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

#51
mtcn77
SIGSEGVfight the greed
Greed? You think any of this would surface if left to Nvidia? Same with tesselators, when AMD finds things they are buried... greed is your only option it will ever see the light of day.
Posted on Reply
#52
Forza.Milan
nvidia claim supporting it, so it is clear, only running on spesific platform, mobo, cpu, etc..
the question is, will it amplied the performance?
and why only on ampere? thats another question :kookoo:
Posted on Reply
#53
wolf
Better Than Native
$ReaPeR$I will gladly overpay for AMD products
$ReaPeR$the greed camp
$ReaPeR$nshitia
$ReaPeR$crapple
Clearly a level headed, rational, vendor agnostic approach, where bang for buck, quality products and a top tier experience reigns supreme.

wait
Posted on Reply
#54
Fluffmeister
wolfClearly a level headed, rational, vendor agnostic approach, where bang for buck, quality products and a top tier experience reigns supreme.

wait
I get told off by the mods for far less :P
Posted on Reply
#55
bug
z1n0xSo 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.
I fail to see the double standard, AMD also restricts this feature to the latest GPU generation.
It's actually not a restriction, GPUs must have built-in support for the feature, if I understood correctly.
Posted on Reply
#56
Blueberries
bugIn a way this could be a G-Sync/FreeSync in reverse.
Yeah I predict SAM will become open with "limited support" on older generation CPUs with future driver updates.
Posted on Reply
#57
FinneousPJ
And who's to say AMD cannot expand the compatibility with future updates if nvidia can? Odd assumption there.
Posted on Reply
#58
Nephilim666
AnarchoPrimitivThe 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.
No one owns these yet. I have an AMD TRX40 system with a Vega 64, I have given plenty of my hard earned to this company, only to be told that a new feature of their GPUs is going to be artificially restricted to their latest CPUs which have the exact same IO die as the previous gen just rubs me the wrong way. There is absolutely no reason to not enable it on Zen 2. I will just compare performance between RX6900 without SAM and an RTX3090 with whatever NVIDIA make work with my system and make a rational reasoned decision.
Posted on Reply
#59
Mussels
Freshwater Moderator
To be honest they may well roll the feature back to older hardware like the 3000 and 4000 series CPUs and even the 400 series boards once AGESA updates come out... but they'd want to do internal testing and be sure it WORKS, unlike that oopsie where they rolled out PCI-E 4.0 to mobos and had to undo it.
Posted on Reply
#60
Nephilim666
MusselsTo be honest they may well roll the feature back to older hardware like the 3000 and 4000 series CPUs and even the 400 series boards once AGESA updates come out... but they'd want to do internal testing and be sure it WORKS, unlike that oopsie where they rolled out PCI-E 4.0 to mobos and had to undo it.
Yes, but in that case the hardware varied. In this case the parts interfacing with the GPU (IO die and whatever traces etc are on the motherboard) are no different to the 5000 series.
Posted on Reply
#61
bug
FinneousPJAnd who's to say AMD cannot expand the compatibility with future updates if nvidia can? Odd assumption there.
I think they will. I guessed above they only went for one particular GPU series so they could shorten their TTM.
But in a world where every post about Nvidia (or Intel) causes knee jerk reactions, I think it's worth pointing out when the company everybody loves to hate happens to take the high road.
Posted on Reply
#62
mechtech
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....
Of course, didn't Apple invent the radius, and round edge and all that?!?!
Posted on Reply
#63
bug
mechtechOf course, didn't Apple invent the radius, and round edge and all that?!?!
Nope. Apple invented the invention.
Posted on Reply
#64
SIGSEGV
bugBut in a world where every post about Nvidia (or Intel) causes knee jerk reactions
the basic laws of physics
Posted on Reply
Add your own comment
Nov 21st, 2024 08:45 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts