#!/usr/bin/env python3

import torch
import os                          # operating system

nMatrix = 500
nRow    = 400
nCol    = 300
nS      = 200

torch.set_num_threads(1)           # for cpu-based hardware
nCPU = os.cpu_count()              # number of available cpu
if (nCPU>2): 
  torch.set_num_threads(nCPU-2)    # leave two for other uses
#
print("\n# number of CPU, threads: ",nCPU,torch.get_num_threads()) 
#
AA = torch.randn(nMatrix,nRow,nCol)            
BB = torch.randn(nMatrix,nCol,nS  )        
#
for ii in range(1000):             # do heavy stuff
  if (ii%50==0):
    print(ii)
  YY = torch.matmul(AA,BB)