Ryzen 4000 and X670 scheduled for late 2020

[SeraphicWings]

Screw this, I deem my 2700X relevant until DDR5 ram and PCIe 4 hit consumer market for an affordable price

[BiG StroOnZ]

Extremely compelling update regarding this topic (Ryzen 4000 / Zen 3):

 

AMD's Ryzen 4000-series CPUs (Zen 3) Shows Large Gains in IPC & Floating Point Performance in Early Testing -

 

Quote

With Intel seemingly unable to squeeze past 5 GHz without developing a new node, and AMD waiting for software to catch up before adding more cores, the present battleground is in IPC (instructions per clock). And Zen 3 is reported to be doing admirably thus far, with improvements approaching 20%. 

 

"According to Red Gaming Tech and Bits n' Chips, a multitude of AMD’s customers have tested Zen 3 and all say the same thing. The new architecture’s redesigned floating-point units have increased IPC in scientific tasks by something close to 50%, while integer work has seen a 10-12% boost. The combination of the two has resulted in a ~17% or greater IPC increase in mixed workloads. Zen 3 will deliver performance gains "right in line with what you would expect from an entirely new architecture."

 

- AMD's Forrest Norrod 

 

A few leaked AMD slides, confirmed and elaborated upon by industry sources, explain how these IPC improvements have come about. Unlike the jump from Zen+ to Zen 2, which merged two quad-core CCXs (core complex) into one octa-core CCD (core complex die), Zen 3 is reported to have unified octa-core CCDs. This does two things, theoretically: radically reduces the average inter-core communication latency and increases the amount of L3 cache each core has available to it.

 

The rumored Zen 3 octa-core CCD design flips that on its head and could take away Intel’s latency advantage in games. Testing has shown that Zen 3 apparently has "significantly enhanced" latency across the chip. Industry sources have also hinted that the L3 cache could get a 40% increase in bandwidth.

 

Apart from IPC, there might not be many other changes with Zen 3. Core counts are expected to stay the same, for a few good reasons; the market isn’t ready, AM4 can’t support more, the software is still trying to catch up, etc.

 

Source 1: https://hothardware.com/news/amd-ryzen-4000-zen-3-rumblings-point-to-huge-gains-in-ipc-and-floating-point-performance

Source 2: https://www.techspot.com/news/83347-zen-3-rumored-flaunting-monumental-ipc-gains-early.html

[StealthArsenal]

This is all very interesting.  I was contemplating abandoning my X299 and 7820X here in the near future for a Ryzen 3900X or 3950X.  I had a 3900X system at launch last year to test and such, but I didn't want to deal with the bugs, so I returned it and went back to X299.  Seems now might be the time to make the move over to Ryzen from X299. 

[JediFragger]

I'm trying to make my 8600k@5Ghz last another 9/10 months before switching. The 3000-series is tempting but Zen3 will def be better on the gaming side it seems

[leadeater]

4 hours ago, JediFragger said:

I'm trying to make my 8600k@5Ghz last another 9/10 months before switching. The 3000-series is tempting but Zen3 will def be better on the gaming side it seems

Same, I have a very strong urge to upgrade but I'm on a even older platform, Ivy Bridge-E.

[Flying Sausages]

2 hours ago, leadeater said:

Same, I have a very strong urge to upgrade but I'm on a even older platform, Ivy Bridge-E.

Zen 3 will going to drop Zen 2 prices so there is another reason for the wait.

[Founders]

16 minutes ago, OlympicAssEater said:

Zen 3 will going to drop Zen 2 prices so there is another reason for the wait.

I wonder how much a 3950X will go for at Micro Center by then... 

[Flying Sausages]

2 hours ago, Founders said:

I wonder how much a 3950X will go for at Micro Center by then... 

Not sure about 3900x and 3950x prices after Zen 3 launched but 8 core and below will be darn cheap. 3700x maybe around $200is like how 3700x done 2700x $389 to $200ish now. 

[tech.guru]

Im not sure you will see a big drop in Zen2. Prices can only go down so far.

[JediFragger]

14 hours ago, leadeater said:

Same, I have a very strong urge to upgrade but I'm on a even older platform, Ivy Bridge-E.

Yup you're doing well! Tbf it's only because I have a 2080Ti that it's so bloody hungry, probably last me another 2 years easy if I had a mid-range card...

[leadeater]

20 minutes ago, JediFragger said:

Yup you're doing well! Tbf it's only because I have a 2080Ti that it's so bloody hungry, probably last me another 2 years easy if I had a mid-range card...

Yea I would have upgraded sooner but then Intel started kneecapping the HEDT product line by cutting PCIe lanes and I didn't want the top end core counts, so I lost interest and it's not like the 6 cores I have now are slow anyway.

 

I'm reluctant to do anything but on the other hand you'll be waiting forever for the next big thing to come because there's always a next big thing. With new consoles coming, which typically raises the lowest bar up on game graphic fidelity, new 7nm GPUs from both parties, new revisions of CPUs, potential graphics API and development focus shifts I just have sense that spending a lot now on an upgrade is bad idea.

 

If used GPU prices weren't garbage I would have actually done that as a bridging measure, dream of the days you could get last gen top end cards for sane pricing.

[Intrafinesse]

On Thanksgiving I replaced my old Dell PC (from summer 2009) with a newly built PC with a Ryzen 5 3600 & x570 mobo.

It will be fine for my needs for 10 years.

On the other hand I wonder what kind of chip I can get in say 5 years as the current chips get outdated.

 

[Windows95]

Why are people assuming x670 will not have chipset fans?

 

im on a q6600 going insane and considering waiting another 8 months to see if it's worth it because I really hate noise and I like to reduce moving parts as much as possible. I dont feel comfortable having some small radius fan on it.

[Windows95]

On 1/1/2020 at 9:30 AM, BiG StroOnZ said:

Extremely compelling update regarding this topic (Ryzen 4000 / Zen 3):

 

AMD's Ryzen 4000-series CPUs (Zen 3) Shows Large Gains in IPC & Floating Point Performance in Early Testing -

 

 

Source 1: https://hothardware.com/news/amd-ryzen-4000-zen-3-rumblings-point-to-huge-gains-in-ipc-and-floating-point-performance

Source 2: https://www.techspot.com/news/83347-zen-3-rumored-flaunting-monumental-ipc-gains-early.html

Quote

" The rumored Zen 3 octa-core CCD design flips that on its head and could take away Intel’s latency advantage in games. "

I remember reading that supposed advantage in games from "latency" is a meme because its not noticeable.

[cj09beira]

2 hours ago, Windows95 said:

I remember reading that supposed advantage in games from "latency" is a meme because its not noticeable.

memory latency can help with high fps, but general latency as in from keyboard input to screen responding should be pretty similar even now,

2 hours ago, Windows95 said:

Why are people assuming x670 will not have chipset fans?

 

im on a q6600 going insane and considering waiting another 8 months to see if it's worth it because I really hate noise and I like to reduce moving parts as much as possible. I dont feel comfortable having some small radius fan on it.

we dont know, x570 needed it in a good part because its a whole IO die again (so there are loads of transistors there)

[Windows95]

1 hour ago, cj09beira said:

memory latency can help with high fps, but general latency as in from keyboard input to screen responding should be pretty similar even now,

we dont know, x570 needed it in a good part because its a whole IO die again (so there are loads of transistors there)

Imagine that I wait for a year of more torture only to be greeted with mobos that still have fans.

[Windows95]

On 1/2/2020 at 4:16 PM, Intrafinesse said:

On Thanksgiving I replaced my old Dell PC (from summer 2009) with a newly built PC with a Ryzen 5 3600 & x570 mobo.

It will be fine for my needs for 10 years.

On the other hand I wonder what kind of chip I can get in say 5 years as the current chips get outdated.

 

I also want to stretch my next build for 10 years except GPU, but having that fan there for 10 years spinning makes me nervous..

[Unixsystem]

5 hours ago, Windows95 said:

Why are people assuming x670 will not have chipset fans?

 

im on a q6600 going insane and considering waiting another 8 months to see if it's worth it because I really hate noise and I like to reduce moving parts as much as possible. I dont feel comfortable having some small radius fan on it.

I believe that x570 came in real hot for the motherboard manufacturers and as a result they probably didn't have a whole lot of time to optimize their designs for cooling a much more power hungry chipset. I'd imagine its a whole lot easier to just slap a small fan on a simple heats ink than it is to design and machine proper heatsinks for a board location that generally doesn't need them. 

 

That said, I'm sure plenty of next generation boards will still use fans, but I'd guess that a combination of chipset power optimizations combined with better mobo designs would allow a lot better passive cooling options. 

[Letgomyleghoe]

On 12/8/2019 at 9:50 PM, TrigrH said:

i disagree think about how long it took to for intel to get 5ghz out of its 14nm chips, 6th gen, 7th gen (some), 8th gen (most), 9th gen (pretty much all).

 

Only time will tell but currently 5ghz on ryzen requires LN2.

But you realize ryzen is on 7nm...

[CarlBar]

On 12/9/2019 at 9:45 AM, Taf the Ghost said:

@porina the ultra-high clocking silicon appears to only be available as an ES, but we know there is higher quality silicon than the 3950X and you can get that pretty close to those numbers already. AMD maybe do some special orders for some specific customer for those parts, but I'd be really surprised if they ever show up anywhere. (Companies that used to use those have gone to ASICs or FPGAs, mostly because AMD created HBM. Go figure, lol.)

 

As for 5 Ghz, Skylake was too dense to really do it. To get there Intel has kept backing off the density of the cores themselves, which is why the thermals, clocks and power usage has kept improving since Kaby Lake. (The actual x86 "core" of a modern SoC is so small relative to the die that I'm surprised this isn't actually the standard practice all together. It might be over the course of next few generations, anyway.)

 

Nice info that i hadn't heard thanks. been wondering since Zen 2 released where the limiting factor on clocks was. I admit i wondered if maybe the IO Die was the issue as i imagine it has to keep everything sync'd and we know how much the process they're using for that hates high frequencies.That said it has been obvious for a bit that the good silicon wasn't making it into consumer products. AMD has kinda gotten bitten by their own success here, they've done so well they can't actually meet demand.

 

Curious if there's any info on TSMC expanding their fab capacity because of this?

[thechinchinsong]

On 12/9/2019 at 6:12 AM, PianoPlayer88Key said:

Well I did give an example of when that kind of a jump actually happened.  Also, Tech Deals said during one of the RogueTech shows, if I heard him right, that he thought the next several years of CPU upgrades could be more like the 1990s instead of the last several years.  Some of us have unfortunately gotten used to relative stagnation in the industry, but it wasn't always that way.  I was a bit young in the 90s (was born in 1981), but I do remember at least some of it.

 

 

I looked up prices of Intel CPUs in some magazine ads (from a local computer magazine, no longer being published) I still have from back in the 1990s to 2000s.  Some vendors had prices all over the place relative to each other, though (for example I saw the same CPU going for like $500 at one place and $350 at another in the same week - the magazine was published weekly).  Also some vendors, I'm guessing because of the price volatility, didn't even publish their prices in the magazine, instead just saying call for current prices.

I mostly looked up CPUs that launched around the approximate price that most mainstream gamers have been buying Intel CPUs the last several years (like i5 or i7 price range - $250 to $350 or so).  Then, for subsequent years, I looked at how far the price had dropped, or if that CPU wasn't listed, picked a higher-tier model that had a lower price, then looked up that year's $250-350 or so range CPUs, generally picking 1 or 2.

 

• In January 1994,
  • (no previous year price reference here)
    • The 486DX2-50 was $279
• In January 1995,
  • The 486DX2-50 had dropped to $105
    • The 486DX4-100 was $355
    • The Pentium 60 was $376
• In November 1995,
  • The 486DX4-100 had dropped to $80
  • The Pentium 75 was $155 (I didn't see the 60 for Nov 1995)
    • The Pentium 100 was $288
• In February 1997,
  • The Pentium 100 had dropped to $99
    • The Pentium 166 was $295
    • The Pentium 166 MMX was $389
• In January 1998,
  • The Pentium 166 had dropped to $98
  • The Pentium 166 MMX had dropped to $112
    • The Pentium 233 MMX was $280
    • The Pentium II 233 was $265
• In January 1999,
  • The Pentium 233 MMX had dropped to $79
  • The Pentium II 266 was $197 (it had been $495 in 1998, I didn't see the 233 for 1999)
    • The Pentium II 400 was $349
• In January 2000,
  • The Pentium II 400 had dropped to $119.95
    • The Pentium III 533 was $299
• In March 2001,
  • The Pentium III 533 had dropped to $114
    • The Pentium III 1000 was $269
• In March 2002,
  • The Pentium III 1000 had dropped to $125
    • The Pentium 4 1.9 was $239
• In March 2003,
  • The Pentium 4 2.0 was $169 (had been $355 in 2002, I didn't see the 1.9 for 2003)
    • The Pentium 4 2.66 was $239
• In August 2004,
  • The Pentium 4 2.8 was $167 (had been $365 in 2003, I didn't see the 2.8 for 2004)
    • The Pentium 4 HT 3.2 was $272

I also had a few magazines with ads / prices going through about September 2007 (I think the Q6600 is in there possibly) but I had already taken a while to look these prices up.  I used to also have copies of the same magazine dating back to 1987, but I don't remember what happened to them.  The oldest one I have is from March 1990, then March 1993 is the next one I have but that one didn't have any CPUs listed individually, although it did have FPUs - they were called x87 back in the day and were separate chips.

 

 

If you're fine with waiting a long time, then maybe you can see that kind of improvement you saw in a couple years in the next several decades. Its a combination of chip technology being harder and harder to improve as well as industry stagnation due to monopoly. This point in time is probably the quickest the industry has improved in performance in a decade or so.

[Taf the Ghost]

10 hours ago, CarlBar said:

 

Nice info that i hadn't heard thanks. been wondering since Zen 2 released where the limiting factor on clocks was. I admit i wondered if maybe the IO Die was the issue as i imagine it has to keep everything sync'd and we know how much the process they're using for that hates high frequencies.That said it has been obvious for a bit that the good silicon wasn't making it into consumer products. AMD has kinda gotten bitten by their own success here, they've done so well they can't actually meet demand.

 

Curious if there's any info on TSMC expanding their fab capacity because of this?

The clock limits for Zen2 are a combination of architectural approach and heat density. It's the reason why the 3950x and the TR3 parts can run so many cores at the same power. The binning for the CCDs are extremely varied, even compared to historic norms. 

[cj09beira]

17 hours ago, Windows95 said:

Imagine that I wait for a year of more torture only to be greeted with mobos that still have fans.

btw unless you run a whole lot of nvme through the chipset that fan may never turn on, soo, there are some youtubers that have talked about it 

[Windows95]

16 hours ago, Waffles13 said:

I believe that x570 came in real hot for the motherboard manufacturers and as a result they probably didn't have a whole lot of time to optimize their designs for cooling a much more power hungry chipset. I'd imagine its a whole lot easier to just slap a small fan on a simple heats ink than it is to design and machine proper heatsinks for a board location that generally doesn't need them. 

 

That said, I'm sure plenty of next generation boards will still use fans, but I'd guess that a combination of chipset power optimizations combined with better mobo designs would allow a lot better passive cooling options. 

Meh, i think mi going to save myself 9 more months of pain and just update right now. Worst case scenario, if the mobo is shit I can always replace it with a x670, but if my old GB x38 dq6 has lasted 10 years and counting, so did every single fan i've ever used.. it should still work. Also modern cases have filters, my old cases were filled with dust, the fraktal ones remain pretty clean.

[akb8812]

Ahhh I want a new motherboard for my 3900x soon! My C6H has started to show it's age a little bit. The latest BIOSes are a bit wonky at times and my local store just got the C8H in stock, very pricey though and I have concerns about the chipset fan.

Any advice? Is x570 worth the upgrade from x370?