NVIDIA cuBLAS 新增 FP64 算法加速科学仿真
Faster Scientific Simulations with New FP64 Algorithms in NVIDIA cuBLAS
NVIDIA 在 cuBLAS 中新增 FP64 算法，用于加速科学仿真中耗时最多的 DGEMM 与 ZGEMM 高精度稠密矩阵乘法。分子化学、材料科学等领域的仿真大部分执行时间都花在这类运算上，cuBLAS 已被 HPC 与 AI 应用广泛用于加速 GEMM 等基础运算。
Many scientific simulations, from molecular chemistry to materials science, spend the majority of their execution time computing high-precision dense general...
Many scientific simulations, from molecular chemistry to materials science, spend the majority of their execution time computing high-precision dense general matrix multiplications (GEMM). These operations are called DGEMM for real 64-bit floating-point numbers and ZGEMM for complex 64-bit floating-point numbers. cuBLAS is widely used by HPC and AI applications to accelerate GEMM and other Basic…
来源：NVIDIA Technical Blog · developer.nvidia.com