EnGenius ECS2512FP. 8-port 2.5G Cloud Switch review
Deepcool CG560 chassis review
Fractal Design Torrent Black RGB TG review
Core i9 12900K DDR4 3600 vs DDR5 5200 performance review
Corsair H150i Elite LCD review
Seasonic Syncro Q704 chassis + Connect PSU review
Fractal Design Ion+ 2 Platinum 860W PSU Review
Crucial P5 Plus PCIe 4.0 M.2 NVMe review
Fractal Design Lumen S28 RGB review (LCS)
WD Red SN700 NVMe SSD review
AMD APU Display Architecture to remain VEGA, phase out in 2022, mention of Rembrandt
It is still based on a rumor, but with AMD APUs you all know there is an IGP installed, an integrated GPU if that makes it more understandable. Current, and near-future lines of APUs will still be based on VEGA (RDNA) micro architecure, and albeit NAVI has made a fashionable introduction for desktop, it seems that NAVI (RDNA2)will not reach AMD APUs before 2020.
As stated this is a rumor, one that comes from ExPreview. The Vega architecture would reach into Cézanne APUs that are expected to be released in 2021. And yeah, if you missed the news on it, Cézanne are APUs that will be based on ZEN3. In the article the Chinese website also makes mention of the fact that TSMC's 7nm process would still be used for this generation. And here's when we crank up the gossip up a notch, after Cézanne there's Rembrandt, these would be based on a TSMC's 6nm node and DDR5 DRAM memory. Here the APUs would switch towards the next, or second-generation RDNA architecture. It is also the timeframe where USB4 and PCI 4.0 would see its introduction into the range.
AMD would also plan a low voltage processor series (Van Gogh) at giving or take 9 watts to take on Intel's Y-series. The Twitterer Komachi Ensaka has also posted an overview of what he expects from the next few years, you can see that listed below. These self-made plots however are based on stuff noticed and expected, and as such hold no validity as to what the final outcome is going to be, ergo I can only label them as rumors until further notice.
7.38 GHz AMD APU on MSI FM2-A85XA-G65 - 10/09/2012 11:55 AM
MSI announced that their brand new FM2-A85XA-G65 has just set a stunning new world-record CPU speed for AMD's new A10 APUs. Featuring MSI's new DigitALL power design with Military Class III componen...
MSI E350IA-E45 - AMD APU Fusion review - 03/21/2011 12:41 PM
We peek at the cutest mITX motherboard from MSI today, have a look at some of its performance on the CPU and GPU side of things but most of all, we'll discuss features as what these products bring to ...
Fox2232
Senior Member
Posts: 11809
Joined: 2012-07-20
Senior Member
Posts: 11809
Joined: 2012-07-20
#5793318 Posted on: 05/28/2020 11:45 AM
From personal experience Navis is not that good in compute...my Vega64 eats a 5700 for supper in FaH, while on medium and underclocked and undervolted.
RDNA/CDNA
From personal experience Navis is not that good in compute...my Vega64 eats a 5700 for supper in FaH, while on medium and underclocked and undervolted.
RDNA/CDNA
user1
Senior Member
Posts: 1828
Joined: 2016-01-29
Senior Member
Posts: 1828
Joined: 2016-01-29
#5793547 Posted on: 05/29/2020 12:29 AM
Vega is quite good with bandwidth utilization ,vega on apus is different that the pcie cards(vega 10/vega20), the extra hbm bandwidth doesnt help vega all that much in avg graphics workloads, but it helps alot for compute, which is what those cards are built for.
I'm sure AMD has some reason not to do it, but I doubt efficiency is one of them, in any form. If anything, wouldn't Vega be more bandwidth dependent because it was designed for HBM? In dedicated video cards, Vega only exists with HBM, after all. Navi wasn't, it works with regular GDDR. In my opinion the difference between Vega and Navi is very glaring in the performance charts, and it's not in Vega's favour. There might be some computation work where Vega could fare better, but that's hardly relevant with APUs.
its not really about efficiency, its more ,if i have 50gb/s of bandwidth and a gpu running at 1000mhz saturates that, running the gpu at 2000mhz wont double performance , if it scales at all. Unless navi has much better memory compression than vega(unlikely), it probably wont make much difference. Dual channel Ddr4 at 3200mt/s nets about 50gb/s peak, that isnt really enough for anything over 720p, its much less than an 8800gtx (90gb/s) and that was 13 years ago, any gpu is going to struggle with such a handycap.Vega is quite good with bandwidth utilization ,vega on apus is different that the pcie cards(vega 10/vega20), the extra hbm bandwidth doesnt help vega all that much in avg graphics workloads, but it helps alot for compute, which is what those cards are built for.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 2689
Joined: 2013-03-10
Die space is a premium and memory bandwidth is a more limiting factor than the raw gflops on apus for laptops/desktop, which dont have high frequency memories like gddr and are limited to a 128bit bus width effectively.
If a new uarch uses more diespace, but doesn't appreciably improve memory performance , potentially it wouldnt make sense to switch.
I'm sure AMD has some reason not to do it, but I doubt efficiency is one of them, in any form. If anything, wouldn't Vega be more bandwidth dependent because it was designed for HBM? In dedicated video cards, Vega only exists with HBM, after all. Navi wasn't, it works with regular GDDR. In my opinion the difference between Vega and Navi is very glaring in the performance charts, and it's not in Vega's favour. There might be some computation work where Vega could fare better, but that's hardly relevant with APUs.