Monday, July 23rd 2018
Top Three Intel 9th Generation Core Parts Detailed
Intel is giving finishing touches to its 9th generation Core processor family, which will see the introduction of an 8-core part to the company's LGA115x mainstream desktop (MSDT) platform. The company is also making certain branding changes. The Core i9 brand, which is being introduced to MSDT, symbolizes 8-core/16-thread processors. The Core i7 brand is relegated to 8-core/8-thread (more cores but fewer threads than the current Core i7 parts). The Core i5 brand is unchanged at 6-core/6-thread. The three will be based on the new 14 nm+++ "Whiskey Lake" silicon, which is yet another "Skylake" refinement, and hence one can't expect per-core IPC improvements.
Leading the pack is the Core i9-9900K. This chip is endowed with 8 cores, and HyperThreading enabling 16 threads. It features the full 16 MB of shared L3 cache available on the silicon. It also has some stellar clock speeds - 3.60 GHz nominal, with 5.00 GHz maximum Turbo Boost. You get the 5.00 GHz across 1 to 2 cores, 4.80 GHz across 4 cores, 4.70 GHz across 6 to 8 cores. Interestingly, the TDP of this chip remains unchanged from its predecessor, at 95 W. Next up, is the Core i7-9700K. This chip apparently succeeds the i7-8700K. It has 8 cores, but lacks HyperThreading.The Core i7-9700K is an 8-core/8-thread chip clocked at 3.60 GHz, but its Turbo Boost states are a touch lower than those of the i9-9900K. You get 4.90 GHz single-core boost, 4.80 GHz 2-core, 4.70 GHz 4-core, and 4.60 GHz across 6 to 8 cores. The L3 cache amount is reduced to the 1.5 MB per core scheme reminiscent of previous-generation Core i5 chips, as opposed to 2 MB per core of the i9-9900K. You only get 12 MB of shared L3 cache.
Lastly, there's the Core i5-9600K. There's far too little changed from the current 8th generation Core i5 parts. These are still 6-core/6-thread parts. The nominal clock is the highest of the lot, at 3.70 GHz. You get 4.60 GHz 1-core boost, 4.50 GHz 2-core boost, 4.40 GHz 4-core boost, and 4.30 GHz all-core. The L3 cache amount is still 9 MB.
The three chips are backwards-compatible with existing motherboards based on the 300-series chipset with BIOS updates. Intel is expected to launch these chips towards the end of Q3-2018.
Source:
Coolaler
Leading the pack is the Core i9-9900K. This chip is endowed with 8 cores, and HyperThreading enabling 16 threads. It features the full 16 MB of shared L3 cache available on the silicon. It also has some stellar clock speeds - 3.60 GHz nominal, with 5.00 GHz maximum Turbo Boost. You get the 5.00 GHz across 1 to 2 cores, 4.80 GHz across 4 cores, 4.70 GHz across 6 to 8 cores. Interestingly, the TDP of this chip remains unchanged from its predecessor, at 95 W. Next up, is the Core i7-9700K. This chip apparently succeeds the i7-8700K. It has 8 cores, but lacks HyperThreading.The Core i7-9700K is an 8-core/8-thread chip clocked at 3.60 GHz, but its Turbo Boost states are a touch lower than those of the i9-9900K. You get 4.90 GHz single-core boost, 4.80 GHz 2-core, 4.70 GHz 4-core, and 4.60 GHz across 6 to 8 cores. The L3 cache amount is reduced to the 1.5 MB per core scheme reminiscent of previous-generation Core i5 chips, as opposed to 2 MB per core of the i9-9900K. You only get 12 MB of shared L3 cache.
Lastly, there's the Core i5-9600K. There's far too little changed from the current 8th generation Core i5 parts. These are still 6-core/6-thread parts. The nominal clock is the highest of the lot, at 3.70 GHz. You get 4.60 GHz 1-core boost, 4.50 GHz 2-core boost, 4.40 GHz 4-core boost, and 4.30 GHz all-core. The L3 cache amount is still 9 MB.
The three chips are backwards-compatible with existing motherboards based on the 300-series chipset with BIOS updates. Intel is expected to launch these chips towards the end of Q3-2018.
121 Comments on Top Three Intel 9th Generation Core Parts Detailed
Notice those low base clocks? And remember how Intel explicitly only guarantees base clocks within TDP? Yeah, that i9, if this is real, will not go far above that base clock under multi-core loads, that's for sure. An OC'd 8700K runs, what, 220-250W at around 5GHz? Adding two cores won't lower that number, that's for sure. Let's be generous and put it at 300W for 8c at 5GHz, if not 350. That needs some hefty cooling.
Considering Intel's stock cooler can't keep up with an i7-8700 (non-K) (yes, it thermal throttles below base clocks), it'll be fun to see how much their non-K 8-core will thermal throttle with stock cooling. Meanwhile, AMD gives you an 8-core with a great stock cooler that keeps cool and quiet - for less money. And it's unlocked, if you want to eke out a few hundred MHz of multi-core performance.
In my eyes, Intel is in serious trouble. Not only marketing - it'd also be troublesome in terms of motherboard VRM ratings and compatibility. While not an issue on mid-range and up motherboards (let alone high-end ones with 400W+ VRMs), low-end boards often have bare-bones VRMs specced to barely exceed the rated wattage of the highest end CPUs they support, with no or next to no cooling. While this would be a marginal issue at best, it would essentially require (a paranoid/protective corporation like) Intel to mark high-end CPUs as "incompatible" with low-end motherboards to avoid potential lawsuits over people frying their VRMs by sticking "compatible" high-wattage CPUs into bargain-basement motherboards.
"...three chips are backwards-compatible with existing motherboards based on the 300-series chipset with BIOS updates."
That would be one hell of a "future proof" gaming CPU.
I don't get the naming scheme here. i9-9900K and i7-9700K being 8-cores. So will HEDT be cramped into i9-9910 i9-9990? I would argue it's time to drop HT from the design for most or all consumer products. HT might have made sense when CPUs had one core, but it's getting harder and harder for operating systems to balance the load, and the cores do suffer in terms of cache and prefetcher efficiency. With 8 cores there is no longer significant gains from HT, and this die space could instead be used for higher IPC. Only those who run heavy compute workloads needs more, and those 0.1% can buy HEDT. It's not just market segmentation, every feature which cost some die space affects price and thermal efficiency. You can make the same argument for quad channel memory, cache redesign, more chipset features etc. etc. All could be nice to have, but would drive up the price of the platform and only be useful for relatively few buyers. If you have any such requirement, just go with HEDT, that's why the segment exists. You pay quite a bit extra, of course. Base clock is all core clock with AVX workload. Some workloads, including gaming, doesn't use AVX, allowing the CPU to boost all cores much higher without increasing the energy consumption. This should not be confused with overclocking all cores (with AVX) to the same clock speed. Then you should clean your glasses. i7-8700/K beats Ryzen 7 2700/X, with 2 fewer cores, and AMD boosting beyond their TDP, and consumes more than Intel. Intel doesn't need a mainstream 8-core CPU to compete with current Ryzens. X299 will be refreshed soon. The successor will be Ice Lake-X coming "next year".
All bout price. If Intel stays within 20% of the corresponding AMD product, Intel's 80-90% market domination continues.
www.techpowerup.com/234864/passmark-stats-indicate-amd-gaining-market-share-vs-intel-thanks-to-ryzen
www.extremetech.com/computing/264853-independent-research-shows-amds-cpu-market-share-steadily-climbing
They still have a minor process advantage, but that's going away soon thanks to their 3-years-late 10nm process and the soon-to-arrive 7nm processes from TSMC and GloFo (which from all reports should be competitive at least in feature size - we'll have to see in terms of power and clock scaling). Considering that Intel has delayed the launch of 10nm several times, and the only "product" they have launched on it is a gimped-beyond-belief i3 with a disabled iGPU and an oddly high TDP (considering it doesn't have an iGPU) that it reportedly strong-armed OEMs into building laptops around to say they have "shipping 10nm", it really wouldn't be surprising if 10nm suffered even more delays.
They also have a <1GHz clock speed advantage on the high end, but chances are that lead will shrink significantly if not disappear outright as AMD moves to a process that wasn't primarily designed for low-power mobile parts. It's true that the 2700X draws a lot of power at high clocks, but that's due to pushing clocks on a process not designed for this. 7nm is very, very likely to change this. Not to mention that the base Zen design is almost scary efficient at lower clocks, beating out Intel in perf/w <=3.5GHz. Intel still wins in mobile (due to low-power RAM and various platform optimizations that they've nailed down over the years), but they're not moving forward much.
Intel also have a ~10% (average) IPC advantage, but AMD has promised significant IPC increases for Zen2. Current rumors say 10-15%, but even if it's as low as 5% average (or average in gaming loads, which matter most to enthusiasts and consumers), that eats significantly into Intel's performance lead as long as clocks increase to match.
In short: Intel is in serious trouble. It needs to get its disastrous 10nm process out the door, preferably yesterday. It needs an architecture update to increase IPC as their arch hasn't changed (at all!) since Skylake. It needs to stop the idiotic chipset segregation, forcing users to pay for new motherboards that aren't necessary at all, which is pushing users away. It needs to get its PR somewhat in line with reality (stop acting like they're light-years ahead of everyone else, and avoid catastrophes like the "28 cores at 5GHz!!!!" debacle, and so on). Intel has so damn much to lose, and over the last year it hasn't shown much in the way of initiative or ability to staunch the bleeding. Of course, they might still pull this off. But I'm not confident in that.
I guess you could say that largeness means they have a lot to lose.. but it still wouldn't be something very noticable just yet.
We still don't know which voltage this CPU will run at during boosting, so wait and see how much the actual consumption will be. AMD gaining some market share is to be expected when they go from totally sucking to having okay offerings in some segments.
The only thing Intel have to fear is the massive AMD hype. Even if we assume the optimistic 15% IPC gain in Zen 2, we'll still have to wait for Zen 3 for AMD to come close to Skylake(2015) in IPC, and that's assuming Intel will do nothing in the meantime. Remember that even though Zen cut over half Intel's advantage, the improvements in Zen is mostly the "low-hanging fruit" and "reversals of mistakes" made in Bulldozer. Pushing IPC another 15% would require more effort than the improvements they did in Zen(1). AMD have promised improvements, not specifically 15%. I don't think Intel is scared if AMD plans to recycle Zen for five generations. The bundled coolers in Ryzen 7 2700/X might be better than the crappy one Intel bundles with several i5/i7 CPUs, but are not neary good enough to properly cool these CPUs, especially not with the super-aggressive boosting done by Ryzen 2. I wish both of them dropped bundled coolers for any >$200 retail CPU. These crappy downdraft coolers don't work well at all in cases, especially when you have enough airflow to cool this and a GPU. Why not make these coolers an optional bundle instead? AMD could instantly shave >$20 off their price. It's sad how many stock coolers are thrown in the trash every year…