Alienware Unleashes the Ultimate AMD Advantage Laptop and Industry-First 480Hz Display Technology

[medi01]

AMD have had the power efficiency advantage for quite some time now.

I still remember Raja time Vega 7, clearly more than just node advantage has bumped AMD's perf/power into top.

 

[ThomasK]

A 480Hz display is more of a marketing gimmick to me. As far as performance is concerned, it's on par with the 3080Ti mobile.

 

[Chrispy_]

I still remember Raja time Vega 7, clearly more than just node advantage has bumped AMD's perf/power into top.

Raja's Vega was all 14nm apart from the Radeon VII which launched 18 months or so after he'd left AMD for Intel. The Radeon VII was actually damn competitive in terms of performance/Watt despite being an almost exact port of the older Vega64 over to TSMC 7nm.

Not only was it almost 50% more efficient, it did that despite being a flagship part clocked 250MHz higher than Vega64 and powering twice the amount of HBM2.

In case my point isn't clear, TSMC 7 handed AMD (or rather, it's fairer to say that AMD paid the premium for) a huge advantage that Nvidia didn't take. RTX 2000-series was TSMC 12 and RTX 3000-series is Samsung 8nm. Even now, the latest and greatest Nvidia 3090Ti is still using a process node that's behind the 2019 TSMC 7FF of Radeon VII and all of the RX 5000-series.

 

[medi01]

Raja's Vega was all 14nm apart from the Radeon VII which launched 18 months or so after he'd left AMD for Intel. The Radeon VII was actually damn competitive in terms of performance/Watt despite being an almost exact port of the older Vega64 over to TSMC 7nm

You have conveniently skipped 2080 that was on a way inferior process node AND more power hungry memory, but had 37-45% more perf/watt.

AMD Radeon VII 16 GB Review

The time has come. We're finally allowed to talk about Radeon VII performance numbers. The company's new flagship graphics card is the world's first to be made using a 7 nanometer production process. Also, it has the largest VRAM size of any card below $1000: 16 GB.

www.techpowerup.com

Oh yeah, and nor was there performance:

AMD Radeon VII 16 GB Review

The time has come. We're finally allowed to talk about Radeon VII performance numbers. The company's new flagship graphics card is the world's first to be made using a 7 nanometer production process. Also, it has the largest VRAM size of any card below $1000: 16 GB.

www.techpowerup.com

The point being made is that is more of an architecture gains, than just process improvements, that got AMD to it's top position.

 

[Chrispy_]

You have conveniently skipped 2080 that was on a way inferior process node AND more power hungry memory, but had 37-45% more perf/watt.

I didn't skip it. AMD on GloFo 14 were way behind Nvidia on TSMC12. The fact that TSMC 7nm brought AMD from way behind to "vaguely competitive" speaks volumes.

A like-for-like copy of dated Vega architecture gained >50% just by moving to a new process says a lot about the advantage of TSMC 7nm back in 2019.

You seem to be arguing that Nvidia were ahead on flagship performance but I'm not even trying to claim that. Firstly, AMD haven't had that in forever! Secondly, they didn't have anything to compete with the 2080 either from a performance or a transistor count. The TU102 was massive at 545mm2 that dwarfed even Vega64 on GloFo 14nm. It also had hardware raytracing to skew the performance metrics in any suite that included raytracing. The Radeon VII, on the other hand was just a tired old Vega64 being used as a test-run for TSMC 7nm. Radeon VII was architecture from 2017 and should be compared to the 2017 Pascal 1000-series GTX cards in terms of technical prowess. By that metric AMD simply gained a victory over Pascal Geforces, simply because of TSMC's new process.

 

[medi01]

The fact that TSMC 7nm brought AMD from way behind to "vaguely competitive" speaks volumes.

How waas Vega 7, that was running on 7nm process, but could not even dream of 2080Ti levels of performance, on top of being 1.5 times behind on perf/watt front, "vaguely competitive"?

Only architectural changes, RDNA1&2 allowed AMD to first close the gap and then beat NV.

 

[Chrispy_]

How waas Vega 7, that was running on 7nm process, but could not even dream of 2080Ti levels of performance, on top of being 1.5 times behind on perf/watt front, "vaguely competitive"?

Only architectural changes, RDNA1&2 allowed AMD to first close the gap and then beat NV.

Is "within 10%" not vaguely competitive to you? Vega64 went from being 30% behind a 2080 to a Radeon VII being just 9% behind a 2080 through the move to TSMC:

You're still also comparing a 2017 architecture designed for GloFo 14nm (not TSMC 7nm) to a 2018 architecture designed for the outset for the TSMC 12nm mode it was mode on. If you've followed any CPU/GPU design in the last decade or so, you should know well that porting a design from one process node to another is not the best way to make a chip and gets far less from the new node than a new design made for that node specifically. AMD, Intel, and Nvidia have all experienced die shrinks with less than ideal gains over the years, which is why the rather significant improvements between Vega64 and Radeon VII were so noteworthy.

I'm not really sure why you're even focusing on the Radeon VII, it was a low-volume part that didn't have any product stack underneath it, lacked many of the features that Nvidia was offering, and simply served to provide something as a placeholder whilst RDNA was being worked on as the designed-for-7nm part, not a 2-year-old port from a different process node and foundry altogether. GPUs are also only half the equation here - TSMC 7nm is also responsible for giving AMD an advantage over Intel in the CPU department, With Zen2 offering significant leaps over Intel at the time, and being a massive step up from the Zen/Zen+ on GloFo 14 again.

Architecture played a part in it, of course, but the big jump in clocks and efficiency was credited to TSMC 7nm.

 

[medi01]

Is "within 10%" not vaguely competitive to you?

No, as the target is 2080Ti and not 2080.

 

[Chrispy_]

No, as the target is 2080Ti and not 2080.

Your target perhaps; You're now moving goalposts on a tangent of argument that you brought up, not me; AMD themselves and all independent reviews compare it to the 2080 because that's the closest equivalent cost, size, transistor count, and performance comparison.

The VII was barely half the price of a 2080Ti despite having much more expensive HBM2, and 5GB more of it as well.
The VII wasn't anywhere near as large as the TU102, almost 6 billion fewer transistors and less than half the physical size. That size comparison isn't down to TSMC7 vs TSMC12, either - Vega64 which was on the larger, older GloFo14 process node was still 40% smaller than TU102 on the denser TSMC12 process.

If you're trying to make an argument based on a 2080Ti vs a Radeon VII, then that's just dumb. That's like saying a 12900KF is better than a Ryzen 5 5600X because it's a grossly imbalanced matchup.

 

[Synthwave]

even older games... i dont see what would run a whopping 480 fps.

i mean even on a good computer CS 1.6 with a 5950x+3090 gets 1400-1500fps, but you need servers with unlocked fps because over 1000 it just bugs out.

and cs 1.6 is not old... its old AS FUCK

even with my 5600x+6800xt some older games don't go super high in fps.

like i replayed Dragon Age origins a few weeks ago which is a 2009 game, and i had what ... 160-180fps ? using Rashade with raytracing i had 60fps, same-ish for Mass Effect.

in reality you have very little games capable or reaching that much fps in game even with the best hardware available 20 years later.

QuakeWorld (most people play it with fixated 500 or 1000 fps), classic Doom, Doom 2016, Doom Eternal, Half-Life 2, Portal 2 and Minecraft comes to mind. There are also CoD: Warzone, Rainbow Six Siege, CS: GO, Valorant and Fornite AFAIK, but I don't play these, so can't confirm first hand.