NVIDIA GH100 GPU, The Next-Gen Flagship Data Center Chip, To Measure Around 1000mm2
Currently, the biggest GPU under production is the NVIDIA Ampere GA100 which measures 826 mm2. If the rumor is correct, then NVIDIA’s Hopper GH100 will go on to become the largest GPU design ever conceived, measuring around 1000mm2, easily topping the current monster GPUs by at least 100mm2. But that’s not all, the die size in question is for a singular GH100 GPU die and we have heard rumors that Hopper will be NVIDIA’s first MCM chip design so considering that we get at least two Hopper GH100 GPUs on the same interposer, the dies alone would measure 2000mm2. All of this means that the interposer would be vastly bigger than what we have seen yet, considering it will pack several HBM2e stacks and other connectivity on board. However, Greymon55 has stated that it is not the GH100 that will feature an MCM but another chip, the GH102. So this means that GH100 is likely to remain a monolithic design but Hopper will feature MCM parts.
— kopite7kimi (@kopite7kimi) January 29, 2022
— Greymon55 (@greymon55) January 29, 2022
— Greymon55 (@greymon55) January 29, 2022
NVIDIA Hopper GPU - Everything We Know So Far
From previous information, we know that NVIDIA’s GH100 accelerator would be based on TSMC’s 5nm process node. Hopper is supposed to have two next-gen GPU modules so we are looking at 288 SM units in total. We can’t give a rundown on the core count yet since we don’t know the number of cores featured in each SMs but if it’s going to stick to 64 cores per SM, then we get 18,432 cores which are 2.25x more than the full GA100 GPU configuration. NVIDIA could also leverage more FP64, FP16 & Tensor cores within its Hopper GPU which would drive up performance immensely. And that’s going to be a necessity to rival Intel’s Ponte Vecchio which is expected to feature 1:1 FP64. It is likely that the final configuration will come with 134 of the 144 SM units enabled on each GPU module and as such, we are likely looking at a single GH100 die in action. But it is unlikely that NVIDIA would reach the same FP32 or FP64 Flops as MI200’s without using GPU Sparsity. But NVIDIA may likely have a secret weapon in their sleeves and that would be the COPA-based GPU implementation of Hopper. NVIDIA talks about two Domain-Specialized COPA-GPUs based on next-generation architecture, one for HPC and one for DL segment. The HPC variant features a very standard approach which consists of an MCM GPU design and the respective HBM/MC+HBM (IO) chiplets but the DL variant is where things start to get interesting. The DL variant houses a huge cache on an entirely separate die that is interconnected with the GPU modules. Various variants have been outlined with up to 960 / 1920 MB of LLC (Last-Level-Cache), HBM2e DRAM capacities of up to 233 GB, and bandwidth of up to 6.3 TB/s. These are all theoretical but given that NVIDIA has discussed them now, we may likely see a Hopper variant with such a design during the full unveil at GTC 2022.
NVIDIA Hopper GH100 ‘Official Specs’:
