Cublas
NVIDIA cuBLAS Introduces FP64 Algorithms for Faster Scientific Simulations
NVIDIA's CUDA Toolkit 13.4.2 accelerates FP64 matrix multiplications with Ozaki-II and 2M algorithms, enhancing performance for scientific simulations.
Cublas
NVIDIA Unveils Grouped GEMM APIs in cuBLAS 12.5 to Boost DL and HPC Performance
NVIDIA's cuBLAS 12.5 introduces Grouped GEMM APIs for enhanced deep learning and HPC workloads.