CDNA 2 did not exist in 2020, too. Oak Ridge knew what nVidia will bring to the market. They have decided to go with a less advanced infrastructure.
NVidia Hopper Speculation, Rumours and Discussion
Yes, they knew, and they still chose what AMD and HPE had on offer. Not only would have NVLink delayed the project, it might not have been available at all without going full NVIDIA, which they clearly didn't want to do.
DavidGraham
Veteran
They rushed the super computer out the door, likely at a great discount from AMD, and the results speak for itself, A single H100 wipes the floor with several "MI250" that are only good for compute density but suffer from severe suboptimal performance at the card level (it's just two GPUs stitched together) and at the bigger scale, due to the slower interconnect .. almost nobody else is using MI250, while A100s and H100s are used left and right everywhere else.
Yeah, only three MI250X systems in Top10 at Top500 list. That's still one more than A100, no H100's in sight. NVIDIA does have couple GV100's there too though.
HPCG list is incomplete because it hasn't been run on all the systems, but still MI250X fits in top 3 spot.
as usual you provide regular bullshit.
Frontier Testing and Tuning Problems Downplayed by Oak Ridge - High-Performance Computing News Analysis | insideHPC
Everything about the Frontier supercomputer, the world’s first exascale system residing at Oak Ridge National Laboratory, is outsized: its power, its scale and the attention it draws. In HPC circles, the attention and talk have increasingly focused on performance problems as the lab gets the...
insidehpc.com
DavidGraham
Veteran
Nvidia coprocessors can be found in 154 of the TOPP500 supercomputers; only seven of the supercomputers are using AMD Instinct cards.
ISC ’22: The AMD-Intel-Nvidia HPC race heats up
At the International Supercomputer Conference, processor rivals AMD, Intel, and Nvidia talk up recent successes, future plans.
www.networkworld.com
Good PR. Just try to read between the lines though.Frontier Testing and Tuning Problems Downplayed by Oak Ridge - High-Performance Computing News Analysis | insideHPC
Everything about the Frontier supercomputer, the world’s first exascale system residing at Oak Ridge National Laboratory, is outsized: its power, its scale and the attention it draws. In HPC circles, the attention and talk have increasingly focused on performance problems as the lab gets the...
Why just link the article he submitted? They are definitely having HW failure issues every few hours and is something I doubt they anticipated when the system was planned.as usual you provide regular bullshit.
Frontier Testing and Tuning Problems Downplayed by Oak Ridge - High-Performance Computing News Analysis | insideHPC
Everything about the Frontier supercomputer, the world’s first exascale system residing at Oak Ridge National Laboratory, is outsized: its power, its scale and the attention it draws. In HPC circles, the attention and talk have increasingly focused on performance problems as the lab gets the...
All-AMD Powered & World's First Exascale Supercomputer, Frontier, Has Been Running Into Issues Ever Since It Powered On
The all AMD-powered & world's first exascale supercomputer, the ORNL Frontier, has been running into issue ever since it powered on.
wccftech.com
So now it turned from A100 and H100 to "Nvidia coprocessors" already?Nvidia coprocessors can be found in 154 of the TOPP500 supercomputers; only seven of the supercomputers are using AMD Instinct cards.
ISC ’22: The AMD-Intel-Nvidia HPC race heats up
At the International Supercomputer Conference, processor rivals AMD, Intel, and Nvidia talk up recent successes, future plans.
Might have bolded other part too, you know, the one he specifes that majority of issues aren't GPU related. Or that they'd have concerns about the AMD hardware part of the puzzle.
DavidGraham
Veteran
The original statement is almost no one is using MI250, there are only 7 machines using it, and two of them are DOE ones (and having major problems), vs dozens of NVIDIA V100, A100 and H100. Heck the announced H100 ones already outnumber MI250 despite being released 2 years ago.
Don't have to, it's already PR crap, the fact of the matter is, the machine is having trouble due to the GPUs and the Interconnect, they have already downgraded the original performance target by 40%, GPU/interconnect problems are responsible for that, as the bulk of the performance relies on them, then there are the constant failures every day, the interconnect plays a major part in this too.
Last edited:
Grace-Hopper Superchip Whitepaper: https://resources.nvidia.com/en-us-grace-cpu/nvidia-grace-hopper?ncid=so-twit-569967
NVIDIA Grace Hopper Superchip Architecture In-Depth | NVIDIA Technical Blog
The NVIDIA Grace Hopper Superchip Architecture is the first true heterogeneous accelerated platform for high-performance computing (HPC) and AI workloads. It accelerates applications with the…
developer.nvidia.com
I'm confused, what exactly is new in async copy interleaved with compute threads?Found this comparision interesting:
Shows how far ahead nVidia really is with their hardware. The problem today is not compute performance. That is cheap. But how to make use of it is the biggest obstactle.
So tl;dr (thoroughly, just quick browse read on (hopefully all) relevant parts) it's just better at it than before especially when Tensor Cores are used?
The difference would however suggest that it's "everything off vs everything on" instead of "everything last gen had vs everything hopper has" on the graph.
TMA is dedicated hw for address generation and mem copy operation.
NVIDIA H100 80GB PCIe Hands on CFD Simulation
We take the NVIDIA H100 80GB PCIe card for a spin with a FluidX3D CFD simulation tool to see how the new card performs
www.servethehome.com
The Green 500 should use HPCG metric or provide the separate list that uses HPCG metric like the Top 500.