• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Intel Quietly Reveals 12-core i9-7920X 2.9 GHz Base Core Clock

Dayum... Coffeelake seems to be the only thing exciting coming from Intel IMO. o_O
 
I would consider the 8-core i7-7820X if it had full access to all of the platforms PCIe lanes. Forcing consumers to pay at least $989 for 44 PCIe lanes is terrible customer service and a quick way to stop people from "upgrading" their Z270 chipset.
 
Not a single sane comment so far… This thing will be exciting in benchmarks.
Compared to what? Intel's 10 core offering? Based on clock differences and presuming the IPC stays consistent, it will benchmark on a similar level to the aforementioned 10 core offering.

Now excuse me while I go pass out from the excitement of this announcement... and your earth-shattering comment about other people's comments.

In other news, Ryzen continues to give Intel's entire line a solid thumping. Intel is tripping and fumbling over themselves to play catch-up. Give it another four months and upgrading any PC is going to be a real joy and won't kill the wallet.
 
In all seriousness it's taken longer than I expected... AMD needs to get a single CCX model out to really compete with the G4560/i5s in gaming, and Intel seems to have been caught sleeping on HEDT which is giving AMD a lot of breathing room right now.

I really hope AMD fixes the CCX latency by isolating certain interdependent tasks onto individual CCX units, that way the dual/quad CCX models will really shine on the gaming performance side, because otherwise, I'm just going to have to wait out for 6-core 1151 chips to get pressed down to the current 7700k pricing, because I really don't like the gaming performance hit based on my workloads.
 
In all seriousness it's taken longer than I expected... AMD needs to get a single CCX model out to really compete with the G4560/i5s in gaming, and Intel seems to have been caught sleeping on HEDT which is giving AMD a lot of breathing room right now.

I really hope AMD fixes the CCX latency by isolating certain interdependent tasks onto individual CCX units, that way the dual/quad CCX models will really shine on the gaming performance side, because otherwise, I'm just going to have to wait out for 6-core 1151 chips to get pressed down to the current 7700k pricing, because I really don't like the gaming performance hit based on my workloads.

Intel is removing G4560 from their lineup! :D So they fixed that problem right there!
 
At first glance I thought Intel went big on a new class of laptop CPU

Shame
 
I wouldn't pay an extra $400 just for an Intel logo, however it's worth remembering that base clocks mean absolutely nothing because the chip will never run that unless it's thermal throttling. I am more interested in how the turbo clocks compare to AMDs.
 
I wouldn't pay an extra $400 just for an Intel logo, however it's worth remembering that base clocks mean absolutely nothing because the chip will never run that unless it's thermal throttling. I am more interested in how the turbo clocks compare to AMDs.

It will pretty much destroy AMD with the turbo.... For anything that's not heavily multi-threaded.... But I'm not buying either of the two, so I'll happily wait till whatever is cheaper in a year or two.
 
It will pretty much destroy AMD with the turbo.... For anything that's not heavily multi-threaded.... But I'm not buying either of the two, so I'll happily wait till whatever is cheaper in a year or two.
Yeah, I'm curious to see how the 12-16c TRs overclock. The real saving grace of the 7700k is the fact that 5GHz is hardly out of reach for most setups while a lot of the AMD stuff struggles to hit 4.

That said, the price has to come down... At some point...
 
As always, I'll take this news and wait for the reviews.If the HEDT consumes more power, it won't really matter. as long as it's performing better than the pricewise competitor, it's a win for intel.
 
But but amd is cheating they glued to cpu together and and..... Intel is only ture multicore cpu.

Don't be stupid.

Intel did this during Core 2
 
My Xeon 2690v3, has base clock 2.6ghz, ist also 12 core, but ist a full chip with 30mb Cache. I dont know what is the deal with this chip
 
By performing worse with higher power requirements like its little brothers?



It really depends on workload, gaming, Ryzen does OK, very out of order and heavily branching work Ryzen shows its cache latency issues. Workstation rendering and other prosumer markets where a new rig every six months to a year is where they will sell a higher volume of chips for more margin is where they aimed and hit though, and where they squarely kick Intel in the nuts.

I guess they are so INFERIOR that they got deals with Sony, and MS for consoles for years to come.

Is cache latency thing really worth the whole extra Ryzen 1800X CPU worth in price difference? I think not.
 
where AMD will be offering the same amount of cores and threads for $799 (final consumer pricing at launch) with a much more impressive 3.5 GHz base clock.

Heh, weird that thread count and frequency only matter when AMD has the lead. The two on their own don't paint a full picture.
 
Sorry Intel, try harder!
 
Aah competition, it's a good thing indeed

...at least for consumer
 
That's assuming Threadripper is faster than Skylake-X.

Reality check: They're not even on-par. AMD has to play the budget brand just like their graphic cards because their products are INFERIOR.
Yes, it's not like Threadripper and Skylake-X performs the same per core.

Well this is interesting... I believe Intel is experimenting right now with their current lineup. The problem being they cannot go crazy with their current architecture otherwise power requirements shoot up which hurts Intel since that is something they have been pushing and touting for awhile…
The architecture is fine. But Intel chose to implement AVX-512, which is a huge part of the CPU, at the cost of higher power consumption. It will probably be a couple of years before we see more applications utilize it, so it's up for discussion whether it was the right choice for Skylake-X. Until the next node shrink, Intel can continue to work on power gating and perhaps tweak the clocks when AVX is not used.
 
Can some tell me just what the hell AVX-512 is and what does it do?
Sure, AVX(Advanced Vector Extensions) is a special unit which can do SIMD(Single Instruction Multiple Data) operations, commonly referred to as vector operations(not to be confused with Vector in C++). AVX is a larger more flexible alternative to SSE.
  • The vector unit can do one type of operation on multiple data elements, while a normal ALU or FPU can usually do up to one operation per clock. It has similarities with how GPUs work.
  • A 256-bit vector unit can do one 256-bit operation, two 128-bit operations, four 64-bit operations, eight 32-bit operations, etc.
  • AVX(Sandy Bridge+) and AVX2(Haswell+) supports up to 256-bit, while AVX-512 supports up to 512-bits operations.
  • AVX supports normal operations like addition, multiplication, etc., but also operations like shuffle, min/max, conditional masks.
  • Performance: Since vector operations replaces huge numbers of conventional instructions, the speedup can be massive. 10-50× speedup is not unusual. Especially operations such as conditional moves, min/max etc. would otherwise require huge amounts of instructions with several conditionals creating branches and stalls, so you can reduce hundreds of clock cycles down to a few.
  • Requirements:
    • Vector operations only work on what we call vectors, which are streams of data. So the data has to be aligned in memory, and you would have to do the same operation to each group of data. Many workloads can't be efficiently vectorized, or at least not without a major effort. Some examples:
      • Games: no
      • Compression: maybe, algorithm dependent
      • Video encoding: maybe, algorithm dependent
      • Web server: no
      • JavaScript in your web browser: no
      • Mathematical simulations: usually yes
    • There is also a overhead cost of moving the data into vector registers, so it's only worth it if you want to do multiple vector operations on the data.
    • Development cost: Code have to be specifically designed to utilize vector operations*. In C/C++ we use special intrinsics, basically macros mapped almost directly to assembly instead of "normal" code. It's not something you can just enable for your existing code, you have to code the specific low-level operations. The memory alignment of the vector data has to be planned, so that part of the application has to be specifically designed for this purpose in mind.
(* automatic vectorization do exist, but that's just in some edge cases not worth mentioning).
 
That's assuming Threadripper is faster than Skylake-X.

Reality check: They're not even on-par. AMD has to play the budget brand just like their graphic cards because their products are INFERIOR.

Just like the current line up from Intel? Intel only have 2 CPU's that are even worth buying at this stage and thats the i7 7700K and he Pentium G4560? The rest AMD crush!
 
Just like the current line up from Intel? Intel only have 2 CPU's that are even worth buying at this stage and thats the i7 7700K and he Pentium G4560? The rest AMD crush!

But now Intel is trying to kill the G4560 for cannibalizing i3 sales
 
If I were to die tomorrow, I would rather have gay porn in my web browsing history than avx-512.
 
Back
Top