wildhorse2k
Member
- May 12, 2017
- 180
- 83
- 71
It would be interesting if Coffe-Lake 6C with cache reworking got also introduced in X299. Then Skylake-X 6C would get obsolete in a few months.
CFL-S is still 256KB L2. That 30 percent figure is a SYSMARK 2014 comparison using a 2C/4T mobile chip to a 4C/8T mobile Coffee Lake.Most certainly. That 30% faster than Kabylake Intel is quoting won't happen without tweaking/reworking the cache and memory subsystem.
That 30% faster than Kabylake Intel is quoting is based on incoming 4c/8t 15W TDP CPU versus SKL i7 7500U, which is a 2c/4t 15W TDP part. It has nothing to do with architectural improvements.Most certainly. That 30% faster than Kabylake Intel is quoting won't happen without tweaking/reworking the cache and memory subsystem.
I should have said the difference wasn't going to be all clocks. Are you saying it is? I'm not putting you on the spot. I respect your opinion a lot.That 30% faster than Kabylake Intel is quoting is based on incoming 4c/8t 15W TDP CPU versus SKL i7 7500U, which is a 2c/4t 15W TDP part. It has nothing to do with architectural improvements.
Did you really think Intel just announced a 30% IPC jump from KBL to CFL?!
I want to hear from these people who do, because I want to ask them why they haven't moved on to Xeon Phi or GPGPU, like the rest of the HPC world have.
AFAIK, CL is Kaby Lake on the 14nm++ process. Same cache arrangement.It would be interesting if Coffe-Lake 6C with cache reworking got also introduced in X299. Then Skylake-X 6C would get obsolete in a few months.
"Once the industry moves to AVX2"... LOL!
Outside specialized number-crunching, and a few particular scenarios, AVX2 hardly applies to most standard code.
Not to mention, Intel has hindered AVX and now AVX2 adoption, by keeping those opcodes limited to their top SKUs, and not providing it top-to-bottom in their CPU stack.
If anything, AMD is finally going to make those opcodes popular, because AMD will have more chips in the field than Intel that support AVX, due to Intel's extreme market segmentation.
(Even AMD's AM1 CPUs support AVX! Yet my Intel Kaby Lake Pentiums, with HyperThreading, do not.)
Just because the world's servers run on Xeons doesn't mean they also make use of AVX2 or in this case AVX512 in a way that is critical to their application.Both those solutions are very proprietary and expensive. And their use cases are even more restricted than AVX2 and eventually AVX-512. Most of the world's servers run on Xeons (AVX2 and soon to be AVX-512). So I want to develop against what I will be deploying to. For the same reason the world does not run on Power8 servers (more advanced than Xeon).
Fake, for the reasons already explained here.
You can tell Skylake X might be a huge success when the entire Amd army is on this thread desperately trying to downplay it
Thank you - sorry about that. So is August still the best known timeline for 6c/12t coffee lake (the one everyone is hoping will do 4.8-5.0Ghz) then?
I think I'm back on the Skylake-X train. I just need to shut up and buy something haha. Reviews are out on the 12th so I guess I'll make a final decision then. I've been stuck in the "just wait another month" trap for way too long.
Agreed. If we look at statistics on Steam http://store.steampowered.com/hwsurvey/processormfg/ we can see that AMD usage on Windows has been dropping and Ryzen changed nothing. And Intel had nothing really interesting during that time. Now with release of Skylake-X and Coffelake it seems this trend will continue.
I would recommend you to be careful and wait at least one month to see if Skylake-X has no serious bugs. If it does then Coffelake may be a better option. I will wait 2 months as I do not want random instability/lockups. That applies to every CPU including Threadripper and Coffelake.
I'm primarily a fan of spending money commensurate with the kind of features that I know I'll need.
Merely having features that the other platform doesn't have does not mean it's better unless you know how you'll put those features to use.
I've seen a lot of threads about why the presence AVX512 or quad channel memory on its own means that Intel platform is better, or in the case of the comment I was responding to, the AMD platform lacking these features means reinforcing the "cheaper" mentality of their platform.
There are two reasons why faster RAM matters in case of Ryzen. One is due to the increased bandwidth in itself - even Kaby Lake 4C can become bandwidth starved. Second, and more importantly, faster RAM means faster inter-CCX communication because of the way the Infinity Fabric works. That is why it is recommended to get the best RAM you can buy if you're buying a Ryzen.
You won't find these use cases discussed in tech reviews, and neither are they of particular interest to the majority of users, including the most heavy content creators(except the storage and expandability options, for which AMD is preparing an option).
Every point I made is applicable when comparing X99 to the existing Ryzen X370 platform, which was the context of the posts.
That has got more to do with the amount of memory than the number of channels. A 32GB quad-channel kit on a 6900K is rarely going to be faster than a dual-rank 32GB dual channel kit on a 1800X.
THINGS DON'T EXIST IN VACUUMHowever this isn't a need/please help me build thread.
Its a discussion thread on SkyLake...
Take your AMD comments to the AMD thread, it doesn't belong here.
again this is not a Ryzen thread.
2/3rds of the people here do not care about ryzen is X, cheaper... or Ryzen is X faster.
Were here to talk about Skylake-X and the LGA2066 platform. NOT Ryzen.
Sigh...
No your trying to derail the thread and bloat up ryzen before the intel CPU is out.
And Skylake X is not X99 its X299. Why are you pulling up a old platform which skylake-x will not support.
again why are you pulling up a old cpu and comparing it with Ryzen?
How do you know the same will apply in a CPU thats unreleased?
Who knows maybe Intel will DONGLE quad Channel memory and most of us will not be able to run it.
Seriously.. just stop... this is NOT a ryzen thread.
Take your Ryzen comments to the 5 other Ryzen threads we have and leave this to Intel.
It will have Vega so...iMac Pro will ship with Xeon Skylake-SP up to 18 cores, huge design win for Intel and a huge snub to Threadripper.
Most certainly. That 30% faster than Kabylake Intel is quoting won't happen without tweaking/reworking the cache and memory subsystem.
https://translate.google.com/transl...en&u=http://kuaibao.qq.com/s/20170601A05KBC00Q: Legend of Intel to launch 1151 interface, six-core Coffee Lake CPU, Gigabyte existing low-end positioning of the B250, H110 motherboard core power supply is usually only 3-4 phase, whether to meet the six-core CPU power supply needs?
A: Intel's next-generation platform, although also using the same pin interface, but in accordance with the design specifications, is not compatible with the current 200 series motherboard. Although the motherboard needs to be replaced, but the new CPU performance on the upgrade will enable consumers to have the power to upgrade the entire platform.
Q: online survey shows that users from SandyBridge after the upgrade of the PC is getting smaller and smaller, followed by Intel 300 series motherboards have been released, it seems that there is not much bright spot, I would like to ask Gigabyte 300 series motherboard market expectations how to see The Does the product line continue to play Gaming?
A: a few years ago it was often said that PC performance has been enough, and then upgrade 10% what is the use? And in fact the application determines the demand, last year's fire is currently the development of VR encountered some bottlenecks, one of the reasons is the lack of computer hardware computing power. Innovation is endless, we will cooperate with the upstream manufacturers to launch a better product, the sound, the network and other existing parts continue to upgrade to a new height. As long as there is no demand to meet, it means that new changes can occur. On the 300 series motherboard, because of the reasons I can not talk about NDA, we can wait for the August conference, when Gigabyte will give you a surprise.
huge design win for Intel and a huge snub to Threadripper.
Gigabyte said
As pointed out earlier, but thanks!That 30% claim has nothing to do with Coffeelake, it's for KBL-R (ULV 15W 2C vs 4C)
THINGS DON'T EXIST IN VACUUM
A discussion on Skylake-X will have to include comparisons with previous Intel products, and what it is up against.
Yes H265 in handbrake is a very nice tool for using that avx2 ability. The problem as i can tell is an oc 1700 vs a oc 6800 is about the same perf for h265 encoding. For similar price as the 1700 the 7700 is slower. What is it worth then?
It illustrates the basic problem that sklx will also face vs tr for that type of workload that uses avx2. A highend 16c tr will probably be faster than a 12c sklx.
It will have Vega so...