Samsung Exynos SoC with AMD RDNA GPU Destroys Competition, Apple 14 Bionic SoC Kneels

[Chrispy_]

LOLcalmdown


And if the GPUs got bigger, as you desire, then they would be capable of higher resolution gaming, and would become bottlenecked by memory bandwidth, which is why AMD hasnt done it. You defanged your OWN argument with this little tidbit.

Apologist arguments like that are why AMD's IGPs are so lame at the moment.

We're not talking about enough of a performance jump to go to much higher resolutions, we're just trying to get barely playable games that run 20-30fps to run at maybe 30-50fps. Even a 50% performance jump is well within the limits of current DDR4.

 

[TumbleGeorge]

But still useless because it sucked up battery

Which part of mobile devices eat much power? Display, CPU part, GPU part, RAM, flash storage, radio transmitter/antenna, other?

 

[Searing]

it was expected, Desktop architectures are more powerful than mobile counterparts, For example the TEGRA x1 is still the most powerful mobile GPU with 256 Cores even after nearly 6 years of duty

What are you talking about, did you actually believe that? The A14's GPU is WAY faster than the Tegra X1, and the iPad Pro's GPU from 3 years ago was way faster also. The M1's GPU which will be in the next iPad Pro is 4x faster, at least.

 

[Totally]

Which part of mobile devices eat much power? Display, CPU part, GPU part, RAM, flash storage, radio transmitter/antenna, other?

Tegra is the SoC CPU/GPU/IO/Memory Controller which is all one part. Anything, well the few, that came specced with a Tegra chip had terrible battery life.

 

[RandallFlagg]

Samsung is back.

Now AMD needs to start using Samsung fabs.

 

[ValenOne]

As far as I'm aware they are using Vega gpu, not RDNA or RDNA2. Its a custom Vega gpu with some RDNA features in it. But even existing mobile gpu's are using old AMD patents, since AMD decided to sell a ton of it patents about a decade ago when they were struggling for money.

Major improvements with RDNA are the lower graphics pipeline latency and "delta color compression everywhere".

 

[Xajel]

it was expected, Desktop architectures are more powerful than mobile counterparts, For example the TEGRA x1 is still the most powerful mobile GPU with 256 Cores even after nearly 6 years of duty

You need to hit Shift+F5 few times..

Tegra has been out performed by multiple SoC.
Yes it was the best performer for few years, but it suffered from high-power consumption, it was one of the reasons the Tegra didn't succeed well in the mobile market (the other reasons are cost and lack of radio silicon).

Today, almost all high-end SoC's from even 2-3 years outperform Tegra, depending on which benchmark and what SoC (which vendor). For example, according to notebookcheck, the Snapdragon 865 is on average over 80% faster than Tegra X1 (both CPU and GPU sides).

It's not like Apple reinvented the wheel with Apple A14 Bionic, they blatantly borrowed/stole everything they had access too but they don't have access to latest technology.
As i read somewhere qualcomm GPU is based on bought IP from AMD many many years ago, so everything in mobile phones space is based on old Amd IP that got refreshed with whatever money qualcomm and probably apple put in R&D.
Samsung made a smart move updating it's GPU to the best architecture available except ray-tracing

When Hector Ruiz was the CEO of AMD, he bought ATi, and after few months the financial crisis started so he sold the mobile and embedded centric part of ATi to Qualcomm to get cash (among other things), this includes the Adreno GPU (which is just an anagram of Radeon, eg.. same letters, different order) and IIRC the Geode processors intended for embedded systems like TV's and so on. Because he felt at that time that those embedded and mobile things were not the future. It was just few years before the exploding of smartphones.

 

[yeeeeman]

Without power figures....this news is for idiots.
An RX6900XT blows A14 out of the water...at 300W.
So when I'll see that this SoC beats A14 at the same power consumption, then I'll buy it.
But I seriously doubt it.

 

[Totally]

Samsung is back.

Now AMD needs to start using Samsung fabs.

No, AMD should be avoiding this as Samsung is known shamelessly steal IP, then drag things out in court regardless the outcome they'll win because by the time everything is settled it won't matter anymore.

 

[RandallFlagg]

No, AMD should be avoiding this as Samsung is known shamelessly steal IP, then drag things out in court regardless the outcome they'll win because by the time everything is settled it won't matter anymore.

Then AMDs growth will be capped pretty hard as Apple, Qualcomm, and possibly Intel suck down TSMCs wafer fab capacity for the next few years. Meanwhile Nvidia will keep knocking out GPUs with Samsung, and Intel CPUs and potentially GPUs with its own fabs.

 

[Totally]

Then AMDs growth will be capped pretty hard as Apple, Qualcomm, and possibly Intel suck down TSMCs wafer fab capacity for the next few years. Meanwhile Nvidia will keep knocking out GPUs with Samsung, and Intel CPUs and potentially GPUs with its own fabs.

Their all in the same boat. Nothing is stopping AMD from taking their share of wafers from TSMC, and not going with Samsung gives them a more favorable terms at TSMC. Pretty sure that's why Nvidia and Intel are throwing in with Samsung in the first place, taking what they can get since they can't get preferred treatment at TSMC.

 

[Vya Domus]

Now AMD needs to start using Samsung fabs.

And go backwards ? LMAO what ?

 

[Caring1]

Destroys might be a strong term, unless they are competing in Robot Wars.

 

[1d10t]

And if the GPUs got bigger, as you desire, then they would be capable of higher resolution gaming, and would become bottlenecked by memory bandwidth, which is why AMD hasnt done it. You defanged your OWN argument with this little tidbit.

Apologist arguments like that are why AMD's IGPs are so lame at the moment.

We're not talking about enough of a performance jump to go to much higher resolutions, we're just trying to get barely playable games that run 20-30fps to run at maybe 30-50fps. Even a 50% performance jump is well within the limits of current DDR4.

It doesn't have to be bigger, or "more" in appropriate term, but new uArch like this RDNA will undoubtedly bring substantial upgrade in mobile space. With Samsung paving pathway to mobile space, I really hope that's more than enough to convince AMD they need to revamp their aging Vega.
AMD been neglected iGPU for far too long, 3 generations with same config and "a clock bump" is lame to put it mildly. Intel has catch up with its 96EU Xe Graphics, as demonstrated by reviewer, its even surpass Vega 10 and close to MX350 in some test.

 

[RandallFlagg]

And go backwards ? LMAO what ?

Meanwhile in the real world...

AMD Reportedly in Plans to Outsource Partial Chip Production to Samsung

It's been doing the rounds in the rumor mill that AMD is looking to expand its semiconductor manufacturing partners beyond TSMC (for the 7 nm process and eventually 5 nm) and Global Foundries (12 nm process used in its I/O dies). The intention undoubtedly comes from the strain that's being...

www.techpowerup.com

 

[renz496]

It'd be great if Samsung allows other competitors access to their chips, frankly the near monopoly of QC on high end phones is just unbearable & I'm not even talking about their baseband (royalty?) shenanigans!

samsung did let other vendor use their SoC but most often they will keep their best for themselves for a generation or two first. the problem with smartphone market is many simply needs qualcomm modem/baseband. even samsung they cannot equip all their phones with their own SoC depending on which market they want to sell their phones to.

You need to hit Shift+F5 few times..

Tegra has been out performed by multiple SoC.
Yes it was the best performer for few years, but it suffered from high-power consumption, it was one of the reasons the Tegra didn't succeed well in the mobile market (the other reasons are cost and lack of radio silicon).

Today, almost all high-end SoC's from even 2-3 years outperform Tegra, depending on which benchmark and what SoC (which vendor). For example, according to notebookcheck, the Snapdragon 865 is on average over 80% faster than Tegra X1 (both CPU and GPU sides).



When Hector Ruiz was the CEO of AMD, he bought ATi, and after few months the financial crisis started so he sold the mobile and embedded centric part of ATi to Qualcomm to get cash (among other things), this includes the Adreno GPU (which is just an anagram of Radeon, eg.. same letters, different order) and IIRC the Geode processors intended for embedded systems like TV's and so on. Because he felt at that time that those embedded and mobile things were not the future. It was just few years before the exploding of smartphones.

the problem with tegra is they are using ARM stock high performance core that is well known not power efficient. even samsung and qualcomm (snapdragon 810) facing similar issue.

 

[R0H1T]

samsung did let other vendor use their SoC

Yes but outside of Meizu & perhaps a handful of others (smaller vendors) I don't recall any major player using them. Hopefully this changes in due course of time.

 

[tfdsaf]

AMD has preferential order at TSMC, but the issue is how many 5nm production is TSMC going to have after it sells to Apple which is the number 1 customer. Maybe AMD will go with the advanced 6nm node, I hear that is quite better than 7n+ about 30% more power savings or 20% faster performance, though the main issue is how much chips is TSMC going to be able to produce on these newer nodes.

I think AMD will have to divide their nodes, so use the 7nm node for some processors, but use 6nm for others. In the GPU space they are likely to go with 6nm or 5nm because they sell less GPU's and they definitely need the power and speed boost to stay competitive with Nvidia.

So I'm thinking Epyc processors with 5nm or 6nm(whichever they choose), Ryzen 6000 and Threadripper still with 7nm. Monile cpu's on 7nm, custom apu's on 7nm, use Samsung's capacity for some GPU's, probably the low and mid range, and big Navi RX 7800 and above on 5nm or 6nm.

 

[renz496]

Yes but outside of Meizu & perhaps a handful of others (smaller vendors) I don't recall any major player using them. Hopefully this changes in due course of time.

Samsung will make sure the latest soc goes to their phone only for competitive reason against other vendor. Other vendor most often gen at best one generation behind than what being use on samsung flagship. But when it comes to soc for smartphone the biggest hurdle are hardware based modem/baseband. And the market are being shape in a way that give absolute advantage towards Qualcomm. Worse they already set thing in stone years ago to ensure they can abuse others legally. The only one that really can fight them back was chinese soc maker that also never play it fair.