• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Intel's "Skymont" E-core Posts a Double-digit IPC Gain Over "Crestmont": Leaked Presentation

Joined
Mar 21, 2016
Messages
2,355 (0.78/day)
Yeah, I have seen this myself with my work laptop. Sometimes the E cores aren't doing much of anything when both(!) P cores are pegged at 100%. And this is running MS Office under Windows 11.

What do you expect in certain workload scenario's the E cores are for MT headroom they aren't intended primary cores, but secondary cores. Peak ST performance will nearly always be on the P cores due HT and clock speed differences, but peak MT favors E cores. The whole point is really to spread the work around for stuff that doesn't need peak ST performance beyond 6 to 8P cores or whatever. Depending on workload scenario's OC on P cores or E cores provides relative advantages and disadvantages.

Typically just dropping E cores clock speeds a bit and pushing P cores a bit harder and/or ensuring they can boost longer w/o thermal problems is fine in practice. Most workloads don't need peak ST performance more than 8 cores anyway. I mean hell we use to live in a world where all we heard was four cores is all you need.

That's still fairly true a good amount of the time since most workloads aren't exactly pegging 8P cores to death or even more than 4P cores in many cases. Workloads vary of course and you can point to whichever data you wish to in order to illustrate or make most points of topic banter arguments.

I'm satisfied with my 14700K for what I got it for it was good deal. Is it perfect not exactly, but does it matter to me not really. Do I even notice in daily operation not all.
 
Joined
May 25, 2022
Messages
92 (0.12/day)
"Double-digit" gains are actually 38% on Int and 68% in FP. It's going to beat Golden Cove folks. Lion Cove may be under 10% faster in Int compared to Skymont since Skymont is going to end up being upwards of 10% or more above Golden Cove.
 
Joined
Mar 16, 2017
Messages
1,870 (0.70/day)
Location
Tanagra
System Name Budget Box
Processor Xeon E5-2667v2
Motherboard ASUS P9X79 Pro
Cooling Some cheap tower cooler, I dunno
Memory 32GB 1866-DDR3 ECC
Video Card(s) XFX RX 5600XT
Storage WD NVME 1GB
Display(s) ASUS Pro Art 27"
Case Antec P7 Neo
What do you expect in certain workload scenario's the E cores are for MT headroom they aren't intended primary cores, but secondary cores. Peak ST performance will nearly always be on the P cores due HT and clock speed differences, but peak MT favors E cores. The whole point is really to spread the work around for stuff that doesn't need peak ST performance beyond 6 to 8P cores or whatever. Depending on workload scenario's OC on P cores or E cores provides relative advantages and disadvantages.

Typically just dropping E cores clock speeds a bit and pushing P cores a bit harder and/or ensuring they can boost longer w/o thermal problems is fine in practice. Most workloads don't need peak ST performance more than 8 cores anyway. I mean hell we use to live in a world where all we heard was four cores is all you need.

That's still fairly true a good amount of the time since most workloads aren't exactly pegging 8P cores to death or even more than 4P cores in many cases. Workloads vary of course and you can point to whichever data you wish to in order to illustrate or make most points of topic banter arguments.

I'm satisfied with my 14700K for what I got it for it was good deal. Is it perfect not exactly, but does it matter to me not really. Do I even notice in daily operation not all.
Except that's often not what I'm seeing. For example, do a copy/paste of a few thousand rows of data into a spreadsheet with calcs. You'd think it would max out all the cores, but instead, it maxes out the 2 P cores of the i7 and the E cores barely do a thing. The sad thing is, these calcs aren't exactly elaborate math--some IFs SUMIFS, and some XLOOKUPS, and not a lot of dependency. It should be right in the MT wheelhouse, but it will often take my CPU what I feel is way too long. Maybe the E cores should be doing this task, and the scheduler is getting is screwed up, I dunno. All I know is I often observe MT tasks not using all the cores.
 
Top