• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Legendary GPU architect Raja Koduri's new startup leverages RISC-V and targets CUDA workloads — Oxmiq Labs supports running Python-based CUDA applicat

erek

erek

Fully [H]
2FA
Joined
Dec 19, 2005
Messages
17,421
""We may be the first new GPU startup in Silicon Valley in 25+ years," wrote Koduri in an X post. "GPUs are not easy."

However, it should be noted that Oxmiq is not building a consumer GPU like AMD Radeon or Nvidia GeForce. In fact, it does not develop all the IP blocks necessary to build a GPU, unlike Arm or Imagination Technology: it does not support full consumer graphics features out-of-the-box (such as texture units, render back ends, display pipeline, ray tracing hardware, DisplayPort or HDMI outputs), so Oxmiq licensees must implement them in silicon themselves, if they plan to build a GPU.

Asset low strategy​

Oxmiq has secured $20 million in seed funding from major tech investors, including mobile and custom AI silicon developer MediaTek, and has already recorded its first software revenue. By focusing on IP licensing instead of costly chip production or even actual silicon implementation, the company maintains high capital efficiency without relying on expensive EDA tools or tape-outs.

"Oxmiq has an impressive bold vision and world-class team," said Lawrence Loh, SVP of MediaTek. "The company's GPU IP and software innovations will drive a new era of compute flexibility across devices, from mobile to automotive to AI on the edge.""

Source: https://www.tomshardware.com/tech-i...pplications-unmodified-on-non-nvidia-hardware
 
Legendary? Nah.

He is just a good salesman, and his product is himself.

He wasted so much of AMD's time and money and then went on to do the same at Intel.

He ain't no "Jim Keller of GPU's" that's for sure.
 
Zarathustra[H] said:
He wasted so much of AMD's time and money
Click to expand...
He's been gone from AMD for quite some time now, and AMD has proven that their GPUs are still Nvidia-lite by every metric. At this point, I'm willing to assume he wasn't the actual problem with AMD's GPU business.
 
Last edited:
I'm so glad this thread didn't die. I wanted so badly to speak about his legacy but didn't want to be the first to throw shade.

Software focused hardware company? What could go wrong?
 
In all fairness…

Nvidia has a RISC-V processor built into every chip it makes.

That chip runs a virtual machine that does the PTX to assembly translation for that specific chip.

That PTX virtual machine interface being ubiquitous across the hardware stack is what makes CUDA work.

AMD hasn’t even started on their version of this tech and Intel is about 1/3’rd of the way to making it work.

If someone else were to build the framework for one and opensource the front end, it would be the first steps towards a proper opensource alternative to CUDA.

Then it would be on the company who integrates to map the back end functionality to the needed hardware assembly code.

But this will take a miracle to get anywhere with AMD and Intel as it potentially shackles them to a 3’rd party that they don’t currently need.
 
You must log in or register to reply here.
Back
Top