Recent content by Dangerman

Was the 2nd version more than 96SM one (116? 108? SMs was it)? And the 1st being the one in my ballpark w/ 96 SMs? I presume with 30% higher transistor density with Blackwell a 96SM GB203 would be slightly smaller than AD103 of amybe 350mm2.

True but if N4X is being used for GB202 there's probably not much difference anyways. And with 128MB L2 Cache & 512-bit bus there's probably not much die space saveable having it on N3E. Well I think it'll be like A100, something that looks like a proto-MCM die which Bryan tweeted about...

Considering there's apparently a 30% transistory density increase I do wonder; where does that put the 96SM rumoured GB203? Because if that is technically smaller than AD103 like maybe 350mm2 I do wonder if that means a 700mm2 GB202 which on N4P/X sounds way more economical than a 600mm2 N3E die.

They can refresh with B200 on 3nm anyways which is next year apparently.

I suppose how big the die will be. 512-bit bus with a 128MB L2 Cache sounds huge.

I think GB203 will be N3 but maybe GB205, 206 & 207 be N4/SF4X? Overall IDK what the SKUs will be because with a 512-bit bus GB202 I do wonder if they can harvest enough 320 bit and 384 bit dies to make 5080s & 5080 Tis with 20 & 24 GB of VRAM? Because I can't see the market acceting another...

Assuming GB202 is 512-bit bus I can see with 2GB Modules the following SKUs: Quadro GB202 - 64GB 5090 Ti (if they do that) - 32GB 5090 - 28GB. 5080 Ti - 24GB. 5080 - 20GB. I would see 5080 cards in this case using cheaper boards along with lower clock speeds than the 5090 ones. To help keep...

I can see assuming 512-bit bus for GB202 and do 448 bit bus for 28GB 5090 and then maybe a 32GB 5090 Ti. My big wonder is GB203 because 16GB won't cut it for an 80 class type card these days and same for 12-ish or so for a 70 class. Like I do wonder if Nvidia has multiple designs they are...

Well a full GB202 being 70% faster raster than a 4090. Defintely don't a full die 5090 Ti having 70+ percent faster raster than the canned 4090 Ti. Increase raster peformance, I get the impression Blackwell is kinda similar to Maxwell in some respects; focusing potentially on "real world"...

I mean Nvidia was planning a 142SM 2.95Ghz Boost 4090 Ti according to XpeaGPU on Twitter in reserve against AMD if the 7900 XTX could dethrone the 4090 even in raster. And Blackwell apparently as at least a doubling of ROPs per GPC and whatever architectural changes planned for Blackwell (I mean...

I mean AD102 is basically a "gaming chip" but used in the RTX 6000 which is used in workstations that involve work with AI (like that Nvidia RTX Workstations annouced last year). And on split in process node it means Nvidia can devote more GB100, 202 etc wafers with 3nm at TSMC which is limited...

Bump this thread because RedGamingTech has some GB20x (for RTX 50) rumours with specs listed: GB207 - 28SM, 96 bit, GDDR7, 3x GPC PCIe 5.0 x4. GB206 - 44SM, 128 bit, GDDR7, 3x GPC PCIe 5.0 x8. GB205 - 72SM, 192 bit, GDDR7, 3x GPC PCIe 5.0 x8. GB203 - 108SM, 256 bit, GDDR7, 3x GPC PCIe 5.0 x16...

I wonder if Nvidia will use 24 Gb modules so meaning they could in theory do a 30GB cut down 5090, full-fat 36GB 5090 Ti and a 72GB Quadro.

Everyone's favourite Nvidia Leaker/Liverpool Fan has spoken: 192 SMs, wonder what memory bit bus (if it's really 512-bit bus) and L2 Cache (64 or 128 if 512-bit bus?) GB202 will have? Would be nice if we get like a 190-192 SM RTX 5090 Ti or something.

With Geometry Acceleration for DLSS4 I do wonder how Blackwell will maybe improve DLSS Super-Resolution? Like DLSS Quality now gives you DLSS Performance levels of performance improvement? Or will Geometry Acceleration be the big thing?