Given that their GPU is 100mm2 smaller than 3080 it's a very good result.
I took a look at RDNA whitepaper and seems that everything is the same or larger, so there should be even more than 45MB of SRAM, but when I...
I don't know how you came up with this. The largest cache on Navi 10 is L2 and it's just 4MB.
That's for sure will turn out great when one will wish 5700 for Christmas.
Duh, that's why I have B550 mobo next to me :)
That's right, but 5600 was an outlier. I don't think they ever cut down any GCN chip that much. Probably something related with yields on N7.
I would prefer something between, like 64CUs. Unless Big Navi would be cheap, then no problem, I can take that.
3080 has some ML features disabled, at least that's what I read on dev forums. For some people it's worth it.
Big companies usually produce a lot of patents, many of them are never implemented in anything.
Depends on the context. HBM is mainly used there is a need for, well, high bandwidth.
There was of course that Intel-AMD processor and Navi 12...
Maybe Ryzen was postponed, but not Epyc?
Are there any Navi 10 die shot? HBM2 controller would be visible if it's the same chip and not Navi 12.
Edit: oh, nevermind
After seeing 128-bit bus I didn't ever think it is. I wonder why they pushed this one into the driver before Big Navi.
I haven't even notice it.
#define ASICREV_IS_VEGA10_M(r) ASICREV_IS(r, VEGA10)
#define ASICREV_IS_VEGA10_P(r) ASICREV_IS(r,...
Yeah, that's my conclusion as well. I guess 20 was too much for Navi, so they've shrank it to shave off some transistors.
Another interesting bit.
m_settings.supportRbPlus = 1;...
I CTRL-Fed the RDNA whitepaper.
The offer on their official websites is not exactly the same as the offer they can present to big clients like AMD and Nvidia.
More suspicious is...
I don't buy the rumour, but if any vendor could deliver faster memory technology at reasonable price, AMD and Nvidia would use it as soon as possible.
People with uncommon names (well, uncommon where they currently live) sometimes goes with more familiar name. When I was working with Koreans some...
Maybe he adapted a more familiar name?
TDP is roughly correlated with a market segment. In theory they could release Oland GPU at 300W, but their target isn't interested in so power...
Intel offers 4S config, but it's pretty rare, so the number shouldn't be much lower.
I recently did some math and got number like 20-30% over 2080Ti.
20 years ago it wasn't uncommon to build a cpu in just 3 years (P6, Conroe, K8). With Zen they started in 2012 and released it 5 years...
He said "right in line with what you would expect from an entirely new architecture."
These names mean something. Zen was introduced in 2017, I...
It's still Zen. We can expect something entirely new after Zen 5.
It's quite muddy wording. "felt better". I don't think in last 20 years IPC improvement ever broke 20% for same microarch family.
To reach 5PTFLOPS it needs a bit more than 128SM. Or really high clocks.
Aside from technical things the whole thing looks too predictable. There's nothing much surprising. AMD has HBCC? What if Nvidia had similar...
That sounds weird. I'm not saying it's impossible, but I can't see how this would work. Especially because tensor cores are quite far from a...
As far as I understand RTX core is a kind of specialized unit like for example FPU. It's used as a part of ray tracing shaders coupled with plain...
Well, TMU is in the CU as well.
Per thread ban seems like a good idea. But applied but a mod, anything automatic could abused by silent majority.
I don't think AMD would disclose their roadmap with Sony if they don't use their off-the-shelf products. Sounds like he makes some guessing.
Quite a bad demo. Looks like they wanted to show off with all these reflections.
My personal contender is Gris. Incredibly easy, beautiful visuals, very well paced learning curve.
Took me 3 hours to beat the game and there was...