Does an 8/8 Zen "Summit Ridge" SKU make good sense?

Page 5 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Does an 8/8 Zen "Summit Ridge" SKU make good sense?


  • Total voters
    52
  • Poll closed .

bjt2

Senior member
Sep 11, 2016
784
180
86
Why a 4c/8c could not be competitive?

INTEL have 3.2 base 8c and will have 4.2 base 4c (kabylake).
AMD have at least 3.4 base 8c. Why can't AMD do the same or better? Zen does not even have the GPU!
 

DrMrLordX

Lifer
Apr 27, 2000
21,582
10,785
136
Look, if there's a price point between 8c/16t and 4c/8t then AMD can sell a 8c/8t chip there. Just do it to move the remainder of 8c chips that they can't sell at 8c/16t prices due to lack of demand (you know that's why Intel sells 4c/4t chips right?).

Also, Eris mandates that 8c/8t chips are a good idea since the number 5 is sacred to her. Hail Eris! Fnord.
 

superstition

Platinum Member
Feb 2, 2008
2,219
221
101
With such a lineup they would have to compete with 8c/16t zen against intel i7 4c/8t.
4c/8t Zen will not match (or beat) intels latest 4c/8t or they would have to sell low clocked 8c/18t at (below) intels i7 price. But then they will have low single thread performance, which they obviously don't want - bulldozer yet again?

If they leave such CPU with unlocked overclocking, they just obsoleted their high end products, which has nothing more than some additional cache and MHz that can be diminished with overclocking. Clearly not worth the price difference that will separate Workstation CPUs from enthusiast desktop CPUs.

meanwhile harvested or artificially gimped 8c/8t Zen will go circles around 4c/8t i7 and will be miles behind full 8c/16t Zen Workstation CPU, making a server premium well deserved.

It is very tricky to have a compelling product lineup that doesn't compete with itself, making obsolete the high profit part of the portfolio.
This is the thinking that prompted me to create the topic. The 8C/8T might offer:

I. The same core/thread count as Bulldozer but with much better efficiency/performance

a) making people who bought Bulldozer and were fans of it not feel unhappy for being pushed toward a smaller core/thread count

b) possibly having more parity with the console paradigm (lots of cores/threads), making porting games easier

c) impressing the tech press and others by offering the same core/thread count as Bulldozer but with higher efficiency/performance — this is good for marketing

II. A part with strong performance that doesn't overly "eat the breakfast" of the 8/18 premium part

a) some will want to buy the 8/16 part just because it has more threads, even if they don't need those extra threads

III. The extra CPU utilization caused by having SMT on will put more pressure on the TDP (related to 14nm LPP limitations), making 8/8 potentially more efficient for less threaded workloads since it may be able to complete tasks more quickly

The overall objective efficiency of disabling working mechanisms that add to the total efficiency of a part might be unfortunate but it's also, as I said, part of the two different types of efficiency (objective and business). Stepping aside from that debate, the point #III is interesting. One type of efficiency is how quickly work is completed. There is also how long a product lasts in the market. Higher single-thread performance could trump having 16 threads since parallelism is hard to extract for the general-purpose desktop.
 

Erenhardt

Diamond Member
Dec 1, 2012
3,251
105
101
Look, if there's a price point between 8c/16t and 4c/8t then AMD can sell a 8c/8t chip there. Just do it to move the remainder of 8c chips that they can't sell at 8c/16t prices due to lack of demand (you know that's why Intel sells 4c/4t chips right?).

Oh that was just wishful thinking on my side. I hoped amd would offer us 8/8 Zen that will be to i7 what i5 is to i3 (8c/8t vs 4c/8t a'la 4c/4t vs 2c/4t)
But from a business perspective, your right. If 8/8 zen is fast, it has nice price gap to fill between 2011 and 1151 CPUs
 

Snarf Snarf

Senior member
Feb 19, 2015
399
327
136
Does it make sense? The answer is maybe. As someone mentioned earlier unless GF process has some flaws that make SMT logic particularly susceptible to failure 4c/8t, 6c/12t, and 8c/16t seem to be the most logical tiers for the initial launch.

If further down the road AMD sees trends in the defects of dies that leave enough full 8c dies that have SMT defects then we will absolutely see one. Intel is the market leader and their position of products is the de facto standard right now. If their ST performance isn't competitive with i5/i7 then they will be forced to sell more threads for competing product tiers. Something like 4c/8t vs i5 4c and 6c/12t vs i7 with the full 8c/16t beast competing with HEDT line. In that scenario there is room in the line up for a 8c/8t priced inbetween 6c/12t.

I wouldn't be surprised at all if on launch all we get are 8c/16t and 6c/12t. I'd imagine the harvested dies need to be collected and binned to fill out the rest of the line up due to release around March.
 

Doom2pro

Senior member
Apr 2, 2016
587
619
106
Someone in the WCCFTech comments seems to think this latest french leak model (AMD 2D3151A2M88E) is a business class 8c/8t eco 65W TDP model. No idea if their breakdown has any validity though.

Rev 2D
Clock 315
2M 2MB cache L2
88E 8c 8t eco
This's a business cpu 65w TDP, no HT.
It's not SR7|SR5 consumer product.
 

DrMrLordX

Lifer
Apr 27, 2000
21,582
10,785
136
Interesting. You can sell all kinds of funny stuff to biz folks, especially if you include that eco tag! It sure would reduce power consumption to just disable SMT.
 

Doom2pro

Senior member
Apr 2, 2016
587
619
106
Interesting. You can sell all kinds of funny stuff to biz folks, especially if you include that eco tag! It sure would reduce power consumption to just disable SMT.

Only problem with this guy's breakdown is, don't the other 8c/16t Engineering Sample IDs we have say 88E also?
 

Snarf Snarf

Senior member
Feb 19, 2015
399
327
136
The performance of the part in the french leaks shows parity with 6900k though at the clock speeds from the AMD demo. No way AMD can keep up with 6900k without SMT enabled on that ES chip.
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,575
126
But Shirley there will be some dies with two modules that don't pass testing?

It's not all or nothing, is it?
 

Doom2pro

Senior member
Apr 2, 2016
587
619
106
But Shirley there will be some dies with two modules that don't pass testing?

It's not all or nothing, is it?

Yes there will be dies with two cores on either side that don't pass snuff or are DOA, maybe they are saving these for a later SKU, possibly with high enough clocks to be better than an 8c/8t.

And stop calling me Shirley.
 

LTC8K6

Lifer
Mar 10, 2004
28,520
1,575
126
I hope AMD initially keeps it simple. 4c/8t, 6c/12t, and 8c/16t.

After things get rolling they can fill in the gaps.
 

MaxDepth

Diamond Member
Jun 12, 2001
8,758
43
91
I think superstition had it right a few posts ago when he mentioned 8c/8t. From my viewpoint this would make sense if the binning of the 8c/16t don't all show 16t operable. Instead of trashing these "failures" they simply lobotomize the failed thread units in BIOS.

So do I start the rumor now that you can buy the 8c/8t units and try your luck with the 8c/16t BIOS?

The rumor said it will be 4/8, 8/8, and 8/16