Friday, November 13th 2020

NVIDIA is Working on Technology Similar to AMD's Smart Access Memory

AMD's Smart Access Memory (SAM) is a new technology that AMD decided to launch with its Ryzen 5000 series CPUs and Radeon RX 6000 series GPUs. The technology aims to solve the problem where a CPU can only access a fraction of GPU VRAM at once, making some bottlenecks in the system. By utilizing the bandwidth of PCIe, the SAM expands its data channels and uses all the speed that the PCIe connection offers. However, it appears that AMD might not be the only company offering such technology. Thanks to Gamer's Nexus, they got a reply from NVIDIA regarding a technology similar to AMD's SAM.

NVIDIA responded that: "The capability for resizable BAR is part of the PCI Express spec. NVIDIA hardware supports this functionality and will enable it on Ampere GPUs through future software updates. We have it working internally and are seeing similar performance results." And indeed, it has been a part of the PCIe specification since 2008. This document dating to 2008 says that "This optional ECN adds a capability for Functions with BARs to report various options for sizes of their memory mapped resources that will operate properly. Also added is an ability for software to program the size to configure the BAR to." Every PCIe compatible device can enable it with the driver update through the software.
AMD's SAM implementation currently requires a Ryzen 5000 series CPU, 500 series motherboard chipset, and the latest Radeon RX 6000 series GPU. NVIDIA's implementation could cover a wide range of hardware, including Intel and AMD CPUs and their respective platforms. That means that even the PCIe 3.0 standard will get some love, as the current Intel desktop platforms are limited to the PCIe 3.0. NVIDIA will use a driver update to enable such a feature, however, it may take some time to arrive as the feature is still being developed.
Source: Gamer's Nexus (Twitter)
Add your own comment

64 Comments on NVIDIA is Working on Technology Similar to AMD's Smart Access Memory

#1
Nephilim666
It was clear from the get go that AMD was deliberately restricting it to 5000-series CPUs since 3000 series have the same I/O die. That it's just an implementation of a feature built into the interface spec is not surprising and it will be a coup if NVIDIA enable it for all SKUs and expose AMD's ruse.
Posted on Reply
#2
xcavax
So this functionality could take advantage of, and so "justify", the Pcie 4 bandwidth
Posted on Reply
#3
deu
Who would have thought! :D But nice with some hardware level competition! No sleeping giants can sleep forever (not Nvidia, nor AMD)
Posted on Reply
#4
lynx29
nice to see AMD spur competition, nvidia would have never released an update for this otherwise. lol
Posted on Reply
#5
mtcn77
Well, it is without saying nvidia poached AMD's HSA leader, Phil Rogers.
Posted on Reply
#6
PerfectWave
Reminds me of a certain software emulation of Asynchronous Computing...
Posted on Reply
#7
Caring1
#MeToo
Nvidia attention seekers.
Posted on Reply
#8
Calmmo
It's totally there guys, don't buy the other product, we swears it.
Posted on Reply
#9
TheEmptyCrazyHead
Whilst it's clear that AMD pulled an 'nvidia' one with the SAM feature requirements, I couldn't help myself visualize the famous words "it just works" after reading the article. I guess the real power of the feature will be felt with the next-gen games and AMD's ability to enamour the developers.
Posted on Reply
#10
ZoneDymo
I was under the impression that this was something MS was already working on and AMD just already released it, but that its coming anyway.
Same to how Nvidia was first with that gpu whatever check box in windows 10.
Posted on Reply
#11
bug
Nephilim666
It was clear from the get go that AMD was deliberately restricting it to 5000-series CPUs since 3000 series have the same I/O die. That it's just an implementation of a feature built into the interface spec is not surprising and it will be a coup if NVIDIA enable it for all SKUs and expose AMD's ruse.
In a way this could be a G-Sync/FreeSync in reverse.
Posted on Reply
#12
Chrispy_
I don't care if it's blatant copying. As long as us consumers get cool, new stuff to play with, I'm good. Everyone knows who did it first, even if Apple will claim they invented it themselves a few years from now....
Posted on Reply
#13
ZoneDymo
Nephilim666
It was clear from the get go that AMD was deliberately restricting it to 5000-series CPUs since 3000 series have the same I/O die. That it's just an implementation of a feature built into the interface spec is not surprising and it will be a coup if NVIDIA enable it for all SKUs and expose AMD's ruse.
Yeah, really dont understand the value in these practices, I mean, do the cpu's not sell well enough on their freaking fastest cpu's on the planet idea?
Do they really need people who just bought 3000 series to pay again for 5000? as if there isnt enough demand already…..

You want the ryzen 1000 - 2000 crowd and maybe some intel people, but you got those already purely on performance of the 5000 series....again really just dont get it.

Same with initially not allowing certain fidelity features on anything but RX5000 for no real reason, nobody with older cards is going to upgrade for that so just allow it on the established products right away….heck I would think that would give AMD hardware some extra value, that "fine whine" technology.
Posted on Reply
#14
AnarchoPrimitiv
Nephilim666
It was clear from the get go that AMD was deliberately restricting it to 5000-series CPUs since 3000 series have the same I/O die. That it's just an implementation of a feature built into the interface spec is not surprising and it will be a coup if NVIDIA enable it for all SKUs and expose AMD's ruse.
OH get off of it, might I remind you that Nvidia has been doing this stuff for years, and the second AMD does it, they need to be "exposed"? Let's not forget that Nvidia has literally, ten times the financial resources that AMD does, and yet, nearly everyone seems to forget this an just has this expectation that AMD should NOT ONLY, be able to compete with Nvidia as a peer, but also to be morally puritanical as well, all while trying to overcome extreme disadvantages to their competition in both Nvidia and Intel, it's completely ridiculous.

The very fact that your complaining about not getting an extra theoretical 2%-10% of performance with a graphics card you don't even own is ridiculous. I never like to assume intentions, but I'm having a hard time believing someone to be this unreasonable, so it comes off as just a pretext.
Posted on Reply
#15
Vya Domus
This begs an interesting question, if this feature was just waiting to be enabled how come NVIDIA only just started to work on this after AMD announced it ? Must be a coincidence, right ...

This isn't the first time something like this happened, with HDR AMD was the first to it, then NVIDIA "somehow" realized their GPUs supported that too but only then did they enabled it.
Posted on Reply
#16
AnarchoPrimitiv
ZoneDymo
Yeah, really dont understand the value in these practices, I mean, do the cpu's not sell well enough on their freaking fastest cpu's on the planet idea?
Do they really need people who just bought 3000 series to pay again for 5000? as if there isnt enough demand already…..

You want the ryzen 1000 - 2000 crowd and maybe some intel people, but you got those already purely on performance of the 5000 series....again really just dont get it.

Same with initially not allowing certain fidelity features on anything but RX5000 for no real reason, nobody with older cards is going to upgrade for that so just allow it on the established products right away….heck I would think that would give AMD hardware some extra value, that "fine whine" technology.
Do you not know the history of Nvidia vs AMD? Especially in the late 2000s to early 2010s? Even when AMD had undisputable better cards at better prices, Nvidia STILL outsold AMD...that can't be explained by rational behavior and comparing reviews. What I'm saying is that AMD's GPU division has a huge uphill climb, and literally, based on all historical precedent, the fact that the 6000 series cards have the performance they need to compete, STILL DOES NOT GUARANTEE AMD DECENT SALES. This feature is not about selling CPUs, it's about selling GPUs primarily. Again, let me remind everyone that AMD is magnitudes smaller than both Nvidia and Intel and neither of them will go on much longer without answering AMD back, so it's essential that AMD makes hay while the sun is shinning so that when their competition does answer back, AMD's resurgence isn't quickly snuffed out and we go back to CPU stagnation and GPU price gouging. I realize a lot of people are just thinking about what's immediately good for them, but try and think about what benefits the consumer in the long run... an AMD that has the financial resources to compete with much larger companies in 5 to 10 years.

I refuse to go back to the era of Intel operating with impunity and giving 5% performance uplifts for high prices,... And just the glimpse we received of the RTX 2000 series price hikes should scare everyone about what would happen if AMD stops competing above midrange with GPUs. I'm not saying any of this as an AMD fan, but a self interested consumer who has greatly enjoyed the last three years and is terrified of it ceasing to exist
Posted on Reply
#17
Mussels
Moderprator
Nephilim666
It was clear from the get go that AMD was deliberately restricting it to 5000-series CPUs since 3000 series have the same I/O die. That it's just an implementation of a feature built into the interface spec is not surprising and it will be a coup if NVIDIA enable it for all SKUs and expose AMD's ruse.
Ruse?

AMD just gave performance figures for estimated gains with a 5000 CPU and x570 - it may well work on 3000 series CPU's on x570 as well, with lesser gains... we dont know yet
Posted on Reply
#18
bug
ZoneDymo
Yeah, really dont understand the value in these practices, I mean, do the cpu's not sell well enough on their freaking fastest cpu's on the planet idea?
Do they really need people who just bought 3000 series to pay again for 5000? as if there isnt enough demand already…..

You want the ryzen 1000 - 2000 crowd and maybe some intel people, but you got those already purely on performance of the 5000 series....again really just dont get it.

Same with initially not allowing certain fidelity features on anything but RX5000 for no real reason, nobody with older cards is going to upgrade for that so just allow it on the established products right away….heck I would think that would give AMD hardware some extra value, that "fine whine" technology.
AMD is hungry. They've been in the red for like a decade.
Posted on Reply
#19
Turmania
If it works on both Intel and Amd, and works on most motherboards, Nvidia will do a good job. But, till then it is just a rumour.
Posted on Reply
#20
Chrispy_
AnarchoPrimitiv
OH get off of it, might I remind you that Nvidia has been doing this stuff for years, and the second AMD does it, they need to be "exposed"? Let's not forget that Nvidia has literally, ten times the financial resources that AMD does, and yet, nearly everyone seems to forget this an just has this expectation that AMD should NOT ONLY, be able to compete with Nvidia as a peer, but also to be morally puritanical as well, all while trying to overcome extreme disadvantages to their competition in both Nvidia and Intel, it's completely ridiculous.

The very fact that your complaining about not getting an extra theoretical 2%-10% of performance with a graphics card you don't even own is ridiculous. I never like to assume intentions, but I'm having a hard time believing someone to be this unreasonable, so it comes off as just a pretext.
Exactly, people need to understand the sales model that drives efforts at any company. AMD make a thing that works with two products they currently manufacture.

They spend x time developing it and y time bugfixing/refining it on those two specific products - Ryzen 5000 and Radeon 6000.

Lots of their current revenue and even more of their future revenue to continue development and research is in those two specific products.

Now, you could say that if they spend 3y - 10y* to bugfix/refine all the dozens of permutations of older Ryzen processors and chipset combination across hundreds of BIOS and lane configurations, then that would be a goodwill gesture - but what it will not do is generate any more revenue. It might generate goodwill and PR, but AMD already have that in spades compared to the competition. Their reputation as the underdog that offers more to consumers than Nvidia or Intel for less money is pretty solid at this point.

At the end of the day, the first priority of these companies is to turn a profit, not to cater to the whims of a technically-literate minority.

* - I just pulled those numbers out of my ass for the sake of making an example. All I'm basing it on is experience that refining a concept to work in the real world usually takes much longer than getting the proof-of-concept prototyle working and that's the point I'm trying to convey there.
Posted on Reply
#21
ZoneDymo
AnarchoPrimitiv
Do you not know the history of Nvidia vs AMD? Especially in the late 2000s to early 2010s? Even when AMD had undisputable better cards at better prices, Nvidia STILL outsold AMD...that can't be explained by rational behavior and comparing reviews. What I'm saying is that AMD's GPU division has a huge uphill climb, and literally, based on all historical precedent, the fact that the 6000 series cards have the performance they need to compete, STILL DOES NOT GUARANTEE AMD DECENT SALES. This feature is not about selling CPUs, it's about selling GPUs primarily. Again, let me remind everyone that AMD is magnitudes smaller than both Nvidia and Intel and neither of them will go on much longer without answering AMD back, so it's essential that AMD makes hay while the sun is shinning so that when their competition does answer back, AMD's resurgence isn't quickly snuffed out and we go back to CPU stagnation and GPU price gouging. I realize a lot of people are just thinking about what's immediately good for them, but try and think about what benefits the consumer in the long run... an AMD that has the financial resources to compete with much larger companies in 5 to 10 years.

I refuse to go back to the era of Intel operating with impunity and giving 5% performance uplifts for high prices,... And just the glimpse we received of the RTX 2000 series price hikes should scare everyone about what would happen if AMD stops competing above midrange with GPUs. I'm not saying any of this as an AMD fan, but a self interested consumer who has greatly enjoyed the last three years and is terrified of it ceasing to exist
I mean sure but it only works if you also have an AMD cpu, atleast at this moment, and not just any AMD cpu but the latest 5000 series....
That is kinda what is so baffeling to me, if they were to allow on all their Ryzen cpu's….well quite a few people have those and they might then think "oh ill get a Radeon card for my next upgrade because it will go well with my cpu".

Now however if you have a 3000 ryzen, you can go either AMD or Nvidia because you dont have access to SAM anyway unless you ALSO spend money to upgrade you cpu….
That is what is so stupid about this.
Posted on Reply
#22
SIGSEGV
The magical black leather jacket just works.
Posted on Reply
#23
Chrispy_
SIGSEGV
The magical black leather jacket just works.
One day soon that'll be as infamous as "you're holding it wrong"
Posted on Reply
#24
z1n0x
So people give AMD shit for restricting it to Ryzen 5000, but a pass to Nvidia for only enabling it on Ampere, even though it been part of the PCIe spec. for a long time.
Don't you just love them double standards, always good for laughs.
Posted on Reply
#25
ZoneDymo
z1n0x
So people give AMD shit for restricting it to Ryzen 5000, but a pass to Nvidia for only enabling it on Ampere, even though it been part of the PCIe spec. for a long time.
Don't you just love them double standards, always good for laughs.
Well I think we all knew Nvidia is pretty much pure scum so that would just be repeating ;)
Posted on Reply
Add your own comment