Show HN: FP32 matmul of large matrices up to 24% faster than cuBLAS on a 4090 https://ift.tt/K8l1r53

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/fadqiWM August 1, 2024 at 12:09AM