News for hackers. Stuff that matters.
Re:Nvidia Unveils Blackwell, Its Next GPU by tgtweak on Wednesday March 20, 2024 @09:55AM (#39766568)
Highly doubt this was the initial idea for nvidia given they were graphics-only for a very long time. CUDA definitely felt like more of a value-add for the first 5-6 years than a concerted effort to build accelerators and to fund that with graphics demand. First "tesla" line of GPUs - which had very little compute-only focus - were in 2007.
Re:Nvidia Unveils Blackwell, Its Next GPU by ksec on Wednesday March 20, 2024 @10:09AM (#39766792)
>First "tesla" line of GPUs - which had very little compute-only focus - were in 2007.

CUDA was first released in ~2006 but started at least in 2004, largely building on top or the momentum of Cg which was released in 2002 and being worked on since 2000. There was at the time in the late 90s about general purpose parallel programming and how it could possible be done on GPUs or doing it on something like PS2 Cell.

I dont know if Nvidia was really started with CUDA in mind in 1993. But Nvidia was into CUDA like GPU usage WAY ahead of anyone else in the field.

Re:Nvidia Unveils Blackwell, Its Next GPU by cma on Wednesday March 20, 2024 @10:23AM (#39767000)
Cell was PS3 (2006)
Re:Nvidia Unveils Blackwell, Its Next GPU by gosub100 on Wednesday March 20, 2024 @10:56AM (#39767529)
Wasn't there a time when people were hacking shaders to do compute tasks and read the results back instead of displaying to the frame buffer?
Re:Nvidia Unveils Blackwell, Its Next GPU by p_l on Friday March 22, 2024 @05:02AM (#39788702)
Yes, multiple such attempts, including complete languages. Very thin hardware support as different GPUs varied very much on what could be done.

GeForce 8 introduced CUDA because graphics pipeline similarly evolved into position where instead of forcing the use of dedicated cores for specific tasks (vector and fragment shaders) due to simple economies of chip making, the Shader Model 4 introducing yet another stage justified making unified shader cores... which could be just as easily used for other tasks.