Those are some sketchy bar charts. If the bar doesn't start at y=0, it's meaningless and just a colorful blob on your slide.
This looks like a really stupid benchmark, no? 4 million cells in a standard aerodynamic simulation isn't enough work to even saturate the host CPUs on these systems, never mind the GPUs which have far "worse" roofline models from a CFD algorithm point of view.
I would not be surprised at all if these benchmarks ran faster if you removed the GPUs completely.
That's the smallest of 4 experiments. It goes upto 140 million cells, where MI300X retains similar performance advantage of around 10% over Nvidia's H100.
Now if only I could purchase one*
*I realize enterprise “GPUs” are difficult to purchase as an individual whether they’re AMD or Nvidia, but AMD might be well-served to mimic their RX 480 strategy (“make a competitive mid-range GPU, distribute it through several board partners, and sell it at rock-bottom prices to get it to as many customers as possible”). If there’s a compelling reason to use AMD hardware over Nvidia, the software support will come. As an extreme example, if one could purchase an MI300X for $50 a pop, surely FAANG and others would invest time and effort into the software side to leverage the cost savings vs Nvidia, who is unquestionably price-gouging due to their monopolistic hold on the enterprise GPU market.
It seems AMD has to choose between monetizing the GPUs right now by selling them at the maximum effective price, or forgoing that gain and selling the GPUs at cost and increasing GPU market share in the future. The choice between short-term gain and long-term gain.
And the splitting into CDNA and RDNA comes from the same direction: market segmentation, to allow much higher prices for the CDNA data-center GPUs, while keeping the gamer-focused RDNA GPUs affordable for mere mortals. Of coures this backfires by making the powerful GPUs not available for mostly anybody anymore to experiment on.
For example this blog post, about how great MI300X is. Really, what do I care -- I'm not a billionaire.
> And the splitting into CDNA and RDNA comes from the same direction: market segmentation
Not really.
Wave64 on CDNA is provably more throughput. But with most video game code written for NVidia's Wave32, RDNA being reworked to be more NVidia-like and Wave32 is how you reach better practical video game performance.
HPC will prefer the wider execute, 64-bit execution, and other benefits.
Video Gamers will prefer massive amounts of 32MB+ of "Infinity cache", which is used in practice for all kinds of screen-space calculations. But this would NEVER be used for fluid dynamics.
They’re unifying the architectures. AMD will move to UDNA for both gaming and data center. The next graphics cards after RDNA4 will be UDNA. Makes sense given how ML-heavy graphics has become.
The point is they shouldn't have done it in the first place. It was obvious right from the start it's a bad idea, except maybe for temporarily boosting short term profits.
The whole AMD AI/ML strategy feels like this - prioritize short term profits and completely shoot themselves in the foot in the long term.
ROCm was clearly designed with Wave64 in mind. It was going to take years for ROCm to be reworked for Wave32 of RDNA.
DirectX shaders however were already ready for Wave32, and other architectural changes that RDNA had. In fact, RDNA was basically AMD changing their architecture to be more "NVidia-like" on many regards (32-wide execute being the most noticeable).
CDNA existed because HPC has $Billion+ contracts with code written for Wave64 and still needing ROCm support. That means staying on the older GCN-like architecture and continuing to support say, DPP instructions or other obscure features of GCN.
---------
Remember how long it took for RDNA to get ROCm support? Did you want to screw the HPC customers for that whole time?
Splitting the two architectures, focusing ROCm on HPC (where the money was in 2018 for GPU Compute research dollars), and focusing on better video game performance for RDNA (where money is for video game / consumer cards) just makes sense.
>The whole AMD AI/ML strategy feels like this - prioritize short term profits and completely shoot themselves in the foot in the long term.
That's what the stock market rewards.
You mean hard in regards of pricing? Because otherwise it’s not really hard to buy enterprise gpus at all.
Nope ... IMO AMD cannot compete on software with nvidia. I bought an rx580 to test rocm/tensorflow ... Only for it to be a buggy mess that was discontinued for support in the next version.
AMD needs to invest a Fsck load of money in software... Until then they can have the greatest compute cards in the world.but it will.mean nothing
Isn't rx580 like 4 gens behind now? It was released in 2017. Probably not the right card for anything AI.
Why would anyone buy a new AMD card if the expectation is that the new one won't work either after support runs out? I use AMD at home and Nvidia A100s at work. There is no need to upgrade an old GPU to a new GPU if all it does is act as a fancy iGPU.
It's tangential, but this is the first time I've seen Fluent installed by simply decompressing a tar, instead of executing their big installer.
Our team has access to multiple systems that either have MI250Xs or H100s. Getting stuff to work with AMD/ROCm is substantially more effort than the NVIDIA/CUDA experience.
Some of this is lack of groundwork/engineering by packages or system administrators, but it seems a decent amount is the relative lack of effort by AMD to make things work well OOTB.
The real question is: is this from lack of effort or simply from NVidia's headstart? Will it get better?
> Will it get better?
It won't, not in any way that will make AMD approximately competitive with Nvidia.
AMD, unlike Nvidia, seems unable to prioritize developers. Here's a summary of last week's charlie-fox when the TinyGrad team attempted to get 2 MI300s for on-premises testing and was rebuffed by an AMD representative. https://x.com/dehypokriet/status/1879974587082912235
warning - no pretty videos in this post