The Intel Broadwell-E Review: Core i7-6950X, i7-6900K, i7-6850K and i7-6800K Tested
by Ian Cutress on May 31, 2016 2:01 AM EST- Posted in
- CPUs
- Intel
- Enterprise
- Prosumer
- X99
- 14nm
- Broadwell-E
- HEDT
Catching Up: How Intel Can Re-Align Consumer and HEDT
Earlier in this piece I stated three reasons why the enterprise market has an out of step cadence with the latest CPU microarchitecture: product stability, regular releases, and platform longevity.
To get stability, using Intel’s tried and tested core makes sense, rather than the latest and greatest. The longevity of each enterprise platform is such that each socket and chipset generation must last for two CPU cycles, allowing a potential upgrade path, but also means that customers aren’t ripping out their installations every 12-18 months with fresh new ones in order to beat the competition. Also, by being behind the mainstream platform at a slightly slower refresh rate, it allows the release of enterprise CPUs to compensate for any process delay on the latest architecture.
But at this point, we are now a generation and a year behind the mainstream and latest microarchitecture. There are features in the latest mainstream Skylake CPUs, such as Speed Shift (the ability to react to high priority frequency requests up to 20x faster to save power and improve user experience), that are not in the enterprise and HEDT products. If the out-of-step and slower cadence continues, we could be two generations behind fairly easily. However, Intel has (inadvertently) developed a get-out-of-jail free card here.
Earlier in the year we reported that Intel is changing its processor development strategy due to a combination of factors including the slowing of Moore’s Law and the difficulty in creating a smaller lithography node to create processors. Intel was on their tick-tock strategy for around a decade, alternating between smaller nodes and new microarchitecture designs to give performance increases every cycle (or half-cycle). Tick-tock was well received and provided Intel and its investors with a steady expectation and revenue stream when the new product delivered and if it met expectation. When Intel hit several bumps with 14nm, tick-tock became an extended 'tiiiick-toock', slowly lengthening out the time between updates. Then this year Intel said that, for the CPU product line based on the Core microarchitecture family at least, would move to ‘Process-Architecture-Optimization’, or a three-stage cycle for 14nm (the current node) and 10nm (the next node).
On the mainstream product segment, this means that the 14nm family, originally featuring Broadwell (tick) and Skylake (tock), will become Broadwell (process), Skylake (architecture) and Kaby Lake (optimization). The level of ‘optimization’ that Kaby Lake will provide is unknown at this point, but what used to be a 24-month cycle can now become a 36-month cycle very easily.
But it is not immediately obvious what this means to the enterprise segment. One would naturally expect the segment to follow the PAO implementation, albeit slower. Here’s Intel’s potential trick for the future: depending on the level of ‘optimization’ in the final stage of the cycle, the enterprise segment has the potential to just bypass and ignore it, keeping the cycle length the same and giving Intel an opportunity to realign the microarchitectures. The net product would be 36 month cycles, spanning 3 product generations at the consumer level and 2 product generations at the enterprise/HEDT level.
That being said, it’s a little bit of conjecture. We have spoken to some senior members of Intel about this, and it was acknowledged that it could be a potential strategy, however as expected nothing like this would be confirmed in a casual conversation even if it was decided at a senior level. It will make an interesting point when the enterprise market rolls around to Skylake-E and Skylake-EP based cores and beyond, if Kaby Lake-E will be a ‘thing’ or not.
Facebook
Twitter
RSS
205 Comments
View All Comments
SAAB340 - Wednesday, June 1, 2016 - link
If possible, can you have a look in to RAM overclocking as well. I believe the memory controller in Haswell-E isn't particularly great. The one in Skylake is way better. I wonder if Broadwell-E has improved there?I know RAM speeds in general don't make that much difference but in certain applications it does.
StevoLincolnite - Tuesday, May 31, 2016 - link
I'm still happily cruising with a 3930K. The 5930K was the twice the price of the CPU alone for what I paid for my 3930K, but it certainly doesn't offer twice the performance and the 6850K looks to be more expensive again.My 3930K still has a few years of life left in it, hopefully AMD can bring Intel's prices downward.
Witek - Thursday, June 16, 2016 - link
@SteveoLincolite - agreed, I am still on 3930K for more than 3 years now, and I would be happy to switch to something faster, but 6800K is essentially same speed, only faster in specialized workloads, and probably 2 time more costly. Going from 6 to 8 cores, only gives me 30% boost, for almost 4-5 times the prices. The 10 core one is a joke.3930K (and it overclocks easily too - 3.2GHz -> 4.2GHz with water cooling non stop in my setop), is still the best value out there probably.
prisonerX - Tuesday, May 31, 2016 - link
It cracks me up that people pay say $300 for a mainstream i7 which is 65% graphics which they don't use, but employ that same silicon for a few more cores and the price is $1000+.People belittle AMD for not having the fastest silicon and then touch their toes price wise for whatever scraps Intel throws them. Particularly funny since mainstream processors were 5% slower in the last generation. It's like people are suffering Stockholm syndrome or something.
Alexey291 - Tuesday, May 31, 2016 - link
Well it's little wonder that the cpu market is slowing down since there are no actual products worth buying from a mainstream purchasers' point of viewEden-K121D - Tuesday, May 31, 2016 - link
People on Haswell are well and good until something extraordinary comes out of intel/AMDMichael Bay - Wednesday, June 1, 2016 - link
When the most exciting thing about a platform refresh is a goddamn usb3.something type-whatever port, writing is on the wall.beginner99 - Tuesday, May 31, 2016 - link
Exactly. It's not slowing down because of smartphones or tablets but because 5% performance increases takes 10 years for the average user to be worth an upgrade.Ratman6161 - Tuesday, May 31, 2016 - link
To take that one step further, for the average user it isn't even 5%. They aren't doing anything with the machine that isn't entirely adequate with what they have. I don't consider myself to be the average user by any means, but my i7-2600K system i built in the spring of 2011 is still more than fast enough for anything I do let alone spend money on a 6700K let alone any of these.mapesdhs - Thursday, June 9, 2016 - link
Indeed! This week I need to put a system together for handling SD video. I have at my disposal a whole range of SB/SB-E i7s, but they're overkill, so I'm going to reuse the parts from my brother's old PC instead, a P55 with an i7 870 which, at 4.2GHz, is still rather good (people forget it was a particularly low latency platform for its time, with boards that really did push what features one could include, some good innovation with slot spacing and other things). My own general tasks system, a 5GHz 2700K, I can't see becoming obsolete for a long time, it handles everything with ease (scores 880 for CB R15).And this is the key problem: it's the very tasks that would benefit the most from real performance and feature improvements where newer products have helped the least, baring in mind the upgrade costs involved and the lack of feature enhancements over the years (how long was it until Intel finally added native USB3 to the top-end chipset?). Given the cost, the gains of the latest top-end CPUs over what was available in 2011 just aren't worth it, which perhaps explains why I see comments even from X58 6-core owners saying they'll stick with their setups for now). Meanwhile, for anyone on a budget who doesn't want to consider 2nd-hand items, it's hard to ignore the value of AMD's current 4c and 6c offerings (heck, the PC I built for my gf is an old Ph2 X4 965 and it's more than adequate), given that really, for response and feel of a normal PC, having an SSD is more important than having the higher IPC of a costly Skylake vs. an FX 6300 or something.
I was shocked at the launch price of the 6700K, and I didn't think Intel would make the same mistake again, but they have. One of the main things I do is offer free upgrade advice for prosumers on a limited budget (typically self-employed artists); atm, the 6950X is so expensive that I'd recommend a 2-socket XEON setup instead without hesitation. 3 years ago this wasn't the case, back then there was a solid rationale for (example) an AE user on a limited budget to build an oc'd 3930K. Today though, what Intel is doing will only help reduce the enthusiast market even further, and I was told by a high street shop owner that the top-end items are the ones which provide the best margins (he said his store couldn't survive on the mainstream level sales). There will be long term self-reinforcing consequences if Intel doesn't change direction. Perhaps Zen will achieve that; certainly many seem to hope it will.