincts tell me this is snake oil.
 
  • Like
Reactions: Zizo007