Intel Cypress Cove Leak: Rocket Lake Blasts past Comet Lake, but what about AMD Zen 3?

Are you dying to hear if Rocket Lake will beat Zen 3? Click here to find out just how close Cypress Cove will get to AMD’s release this holiday season…

0:00 Rocket Lake will be better than Comet Lake
1:58 Cypress Cove Information Overview
4:43 Rocket Lake iGPU Info
7:12 Should you be excited for Rocket Lake?
8:00 Tiger Lake Info
10:19 Rocket Lake vs Zen 3

Address Fan Mail to:
Moore's Law Is Dead,
PO Box 10468
Peoria, IL 61612

Broken Silicon [A PC Hardware Podcast] is available on ALL platforms.

All Music by SAHARA:

Broken Silicon Logo by Tom.
Broken Silicon burning graphic by Tom & Sulphurous:

MAJOR SPONSORS:

LINKS!!!!!!:

[twotonewatermalone]

Too many god damn lakes and coves for me to care anymore

[IssuesVFX]

I get so confused keeping up with intel cpus

[mauricio]

The dude choosing architecture names over there at Intel is a total squizophrenic.... I'm amazed the next one isn't called Covelake or Lake Cove.

[bilalfouzi]

Tom can you plrase make a video explaining these coves and lakes and bridges and rockets please

[seasesh]

Anything tech related: exists
Tom: kowalski analysis

[LoftySkinner]

Boiling lakes and burning coves,
Everyone's favourite PCB-mounted stoves

[asteroiddropper]

I mean feeling confidential about having all these leaks is accurate too lmao.

[raddad]

Here I am, still treading along on my Sandy Bridge... going to step right over all these Coves and Lakes right into Zen3 I think.

[darcrequiem]

When are we getting Cove Lake? Edit: Wow, his dog seems to know when his videos are ending. This is the second time I've notice his dog leaving right near the conclusion.

[karol]

13:26 he definitely did enjoy your video, Look at his tail! :D

[Músico_Aventaleiro]

Have you seen the new Coreteks video? I would like to know your opinion :)

[RyugaHidekiOrRyuzaki]

Tom any videos in the works related to what Coreteks talked about in his latest video?

[ecophreak]

Here's hoping to 2022, exciting times for pc users

[eyastremsky]

Hey, can you maybe make a timeline info graphic for confirmed and rumored product launches for the chips of all 3 companies, I thinks at this point I'm completely lost :(

[roebbiej]

Could you sometimes explain a bit more about all the coves and lakes... I don't really understand what is going on if you're name dropping a lot of then in a video. Or am I just a noob

[pam]

Wake me up when Intel finally re-captures the long lost magic they had with X99.

[Speak_Out_and_Remove_All_Doubt]

Sounds like Intel might be doing what I was hoping for and writing about last year, HBM for system memory. Memory speed is the main thing holding back CPUs and even more so APUs today. That's why AMD upcoming desktop APUs are getting tested with 5600MHz DDR4 and Nvidia are bringing 21Gbps+ GDDR6X memory to Ampere. But HBM on the die of the APUs would be massive performance boost, if there was enough to replace normal DDR memory altogether or maybe like 32GB to act like a massive cache before DDR. And it really would be as expensive as you think...
Anyway, here's what I was saying last year:
"I don't get why AMD (or Intel but it's very early days for them with decent graphics) haven't yet made a proper high end APU complete with HBM on chip for the desktop markets yet?
Maybe the upcoming 5nm will allow this revolution but surely the ultimate aim for Intel or AMD APUs it to win as many segments as possible and this includes the high end?
There are a few segments where APUs aren't suitable, things like very specialist server and AI stuff as the ratios of CPU vs GPU vs memory is very different or the enthusiast market that will want the option of different configurations and the dedicated parts allows for tweaking the cooling solutions, overclock higher and swap out parts at different times but on the whole APUs have low cost builds covered very nicely but a large APU could perfectly serve up to the high end too if done right.

In the next few years both AMD and Intel will have the ability to build APUs with massive CPU performance, massive GPU performance and enough HBM3 stacked system memory to be used as the unified system memory for both CPU and GPU, and so getting rid of the slow and energy expensive off chip DRAM. This has to be where these companies are heading long term isn't it???

So lets say in 2022 when 5nm is pretty mature then AMD builds an APU with 16 CPU core, 120CU and 32GB HBM3. I know this sounds crazily expensive to achieve right now but when you actually sit down and look at the costs it's honestly the better value route for performance.

The costs of separately putting together a high end system in 2022 would be roughly as follows:

CPU (16 Cores Zen 4) = $500
GPU (120CU RDNA 3.0 with 16GB GDDR6) = $1200
RAM (32GB DDR5) = $400
MOBO (high end board) = $600 (probably needs to be a specialist embedded design)
Water Cooler = $300 (very high end AIO cooling required to control temperatures)

Total = $3000

So the first question is, could AMD sell this chip for less than $1700? I would say yes very easily given the XSX chip is roughly half this chip and they sell that for probably less than ~$100! Now ok, that is in massive quantities and the HBM memory will add a lot to the costs but not too get it close to $1700 and so it would still be a high margin product for anyone who makes it.

The XSX is 360mm^2, so with a doubling of pretty much everything and a move to 5nm I would project this chip to be no bigger than 600mm^2, which is certainly big but still very doable. It would actually be around the same size and design as AMD's Fiji chip which had a launch price of just $649 back in 2015.

Plus if AMD sold the entire system kit together for around $3000 then there is a lot of profit to be made and a lot of performance for the customer. Win-Win!

With densities and efficiencies afforded by the advanced 19 layer EUV process on TSMC's 5nm node plus Zen 4's power efficiencies plus RDNA 3.0 being 50% more power efficient than RDNA 2.0 which is 50% more efficient than RDNA 1.0, I truly believe this seemingly fanciful chip is actually easily disable of there is a will to make it.

It's also scalable too, so you could have half these specs for half the price for a different price point. Granted, clocks might have to be tamed a little to keep temperatures under control as transistor density will be very high but I would think the massive bandwidth and ultra low latencies of having the system memory on chip would more than makes up for lower clocks.

Maybe the CU count won't be the most important thing to focus on in the future, maybe it will be all down to the number of accelerators they can include on a self-contained, purpose built, giant, higher performance APU with ultra low latency insanely wide bandwidth memory that will actually be the key differentiator allowing for things not possibly on a non-APU system.

I'm not saying this is a perfect fit for all use cases but it would amazingly powerful for a lot of gamers, workstations, programmers, high-res professional image editing, 3D rendering, etc, etc.

These types of chip would be perfect for something like the Apple Mac Pro in 2022 or maybe if MS wants to being a desktop Surface machine to compete with Apple in this space?

Intel and AMD and currently locked in a fierce battle for CPU supremacy, Intel is also doing what it can to start a battle in the GPU space too but ultimately the victor will be the company that truly nails APUs at the majority of performance segments.

For whatever reason we have yet to see a powerful APU come to the desktop, it's only low cost, low power stuff but even though AMD seems to be doing all the ground work to set this up maybe it will be Intel that brings something truly special first? There are already rumours Intel are playing around with big.LITTLE CPU cores which lends itself to APU designs from a thermal management standpoint. Plus Intel are doing their utmost to build a decent scaleable graphics with it's Xe range. But the biggest indicator of Intel's intentions is their work on Foveros which shows they understand the future needs all in one APUs with system memory on the die but again it's just down to which company beings a finished product to market first.

I guess it's just 'watch this space' for who does it first but this is certainly the future of computing. What is very interesting is ARM based chips are way ahead of x86 when it comes to all in one chip design, just look at the likes of Fujitsu's A64FX, this is an incredible chip. So x86 has to be careful to not be caught napping. If Intel or AMD don't make a super high end APU soon then I think Apple will make it using either ARM or even their own design using the RISC V architecture to completely relinquish their dependence on everyone else for all of their ranges. Amazon are kind of making ARM APUs, Huawei do, Google do, Nvidia too, ok all these are very different types of chips to what I am talking about above but what I'm saying is they all have the experience of designing very high performance, complex chips and with Windows already supporting ARM and emulators working pretty well now then a move away from x86 could happen very quickly if one of these massive players nails a super powerful APU with key accelerators for the PC market.

One thing is for sure, we have an amazing few years ahead of us."

[LaskaiTamas]

11:30 Zen 3 will have much higher IPC. Zen 2 already has 18% more IPC (4 GHz vs 4 GHz) than the 9900K in multithreaded applications (not in gaming, they are equal in gaming) so with Rocket lake Intel only will catch up to Zen 2. Zen 3 will have another 15% IPC (hopefully) and with the same clock speeds Zen 3 will crush Rocket Lake.

[pilsen]

Love your shows, you Cyrix fanboy. Lol keep up the great work on keeping us informed on all the new cpu technologies.

[NANOTECHYT]

Another day, another Moore's Law is Dead video, another leak, another like on the video!