Intel's Coffee Lake 8700K Will Offer More Than a Bump in Cores
PC enthusiasts will be french pressed to find a better gaming CPU in 2017.
The slow drip of information on Intel’s upcoming Coffee Lake products continues to fill our styrofoam cups. Previous reports have hinted that the new architecture from Intel will see the light of day before the end of this year and bring some meaningful changes to the company’s mainstream computing lineup. The Core i7 series will get its first 6-core part, expected to be named i7-8700K when the platform launches.
While the increased core count would normally be enough to whip up excitement for the launch, new leaks from an Intel retail training slide show that Intel is promising a single-threaded performance gain of more than ten percent over the reigning king of single-core speed, the Core i7-7700K. The Kaby Lake release earlier this year was a letdown for owners of Intel’s Skylake i7-6700K since the 7700K offered no additional performance when the two CPUs were compared clock for clock.
Intel’s slide also claims a more than 50 percent gain in performance over the 7700K in heavily-threaded workloads, which makes sense when the additional cores on the 8700K are considered. All of this is good news for Intel fans since AMD has been eating Intel’s lunch in multi-threaded performance with its Ryzen CPUs that launched in the Spring. Intel’s Kaby Lake parts offered little advantage over the Ryzen CPUs except in lightly-threaded gaming and a few older apps.
There is currently no official release date for the 8700K, though Intel is expected to formally announce the new lineup on August 21st. Hopefully I‘m not blinded by the solar eclipse and will be able to see the 8700K in action.
-
Chris Jarrard posted a new article, Intel's Coffee Lake 8700K Will Offer More Than a Bump in Cores
-
-
-
I can't make sense of where the gain is coming from. The slide just talks about a perf "boost". Does that mean higher clock single-core boost due to high frequencies on the Turbo Boost feature? Or is it a real IPC gain? (My guess is the former otherwise they would be very explicit in the advertising since IPC gain is way more worthy of notice.)
-
-
-
i have a friend who does cpu design at intel. this might be really common knowledge as i understand very little in the way of this sort of thing, but he's told me that most of the current gains are coming from instruction sets that allow the cpu to guess what it is going to do next. at a certain threshold, when it's right x% of the time, it becomes useful. like if it gets "step A" it automatically does steps B-F as well, and if in fact that's what the request is, it's already there. if it's not, then it just backtracks and goes again.
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Ok, cool. Thoughts on something like this? https://pcpartpicker.com/list/fgy7LD
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
it must be! because the way AnandTech accidentally tested originally by disabling SMT actually shows better performance than AMD 'game mode' which disables a core!
When in 16C/16T mode, performance in CPU benchmarks was higher than in 8C/16T mode.
When in 16C/16T mode, performance in CPU gaming benchmarks was higher than in 8C/16T mode.
like... da fuq? did no one at AMD do any benchmarks on this?
-
-
-
-
-
-
-
-
-
-
-
Well...potatoes!
I was so excited because I thought it was 30% IPC, lol. You're right, I was in fantasy land...
The 30 percent boost came in one benchmark—SYSmark 2014 version 1.5—and applies to 15W U-series mobile processors. The comparison pits an i7-7500U (2.7GHz base, 3.5GHz turbo) with two cores and four threads against an unnamed next generation chip. The new chip has an unspecified base clockspeed, a 4GHz turbo, and doubles the number of cores and threads to four and eight. The 8th generation chip is built on a refined iteration of Intel's 14nm process.
-
-
-