AMD Claims Radeon RX 6500M is Faster Than Intel Arc A370M Graphics

[AleksandarK]

A few days ago, Intel announced its first official discrete graphics card efforts, designed for laptops. Called the Arc Alchemist lineup, Intel has designed these SKUs to provide entry-level to high-end options covering a wide range of use cases. Today, AMD has responded with a rather exciting Tweet made by the company's @Radeon Twitter account. The company compared Intel's Arc Alchemist A370M GPU with AMD's Radeon RX 6500M mobile SKUs in the post. These GPUs are made on TSMC's N6 node, feature 4 GB GDDR6 64-bit memory, 1024 FP32 cores, and have the same configurable TDP range of 35-50 Watts.

Below, you can see AMD's benchmarks of the following select games: Hitman 3, Total War Saga: Troy, F1 2021, Strange Brigade (High), and Final Fantasy XIV. The Radeon RX 6500M GPU manages to win in all of these games, thus explaining AMD's "FTW" hashtag on Twitter. Remember that these are vendor-supplied benchmarks runs, so we have to wait for some media results to surface.


View at TechPowerUp Main Site | Source

 

[usiname]

They could just use the igpu in 6800hx, it still will be faster

 

[AnotherReader]

The results look reasonable considering the 6500M should be 80% of a RX580. That is much faster than a 1050 Ti equivalent which is what the A370M is.

 

[Thimblewad]

I was quietly hoping Intel is going to bring something to the market and maybe there will be a third player, but no, hahahaha.
I was also expecting this to happen. Intel is ages behind in the GPU territory which was also apparent in their previous iGPU iterations.
Maybe they'll be able to do something with the compute performance, but game optimization is far, far away from adequate...

 

[ARF]

Intel is not a specialist in creating competitive graphics architectures. For decades, it has been specialising in creating low-end integrated graphics.
This is like pushing a biathlon athlete to compete in cross-country skiing, of course he won't win.

 

[Sabotaged_Enigma]

So what are all these many more transistors for? To produce more heat?

 

[ARF]

AMD has almost always dominated over Nvidia in the performance per die area / transistors count metrics.
It is not a surprise that Intel needs many more transistors for achieving a relative performance level.

 

[Deleted member 24505]

Even if ARC v1 is turd, Intel have billions of dollars to piss up the wall to perfect it, so it might be a joke now, but don't write them off.

 

[ThrashZone]

Hi,
It's cool when amd trolls intel

 

[ARF]

Hi,
It's cool when amd trolls intel

I think that the only thing that AMD wants is to sell its own products based on their quality and merits. Something that it has always had problems with, because we all know the anti-competitive measures practiced both by Intel (the mother of all programs) and Nvidia (GeForce partner program).

 

[zlobby]

Doh! Of course it will be slower. It's their first attempt at this segment and they can't just chanve things on the fly.

If top brass allows for it, many more billions will be poured into R&D and intel can finally produce something in the ballpark of 1050Ti!

 

[Recus]

based on their quality and merits

 

[lexluthermiester]

AMD Claims Radeon RX 6500M is Faster Than Intel Arc A370M Graphics​

Baseless claim until it's actually been tested/benchmarked.

 

[AnotherReader]

Baseless claim until it's actually been tested/benchmarked.

Technically true, but given Intel's own claims, and the characteristics of the GPU that the 6500M is derived from, this looks credible.

 

[usiname]

Baseless claim until it's actually been tested/benchmarked.

Keep dreaming for mircale, you are more likely to find Narnia in your closet than 370m to be faster than 6500m in gaming

 

[windwhirl]

Keep dreaming for mircale, you are more likely to find Narnia in your closet than 370m to be faster than 6500m in gaming

Well, then there's two of us now wanting some actual proof for either claim.

 

[LabRat 891]

AMD should've probably released the mobile part first. All the bad PR around the 6500XT desktop part isn't going to do this any favours.
The 6500XT does do surprisingly well for all its limitations. The mobile variant isn't much weaker, so it should perform pretty well, regardless of perception.

 

[usiname]

Well, then there's two of us now wanting some actual proof for either claim.

if you are so naive let's bet money.Someone enough brave?

 

[lexluthermiester]

Technically true, but given Intel's own claims, and the characteristics of the GPU that the 6500M is derived from, this looks credible.

To be fair, Intel's claim on IRIS graphics were very close to the actual performance numbers rendered. So they have at least some credibility. AMD has been a bit more fudgy with the numbers claims and that is down to just lackluster marketing.

The proof is in the pudding! Once the products are reviewed and benchmarked we will know the real deal.

Well, then there's two of us now wanting some actual proof for either claim.

Exactly!

 

[Dranzule]

To play devil's advocate, at least the A370M has a really big media engine(relative to the 6500M) as well as XMX to deal with. Both have RT implementations, so I thought that's not needed to add until we know better of how Intel's RT works.

 

[ModEl4]

It's not so bad!
In the worst case scenario desktop DG2-512 will have a little bit better 4K performance/TFlop ratio than VEGA 64 and the same will be true for desktop DG2-128 vs RX 470 regarding FHD/QHD performance/TFlop ratio.
Compared to Nvidia Ampere, desktop DG2-512 will have at MAX -5% 4K performance/TFlop vs RTX 3070 and DG2-128 will have better FHD performance/TFlop ratio vs RTX 3050 (DG2-256 would have been the same vs RTX 3050)
The above predictions are very specific and safe imo, they will not fail.
The performance issues are easily fixed with the correct pricing, they only have to avoid major (deal breaking) issues with their software/drivers and everything will be O.K.
EDIT: regarding transistor counts / performance ratios, yes it will be worse than RDNA2 but the design is more advanced and the ratio is influenced from the immature drivers that Intel will have (and don't forget that nearly all the market-developers optimizing their engines for RDNA2-consoles!

 

[RedBear]

To play devil's advocate, at least the A370M has a really big media engine(relative to the 6500M) as well as XMX to deal with. Both have RT implementations, so I thought that's not needed to add until we know better of how Intel's RT works.

Agreed, it's what I meant to reply to the question above what the transistors are there for.

To be honest, I thought this tweet was an April Fool initially, but I had missed the frame rate benchmarks at medium settings for those games that Intel has really released, I guess it's a serious thing, despite the kind of juvenile "FTW" hashtag.

 

[looniam]

needless to say:

To play devil's advocate, at least the A370M has a really big media engine(relative to the 6500M) as well as XMX to deal with. Both have RT implementations, so I thought that's not needed to add until we know better of how Intel's RT works.

huh, thats why amd pointed out the transistors. same shaders/ROPs/bit bandwidth and TDPs.
tbh, those graphs look like GCN's first six months compared to those never settle bundles. (hi raja!)

amd, i'm not impressed w/your marketing.

 

[Steevo]

needless to say:

View attachment 242086

huh, thats why amd pointed out the transistors. same shaders/ROPs/bit bandwidth and TDPs.
tbh, those graphs look like GCN's first six months compared to those never settle bundles. (hi raja!)

amd, i'm not impressed w/your marketing.

It’s undeniably true the 6500 is at least a little faster, has far fewer transistors, and being built on the same node clocks better.

I would bet Intel is/was betting on how well their architecture performed in compute to sell some GPUs, and sell a lot of mining and compute cards to build a Nvidia ecosystem. They may have succeeded.

 

[looniam]

It’s undeniably true the 6500 is at least a little faster, has far fewer transistors, and being built on the same node clocks better.

I would bet Intel is/was betting on how well their architecture performed in compute to sell some GPUs, and sell a lot of mining and compute cards to build a Nvidia ecosystem. They may have succeeded.

compare die sizes 157mm^2 vs 107mm^2 and media engines (features!), the transistor discrepancy is a wash, imo. not to mention intel hasn't given gaming speeds, just base.

still, i would expect amd to have a lead in games just from drivers - and that will continue until it changes.