Show HN: FP32 matmul of large matrices up to 24% faster than cuBLAS on a 4090 https://ift.tt/c3P7lwz

Show HN: FP32 matmul of large matrices up to 24% faster than cuBLAS on a 4090 I decided to share a CUDA kernel I wrote over 5 months ago. Nvidia's hardware and software may surprise you. https://ift.tt/2f1UcIC August 1, 2024 at 12:09AM

Comments

Popular posts from this blog

Show HN: Samsar One Version One is now live https://ift.tt/THDkKSc

"Love Story Is Written In..." Ex-India Opener On MS Dhoni's Knock vs LSG

Show HN: Krixik – Easily sequence small/specialized AI models (pip-installable) https://ift.tt/9nDHzUF