Earlier quoted context omitted.
[flagged]
Stop trolling and throwing around wild accusations. Here are your words: >You need big companies with scale that pay huge wages as those mean a lot more tax revenue. Now provide proofs that we need some big corps dodging taxes, including FAANG, and not more small and middle-sized business.
AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
171–180 of 273 posts
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#172Earlier quoted context omitted.
Isn't SXM5 higher bandwidth? It's 900 GB/s of bidirectional bandwidth per GPU across 18 NVLink 4 channels. The NVL's are on PCIe 5, and even w/ NVLink only get to 600 GB/s of bandwidth across 3 NVLink bridges (across only pairs of cards)? I haven't done a head to head and I suppose it depends on whether tensor parallelism actually scales linearly or not, but my understanding is since the NVL's are just PCIe/NVLink pa…
> but I think it's one that's mostly about Nvidia's platform dominance and profit margins more Profit margins and dominance are result from performance, not the other way around. It does not matter if Nvidia tools are better when you deploy large number of chips for inference and it does more flops per watt or second. It's seller market and if AMD can't ask high price, their chip do not perform. ---- Question: People…
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#173Earlier quoted context omitted.
[flagged]
Even if a company doesn’t pay taxes, its masses of highly paid workers do. Each of those SWEs making $300k+ are paying more in taxes than the entire earnings of the average EU dev.
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#174Earlier quoted context omitted.
World Bank: European Union gdp per capita for 2022 was $37,433, a 3.33% decline from 2021. U.S. gdp per capita for 2022 was $76,330, a 8.7% increase from 2021. It's not even close?
GDP per capita as a stand alone metric doesn't mean much.
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#175Earlier quoted context omitted.
Except you do have 26 different rules. It's a single market on paper as the eu only mandates a small subset of common rules and regulations such as removing tarrifs or freedom of movement, but have you ever tried in practice to launch your company from Belgium to France or from Netherlands to Belgium or from Austria to Germany, or from Romania to Italy? It's much more difficult when the rubber hits the road as every…
Europe is a single market with regards to imports and exports, and that's what matters most for a business. Low wages more than compensate for regulatory annoyances. No shortage of subsidies either. California has more burdensome regulations and higher taxes than other states and yet it's home to silicon valley.
We're talking about scaling internal companies across EU, not about imports and exports. And scaling local start-up across the EU is a regulatory and legal nightmare for small companies.
Shipping and selling imports and exports of commodities are a solved problem for decades, but scaling a on-line notary service for instance, that works both in Germany and in Italy, isn't. The EU doesn't help much with that as they only say you should have no tariffs between each other, not that you shouldn't have various legal, cultural and bureaucratic protectionism idiosyncrasies in place. The EU won't and can't force countries to improve that to make doing business easier for cross-country start-ups.
EU countries have a lot more roadblocks between each others than US states do when ti comes to scaling businesses.
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#176Earlier quoted context omitted.
Can you explain the cuda-less stack a little more or provide a source?
some people emit llvm ir (maaaaybe ptx) directly instead of using the C/C++ frontend to CUDA. that's absolutely the only optional part of the stack and also basically the most trivial (i.e., it's not the frontend that's hard but the target codegen).
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#177Earlier quoted context omitted.
The DAX is only 40 companies, most of which make real products rather than advertising mechanisms. Making real physical things just doesn't scale, and never will. While I would enjoy a US tech salary, I'm not sure we want a world where all manufacturing is set aside to focus on the attention economy. Nvidia value deserves to be much higher than any company on the DAX (maybe all of them together, as it currently is) -…
> but how much of that current value is real rather than an AI speculation bubble? I mean, by definition given that it trades freely their market cap is real. Your market cap today is what the market thinks your future cash flows are worth. The bubble and the bubble popping should in theory both be priced into Nvidia's market cap. What isnt' is events the market doesn't anticipate, AMD coming out with a current gener…
This is a bit of a tired viewpoint, and is evidently proven not true time after time. The collective despair/euphoria of market participants is extremely powerful and well documented, at least as far back as dutch tulips.
Stock valuations are relative, and they are relatively misvalued most of the time. That's why there are (albeit rare) funds that are capable of outperforming the market for decades - Berkshire, and Medallion for example.
It's certainly possible that AMD is valued (almost) fairly. It's just as likely that it's relatively misvalued for no reason other than emotions (lack of hype).
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#178Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#179Earlier quoted context omitted.
The salt is in the plain sight. The do the standard AMD comparison: 8x AMD MI300X (192GB, 750W) GPU 8x H100 SXM5 (80GB, 700W) GPU The fair comparison would be against 8x H100 NVL (188GB, Price tells a story. If AMD performance would be in par with Nvidia they would not sell their cards for 1/4 price.
AMDs deep learning libraries are very bad the last time I checked, nobody uses amd in that space for that reason. Nvidia has a quazi monopoly, that's the main reason for the price difference IMHO.
Re: AMD's MI300X Outperforms Nvidia's H100 for LLM Inference
#180Earlier quoted context omitted.
.... while all of the content is hosted on Linux servers, and you're listening to music through a Swedish app. That is running on silicone made in Taiwan. Using equipment that can currently only be manufactured in Belgium and Germany. On a Mac you are using a British instruction set. Also in terms of tech innovation: What part of the US-based tech innovation couldn't have been (and actually were) achieved with open-s…
>EU per Capita GDP in 2022 is the same as USA 2016. Was the USA in 2016 struggling but now isn't? Absolutely the US would be struggling if the GDP was still 2016 values with today’s costs.
So it boggles my mind that your parent tried to make a point by equating USA 2016 with EU 2022 GDP/capita as if nothing's wrong with that. Are some people that oblivious?