time_mat_mul.c min time 5 seconds, min stability 10 Linux, gcc, Athlon 2100+ 1.73GHz 256KB cache
| 1.00  2.00  3.00  4.00| | 1.00  0.50  0.33  0.25| | 2.04  1.42  1.16  1.00|
| 5.00  6.00  7.00  8.00| | 0.20  0.17  0.14  0.12| | 7.59  4.77  3.69  3.08|
| 9.00 10.00 11.00 12.00|*| 0.11  0.10  0.09  0.08|=|13.15  8.12  6.23  5.17|
|13.00 14.00 15.00 16.00| | 0.08  0.07  0.07  0.06| |18.70 11.48  8.76  7.25|
matmul A[0] 2.04103 at 4
tmeas=7.97, t_prev=0, rep=16777216 
N=4 matmul time=4.74751e-07, lin=0.741798 

matmul A[0] 2.09416 at 5
tmeas=7.19, t_prev=0, rep=8388608 
N=5 matmul time=8.57711e-07, lin=0.686169 

matmul A[0] 2.12056 at 6
tmeas=5.75, t_prev=0, rep=4194304 
N=6 matmul time=1.3721e-06, lin=0.635231 

matmul A[0] 2.13369 at 7
tmeas=9.15, t_prev=0, rep=4194304 
N=7 matmul time=2.18391e-06, lin=0.63671 

matmul A[0] 2.13976 at 8
tmeas=6.48, t_prev=0, rep=2097152 
N=8 matmul time=3.0899e-06, lin=0.603497 

matmul A[0] 2.14174 at 10
tmeas=9.78, t_prev=0, rep=1048576 
N=10 matmul time=9.32217e-06, lin=0.932217 

matmul A[0] 2.13803 at 12
tmeas=8.13, t_prev=0, rep=524288 
N=12 matmul time=1.54877e-05, lin=0.896277 

matmul A[0] 2.12943 at 15
tmeas=7.62, t_prev=0, rep=262144 
N=15 matmul time=2.9068e-05, lin=0.861274 

matmul A[0] 2.12047 at 18
tmeas=6.42, t_prev=0, rep=131072 
N=18 matmul time=4.9057e-05, lin=0.84117 

matmul A[0] 2.10966 at 22
tmeas=5.73, t_prev=0, rep=65536 
N=22 matmul time=8.73566e-05, lin=0.820404 

matmul A[0] 2.09837 at 27
tmeas=5.21, t_prev=0, rep=32768 
N=27 matmul time=0.000159149, lin=0.808562 

matmul A[0] 2.08755 at 33
tmeas=9.39, t_prev=0, rep=32768 
N=33 matmul time=0.00028656, lin=0.797396 

matmul A[0] 2.0765 at 41
tmeas=8.87, t_prev=0, rep=16384 
N=41 matmul time=0.000541687, lin=0.785953 

matmul A[0] 2.06628 at 51
tmeas=8.42, t_prev=0, rep=8192 
N=51 matmul time=0.00102722, lin=0.774379 

matmul A[0] 2.05734 at 63
tmeas=7.85, t_prev=0, rep=4096 
N=63 matmul time=0.00191895, lin=0.767434 

matmul A[0] 2.04928 at 78
tmeas=7.36, t_prev=0, rep=2048 
N=78 matmul time=0.00359375, lin=0.757293 

matmul A[0] 2.04203 at 97
tmeas=6.85, t_prev=0, rep=1024 
N=97 matmul time=0.00669922, lin=0.734022 

matmul A[0] 2.03563 at 121
tmeas=6.75, t_prev=0, rep=512 
N=121 matmul time=0.0132031, lin=0.745282 

matmul A[0] 2.03009 at 151
tmeas=6.96, t_prev=0, rep=256 
N=151 matmul time=0.0272266, lin=0.790791 

matmul A[0] 2.02538 at 188
tmeas=7.63, t_prev=0, rep=128 
N=188 matmul time=0.0596094, lin=0.8971 

matmul A[0] 2.02129 at 235
tmeas=8.87, t_prev=0, rep=32 
N=235 matmul time=0.277031, lin=2.13464 

matmul A[0] 2.01785 at 293
tmeas=8.93, t_prev=0, rep=16 
N=293 matmul time=0.558125, lin=2.21885 

matmul A[0] 2.01491 at 366
tmeas=6.5, t_prev=0, rep=8 
N=366 matmul time=0.811875, lin=1.65595 

matmul A[0] 2.01243 at 457
tmeas=5.15, t_prev=0, rep=2 
N=457 matmul time=2.575, lin=2.69792 

matmul A[0] 2.01035 at 571
tmeas=10.78, t_prev=0, rep=2 
N=571 matmul time=5.3875, lin=2.89387 

matmul A[0] 2.0086 at 713
tmeas=21.87, t_prev=0, rep=2 
N=713 matmul time=10.9375, lin=3.01752 

matmul A[0] 2.00714 at 891
tmeas=43.36, t_prev=0, rep=2 
N=891 matmul time=21.6925, lin=3.06674