DeepSeek: X2 Speed for WASM with SIMD

Re:DeepSeek: X2 Speed for WASM with SIMD by spease on Tuesday January 28, 2025 @01:37PM (#42856108)

The nature of this PR looks like it’s very LLM-friendly - it’s essentially translating existing code into SIMD.

LLMs seem to do well at any kind of mapping / translating task, but they seem to have a harder time when you give them either a broader or less deterministic task, or when they don’t have the knowledge to complete the task and start hallucinating.

It’s not a great metric to benchmark their ability to write typical code.

[ Parent | on HN ]

Re:DeepSeek: X2 Speed for WASM with SIMD by kridsdale3 on Tuesday January 28, 2025 @03:22PM (#42857477)

Sure, but let's still appreciate how awesome it is that this very difficult (for a human) PR is now essentially self-serve.

How much hardware efficiency have we left on the the table all these years because people don't like to think about optimal use of cache lines, array alignment, SIMD, etc. I bet we could double or triple the speeds of all our computers.

[ Parent | on HN ]

Re:DeepSeek: X2 Speed for WASM with SIMD by spease on Tuesday January 28, 2025 @07:19PM (#42859897)

Hopefully this results in some big improvements with compilation.

[ Parent | on HN ]