NVIDIA DGX A100: powered by up to 16x next-gen Ampere GA100 GPUs

NVIDIA most likely would've unveiled its Ampere GPU architecture and this new DGX A100 system at its GPU Technology Conference (GTC) in March, but it was canceled over the COVID-19 coronavirus outbreak. We are now told to GET AMPED for a GTC 2020 keynote presentation from NVIDIA founder and CEO Jensen Huang on May 14, at 6AM PST.

Still, we're now being teased with the new Ampere-based DGX A100 system that packs Ampere GPUs that, right now -- we don't know much about but can expect them to be monsters. A new entry has popped up in the Justia trademark database, with NVIDIA filing an application for the DGX A100 trademark.

The first DGX systems were named DGX-1 and DGX-2 but it seems that NVIDIA won't be naming the Ampere-based system DGX-3 but rather DGX A100. If this is true, we now have the GA100 teased -- the first GPU based on the new Ampere architecture.

We should expect somewhere betweewn 8 to 16x GA100s used on the DGX A100, since the DGX-2 packed a huge 16x Tesla V100 GPUs.

• Check these truly monsterous specs on NVIDIA's new GeForce RTX 3080 Ti, check that out here.
• Also, Intel's new "Father of All" GPUs that could BEAT the RTX 3080 Ti, read here.

(New) NVIDIA Ampere GA100 Specs

• 8192 CUDA cores @ 1750MHz boost
• 1024 Tensor Cores
• 256 RT Cores
• Unknown amount of GDDR6 @ 16Gbps
• Unknown TDP
• 7nm

More reading on NVIDIA Ampere:

NVIDIA Ampere GPUs

• GA102 - 84 SMs / 5376 CUDA cores / 12GB GDDR6 / 384-bit bus - 40% faster than RTX 2080 Ti
• GA103 - 60 SMs / 3840 CUDA cores / 10GB GDDR6 / 320-bit bus - 10% faster than RTX 2080 Ti
• GA104 - 48 SMs / 3072 CUDA cores / 8GB GDDR6 / 256-bit bus - 5% slower than RTX 2080 Ti

Older NVIDIA Ampere GA100 Specs

• 8192 CUDA cores @ 2GHz (2.2GHz boost)
• 1024 Tensor Cores
• 130 RT Cores
• 48GB of HBM2e memory @ 1.2GHz
• 300W TDP
• TSMC 7nm+
• 36 TFLOPs peak output

I've already written about rumors that NVIDIA's next-gen Ampere GPU architecture would be up to 75% faster than current-gen GPUs such as the Turing architecture, right after rumors that Ampere would offer 50% more performance at half the power of Turing. This is pretty crazy stuff right there.

Not only that, but we've got some rumored specs on the purported GeForce RTX 3080 and GeForce RTX 3070 graphics cards, which will both be powered by NVIDIA's new Ampere GPU architecture.

We've already heard that Ampere would offer 50% more performance at half the power of Turing, which sent the hairs on my neck standing up. Better yet, you can read about the leaked specs on the purported Ampere-based GeForce RTX 3080 and GeForce RTX 3070 right here.

GA103 (GeForce RTX 3080)

• 10/20GB GDDR6
• 320-bit memory interface
• 60 SMs
• 3480 CUDA cores

GA104 (GeForce RTX 3070)

• 8/16GB GDDR6
• 256-bit memory interface
• 48 SMs
• 3072 CUDA cores

AMD also just revealed its next-gen RDNA 2 / Navi 2X plans, something we referred to as Big Navi until just recently. Those specs are monstrous, but they pale in comparison to what NVIDIA has planned for its flagship HPC destined Ampere GA100 beast.

AMD RDNA 2 / Navi 2X / Big Navi Specs

• 7nm node (confirmed)
• RDNA 2 architecture (confirmed)
• 80 compute units
• 5120 stream processors
• 17.5 TFLOPs compute performance
• Hardware ray tracing support (confirmed)