Intel Launches New Core i9-9980XE 18-Core CPU With 4.5GHz Boost Clock (hothardware.com)

MojoKid writes: When Intel officially announced its 9th Generation Core processors, it used the opportunity to also unveil a refreshed line-up of 9th Gen-branded Core-X series processors. Unlike other 9th Gen Core i products, however, which leverage an updated Coffee Lake microarchitecture, new processors in Intel's Core-X series remain based on Skylake-X architecture but employ notable tweaks in manufacturing and packaging of the chips, specifically with a solder TIM (Thermal Interface Material) under their heat spreaders for better cooling and more overclocking headroom. The Core i9-9980XE is the new top-end CPU that supplants the Core i9-7980XE at the top of Intel's stack. The chip features 18 Skylake-X cores (36 threads) with a base clock of 3.0GHz that's 400MHz higher than the previous gen. The Core i9-9980XE has max Turbo Boost 2.0 and Turbo Boost Max 3.0 frequencies of 4.4GHz and 4.5GHz, which are 200MHz and 100MHz higher than Intel's previous gen Core i9-7980XE, respectively.

In the benchmarks, the new Core i9-9980XE is easily the fastest many-core desktop processor Intel has released to date, out-pacing all previous-gen Intel processors and AMD Threadripper X series processors in heavily threaded applications. However, the 18-core Core i9-9980XE typically trailed AMD's 24 and 32-core Threadripper WX series processors. Intel's Core i9-9980XE also offered relatively strong single-threaded performance, with an IPC advantage that's superior to any AMD Ryzen processor currently.

Comments

Pricing

[TFlan91]

The pricing though... AMD still edges out in my book.

Re:Pricing

[Joce640k]

If that's the price of bragging rights then I'll skip this one.

Re:Pricing

[Anonymous Coward]

That's a just released CPU model of course, which is always exorbitant when dealing with anything. CPUs, gadgets, whatever.. just released = recoup R&D.

What bugs me is -- 36 threads. SMP should be perma-off I'd say, everything I've read shows security issue after issue after issue with hyperthreading.

Re:Pricing

[Anonymous Coward]

AMD = made in China/Taiwan
Intel = made in America

Intel wins hands down. It's time for America to get real.

Re:Pricing

[omnichad]

SMP should be perma-off I'd say

So you want a single core computer? It has nothing to do with hyperthreading (which itself is related to SMT). Speculative execution is only one of the optimizations involved, and the one that has all the security issues.

Re:Pricing

[alvinrod]

It's not quite that simple. Both companies do all of their packaging (final assembly) in Asia, so no one gets bragging rights on that part and everyone's CPUs read "Made in China" or "Made in Malaysia".

You would need to look at where the chip is diffused. I believe that the current AMD Zen chips are being produced at Global Foundaries Fab 8 which is located in New York. The next batch are being done at TSMC, so you would have a point there.

I believe that the design teams for both CPUs are largely in the U.S. as well, but both AMD and Intel have some smaller teams throughout the world.

Re:Pricing

[Kjella]

If that's the price of bragging rights then I'll skip this one.

The price of bragging rights is always more than what most can afford. Otherwise, what's there to brag about?

Re:Pricing

[Anonymous Coward]

Actually you are both wrong. Intel's major fabs are in the US and AMD uses Global Foundries whose main CPU fabs are in Germany and the US. They both have plants elsewhere but they handle other products. Most other products including Apple's SoCs are made in Taiwan though under contract with TSMC who are aside from Global Foundries probably the largest gun for hire fab around. Samsung has their own fabs as well. There are a lot of fabs in the PRC and many chinese chips are made there but Intel and AMD chips aren't

Re:Pricing

[Anonymous Coward]

Taiwan is not China though it is true that TSMC's assembly is in China as is Intel's and Global Foundry's.

Also, arguably, Intel would not be the dominant force they are today without the Israeli design team. They were the original source of the IPC magic. When America needs high tech innovation, that's where we go for design. The Israeli's are also the source of many of our most advanced military techs like their awesome helmet displays for pilots.

Re:Pricing

[Anonymous Coward]

Why would you brag about being wallet-raped by Intel out of about $500? Are you simple? The ONLY people who get to "brag" in that instance are the reviewers who get free parts for effusive product blowjobs - and they're whores.

Re:Pricing

[gweihir]

As soon as you look at prices and availability, Intel is utterly naked.

Re: Pricing

[Anonymous Coward]

You have to be severely inbred to believe what you is wrote.

Re: Pricing

[Anonymous Coward]

You're absolutely retarded, all the Israeli team did was resurrect the Pentium III design after the P4 netburst catastrophe.

Re:Pricing

[Anonymous Coward]

Dipshit.

Re:Pricing

[Tough Love]

For bragging rights it's tough to beat a 32 core 2990WX Threadripper, now going $1730, that is, $150 less than the Intel part with 14 more cores. For that matter, a 16 core 1950X for $650 probably still makes you the best desktop on the block.

Of course, what we all really want is a 7nm 32 core Castle Peak Threadripper, possibly going to be announced about eight weeks from now. The ultimate desktop hotrod. Still TR4, so can do the build now with a 1950X as a placeholder, or a 1900X for $353, still a highly respectable part.

AMD currently owns the enthusiast sector with good reason.

Re:Pricing

[Tough Love]

My Ryzen says "diffused in USA", which translates as "made in USA, packaged in China". Wherever it's made, the lion's share of the profits are from selling the chip, not making it, and that all comes back to USA.

Re: Pricing

[Tough Love]

In other words, the Israeli guys knew what they were doing.

Re: Pricing

[Anonymous Coward]

Stealing from someone smarter? Seems par for the course.

Re:Pricing

[Highdude702]

Go watch the Linus Tech Tips review released yesterday. That is how I wish all reviewers of products were. Whether getting the parts free or paying for them from their own pocket.

Re:Pricing

[Highdude702]

Afaik AMD chips are assembled in the USA. Some in New York and some in Florida. My R7-1700 was assembled in Florida. Both AMD and Intel are US companies. Meaning they were all designed here.

Re: Pricing

[Highdude702]

From reading, well atleast attempting to... You have 0 room to speak.

Re: Pricing

[Tough Love]

Those smart guys who were busy elongating the pipeline?

Progress!

[Anonymous Coward]

Now windows crashes even faster!

Re:Progress!

[Locke2005]

And Linux can now complete infinite loops in 2 seconds, instead of 5!

Re:Progress!

[Highdude702]

Define "Linux can now complete infinite loops in 2 seconds, instead of 5!" please. I have never had such problem. I have seen the infinate boot loops due to bad motherboard firmware or windows updates. I have not had either of those two issues on Linux what wasn't on an embedded device.

So in summary, AMD is still better...

[Anonymous Coward]

"However, the 18-core Core i9-9980XE typically trailed AMD's 24 and 32-core Threadripper WX series processors"

Solder TIM?

[thegarbz]

So Intel finally adopt something that the modding community have been doing for years? Seriously late to the game guys. There's a reason Intel de-lidding is frequently done while there's borderline no point in doing it on AMD's high end offerings.

Re:Solder TIM?

[Anonymous Coward]

you mean to return to it... 5thgen and earlier hedt was soldered.

Or maybe not

[Anonymous Coward]

"an IPC advantage that's superior to any AMD Ryzen processor currently"

cherry picking a preferred reality is fun!

Re:Or maybe not

[barc0001]

Yep, and you demonstrate that wonderfully. The AMD Threadripper is better for some things, the Intel chip is better for some things, and *depending on your needs and budget* each could be "better".

Intel wins the IPCs, but is crushingly expensive. Many people would take the half price of the AMD part and be quite happy with it. Others for whom money isn't that much of an object will go with the 9980XE. Still others who need Blender, Cinebench or POVRay workloads done would be fools to buy anything but the Threadripper.

All in all, everyone has a different need and will cherrypick based on that need.

Re:Or maybe not

[Anonymous Coward]

I like the TR parts but they really need to cut down the idle power, 100W+ at idle (!)

Re:Or maybe not

[Anonymous Coward]

I'm still not sold on Intel. What about their security vulnerabilities??? I didn't see any mention of those being fixed. AMD is about to release a 64 core processor, so in terms of performance there are better alternatives than this.

Re:Or maybe not

[Tough Love]

Intel wins the IPCs

Not for very much longer. And for me, like most of us, value is the decider. I'm also finding AMD's thermal performance excellent these days, and I just love how long the sockets last. AM4 really delivered on its future-proof promise.

Re:Or maybe not

[Tough Love]

I like the TR parts but they really need to cut down the idle power, 100W+ at idle (!)

Tom's Hardware says 35 watts for the 2990WX at idle.

For my trusty Ryzen 1700 box, the entire system power measured at the wall is 38 watts at idle.

Re:Or maybe not

[Highdude702]

Zen 2 should fix that IPC offset. Putting Intel in 2nd place for he first time in a decade! The next few cpu cycles should should be great for us consumers! I love when the competition is razer sharp on both sides! Consumers always win in these situations. But as of today you're 100% correct and you need to always use the right tool for the job.

Re:Or maybe not

[Highdude702]

That's one of the leading reasons AMD is considered the budget conscious chip maker. Sure you may not be able to use all of the latest and greatest features of the new chip but you can buy it and use it until you can afford the newer chipset that supports all of the new features. And it will still be faster than the old generation chip you replaced it with. If you're not like me and keep all old hardware, you could even sell it used to offset the price of the new motherboard with no downtime waiting to buy a new motherboard.

Re:Or maybe not

[Highdude702]

That 64 core processor is going to have a hearty price tag at launch though. Not to mention the board and cooler for it.

LTT

[Anonymous Coward]

Funny, LTT got radically different results depending on if it was AVX, AVX2, or non-AVX workloads. So, not exactly a huge win. Instead, often a marginal win to upwards of a 17% win...vs Intel.

Re:LTT

[Highdude702]

It's Intel, did you expect anything less? Let's be fortunate we have reviewers like Linus that care more about informing the viewer/consumer than appeasing the company for giving him free hardware.

Fewer Cores and Hypertrheading is likely better

[Crashmarik]

For almost all desktop use.

Unless your desktop is doing something that parallelizes really well you probably will never notice the benefits of this.
Even things that benefit from parallel processing are far better served by running them on truly parallel architectures. You have an application that can support fine grained parallelism, why run it on 18 cores of X86 when you run it on 1500 cores off a graphics card ?
 

Re:Fewer Cores and Hypertrheading is likely better

[Anonymous Coward]

One last hurrah. It has a TDP of 185 and averages at 196 TDP. This Reminds me of Pentium 4 getting to 4ghz at any cost. The failure if the 10nm node isn't killing Intel... yet.

Re:Fewer Cores and Hypertrheading is likely better

[Anonymous Coward]

Should use a crockpot as a heatsink and let it double as a slow cooker.

Re:Fewer Cores and Hypertrheading is likely better

[GregMmm]

What someone could use this for is virtualization on your desktop. But at that price you might as well get a Xeon proc and call it a day.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Sounds about right. I am sure it would be the cat's pajamas at simulating a small network of processors and testing your program on them.

Re:Fewer Cores and Hypertrheading is likely better

[Anonymous Coward]

Why waste power on virtualization?

Re:Fewer Cores and Hypertrheading is likely better

[macklin01]

Shared memory parallel codes (OpenMP) could benefit, though. Many (originally single-threaded) or homemade scientific applications run in this space: get some parallelism for relatively little work (insert pragmas, be careful to be thread safe, and test test test), without all the extra work of redesigning those simulations for efficient message passing.

You certainly find problems where it is much better bang for the buck to throw an expensive processor and OpenMP ( O($10^2 to $10^3) ) at a problem than to throw specialized MPI development effort ( O($10^4 to $10^6) ) at that problem. Especially when the first step to any hybrid OpenMP-MPI code is to work on single compute node performance with OpenMP, before connecting nodes with MPI.

Re:Fewer Cores and Hypertrheading is likely better

[BrendaEM]

I don't agree with your blanket generalization, ending in an unresolved comparison. Better for what?

The processor is made and optimized for running parallel tasks. Chores like raytracing, video transcoding and export, photo editing filters, science applications, and web-servers generally like this kind of processor.

I am in no way an Intel fan, but a 4.5GHz boost clock is quite respectable. I should think that it can handle single-core and low-core tasks well.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Unless your desktop is doing something that parallelizes really well

I thought I was pretty clear saying that. Just how much of a performance boost is your web browser going to get from extra cores when it should just stop running scripts/vidoes in windows/tabs that don't have focus ? or for that matter your word processor or video game ?

Chores like raytracing, video transcoding and export, photo editing filters, science applications, and web-servers generally like this kind of processor

Well ray tracing is almost certainly better handled by a GPU these days, same for video transcoding. Web Server that needs parallelism is a server application not a desktop application. Some science applications certainly but if they parallelize easily and well then it's back to the GPU architectures once again.

Re:Fewer Cores and Hypertrheading is likely better

[thegarbz]

You have an application that can support fine grained parallelism, why run it on 18 cores of X86 when you run it on 1500 cores off a graphics card ?

Because a graphics card is not just 375 traditional CPUs jammed into a single package and just because something can scale to 18 cores doesn't mean it would run better on 1500 GPU cores.

Re:Fewer Cores and Hypertrheading is likely better

[Anonymous Coward]

what do you think the hedt line is based on... it is a xeon core...

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

You have an application that can support fine grained parallelism , why run it on 18 cores of X86 when you run it on 1500 cores off a graphics card ?

Because a graphics card is not just 375 traditional CPUs jammed into a single package and just because something can scale to 18 cores doesn't mean it would run better on 1500 GPU cores.

You really have a desperate need to learn how to read or at least learn what the relevant terminology actually means.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Your desktop is almost always doing something that parallelizes really well. For example, browsing - each tab runs in a separate thread. And with Vulkan/DX12 games now will use as many cores as you have, to feed a big GPU. The classic one is gaming and streaming, that used to be an issue before Ryzen.

If you are compiling or doing anything with video there is no such thing as too many cores.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Browsing separate tabs really shouldn't be taking cpu at all. Haven't looked at Firefox's source but I will typically have a hundred plus tabs open and notice very little draw on my cpu resource. Right now it's pulling 5.1% on a quad core cpu with a guess at around a 100 tabs open and and at least 5 that are interactive. Streaming once again suspect the optimum use of the dollars is buying a higher end graphics card.

Re:Fewer Cores and Hypertrheading is likely better

[Anonymous Coward]

I'll prefer "wasting" power on virtualization to wasting it on having a dozen computers (which there is no physical space for) running at not anywhere near their capacity, thank you very much for your insights.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Play videos in multiple tabs. Access multiple crappy javascript sites. There are any number of ways to consume cpu in multiple tabs. I can only presume that you never looked at CPU consumption while browsing. In theory, browsing should be efficient. In practice, it isn't.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

And you don't seem to be clear on the distribution of work between CPU and GPU. It takes more cores to feed a bigger GPU. You go tell the streamers that they don't need multiple cores. They know otherwise.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Actually I just did that's where my numbers came from. Can't say I am ever playing more than 2 videos at a time

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

And you don't seem to be clear on the distribution of work between CPU and GPU. It takes more cores to feed a bigger GPU. You go tell the streamers that they don't need multiple cores. They know otherwise.

Yeah that's a function of memory bandwidth more than anything else. You can throw all the cores you want at it, it doesn't matter if you don't have the bandwidth. You may have noticed that GPUs generally have much much wider memory ?

Anyway just for reference. You're taking data from the frame buffer, ideally encoding on the card using the card, then moving it out and maybe formatting with the CPU.

You might want to look up how the architecture is actually laid out and how this works.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

You are still confused. GPUs have high on-board memory bandwidth because they use it internally for texel and vertex fetching etc. Graphics features like filtering are highly memory intensive with typically multiple accesses per texel per raster op in on board memory. The bandwidth the CPU uses to upload primary data to the GPU is comparatively much less. Unless you made a major mistake, like not populating both controller channels, your streaming setup is unlikely to bottleneck on memory, including reading the framebuffer per frame.

You don't encode video on the GPU while rendering unless you are OK with dropping the frame rate. Another practical reason: your streaming software probably doesn't support it. This is typically done on CPU cores using the SIMD unit.

"You may have noticed that GPUs generally have much much wider memory"... I feel that you are just burping out random factoids you picked up somewhere in the hope that you can bluster your way through trying to make a point about not needing cores. Explain it to the streamers, who won't have a lot of patience for your theories because they know otherwise.

Re:Fewer Cores and Hypertrheading is likely better

[Anonymous Coward]

One last hurrah. It has a TDP of 185 and averages at 196 TDP. This Reminds me of Pentium 4 getting to 4ghz at any cost. The failure if the 10nm node isn't killing Intel... yet.

It is nice to have all the cores in one chip. Coding for a CPU is certainly less of a pain, and if you have a bunch of pipe-lined producer consumer stuff you might be able to use them all, though it ain't easy.

I wonder if this all on a chip design could be simplified for at least some use cases. What about something like this?

A core with 1GB of memory and an interface to system ram/peripherals.
At least say 16 cores.
Some portions of system ram/peripherals can be hardware limited to a particular core.

For instance you may run untrusted web sites on different dedicated cores. If that was the case, then presumably you could have locked out access to any disk writes prior to allowing content to load. (The CPU core can no longer see that memory/io region without a full reset.) Then the user can interact with the site through a window with hardware isolation.

This would seem one way to seriously mitigate sepctre and all the rest. Simply put if processes peeking at CPU cache and such is a problem, then physically separate them. You should be able to run a debugger, and unless you are attached to the right cores, you see nothing from the core's memory. Of course some processes might need multiple cores, but nothing stops aggregation

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

You are still confused. GPUs have high on-board memory bandwidth because they use it internally for texel and vertex fetching etc.

Says the guy who can't separate outcome from cause. Why they were initially designed that way is irrelevant.

You don't encode video on the GPU while rendering unless you are OK with dropping the frame rate.

Well seeing as encoding on a GPU is 4 to 5 times faster than on a CPU and it saves the time time of fetching unencoded video from the frame buffer to system memory. I'll be glad to trade the overhead. That is trade.

I feel that you are just burping out random factoids

Projection seems to be strong with you, so is feeling over actual understanding

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

So, crashing the party to showcase your awe inspiring intellect then.

You don't encode video on the GPU while rendering unless you are OK with dropping the frame rate.

seeing as encoding on a GPU is 4 to 5 times faster than on a CPU and it saves the time time of fetching unencoded video from the frame buffer to system memory. I'll be glad to trade the overhead.

Why is it necessary to explain it to you in words of one syllable? Lose frame rate.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Thanks for showing me wrong.

I should have gone with my first impression that you were an idiotic troll when you said this

Play videos in multiple tabs. Access multiple crappy javascript sites. There are any number of ways to consume cpu in multiple tabs
https://slashdot.org/comments....

But I gave you the benefit of the doubt. My bad.

Now you are coming up with this

Why is it necessary to explain it to you in words of one syllable? Lose frame rate.

And you have removed all doubt.

You turn on streaming you are going to lose frame rate no matter what you do. The questions are, how are you are going to lose more and what is the best use of resources to build the system.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

the questions are, how are you are going to lose more and what is the best use of resources to build the system.

Tying up GPU compute units isn't it. You obviously are no gamer. But you are a loudmouth.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

the questions are, how are you are going to lose more and what is the best use of resources to build the system.

Tying up GPU compute units isn't it. You obviously are no gamer. But you are a loudmouth.

Geez can't you even get the terms you're talking about right ? It isn't the set of gamers but subset of gamers that stream.

Instead of being an asshole, try actually learning about what you are talking about. Then you wont wind up saying stupid things and cherry picking horrifically bad examples like "Trying to watch videos in closed tabs", to show you're not an idiot.

Re:Fewer Cores and Hypertrheading is likely better

[AmiMoJo]

Ryzen and Threadripper have more than just extra cores. More PCIe lanes, for example. Stuff that matters for workstations.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

So you are lecturing others on not being an asshole, got it.

Did you really just type "watch videos in closed tabs"? You're losing it, go take your meds.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Ryzen and Threadripper have more than just extra cores. More PCIe lanes, for example. Stuff that matters for workstations.

Absolutely true. Without looking I would also bet the supporting chipsets are higher end as well

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Did you really just type "watch videos in closed tabs"? You're losing it, go take your meds.

No you did

Play videos in multiple tabs. Access multiple crappy javascript sites. There are any number of ways to consume cpu in multiple tabs
https://slashdot.org/comments.... [slashdot.org]

So you are lecturing others on not being an asshole, got it.

I expect you get lectured about being an asshole a hell of a lot.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Just curious, how did "multiple tabs" become "closed tabs" in your mind?

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Just curious, how did "multiple tabs" become "closed tabs" in your mind?

Not curious, just stupid, figure it out for yourself.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

I hope you realize that javascript in tabs continues to run even when you're not looking at it. Are you as stupid as you seem?

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Still don't comprehend how little you know do you ?

Re:Fewer Cores and Hypertrheading is likely better

[thegarbz]

And you desperately need to understand the differences between a CPU and a GPU in the way that their processing actually works. Or you need to go home and spin up 1500 VMs using only a single core on your graphics card. Good luck getting that to boot before Christmas.

"I have cores" != "I can do anything you can do" and regardless of how parallel your application gets they will not necessarily run faster or better on a GPU, a specific device designed to run a very VERY specific subset of instructions compared to a GPU.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

And you desperately need to understand the differences between a CPU and a GPU in the way that their processing actually works. Or you need to go home and spin up 1500 VMs using only a single core on your graphics card. Good luck getting that to boot before Christmas.

You can't seriously be that stupid ?

I have cores" != "I can do anything you can do" and regardless of how parallel your application gets they will not necessarily run faster or better on a GPU, a specific device designed to run a very VERY specific subset of instructions compared to a GPU.

I guess you can be that stupid. But at least you looked up the meaning of Fine Grained Parallelism. Unfortunately you failed to comprehend.

You have heard of this new thing that was invented called math maybe ? Why don't you just do the numbers and work out just how much of a performance advantage would be needed for 18 processors to outperform 1500 or say 3000 if you run 2 or well you get the idea.

Oh and this part ""I have cores" != "I can do anything you can do" that is just fundamentally wrong. Unless the processor in question isn't Turing complete and you only need 1 instruction to be turing complete, I have core do indeed absolutely mean I can do anything your cpu can do.

Re:Fewer Cores and Hypertrheading is likely better

[Highdude702]

The main reason to have more cores is to be able to do more things at once. Remember when you used to be limited by your cpu how many things you could do at once without bogging everything down? You no longer have to worry about closing chrome when you go to play your game for a few hours. Providing you have the ram overhead to make up for chromes memory leaks(seriously they have had memory leaks for a decade, literally since day 1 what gives Google??)

Re:Fewer Cores and Hypertrheading is likely better

[thegarbz]

Fine grained parallelism does not have anything to do with if something is better or worse to do on a CPU than a GPU. But since you're all insults and no substance I'm sure you realised that a while back too. But whatever I'll go down to your level.

Oh and this part ""I have cores" != "I can do anything you can do" that is just fundamentally wrong.

Oh wow. I can't believe you called me stupid and then wrote a line like that when we were discussing performance. Tell you what, go dig out the old Turing machine (which as I think I may need to point out to you anyway is actually Turing complete), have it process your Slashdot reply and then report back on the stupidity of your comment.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Oh wow. I can't believe you called me stupid

Why is that difficult to believe with your attitude I am sure lots of people call you stupid.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Yeah that's true.
It's just that for most people the number of things they want to do at the same time is less than what their rigs can currently handle

Re:Fewer Cores and Hypertrheading is likely better

[thegarbz]

Interesting given who it was that started with the name calling. I think everyone has learnt a bit about you today. Your other post just now was equally retarded.

Re:Fewer Cores and Hypertrheading is likely better

[Highdude702]

But we're nerds... Do we really care about those people?? :)

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

I comprehend than you have a screw loose.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

And I comprehend you don't anything about how a browser works.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Perhaps your brain fever leads you to imagine that videos stop decoding when you switch tabs.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Mine no. People who make the browser could be.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

So you understand that a browser can consume CPU per tab by decoding a video per tab.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

So you understand that a browser can consume CPU per tab by decoding a video per tab.

HAHAHA

You still are so fucking stupid.

Try doing a little research on how this actually works and how CPU video decoding actually works.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Just in case, I verified using appropriate tools. I doubt you are capable of that.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Unh hunh

Somehow I doubt you even knew what to check

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

You've made it abundantly clear your technical skill rounds to zero. And you're delusional, that's heady stuff. Must be confusing to be inside you.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

You've made it abundantly clear your technical skill rounds to zero. And you're delusional, that's heady stuff. Must be confusing to be inside you.

Unh hunh. Just for the fun of it, I am going to suggest you bounce your position off someone else.

I am going to guess they will do exactly what I did, which is first try to explain why you are wrong and then write you off as the moron you are.

Ciao

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Your attempt at explanation was exactly what confirmed you have no technical skill. You're the old fart shouting at the cloud.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Oh I don't know

I am not the guy who thinks playing videos you can't see is a good reason to have more cores.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

So the straw you're hanging onto is, exactly one use case doesn't apply to you.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

So the straw you're hanging onto is, exactly one use case doesn't apply to you.

If that's what you want to think. it's pretty hard to get as many things wrong as you managed to.

Just consider this tough love from me to you

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

I'm considering you to be obsessed, with a screw loose.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Yeah I'll just chalk that up to you being wrong about one more thing in this conversation.

And you're still to stupid to figure out how you're wrong except when I tell you.

That's really kind of sad for you.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

Delusional.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

Yeah you are proof truly crazy people think everyone else is.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

If you are not delusional then tell me how I'm wrong. Be specific and concise, but do provide enough detail to prove your case. I bet you can't even remember what you were arguing about, much less why, or what you hope to get out of it.

Re:Fewer Cores and Hypertrheading is likely better

[Crashmarik]

If you are not delusional then tell me how I'm wrong. Be specific and concise, but do provide enough detail to prove your case. I bet you can't even remember what you were arguing about, much less why, or what you hope to get out of it.

Nah I'm comfortable with the situation here. Why don't you use your "tools" to figure out where you were wrong ?

As to what I got out that I will give you, it's amusing as hell watching you twist in the wind.

Feel free to prattle on that's my last word here.

Re:Fewer Cores and Hypertrheading is likely better

[Tough Love]

So you've got no point, that's what I thought.

Vulnerabilites

[cyberchondriac]

I didn't see any mention of addressing Meltdown, Spectre, L1TF.. so I assume those general architecture issues are not yet addressed, this is still Skylake.

Re:Vulnerabilites

[thegarbz]

And no one running these processors will care. In fact most of the people affected by Spectre and Meltdown are likely running Xeons.

Re:Vulnerabilites

[Tough Love]

Fact is, people do care. Whether it is a perception of sloppy Intel engineering, or security, people do care.

Re:Vulnerabilites

[thegarbz]

Nope. A couple of angry nerds care, and a couple of system administrators of large virtual servers care. If there is one thing that has been made 100% clear by people, their reaction to this, Intel's shareprice, Intel's marketshare, it's that people in the general case to mean the vast majority of computers users, most definitely do NOT care.

Re:Vulnerabilites

[Tough Love]

You are out of touch. Take a quick run around the comments section on any Intel vs AMD article and you will find Meltdown frequently cited. And Meltdown has gone mainstream. Even the business pages talk about it because it is affecting Intel's stock price.

See, it's like GMO, it may or may not affect you directly but it is always a concern and a source of endless debate, such as this. The only way out of this for Intel is to fix it definitively in hardware as opposed to papering over by minor circuit tweaks, costly microcode workarounds and disgusting OS hacks. That isn't going to happen until Cannon Lake.

The Meltdown deniers are just angry nerds like you.

Re:Vulnerabilites

[thegarbz]

Frequently cited means nothing ultimately. Bitcoin and blockchain technology is frequently cited too, and ultimately it was a management discussion fad that went no where. While we frequently cite things it means nothing when ultimately business practices haven't changed.

Now that isn't universal. There has definitely been work in the cloud space, which makes perfect sense too since they actually have direct exposure to the issue as their business model relies on having people run their code on machines you own.

The Meltdown deniers are just angry nerds like you.

It's interesting you call us deniers. Unlike say climate deniers who actively ignore the science I have yet to see the Meltdown proponents (is that the opposite of a denier) actually demonstrate a problem.

I said it in another post: Meltdown, Spectre, and this entire speculative execution issue is among the most high profile series of bugs that are widely unpatched / unpatchable for a great deal of people. Yet actual working exploits outside of carefully controlled lab experiments, or balls out just prove I can copy some random bits which I can't identify as belonging to something have yet to be seen or developed... a full year later.

So yes, I guess I am a "denier". I probably will continue to be a "denier" since it's this is the most sensibile state to be in after risk assessing my exposure to these alegedly horrible security risks.

Sidenote: I bought a Ryzen recently, you may have seen me reference it in other posts. But fear not Speculative Execution didn't factor into the purchasing decision in the slightest.

Re:Vulnerabilites

[Tough Love]

actual working exploits outside of carefully controlled lab experiments, or balls out just prove I can copy some random bits which I can't identify as belonging to something have yet to be seen or developed... a full year later.

Wow, where have you been?

Q: Has Meltdown or Spectre been abused in the wild?
A: We don't know.

Re:Vulnerabilites

[thegarbz]

Thanks for proving my point. You just linked me to a whole series of lab experiements which require up front knowledge of the computer in question.

If someone is in a position to gain enough knowledge about your machine to use any of the examples you just linked to, to pardon my French, you're already properly fucked, ... or your a cloud / VM provider which as I pointed out earlier are exactly the kind of people who are actively at risk here.

In terms of security risk for the 99.9% of people out there, this ranks lower than simply owning a modem or daring to connect to a public WiFi hotspot.

Re:Vulnerabilites

[Tough Love]

In terms of security risk for the 99.9% of people out there, this ranks lower than...

Says random internet guy, knowing better than the security researchers.

Re:Vulnerabilites

[thegarbz]

Except security researches have said nothing other than: "Look what I can do in the lab" Followed by "We don't know if there's anything else out there"

But hey, we're all random internet guys. Maybe I should make a fancy website with a scary looking logo and then people will listen to me.

Re:Vulnerabilites

[Tough Love]

You are particularly random, and full of shit. See "we don't know" re exploits in the wild. You just go right ahead and respell that as "there are none" and go back to your crack pipe. I will go with the Linux devs, who know just a bit more about it than you and released yet another costly mitigation today.

Re:Vulnerabilites

[thegarbz]

See "we don't know" re exploits in the wild. You just go right ahead and respell that as "there are none" and go back to your crack pipe.

We don't know a lot of things. But generally we don't use a complete unknown combined with a low risk profile and then burn everything to the ground in the name of security. You don't know what zero days are present in the firmware of your router right now, why are you still on the internet?

I will go with the Linux devs, who know just a bit more about it than you and released yet another costly mitigation today.

Again what has that got to do with the risk assessment? The devs have to do this because there are some scenarios where the mitigation is most definitely required. I've said that up front. In fact Linux more than anything is the OS most likely used by those 0.1% that actually need to worry about Speculative Execution vulnerabilities.

I trust those devs too. They are clever. They understand that every vulnerability comes with a risk associated with it, and that this risk varies, and just like every other specter and meltdown based mitigation they made it optional for a reason, because they know what they are talking about.

Re:Vulnerabilites

[Tough Love]

generally we don't use a complete unknown combined with a low risk profile and then burn everything to the ground in the name of security

Hyperbole. Nobody is burning things to the ground, and we are not dealing with a complete unknown. Take your intellectually false argument at face value gives us Windows and the mess that Windows users find themselves in today.

Re:Vulnerabilites

[thegarbz]

Hyperbole. Nobody is burning things to the ground

Indeed it was. Doesn't change the fact that here we are talking about product launches that are being dismissed for irrelevant reasons while at the same time you happily expose yourself to incredible risks in other ways.

and we are not dealing with a complete unknown

Indeed we're not dealing with a complete unknown. We're dealing with a complete unknown as to if this is being exploited in the public, but on the rest of the topic what we *actually know* is that for a normal user the risk is incredibly frigging small.

Take your intellectually false argument at face value gives us Windows and the mess that Windows users find themselves in today.

Wow. Just wow. Talk about intellectually false arguments. Speaking of the mess of Windows users why not look at how much malware actually affects the core OS. Let me guess, you also think that running Windows is a major risk due to malware despite the fact that the vast majority of malware spreads not through exploits of the OS, but rather though exploits of the software that users use, and the general stupidity of those users.

You sound like a typical Linux user, smug in the superiority of the fact that there are less commoners on your platform but completely oblivious to the fact that if your OS had the Windows market share we'd be talking about how insecure Linux is because users are running "sudo chmod 777 britneyspears.jpg & ./britneyspears.jpg" like the instructions told them to.

If you think doing a risk assessment is intellectually false please don't ever end up working in security. ... Or safety. ... Or investment where you're in charge of someone else's money.

Re:Vulnerabilites

[Tough Love]

Indignant Windows hack reacts indignantly to suggestion that Windows remains a rotten swiss cheese of vulnerabilities after all these years, news at 11.

Re:Vulnerabilites

[thegarbz]

Just another comment of yours showing that you have no understanding of risk mittigation.

Re:Vulnerabilites

[Tough Love]

You a risk denier, unlike everybody else in the picture, Including Intel.

Re:Vulnerabilites

[thegarbz]

You a risk denier, unlike everybody else in the picture, Including Intel.

"Risk denier". Okay I take it back. It's not that you don't understand risk mitigation, you don't understand risk or the risk assessment process at all.

But for future reference: Someone who has done a risk assessment and deems there to be no problem with the current practices is not a "denier" they are deemed to have "accepted" risk.

But hey, enjoy your Linux comfort blanket. I hope for your sake that you never get the year of Linux on Desktop, or you may just find out how very wrong you are about the role OSes play in vulnerabilities. Right now I'll leave you to your blissful ignorance.

Re:Vulnerabilites

[Tough Love]

Whoever you are assessing risks for is in danger.

Re:Vulnerabilites

[thegarbz]

Whoever you are assessing risks for is in danger.

Another great statement without any backup, context or knowledge.

Hey guess what is in the news today, it would appear those Linux developers you held such a high opinion of have changed their tune even further not only allowing the Spectre mitigations to be disabled, but actively disabling them by default in stable branches of 4.20 making the fixes opt-in.

It would seem that marginal increases in security do not trump a few percent performance gains as decided by experts. Maybe we're all putting the world at risk. Oh Noes!

But keep fighting the good fight buddy. More power to you.

Re:Vulnerabilites

[Tough Love]

We were talking about Meltdown dumbo.

Re:Vulnerabilites

[thegarbz]

Maybe you should re-read the very first thing you wrote...

branch prediction vulnerability?

[smoothnorman]

Does i9 cure, or even address, Spectre or Meltdown?

Re:branch prediction vulnerability?

[Anonymous Coward]

Nope.

Re:branch prediction vulnerability?

[gweihir]

If they did, they could not fake benchmarks like this.

Re:branch prediction vulnerability?

[DontBeAMoran]

Is sure addresses them! They're even faster than before!

Just in time for Winter..

[supercell]

I needed a new space heater. Now I can just pick up a 9980XE and warm my home and play Crysis.

Re:Just in time for Winter..

[DamnOregonian]

warm my home and play Crysis.

On medium settings

Re:Just in time for Winter..

[PeeAitchPee]

If you wanted a heater, the 2nd gen Threadripper 2950X uses more power (TDP) for a lot less money . . .

Of Course A Thread Ripper Outperforms It

[Greyfox]

The question is, does a Thread Ripper outperform a dual or quad core Xeon system, and can you justify the price of the Xeon system for the amount of extra performance you get. If my code doesn't support distributing processing out to the network, having a huge machine with 4 xeons and a mind-boggling amount of RAM on it might be the only way to accomplish what I need to accomplish. You just have to expect you're going to spend a LOT of money for that machine.

I have a system encoding 8 1080p video streams to webm in real time. It's currently running on a dual 10 core (40 threads) Xeon system and has enough processing left over to do some analysis of those video streams (OCR, Image Recognition et al.) I want to test it with a Thread Ripper, which would halve the cost of my processors, to see if it can do at least as well a job as the Xeons do. I'm one of the guys Intel is trying to hang onto.

Re:Of Course A Thread Ripper Outperforms It

[Anonymous Coward]

Why aren't you encoding on a GPU... a modern GPU will be far cheaper than CPU encoding.

Re:Of Course A Thread Ripper Outperforms It

[Anonymous Coward]

The bigger question is - why the hell are you still writing software that depends on CPU for speed? Why have you not deployed synergistic cloud blockchain technology? Why are you still using technology of the past rather than distributed blockchain technology, in the cloud? Hmmm? Luddite much?

Synergistic cloud-layered distributed blockchain techology computing is where it's at.

Re:Of Course A Thread Ripper Outperforms It

[Anonymous Coward]

If your Xeons are "old" and don't have AVX2, they might be heavily outperformed.
If they have it (Haswell, Broadwell) perhaps they're in a good enough range vs the 16-core Threadripper. Then, there's the 24-core Threadrippper which might have very much bang for the buck still and should be quite better.

having a huge machine with 4 xeons and a mind-boggling amount of RAM on it might be the only way to accomplish what I need to accomplish. You just have to expect you're going to spend a LOT of money for that machine.

If you really get a lot of RAM that's where it gets unaffordable. e.g. 1.5TB or 2TB, don't really wanna look up that.

Does your software play well with NUMA? (non uniform memory architecture). Your dual CPU is NUMA, a Threadripper is NUMA, a 7980XE or 9980XE isn't NUMA. But in your situation, just running 8 times the same thing this seems trivial enough to not care much. BTW the top of the range is very poor value so you'd better look at i9 7960X or 7940X (or 9940X...), the latter probably good enough at replacing the dual Xeon?

Another thing yet the recent Intels have AVX512 and that may be useful to your purpose but all your software has to be updated.. A dramatic example of this is the dual POWER9. Really competitive with the AMDs and Intels, you overpay for the motherboard. But before encoding software etc. get updated for its SIMD it just may be slow at what you're doing (doing it all on regular ints and floats!) so you have to go with x86.

Hello again Mr.7980XE

[Z80a]

I see you got a fancy new power curve, soldered TIM and nothing else!

Awesome!

[Locke2005]

If I buy one of these, will I get laid more often?

Re:Awesome!

[Anonymous Coward]

Can't calculate your percentage increase since division by zero is undefined.

Re:Awesome!

[Anonymous Coward]

So it's just as likely to be infinitely more likely!!! Yes! Ordering as I type!

Re:Awesome!

[Anonymous Coward]

You're more likely to get laid in Maths class than Computer Architecture, sport. Just saying...

Re:Awesome!

[gweihir]

Well, you will get fu**** by Intel. No idea whether that counts for you.

Re:Awesome!

[Anonymous Coward]

There's no such thing as "Maths class" since about 120 years ago, dinosaur fucker. Try again "sport"

Re: Awesome!

[Anonymous Coward]

Yes! you will be instantly screwed the moment your payment clears!

Re:Awesome!

[Anonymous Coward]

Hint (say the following in a John Cleese voice): I'll bet your gay.

As Linus said:

[Locke2005]

"We all know Linux is great... it does infinite loops in 5 seconds." -- LinusTorvalds

Now it can do it in under 2 seconds!

The Problem Is Microsoft

[Anonymous Coward]

That's great and all, but the problem is Microsoft licensing.

Having to license 18 cores or 36 cores rather than the minimum 16 cores is expensive as fuck.

36 cores Windows Server 2019 Datacenter edition you're looking at ~$13k pe host. Have a three ESXi host cluster? That's $39,000 in just Microsoft Windows Server 2019 licenses alone.

Of course, if you're running KVM/Xen and Linux VMs there's virtually(ha!) no license cost. But, no one does that. Even the Linux people will be paying Citrix and Red Hat many Bennie.

Re:The Problem Is Microsoft

[gweihir]

Nobody sane has real workloads on Windows servers...

Re:The Problem Is Microsoft

[Anonymous Coward]

Well, that's kind of the problem. These chips along with Threadripper, are classified as "High End *Desktops*", something like a crossbreed between a gaming machine and a workstation. Serious workloads would imply workstations or servers,(or processing nodes, whatever), and that would mean Xeons and EPYCs (and possibly not Windows).

Of course this doesn't mean you can't run serious work on them, particularly if you're willing to switch to Linux, but the assumption would probably be that you'd use Windows.

18-core iMac Pro trounces it

[Anonymous Coward]

iMac Pro official GeekBench multicore 47011 (an average that includes many poorly-run tests). My own tests routinely achieved well over 48K and Geekbench history shows several results over 50K (which might be "fake").

Core i9-9980XE multicore 43743

Re:18-core iMac Pro trounces it

[Anonymous Coward]

Plus the iMac Pro uses ECC memory, which I'm pretty sure the XE won't.

Re:18-core iMac Pro trounces it

[Anonymous Coward]

AMD's Zen and Zen2 support ECC. It's a much better choice for the enthusiast, small business, or a researcher who needs to get things done. You also get more PCIe lanes with AMD. To get those features from Intel you get forced onto Xeon which costs substantially more. AMD all the way.

Re:18-core iMac Pro trounces it

[Anonymous Coward]

Not exactly, the lower end of "Skylake-X Refresh" that is 9800X, 9820X have all their lanes enabled - 44 lanes of PCIe on the CPU and 24 on the chipset.

Remains the issue of ECC but AMD has this situation where the CPU officially support ECC and the motherboard doesn't so if you go for it, triple check everything (must be unbuffered ECC)

As do older Intel CPUs

[Anonymous Coward]

Really, price-performance-wise, it's:

1. AMD
2. old Intel
3. new Intel

Intel's current line-up feels more like a joke or an insult than anything else.

How many more re-hashes of the same CPU do they plan to insult us with?
It's only a matter of time, before they start using unwords like "IP" and declare remakes, prequels and sequels the new normal, like the media mafia.

Re:As do older Intel CPUs

[Highdude702]

I'm going to assume atleast one more once consumer zen 2 hits middle of next year since they won't have 10nm ready until end of year(maybe).

Nonsensical comparison. What about quad TR?

[Anonymous Coward]

> The question is, does a Thread Ripper outperform a dual or quad core Xeon system

No, that is absolutely not the question.

Because then I can just build a quad TR system too. Or go full rack, and have myself a beowulf cluster of TRs.

Re:Nonsensical comparison. What about quad TR?

[Highdude702]

No you can not build a quad TR system. One cpu per machine until you get to epyc. The 2 becomes maximum currently.

It's not the fastest desktop processor

[aliquis]

It's not the fastest desktop processor when it trails 24 and 32 core ThreadRippers.

That's not how it works. Fastest doesn't mean slower.

Re:It's not the fastest desktop processor

[Anonymous Coward]

It's more like "fastest, if you keep it in first gear and only drive on specific tracks, then it's .2 seconds quicker.... for only $50,000"

Re:It's not the fastest desktop processor

[EvilSS]

It's not the fastest desktop processor when it trails 24 and 32 core ThreadRippers.

That's not how it works. Fastest doesn't mean slower.

In the benchmarks, the new Core i9-9980XE is easily the fastest many-core desktop processor Intel has released to date

I didn't realize Intel was releasing ThreadRipper CPUs.

Re:It's not the fastest desktop processor

[aliquis]

Fair point. Guess I shouldn't be "almost reading" and answering stories early in the morning on the phone while walking the cat.

No Point in Single Thread Tests

[Anonymous Coward]

There is absolutely no point in even measuring single-thread performance, because there isn't any excuse for software being singly threaded anymore.

Software that is not multi-threaded is like chili without meat. Pointless.

Re:No Point in Single Thread Tests

[gweihir]

Aaaaaaand fail. There are tasks that are inherently single-thread and these are not exotic ones.

95-core Pantyripper

[PopeRatzo]

I'm holding out for all the cores.

Re:95-core Pantyripper

[Anonymous Coward]

640 cores should be enough for any Pantyripper. Hold on tight!

Captcha: overdose

Butt!!!! Butt!!!!

[Anonymous Coward]

Butt how many frames per second in Doom??????????

Hardware vs Software

[DidgetMaster]

Why will people shell out an extra $300 for a processor that is 10% faster, but they won't pay $10 for a new software program that runs twice as fast as the one they are using?

Re:Hardware vs Software

[Anonymous Coward]

Did you pay for shareware back in the day?

Re:Hardware vs Software

[DidgetMaster]

As a matter of fact, I did. But what does that have to do with my question?

Re:Hardware vs Software

[Anonymous Coward]

Most people didn't. We seem to value hardware much more than software. Perhaps because hardware is tangible and software is ephemeral. I'm agreeing with your sentiment and I don't know the answer.

Re:Hardware vs Software

[friedmud]

This also kills me with cell-phones. People will pay ~$1000 for a phone... but refuse to buy $1 apps to use on it. They will go WAY out of their way to find a "free" app that does something similar...

I absolutely cannot understand this phenomenon.

Re:Hardware vs Software

[Bert64]

I'd rather pay nothing for a pirate version that removes drm code and thus runs faster than the paid version...

Re:Hardware vs Software

[Bert64]

Many do the opposite, they will buy (or pirate) expensive software because "its the thing to have" but then skimp out on the hardware to run it on.

All you fanboys need to chill

[PeeAitchPee]

The "best" CPU is always the best one for *your* workload. If that's max single-threaded performance and money doesn't matter, then that means Intel, and it likely will for awhile. If we're talking about a workload that can be processed massively in parallel, then AMD has earned a seat at the table. I like the "High End CPUs - Intel vs AMD" benchmarks at PassMark -- should enable plenty of dick-waving no matter who you are. Take the time to understand your workload in detail, set your budget, and choose. Whatever you buy will be obsolete in a few years anyway. ;-)

Re:All you fanboys need to chill

[Highdude702]

AMD is claiming Zen 2 29% IPC lift. If it's anything like what they said before release of zen 1 we may see 35-40% IPC lift. Even the former outs Intel in 2nd place. Hopefully they can get 10nm working sooner than later to keep innovation flowing.

Nice editing...

[Anonymous Coward]

The Core i9-9980XE has max Turbo Boost 2.0 and Turbo Boost Max 3.0 frequencies of 4.4GHz and 4.5GHz, which are 200MHz and 100MHz higher than Intel's previous gen Core i9-7980XE, respectively.

Swap your numbers around, msmash, you big dummy.

The Problem

[Anonymous Coward]

The problem with that kind of thinking is that it can lead to circular logic. Who needs more cores when our software is single threaded? Who needs multi-threaded software when all we have is single (OK, few) cores?

This isn't theoretical. I keep hearing from gamers how there's "no point" to having more than 4 cores (or threads) because the current game engines don't support them. However the engine designers don't bother supporting more than 4 cores because... there are so few of them in the hands of gamers!

If you acquire the cores, the software will follow. The adoption sequence is as right and inevitable as rain: First the hardware appears, then OS support, then applications. Middleware might be in there somewhere too, just before applications.

Furthermore more cores is one of the few avenues of increasing CPU processing power. It is important to be clear on that.

And no, GPU cores cannot substitute, they are very slow by comparison to CPU cores. I mean GPU acceleration is great and all, but it is a niche opportunity when considering the entire software universe.

Is that "IPC advantage"

[Anonymous Coward]

Is that "IPC advantage" calculated pre or post the thousand or so security patches to the microcode that cut performance by up to 40%?

YAY more Hz...

[ElitistWhiner]

SteveJobs R&D proved cores greater than 2X exhibit diminishing throughput on Intel for Darwin. A lot has changed; Darwin included as well as MacOS X with GPU onboard processing et. al. with cores doing look ahead, graphics, memory, etc...

Could a generous anonymous type Avie Tevenian kernel nerd step in to raise all knowledge; level to the state of art on silicon? Are Hz marketing ' Intel' real world throughputs 'Inside'.

ZIP/c6gunner: IMPERSONATING me AGAIN? apk

[Anonymous Coward]

You're caught impersonating me c6gunner (your name's the submitter signing "APK") https://linux.slashdot.org/com... & you ALTERED /.ers PRAISE of my work (not yours you don't even HAVE).

(Don't throw stones if you live in a glass house vs. me: RIGHT ZIP? https://yro.slashdot.org/comme... )

*** IGNORANT LYING CHIMP "ZIP" SHOT DOWN FOR HIS LIES & TECH FUCKUPS vs. me https://games.slashdot.org/com...

LIAR ZIP says he has no account "I don't have an account, so I don't have mod points" https://news.slashdot.org/comm...

Yet LIAR ZIP says he downmods my posts (IMPOSSIBLE MINUS AN ACCOUNT on /.): "I down-modded a few of your post on other threads" - by Anonymous Coward "ZIP" on Thursday October 11, 2018 @11:31AM (#57461058) FROM https://yro.slashdot.org/comme...

These PUSSY bullshit artists aren't bullies - they're worse - they're pussy ass PUNKS & talkers (all talk "ne'er-do-well" DO-NOTHINGS).

APK

P.S.=> Hosts can stop portsmash (blocking downloads of it) "You basically have to already be able to run your own evil code on a machine in order to PortSmash it." from https://www.theregister.co.uk/... not Spectre/Meltdown AFAIK (but it's POSSIBLE it might but NOT TOTALLY SURE here (vs. say, RPC using them which would be REMOTE vs. LOCAL as in portsmash above) per https://meltdownattack.com/mel... &/or https://spectreattack.com/spec... ACADEMIC RESEARCH into their mechanics ) - & U FAIL a PORTFILTERING TEST https://yro.slashdot.org/comme... ... apk

Gets hot

[thunderclees]

Fantastic, but will it be able to run on full capacity without catching fire.

Random Internet Dude

[Anonymous Coward]

Random Internet Dude thinks that Firefox runs on his video card. No, not just the video rendering, the entire browser! In fact why have a computer Internet Dude? Why not just buy the video card, plug that into a power supply, load Firefox (I'll leave that to you to figure out), and Boom! Internet goodness! CPUs are for loozers!!

I'll also leave it to you to figure out how your network connection works, with that damn fine video card of yours.

But...

[Doc Right]

9900k is still faster in non-multi-threaded gaming. Threadripper still stomps it in multi-threaded tasks. So, it looks like Intel is banking on consumers to buy it because it has a bigger number stamped on it.