Ryzen Threadripper 3970XとNVIDIA RTX 3090を使ってnumpy(Intel MKL and OpenBLAS)とcupyでベンチマーク [追記：jaxでも計測した]
numpy でベンチマーク # ファイル名: numpy_benchmark.py import os os.environ["OPENBLAS_NUM_THREADS"] = "32" # import mkl # mkl.set_num_threads(32) import numpy as np import time from threadpoolctl import threadpool_info from pprint import pp pp(threadpool_info()) np.show_config() N_LOOP = 5 calc_eigh_time_list = [] calc_inv_time_list = [] calc_dot_time_list = [] calc_norm_time_list = [] for size in [5000, 10000, 20000]: print(f"size : {size}") for i in range(3): np.random.seed(i) X = np.random.randn(size, size) t_start = time.time() np.linalg.eigh(X @ X.T) calc_eigh_time_list....