These nascent inference chip efforts are reminding me of the early 3dfx / riva / mach / powervr days. Will be interesting to see if inference chips are here to stay and, if so, who the eventual dominant player(s) will be

▲ ehnto 4 hours ago | parent | next [-]

Which in turn reminds me of Soundblaster audio cards! I suspect inference chips are closer to the GPU story than the Soundblaster story though.

I remember one soundblaster card I bought came with a Lara Croft demo, that exploited the incredible immersion of real time dynamic reverb.

Genuinely I think game audio took a few steps back from that heady era, the innovation in audio likely didn't sell as many cards as graphics innovations did.

	▲	bayindirh 4 hours ago \| parent \| next [-]
		EAX was very powerful in its heyday, but it has died because of a thousand cuts. First we had to have the audio processor. Good EAX was available on top of the line cards, and they were not always cheap. Lower end chips got less features. Then we had to have the speaker setup to have the greatest sound, or needed to get a real 5.1 headphones, which were bulky and never provided the same fidelity. Then Microsoft changed the Windows driver model, cutting the driver's direct access to the card. All of the timing sensitive effects were gone in an instant. I remember installing the new drivers and getting literally nothing. Sound Blaster was the only card with an hardware mixer, and Microsoft didn't feel like enabling them. Mixing at the DirectX layer killed the cards. Soundblaster's very closed stance didn't help them either. None of the cards after Audigy2 worked with Linux when I had my desktop system. After my Audigy2ZS, I moved to Asus Xonar D2X. Its positional audio capabilities were nice, but I mostly bought it for its Linux support and sound quality, and that was top notch in that regards. Then sound cards became commodity. Everybody stopped making good cards. Musicians moved to audio interfaces, audiophiles moved to DACs. Just looked to the SoundBlaster website. Internal cards are very limited. One DAC, one DTS enabled 7.1 sound card for PC cinema systems, three game oriented lower end cards, nothing else.
	▲	noir_lord 4 hours ago \| parent \| prev [-]
		On board got "good enough" and the separate cards died away. In fairness on board (depending on the board but on the whole) is pretty good.

▲ wmf 3 hours ago | parent | prev | next [-]

Every company is designing their own chips so the dominant players will be one level down: Broadcom, TSMC, Hynix/Samsung/Micron, etc.

▲ thimabi 3 hours ago | parent | prev | next [-]

> Will be interesting to see if inference chips are here to stay

To me, the efficiency gains of inference chips are so significant that they are certainly here to stay — barring a revolution of sorts that leads to a world devoid of AI as we know it.

▲ ignoramous 3 hours ago | parent | prev [-]

> who the eventual dominant player(s) will be

This couldn't have been easy. The team at OpenAI has worked a miracle.

  For example, Meta and Microsoft’s AI ASIC programs not getting off the ground despite being at it for much longer shows that cost is only one part of the equation.

	▲	rustystump 3 hours ago \| parent [-]
		I bet cost is of no issue with the capx where it is at. It is almost certainly organizational. Meta throws money at every problem and it never seems to workout for them.