NVIDIA Teases Ampere GPU Powered DGX A100 Supercomputing System Ahead of GTC 2020, Calls It The Worlds Largest Graphics Card!
NVIDIA has posted a teaser of its next-generation Ampere GPU powered DGX A100 system which is expected to be announced at GTC 2020 on 14th May 2020. The first references to the system were spotted just a week ago but it looks like we are definitely getting a major HPC announcement from NVIDIA this week.
NVIDIA's CEO, Jensen Huang, Teases Next-Generation Ampere GPU Powered DGX A100 System For HPC
The specific name for the DGX system is DGX A100 which has a lot to say. The DGX system is solely designed for the deep learning and HPC community, offering supercomputing capabilities inside a workstation form factor. NVIDIA has released DGX solutions based on its Pascal and Volta GPUs but with the release of Ampere GPU imminent, a new DGX solution has to be designed.
In the teaser video which can be seen below, NVIDIA's CEO, Jensen Huang, can be seen taking out a huge DGX A100 mainboard fresh out of the oven. The video titled 'What's Jensen been cooking' is followed by the description 'The World's largest graphics card, fresh out of the oven".
The Volta line of DGX systems was streamlined to offer more options to HPC users. We saw several variants ranging from the DGX Station which featured a total of four Tesla V100 GPUs all the way to the 16 Tesla V100 housing DGX-2 monster which NVIDIA had termed as the "World's Largest GPU".
With Ampere GPU, NVIDIA would be releasing its latest DGX A100 system. The name makes it clear that the system would be based on the GA100 GPU. The GA100 GPU would be the biggest chip in the Ampere lineup and would definitely feature one of the flagship 128 SM configurations that we expect to see on an NVIDIA GA100 chip.
The specific DGX A100 mainboard that Jensen just cooked features a total of 8 Ampere GPUs and are outfitted with massive heatsinks. Do note that DGX A100 systems are designed for server/HPC environments and hence are passive cooled. There are six heatsinks adjacent to the GPUs which might be featuring interconnect switches for GPU-to-GPU & GPU-to-CPU communications. There's much to be revealed so I'd suggest we wait two more days for Jensen to reveal the goodies himself.
NVIDIA may start off its Ampere line of DGX systems in a more traditional manner, offering 8 Tesla GPU configurations in the beginning and moving on to the larger and denser parts later on as the yields get better for the new Ampere chips.
NVIDIA Tesla Graphics Cards Comparison
|Tesla Graphics Card Name||NVIDIA Tesla M2090||NVIDIA Tesla K40||NVIDIA Telsa K80||NVIDIA Tesla P100||NVIDIA Tesla V100||NVIDIA Tesla Next-Gen #1||NVIDIA Tesla Next-Gen #2||NVIDIA Tesla Next-Gen #3|
|GPU Name||GF110||GK110||GK210 x 2||GP100||GV100||GA100?||GA100?||GA100?|
|Transistor Count||3.00 Billion||7.08 Billion||7.08 Billion||15 Billion||21.1 Billion||TBD||TBD||TBD|
|CUDA Cores||512 CCs (16 CUs)||2880 CCs (15 CUs)||2496 CCs (13 CUs) x 2||3840 CCs||5120 CCs||6912 CCs||7552 CCs||7936 CCs|
|Core Clock||Up To 650 MHz||Up To 875 MHz||Up To 875 MHz||Up To 1480 MHz||Up To 1455 MHz||1.08 GHz (Preliminary)||1.11 GHz (Preliminary)||1.11 GHz (Preliminary)|
|FP32 Compute||1.33 TFLOPs||4.29 TFLOPs||8.74 TFLOPs||10.6 TFLOPs||15.0 TFLOPs||~15 TFLOPs (Preliminary)||~17 TFLOPs (Preliminary)||~18 TFLOPs (Preliminary)|
|FP64 Compute||0.66 TFLOPs||1.43 TFLOPs||2.91 TFLOPs||5.30 TFLOPs||7.50 TFLOPs||TBD||TBD||TBD|
|VRAM Size||6 GB||12 GB||12 GB x 2||16 GB||16 GB||48 GB||24 GB||32 GB|
|VRAM Bus||384-bit||384-bit||384-bit x 2||4096-bit||4096-bit||4096-bit?||3072-bit?||4096-bit?|
|VRAM Speed||3.7 GHz||6 GHz||5 GHz||737 MHz||878 MHz||1200 MHz||1200 MHz||1200 MHz|
|Memory Bandwidth||177.6 GB/s||288 GB/s||240 GB/s||720 GB/s||900 GB/s||1.2 TB/s?||1.2 TB/s?||1.2 TB/s?|
NVIDIA's Ampere GPUs are definitely going to shake things up in the HPC market with several variants already leaked and performance being rated at around 30 TFLOPs (FP32). We will keep you updated as more info comes prior to the 14th of May when NVIDIA will be presenting its next-gen GPU lineup.