Speculation and Rumors: Nvidia Blackwell ...

[trinibwoy]

What you mean by mistake? Take a look at the timeline. By the point NVIDIA sold/licensed GDeflate to Microsoft, they had already the hardware decompression unit ready. "Hardware accelerated JPEG decompression" in Hopper rings a bell? They had deflate support, 2 years ago.

Well Nvidia talked about hardware LZ and deflate decompression at GTC 2021. Direct Storage came out in 2022. Not seeing any real opportunity to bamboozle the competition here.

Btw, are deflate and gdeflate interchangeable? How exactly does a hardware deflate decompressor help with DS gdeflate?

 

[Ext3h]

Btw, are deflate and gdeflate interchangeable? How exactly does a hardware deflate decompressor help with DS gdeflate?

Not bitstream compatible, but only a couple of bit shuffles and extra padding bits away from being. Also more constrained.

If you have a hardware deflate decompressor, is trivial to extend it for GDeflate. But it does require to patch the frontend.

Same as LZ4 is mostly just Deflate with a different frontend extension that directly skips Huffman decoding.

Still the same though - even though it's 99% the same logic blocks, it's still an incompatible bitstream unless you were prepared.

 

[pjbliverpool]

Not bitstream compatible, but only a couple of bit shuffles and extra padding bits away from being. Also more constrained.

If you have a hardware deflate decompressor, is trivial to extend it for GDeflate. But it does require to patch the frontend.

Same as LZ4 is mostly just Deflate with a different frontend extension that directly skips Huffman decoding.

Still the same though - even though it's 99% the same logic blocks, it's still an incompatible bitstream unless you were prepared.

So are you suggesting that the hardware decompressor in Blackwell will be capable of decompressing both GDeflate and LZ4? And so devs can choose to use either format, both of which will be handled by dedicated hardware in Blackwell, but by either CPU or GPU compute (depending on format used) on all other GPU architectures?

And that the max decompression rate of the unit is presumably PCIe5 16x, so 64GB/s?

 

[Ext3h]

So are you suggesting that the hardware decompressor in Blackwell will be capable of decompressing both GDeflate and LZ4?

That would be my expectation, yes. If there is any hardware, all 3 formats are supported.

And that the max decompression rate of the unit is presumably PCIe5 16x, so 64GB/s?

Uncertain about that, not on consumer grade silicon. 64GB/s would be over engineered for several more SSD generations. But I do expect that non-consumer silicon does achieve that data rate, and be it only for multiple streams.

 

[SlmDnk]

NVIDIA Partners Expect Q4 for GeForce RTX 5090 and RTX 5080 Graphics Cards

NVIDIA is reportedly targeting the fourth quarter for the release of its upcoming RTX 50 series GPUs, following the introduction of its Blackwell GPU for data centers.

www.guru3d.com

 

[Albuquerque]

Ugh.

Already time to upgrade the folding rig?!?

 

[del42sa]

https://wccftech.com/jim-keller-cri...on-rnd-cost-says-achievable-in-1-billion-usd/

Jim Keller Criticizes NVIDIA’s Blackwell’s $10 Billion R&D Cost, Says It Could’ve Been Achievable In $1 Billion​

 

[Seanspeed]

I have no doubt the $10b claim is an exaggeration or misleading to some decent degree. It's not actually bad PR for them to talk about the immense amount of money they can spend on something when they're the leaders. It makes them look super healthy and impossible to compete with.

 

[troyan]

https://wccftech.com/jim-keller-cri...on-rnd-cost-says-achievable-in-1-billion-usd/

Jim Keller Criticizes NVIDIA’s Blackwell’s $10 Billion R&D Cost, Says It Could’ve Been Achievable In $1 Billion​

So why hasnt it done by some else? And does he know that NVLink 5 has 1.8 TB/s bandwidth?!

 

[DavidGraham]

This was a joke by Jim Keller, nothing more.

 

[DegustatoR]

Maybe not a joke but him doing his own PR off that.

 

[troyan]

This was a joke by Jim Keller, nothing more.

What was the joke? nVidia is doing this "joke" since Volta with NVLink...

 

[pharma]

NVIDIA GeForce RTX 5080 GPUs To Launch First, RTX 5090 Follows Soon After In Q4 2024

NVIDIA's GeForce RTX 50 "Blackwell" GPU family should kick off with the RTX 5080 graphics card first & followed by the flagship RTX 5090.

wccftech.com

According to Kopite7kimi the RTX 5080 release should preceed the RTX 5090.

The NVIDIA GeForce RTX 50 "Blackwell" GPU family is expected to launch in Q4 2024 and will first include two products, the GeForce RTX 5090 & the GeForce RTX 5080. With the "Ada Lovelace" RTX 40 lineup, we saw NVIDIA introduce the GeForce RTX 4090 first followed by the RTX 4080. Both top-tier cards launched a month apart from each other but this time, it looks like NVIDIA has decided to launch the "80" model first.

https://twitter.com/i/web/status/1787645742510993853

 

[trinibwoy]

It’s 100% not ture. I would put money on that.

 

[arandomguy]

Just throwing out some possiblilties here.

RTX 2080 ended up having availablity one week earlier than RTX 2080ti.

RTX 5090 if being the dual MCM design might be reserved for Pro Viz and FE with AiB availability later (or at all) due to various factors and considerations.

Especialy if RTX 5090 does end up having >24GB via a larger bus size they're going to want to heavily control how they product segment that as a feature.

I've thrown this theory out before but I have a feeling 5xxx/Ada will sell on features and other factors initially and this may be the trend going forward with $/performance being relegated to mid-gen.

 

[trinibwoy]

RTX 5090 if being the dual MCM design might be reserved for Pro Viz and FE with AiB availability later (or at all) due to various factors and considerations.

You think there’s a chance Nvidia will waste precious CoWoS capacity on a lowly 5090? Seems unlikely especially if there’s no competition in the high end.