New AMD Polaris based GPU

lifeblood

Senior member
Oct 17, 2001
971
63
91
So PCOnline and a few others are reporting an AIB has just confirmed a new Polaris based GPU that will be released in mid October. Naming of the new GPU has not been confirmed.

I really have to call BS on this rumor. The reason is the lack of a name for the GPU. If it's going to be released in mid October (a week away) then all the boxes with the name clearly printed on it have already been produced and cards actually packaged into those boxes. Their is no way the official name is not widely known by just about everyone at the AIB. The Janitor would even know the name at this point.

I so wish this was true. I would love to see an updated 12nm Polaris GPU released right before the Christmas buying season. My GTX 770 is getting a little long in the tooth and could use a replacement. But this rumor only makes me doubt such a thing is happening.
 

lifeblood

Senior member
Oct 17, 2001
971
63
91
The rumors vary but, yea, switching to the 12nm process would allow them to bump the clocks up.

I wounder if a 10% clock bump would actually net 10% more frames? And would that make much of a difference?
 

arandomguy

Senior member
Sep 3, 2013
513
133
116
This could hit that break point in terms of performance delta for 9xx/3xx series buyers to consider an upgrade. In that sense it's "exciting" as the only previous minimum choice was the GTX 1070.
 

NTMBK

Diamond Member
Nov 14, 2011
8,671
1,603
126
Clock bumps, improved efficiency and some faster GDDR5? Better than nothing I guess.
 

nurturedhate

Golden Member
Aug 27, 2011
1,637
432
136
IF AMD can achieve a 15% performance bump through clock speed and memory speed increases and slot it in at $240 it would be a solid card.
 

amenx

Platinum Member
Dec 17, 2004
2,653
405
126
IF AMD can achieve a 15% performance bump through clock speed and memory speed increases and slot it in at $240 it would be a solid card.
Yep, thats the money making sweet spot. Its volume sales would generate far more revenue for a GPU maker than a 2080ti ever could.
 

Mopetar

Diamond Member
Jan 31, 2011
4,684
876
126
The rumors vary but, yea, switching to the 12nm process would allow them to bump the clocks up.

I wounder if a 10% clock bump would actually net 10% more frames? And would that make much of a difference?
They need to get the memory clocks up more than anything else as that's where the best performance gains came from. Realistically they'd be better off adding faster RAM and not pushing the clocks as much so that the stock power draw isn't as ridiculous, especially when coupled with the inadequate default cooler. Bin the best chips and let the third parties sell the crazy OC parts that may contribute to local brownouts.
 
  • Like
Reactions: Head1985

decaz

Junior Member
Feb 15, 2018
2
0
11
The original PCOnline articles have very unclear statement about new Polaris, maybe most important part is it heard from the source that new Polaris would have more SPs.
 
Last edited:

kawi6rr

Senior member
Oct 17, 2013
557
143
116
If they can get a legit 10% bump in performance from the new process then the 580/570 which are both really good cards will be a nice increase in performance and put the 1060 in it's review mirror. Still not enough for me to upgrade from my current 570 but you never know, 580+ or whatever they'll call it would be a nice increase over my current 570.
 

LTC8K6

Lifer
Mar 10, 2004
28,523
1,568
126
It will have to deal with 2060 and 2050 cards, though. They will both certainly get bumps in CUDA cores, regardless of what GPU they actually are.
 

prtskg

Senior member
Oct 26, 2015
246
83
101
If AMD is really going with it, I hope they improve vram also to deal with bandwidth issues. Otherwise this refresh won't have much performance improvement but then again refreshes are generally like that.
 

Headfoot

Diamond Member
Feb 28, 2008
4,423
622
126
hope this isn't true. Yet another rebrand with a clock bump from the 480 would be incredibly disappointing. Ever since the r9 290 hit $250ish in 2014ish we have only seen very small increases in performance, or price/performance in the 200-$250 slot. 5 years they continue to linger on 290/290x/390 class performance at the same or similar price. What a joke
 
Last edited:

LTC8K6

Lifer
Mar 10, 2004
28,523
1,568
126
When are those cards being released?
That probably depends on what AMD releases to compete with the 1060/1050 cards, and when.

If AMD's cards are looking like they will be faster, then NV will probably release the 2060/2050 a little earlier.

If not, then NV probably waits longer.
 

GodisanAtheist

Platinum Member
Nov 16, 2006
2,150
542
136
Now that NV has moved on to GDDR6 for their 20xx series, I would have to assume prices/capacity for GDDR 5x would become more favorable. As such, it would be nice to see AMD let Polaris stretch it's legs.

It's sounds ridiculous to say (because I think the speculation in this thread suggesting a straight rebrand for the prebuilt market is likely correct) but maybe AMD don't want their Polaris cards getting too close to Vega 56 performance territory otherwise they'll never move another Vega card again and so will make paltry changes.
 

beginner99

Diamond Member
Jun 2, 2009
4,497
840
126
Now that NV has moved on to GDDR6 for their 20xx series, I would have to assume prices/capacity for GDDR 5x would become more favorable. As such, it would be nice to see AMD let Polaris stretch it's legs.
GDDR5x is essentially GDDR6 from micron. Eg. it's much more similar or actually almost identical to GDDR6 and has a big difference to GDDR5. AMD would have to create a gddr5x memory controller. At that point they will need a new die and new masks so they could just s well add more CUs. But for what? To compete with Vega 56? The BOM for sure would be smaller what would that be enough to make up for development costs? I doubt it. Navi will be out in about 1 year, just not enough time for this to be worth it.

If this actually happens, it will be another rebrand and they could use 10gbps gddr5, so 20% increase in BW + some higher clocks for maybe max 20% increase on 12 nm. But even that, why invest the money into such a product?
 

Shmee

Memory and Storage, Graphics Cards
Super Moderator
Sep 13, 2008
4,312
445
126
If a Polaris refresh uses GDDR6, that could help it quite a bit compared to the 580, and depending on price, it could sell very well at mid range. Probably not on level of Vega, not quite, but it would help bump up mid range performance for OEM sales and new buyers etc. Might even make a great mining card, though time will tell what memory is used and the actual performance.
 
Mar 11, 2004
20,019
2,239
126
Now that NV has moved on to GDDR6 for their 20xx series, I would have to assume prices/capacity for GDDR 5x would become more favorable. As such, it would be nice to see AMD let Polaris stretch it's legs.

It's sounds ridiculous to say (because I think the speculation in this thread suggesting a straight rebrand for the prebuilt market is likely correct) but maybe AMD don't want their Polaris cards getting too close to Vega 56 performance territory otherwise they'll never move another Vega card again and so will make paltry changes.
I believe GDDR6 is only 20% more expensive than GDDR5, so unless there's shortages or something (or maybe they'd like to have those chips for Navi, especially if the rumors of Navi coming out in the 1st half of the year hold true), it'd likely be best to go with it. It'd be fast enough that they could even go with a less wide memory bus and fewer chips, which could possibly offset the increased cost of the memory itself (and would mean simpler boards, probably even less power), all while offering a good bandwidth boost (say they go from 256 bit to 192, that's a 25% decrease, but going to say 12Gbps GDDR6 would be 50% faster, which even with a 25% narrower memory bus gives you 37.5% increased bandwidth; heck they could go to a 128bit bus with 14Gbps memory and they'd still see a 37.5% bandwidth increase over 8Gbps 256bit Polaris; although I'm not sure on density - meaning I don't know what bus width they could go to and still offer 8GB VRAM).

So more memory bandwidth, less power (per chip, possibly less wide bus), coupled with improvements in the GPU, and AMD will likely talk up the perf/W more than the outright performance improvements. Say they get a 12.5% performance improvement (with 7.5% coming from the increased bandwidth, 5% from improved clocks) but get a 20% improvement in perf/W, they'd want to focus on the latter.

I doubt that. AMD has likely already sold the bulk of the Vega cards they were going to (to gamers at least, they probably would like to see more in the pro market). And since this likely will have higher margins, AMD would probably not have too much issue if they sell much more of these than Vega cards. Unless they increase CU counts by like 25%, clocks by 15%, and get 60%+ increased memory bandwidth, Vega should be able to pretty easily outperform this.

They'd make paltry changes because doing anything more wouldn't be worth the cost right now. This chip would likely be about appeasing OEMs most of all. I personally have a hunch that its also setup so that it'll be their $200 and below product, while Navi stakes out the $200-400 range (depending on how good it is, it might even be able to go $300-500, and then they could probably price it more aggressively as needed to, with it likely moving down to take over the old Polaris range at some point, maybe 2020).

GDDR5x is essentially GDDR6 from micron. Eg. it's much more similar or actually almost identical to GDDR6 and has a big difference to GDDR5. AMD would have to create a gddr5x memory controller. At that point they will need a new die and new masks so they could just s well add more CUs. But for what? To compete with Vega 56? The BOM for sure would be smaller what would that be enough to make up for development costs? I doubt it. Navi will be out in about 1 year, just not enough time for this to be worth it.

If this actually happens, it will be another rebrand and they could use 10gbps gddr5, so 20% increase in BW + some higher clocks for maybe max 20% increase on 12 nm. But even that, why invest the money into such a product?
I'm not sure the differences are that big. Nvidia supported GDDR5X on the 1080 while the 1070 had GDDR5. Plus they already were putting in the work to make a GDDR6 controller. In fact it might have benefits for Navi for them to get some experience with GDDR6 prior to it. Its to appease OEMs likely more than any other reason. Pairing these with Ryzen 2000 series should be great combo for OEMs. And since OEMs probably won't have Ryzen 2 and Navi chips til Computex or later, there's time to sell these in that market.

GDDR6 potentially lets them reduce the memory bus and use less chips, which means smaller cards would be possible, maybe even half-height cards for low profile/SFF systems. Because OEMs need cards, and pairing AMD CPUs with AMD video cards will be good for AMD. While OEMs will be lower margin, they make up for it in revenue, which brings stability to AMD's finances. They outright said this somewhat recently (about them fine with lower margin markets when it lets them sustain solid revenue).

If a Polaris refresh uses GDDR6, that could help it quite a bit compared to the 580, and depending on price, it could sell very well at mid range. Probably not on level of Vega, not quite, but it would help bump up mid range performance for OEM sales and new buyers etc. Might even make a great mining card, though time will tell what memory is used and the actual performance.
Yeah. I've seen some people claim that Polaris is bandwidth limited quite a bit, which if that's true, upping the bandwidth could bring gains that outpace the clock speed improvements. It shouldn't be above $300 and likely would be $250 tops. Definitely shouldn't be pushing near Vega. Exactly, this is to make a good pairing with Ryzen 2000 series, for DIYers, but more importantly, OEMs.
 
  • Like
Reactions: prtskg

neblogai

Member
Oct 29, 2017
144
49
71
If a Polaris refresh uses GDDR6, that could help it quite a bit compared to the 580, and depending on price, it could sell very well at mid range. Probably not on level of Vega, not quite, but it would help bump up mid range performance for OEM sales and new buyers etc. Might even make a great mining card, though time will tell what memory is used and the actual performance.
The way I see it- for Polaris to use GDDR6 and not GDDR5 would require a redesign of the chip. If that is done- it may as be done with Vega architecture, which clocks much higher; which could then be done on 12nm 7.5 libraries to improve it further. etc. But we hear the talk of it being Polaris. Thus- Polaris30 must be the exact same as Polaris10, only on better process. Use faster 9Gbps VRAM for 12.5% increase in bandwidth, and you get ~10% overall performance increase without investing tens of millions into new chip design. This should be enough for midrange till 7nm and GDDR6 become cheaper and more available.
 

ZippZ

Member
Jul 24, 2000
108
13
81
A 12nm Polaris could be used in laptops where AMD is notably absent except for their APUs. Downclock them and combined with the 12nm process maybe power is low enough to compete with nvidia in mid-range performance. On the downside it would be hard to compete since Polaris is getting old and Nvidia has the whole market to themselves.
 

ASK THE COMMUNITY