News for hackers. Stuff that matters.
Re:The FPGA Turns 40! by checker659 on Monday June 23, 2025 @07:07PM (#44361123)
I think FPGAs (or CGRAs really) will make a comeback once LLMs can directly generate FPGA bitstreams.
Re:The FPGA Turns 40! by 15155 on Monday June 23, 2025 @07:32PM (#44361296)
What does "directly generate FPGA bitstreams" mean?

Placement and routing is an NP-Complete problem.

Re:The FPGA Turns 40! by duskwuff on Monday June 23, 2025 @08:06PM (#44361507)
And I certainly can't imagine how a language model would be of any use here, in a problem which doesn't involve language.
Re:The FPGA Turns 40! by 15155 on Monday June 23, 2025 @08:08PM (#44361522)
They are "okay" at generating RTL, but are likely never going to be able to generate actual bitstreams without some classical implementation flow in there.
Re:The FPGA Turns 40! by buildbot on Monday June 23, 2025 @09:00PM (#44361853)
I think in theory, given terabytes of bitstreams, you might be able to get an LLM to output valid designs. Excepting hardened IP blocks, a bitstream is literally a sequence of sram configuration bits to set the routing tables and LUTs. Given the right type of positional encoding I think you could maybe get simple designs working at a small scale.
Re:The FPGA Turns 40! by CamperBob2 on Monday June 23, 2025 @09:08PM (#44361898)
I'd expect a diffusion model to outperform autoregressive LLMs dramatically.
Re:The FPGA Turns 40! by buildbot on Tuesday June 24, 2025 @11:09PM (#44373333)
Certainly possible! Or perhaps a block diffusion+autoregressive model or something like GPT 4o's image gen.
Re:The FPGA Turns 40! by checker659 on Tuesday June 24, 2025 @09:05AM (#44365795)
AI could use EDA tools
Re:The FPGA Turns 40! by throwawayabcdef on Monday June 23, 2025 @11:01PM (#44362525)
No need. I gave ChatGPT this prompt: "Write a data mover in Xilinx HLS with Vitis flow that takes in a stream of bytes, swaps pairs of bytes, then streams the bytes out"

And it did a good job. The code it made probably works fine and will run on most Xilinx FPGAs.

Re:The FPGA Turns 40! by pjc50 on Tuesday June 24, 2025 @06:27AM (#44364625)
> The code it made probably works fine

Solve your silicon verification workflow with this one weird trick: "looks good to me"!

Re:The FPGA Turns 40! by throwawayabcdef on Tuesday June 24, 2025 @07:51AM (#44365148)
Its how I saved cost and schedule on this project.
Re:The FPGA Turns 40! by ben_w on Tuesday June 24, 2025 @08:22AM (#44365398)
I don't even work in hardware, and yet even I have still heard of the Pentium FDIV bug, which happened despite people looking a lot more closely than "probably works fine".
Re:The FPGA Turns 40! by imtringued on Tuesday June 24, 2025 @02:45AM (#44363460)
AMDs FPGAs already come with AI engines.