Read on Twitter
2/ Nvidia announced A100 this morning and you can read about it from any number of outlets, e.g. https://www.nextplatform.com/2020/05/14/nvidia-unifies-ai-compute-with-ampere-gpu/
3/ Nvidia, as usual, have themselves published a great set of detailed blogs about the architecture and specs, really diving into the approaches they've taken and how they might impact workloads. https://devblogs.nvidia.com/nvidia-ampere-architecture-in-depth/
4/ There's a specific couple of lines in the overview that I think are worth talking about as an #HPC community. Here they are:
5/ A100's peak DP performance of 9.7 TF is a 30% uplift from V100's 7.5 TF, however this is coming at a socket-level power uplift of 33%. This is a 7nm chip versus V100's 12nm. So where did all the new capability go?
Specialization.
Specialization.
6/ A100 obviously has a ton of new interesting features (e.g. acceleration for structured sparsity, TF32) that are focused on delivering boosts to common data and compute patterns. The one I want to call out here is the expansion of the "Tensor Core" all the way to FP64.
7/ The new DP Tensor Core uses a "DMMA" operation to multiply two 2x4 FP64 matrix panels in a single instruction. Using this enhanced throughput, they produce a second performance number: 19.5 TF
Nvidia's math libraries will make use of this heavily. https://blogs.nvidia.com/blog/2020/05/14/double-precision-tensor-cores/
Nvidia's math libraries will make use of this heavily. https://blogs.nvidia.com/blog/2020/05/14/double-precision-tensor-cores/
8/ Those familiar with microarchitecture will understand that this is a far more efficient way to do a matrix calculation than individual FMAs - you skip all the control flow of instruction issue while also avoiding the need for register writes/reads of all the intermediate sums.
9/ What is more impactful to things like #Top500 is that this DMMA acceleration works for HPL, but does narrow (further) the application space that can take advantage of that level of FLOPS. It's not something that can be captured currently in the #Top500 metrics.
10/ This is the nature of "late-Moore" specialization: resources are applied to subsets of workloads (in this case, dense matrix math) to accelerate them, while having limited value to others.
11/ It is important for #HPC - as a community - to be more detail-oriented and to keep track of what is being accelerated and what is being left behind as we move into more of this specialization. We really need a broader set of metrics and benchmarks to do that.
12/ P.S. a lot of people have leapt to thinking about "whole-chip" specialization in this era. A100 (and Intel x86 extensions, and SVE...) shows there's still a ton of room for applying specialization within existing cores and architectures in a way that makes adoption easy.
13/ P.P.S. congrats to Nvidia on launching another fascinating chip - and more importantly committing to doing the software lifting to make it useful for real #HPC and #AI workloads.
