-
Notifications
You must be signed in to change notification settings - Fork 0
/
out.20.pretune
1595 lines (1573 loc) · 90.1 KB
/
out.20.pretune
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
SU3 with improved KS action
Microcanonical simulation with refreshing
Rational function hybrid Monte Carlo algorithm
MIMD version 7.8.1
Machine = MPI (portable), with 1 nodes
Host(0) = a04n09
Username = gottlieb
start: Thu Feb 22 15:50:53 2018
Options selected...
Generic double precision
C_GLOBAL_INLINE
DBLSTORE_FN
D_FN_GATHER13
FEWSUMS
KS_MULTICG=HYBRID
KS_MULTIFF=FNMAT
VECLENGTH=4
INT_ALG=INT_3G1F
HISQ_REUNIT_ALLOW_SVD
HISQ_REUNIT_SVD_REL_ERROR = 1e-08
HISQ_REUNIT_SVD_ABS_ERROR = 1e-08
HISQ_FORCE_FILTER = 5e-05
HISQ_FF_MULTI_WRAPPER is ON
type 0 for no prompts, 1 for prompts, or 2 for proofreading
nx 20
ny 20
nz 20
nt 20
#node_geometry 1 1 1 1
#ionode_geometry 1 1 1 1
iseed 5682304
n_pseudo 5
load_rhmc_params rat.m013m065m838
beta 5.6
n_dyn_masses 3
dyn_mass 0.013 0.065 0.838
dyn_flavors 2 1 1
u0 0.85535
n_pseudo 5
Loading rational function parameters for phi field 0
naik_term_epsilon 0
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (9,9)
# Approximating the function (x+4*0.013000^2)^(2/4) (x+4*0.065000^2)^(1/4) (x+4*0.200000^2)^(-3/4) (x+4*99.900000^2)^(0/4)
# Converged at 1215 iterations, error = 4.464654e-10
# Rational function for MD
y_MD -2 -1 3 0
z_MD 4 4 4 4
m_MD 0.013 0.065 0.2 99.9
order_MD 9
Loading order 9 rational function approximation for MD:
f(x) = (x+4*0.013000^2)^(-2/4) (x+4*0.065000^2)^(-1/4)
(x+4*0.200000^2)^(3/4) (x+4*99.900000^2)^(0/4)
res_MD 1
res_MD 0.00514784
res_MD 0.00612558
res_MD 0.00828319
res_MD 0.0121182
res_MD 0.0189525
res_MD 0.0294186
res_MD 0.0184701
res_MD 0.0126582
res_MD 0.00426269
pole_MD 99.9
pole_MD 0.000707741
pole_MD 0.000998278
pole_MD 0.00180478
pole_MD 0.00374111
pole_MD 0.00819894
pole_MD 0.0169616
pole_MD 0.0369479
pole_MD 0.075128
pole_MD 0.127496
# CHECK: f(1.000000e-15) = 2.698640e+01 = 2.698640e+01?
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (11,11)
# Approximating the function (x+4*0.013000^2)^(2/8) (x+4*0.065000^2)^(1/8) (x+4*0.200000^2)^(-3/8) (x+4*99.900000^2)^(0/8)
# Converged at 1458 iterations, error = 3.338720e-12
# Rational function for GR
y_GR 2 1 -3 0
z_GR 8 8 8 8
m_GR 0.013 0.065 0.2 99.9
order_GR 11
Loading order 11 rational function approximation for GR:
f(x) = (x+4*0.013000^2)^(2/8) (x+4*0.065000^2)^(1/8)
(x+4*0.200000^2)^(-3/8) (x+4*99.900000^2)^(0/8)
res_GR 1
res_GR -4.00609e-06
res_GR -1.59992e-05
res_GR -4.46557e-05
res_GR -0.000113141
res_GR -0.000272821
res_GR -0.00061068
res_GR -0.00191397
res_GR -0.00501872
res_GR -0.0107967
res_GR -0.0183603
res_GR -0.0205676
pole_GR 99.9
pole_GR 0.000746657
pole_GR 0.00103376
pole_GR 0.00169328
pole_GR 0.00307417
pole_GR 0.00589412
pole_GR 0.0115793
pole_GR 0.023595
pole_GR 0.0438366
pole_GR 0.0766925
pole_GR 0.119109
pole_GR 0.153573
# CHECK: f(1.000000e-15) = 1.924986e-01 = 1.924986e-01?
# Rational function for FA
y_FA -2 -1 3 0
z_FA 8 8 8 8
m_FA 0.013 0.065 0.2 99.9
order_FA 11
Loading order 11 rational function approximation for FA:
f(x) = (x+4*0.013000^2)^(-2/8) (x+4*0.065000^2)^(-1/8)
(x+4*0.200000^2)^(3/8) (x+4*99.900000^2)^(0/8)
res_FA 1
res_FA 0.000276243
res_FA 0.000526223
res_FA 0.000880659
res_FA 0.00147388
res_FA 0.00250347
res_FA 0.00440441
res_FA 0.0090907
res_FA 0.0111671
res_FA 0.0124877
res_FA 0.0105293
res_FA 0.00437892
pole_FA 99.9
pole_FA 0.000712193
pole_FA 0.000935541
pole_FA 0.00147894
pole_FA 0.00263078
pole_FA 0.00499302
pole_FA 0.00976792
pole_FA 0.0187538
pole_FA 0.0348901
pole_FA 0.0628417
pole_FA 0.102834
pole_FA 0.143271
Loading rational function parameters for phi field 1
# CHECK: f(1.000000e-15) = 5.194844e+00 = 5.194844e+00?
naik_term_epsilon 0
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (7,7)
# Approximating the function (x+4*0.200000^2)^(1/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
# Converged at 327 iterations, error = 2.398230e-07
# Rational function for MD
y_MD -1 0 0 0
z_MD 4 4 4 4
m_MD 0.2 99.9 99.9 99.9
order_MD 7
Loading order 7 rational function approximation for MD:
f(x) = (x+4*0.200000^2)^(-1/4) (x+4*99.900000^2)^(0/4)
(x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
res_MD 0.14923
res_MD 0.046061
res_MD 0.1138
res_MD 0.274536
res_MD 0.687619
res_MD 1.83201
res_MD 5.87481
res_MD 38.0862
pole_MD 99.9
pole_MD 0.185283
pole_MD 0.375399
pole_MD 1.05812
pole_MD 3.40313
pole_MD 11.7405
pole_MD 45.73
pole_MD 283.916
# CHECK: f(1.000000e-15) = 1.581138e+00 = 1.581139e+00?
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (9,9)
# Approximating the function (x+4*0.200000^2)^(1/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
# Converged at 422 iterations, error = 1.700228e-09
# Rational function for GR
y_GR 1 0 0 0
z_GR 8 8 8 8
m_GR 0.2 99.9 99.9 99.9
order_GR 9
Loading order 9 rational function approximation for GR:
f(x) = (x+4*0.200000^2)^(1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_GR 2.73277
res_GR -0.00512886
res_GR -0.0204789
res_GR -0.0639514
res_GR -0.192686
res_GR -0.585195
res_GR -1.85803
res_GR -6.68946
res_GR -34.4017
res_GR -617.898
pole_GR 99.9
pole_GR 0.186425
pole_GR 0.315826
pole_GR 0.679106
pole_GR 1.64209
pole_GR 4.20254
pole_GR 11.2153
pole_GR 32.0724
pole_GR 110.326
pole_GR 764.415
# CHECK: f(1.000000e-15) = 7.952707e-01 = 7.952707e-01?
# Rational function for FA
y_FA -1 0 0 0
z_FA 8 8 8 8
m_FA 0.2 99.9 99.9 99.9
order_FA 9
Loading order 9 rational function approximation for FA:
f(x) = (x+4*0.200000^2)^(-1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_FA 0.365929
res_FA 0.0109316
res_FA 0.0292903
res_FA 0.0678756
res_FA 0.157093
res_FA 0.370027
res_FA 0.906451
res_FA 2.45234
res_FA 8.71503
res_FA 75.8971
pole_FA 99.9
pole_FA 0.178875
pole_FA 0.290944
pole_FA 0.612037
pole_FA 1.46486
pole_FA 3.72845
pole_FA 9.8933
pole_FA 27.9493
pole_FA 92.735
pole_FA 546.062
Loading rational function parameters for phi field 2
# CHECK: f(1.000000e-15) = 1.257433e+00 = 1.257433e+00?
naik_term_epsilon 0
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (7,7)
# Approximating the function (x+4*0.200000^2)^(1/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
# Converged at 327 iterations, error = 2.398230e-07
# Rational function for MD
y_MD -1 0 0 0
z_MD 4 4 4 4
m_MD 0.2 99.9 99.9 99.9
order_MD 7
Loading order 7 rational function approximation for MD:
f(x) = (x+4*0.200000^2)^(-1/4) (x+4*99.900000^2)^(0/4)
(x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
res_MD 0.14923
res_MD 0.046061
res_MD 0.1138
res_MD 0.274536
res_MD 0.687619
res_MD 1.83201
res_MD 5.87481
res_MD 38.0862
pole_MD 99.9
pole_MD 0.185283
pole_MD 0.375399
pole_MD 1.05812
pole_MD 3.40313
pole_MD 11.7405
pole_MD 45.73
pole_MD 283.916
# CHECK: f(1.000000e-15) = 1.581138e+00 = 1.581139e+00?
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (9,9)
# Approximating the function (x+4*0.200000^2)^(1/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
# Converged at 422 iterations, error = 1.700228e-09
# Rational function for GR
y_GR 1 0 0 0
z_GR 8 8 8 8
m_GR 0.2 99.9 99.9 99.9
order_GR 9
Loading order 9 rational function approximation for GR:
f(x) = (x+4*0.200000^2)^(1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_GR 2.73277
res_GR -0.00512886
res_GR -0.0204789
res_GR -0.0639514
res_GR -0.192686
res_GR -0.585195
res_GR -1.85803
res_GR -6.68946
res_GR -34.4017
res_GR -617.898
pole_GR 99.9
pole_GR 0.186425
pole_GR 0.315826
pole_GR 0.679106
pole_GR 1.64209
pole_GR 4.20254
pole_GR 11.2153
pole_GR 32.0724
pole_GR 110.326
pole_GR 764.415
# CHECK: f(1.000000e-15) = 7.952707e-01 = 7.952707e-01?
# Rational function for FA
y_FA -1 0 0 0
z_FA 8 8 8 8
m_FA 0.2 99.9 99.9 99.9
order_FA 9
Loading order 9 rational function approximation for FA:
f(x) = (x+4*0.200000^2)^(-1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_FA 0.365929
res_FA 0.0109316
res_FA 0.0292903
res_FA 0.0678756
res_FA 0.157093
res_FA 0.370027
res_FA 0.906451
res_FA 2.45234
res_FA 8.71503
res_FA 75.8971
pole_FA 99.9
pole_FA 0.178875
pole_FA 0.290944
pole_FA 0.612037
pole_FA 1.46486
pole_FA 3.72845
pole_FA 9.8933
pole_FA 27.9493
pole_FA 92.735
pole_FA 546.062
Loading rational function parameters for phi field 3
# CHECK: f(1.000000e-15) = 1.257433e+00 = 1.257433e+00?
naik_term_epsilon 0
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (7,7)
# Approximating the function (x+4*0.200000^2)^(1/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
# Converged at 327 iterations, error = 2.398230e-07
# Rational function for MD
y_MD -1 0 0 0
z_MD 4 4 4 4
m_MD 0.2 99.9 99.9 99.9
order_MD 7
Loading order 7 rational function approximation for MD:
f(x) = (x+4*0.200000^2)^(-1/4) (x+4*99.900000^2)^(0/4)
(x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
res_MD 0.14923
res_MD 0.046061
res_MD 0.1138
res_MD 0.274536
res_MD 0.687619
res_MD 1.83201
res_MD 5.87481
res_MD 38.0862
pole_MD 99.9
pole_MD 0.185283
pole_MD 0.375399
pole_MD 1.05812
pole_MD 3.40313
pole_MD 11.7405
pole_MD 45.73
pole_MD 283.916
# CHECK: f(1.000000e-15) = 1.581138e+00 = 1.581139e+00?
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (9,9)
# Approximating the function (x+4*0.200000^2)^(1/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
# Converged at 422 iterations, error = 1.700228e-09
# Rational function for GR
y_GR 1 0 0 0
z_GR 8 8 8 8
m_GR 0.2 99.9 99.9 99.9
order_GR 9
Loading order 9 rational function approximation for GR:
f(x) = (x+4*0.200000^2)^(1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_GR 2.73277
res_GR -0.00512886
res_GR -0.0204789
res_GR -0.0639514
res_GR -0.192686
res_GR -0.585195
res_GR -1.85803
res_GR -6.68946
res_GR -34.4017
res_GR -617.898
pole_GR 99.9
pole_GR 0.186425
pole_GR 0.315826
pole_GR 0.679106
pole_GR 1.64209
pole_GR 4.20254
pole_GR 11.2153
pole_GR 32.0724
pole_GR 110.326
pole_GR 764.415
# CHECK: f(1.000000e-15) = 7.952707e-01 = 7.952707e-01?
# Rational function for FA
y_FA -1 0 0 0
z_FA 8 8 8 8
m_FA 0.2 99.9 99.9 99.9
order_FA 9
Loading order 9 rational function approximation for FA:
f(x) = (x+4*0.200000^2)^(-1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_FA 0.365929
res_FA 0.0109316
res_FA 0.0292903
res_FA 0.0678756
res_FA 0.157093
res_FA 0.370027
res_FA 0.906451
res_FA 2.45234
res_FA 8.71503
res_FA 75.8971
pole_FA 99.9
pole_FA 0.178875
pole_FA 0.290944
pole_FA 0.612037
pole_FA 1.46486
pole_FA 3.72845
pole_FA 9.8933
pole_FA 27.9493
pole_FA 92.735
pole_FA 546.062
Loading rational function parameters for phi field 4
# CHECK: f(1.000000e-15) = 1.257433e+00 = 1.257433e+00?
naik_term_epsilon -0.358197
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (7,7)
# Approximating the function (x+4*0.838000^2)^(1/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
# Converged at 254 iterations, error = 1.451256e-10
# Rational function for MD
y_MD -1 0 0 0
z_MD 4 4 4 4
m_MD 0.838 99.9 99.9 99.9
order_MD 7
Loading order 7 rational function approximation for MD:
f(x) = (x+4*0.838000^2)^(-1/4) (x+4*99.900000^2)^(0/4)
(x+4*99.900000^2)^(0/4) (x+4*99.900000^2)^(0/4)
res_MD 0.123225
res_MD 0.217719
res_MD 0.442066
res_MD 0.826188
res_MD 1.62971
res_MD 3.61674
res_MD 10.5096
res_MD 67.0971
pole_MD 99.9
pole_MD 3.0161
pole_MD 4.35504
pole_MD 7.97962
pole_MD 17.0841
pole_MD 41.5742
pole_MD 123.226
pole_MD 643.266
# CHECK: f(1.000000e-15) = 7.724369e-01 = 7.724369e-01?
# New rational function
# Approximation bounds are [1.000000e-15,9.000000e+01]
# Precision of arithmetic is 75
# Degree of the approximation is (9,9)
# Approximating the function (x+4*0.838000^2)^(1/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
# Converged at 328 iterations, error = 1.426221e-13
# Rational function for GR
y_GR 1 0 0 0
z_GR 8 8 8 8
m_GR 0.838 99.9 99.9 99.9
order_GR 9
Loading order 9 rational function approximation for GR:
f(x) = (x+4*0.838000^2)^(1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_GR 3.00731
res_GR -0.0532344
res_GR -0.176732
res_GR -0.427264
res_GR -0.977907
res_GR -2.28828
res_GR -5.8209
res_GR -17.8443
res_GR -84.0324
res_GR -1466.92
pole_GR 99.9
pole_GR 3.02524
pole_GR 3.96609
pole_GR 6.10394
pole_GR 10.5306
pole_GR 19.7596
pole_GR 40.1654
pole_GR 91.6686
pole_GR 266.728
pole_GR 1678.31
# CHECK: f(1.000000e-15) = 1.137807e+00 = 1.137807e+00?
# Rational function for FA
y_FA -1 0 0 0
z_FA 8 8 8 8
m_FA 0.838 99.9 99.9 99.9
order_FA 9
Loading order 9 rational function approximation for FA:
f(x) = (x+4*0.838000^2)^(-1/8) (x+4*99.900000^2)^(0/8)
(x+4*99.900000^2)^(0/8) (x+4*99.900000^2)^(0/8)
res_FA 0.332523
res_FA 0.0679576
res_FA 0.156901
res_FA 0.293908
res_FA 0.542476
res_FA 1.03576
res_FA 2.13306
res_FA 5.11817
res_FA 17.1666
res_FA 148.027
pole_FA 99.9
pole_FA 2.96457
pole_FA 3.79677
pole_FA 5.7428
pole_FA 9.78765
pole_FA 18.1889
pole_FA 36.5712
pole_FA 81.9291
pole_FA 228.11
pole_FA 1208.27
Maximum rational func order is 11
Naik term correction structure of multi_x:
n_naiks 2
n_pseudo_naik[0]=4
n_orders_naik[0]=30
eps_naik[0]=0.000000
n_pseudo_naik[1]=1
n_orders_naik[1]=7
eps_naik[1]=-0.358197
n_order_naik_total 37
LAYOUT = Hypercubes, options = hyper_prime,
automatic hyper_prime layout
ON EACH NODE 20 x 20 x 20 x 20
Mallocing 256.0 MBytes per node for lattice
Disabling GPU-Direct RDMA access
QUDA 0.9.0 (git v0.9.0a1-with_v.0.8_milc_interface-115-ge150ee4-sm_60)
Found device 0: Tesla V100-SXM2-16GB
Using device 0: Tesla V100-SXM2-16GB
WARNING: Data reordering done on GPU (set with QUDA_REORDER_LOCATION=GPU/CPU)
WARNING: Using device memory pool allocator
WARNING: Using pinned memory pool allocator
Loaded 1478 sets of cached parameters from /gpfs/alpinetds/csc190/scratch/gottlieb/run/tune/tunecache.tsv
WARNING!!: Resetting random seed
Made lattice
Made nn gathers
Made 3nn gathers
Finished setup
Aggregate time to setup 3.873897e+02
warms 0
trajecs 2
traj_between_meas 2
microcanonical_time_step 0.2
steps_per_trajectory 2
cgresid_md_fa_gr 2.5e-08 2e-08 2e-08
max_multicg_md_fa_gr 1750 1750 1750
cgprec_md_fa_gr 2 2 2
cgresid_md_fa_gr 5e-08 2e-08 2e-08
max_multicg_md_fa_gr 1750 1750 1750
cgprec_md_fa_gr 2 2 2
cgresid_md_fa_gr 5e-08 2e-08 2e-08
max_multicg_md_fa_gr 1750 1750 1750
cgprec_md_fa_gr 2 2 2
cgresid_md_fa_gr 5e-08 2e-08 2e-08
max_multicg_md_fa_gr 1750 1750 1750
cgprec_md_fa_gr 2 2 2
cgresid_md_fa_gr 5e-09 2e-09 2e-09
max_multicg_md_fa_gr 1750 1750 1750
cgprec_md_fa_gr 2 2 2
prec_ff 2
number_of_pbp_masses 3
max_cg_prop 1750
max_cg_prop_restarts 5
npbp_reps 1
prec_pbp 2
mass 0.013
naik_term_epsilon 0
error_for_propagator 2e-07
rel_error_for_propagator 0
mass 0.065
naik_term_epsilon 0
error_for_propagator 2e-07
rel_error_for_propagator 0
mass 0.838
naik_term_epsilon -0.358197
error_for_propagator 2e-08
rel_error_for_propagator 0
fresh
#reload_serial l1216b560m013m065m838.test
forget
unit gauge configuration loaded
CHECK PLAQ: 3.0000000000000000e+00 3.0000000000000000e+00
CHECK NERSC LINKTR: 1.0000000000000000e+00 CKSUM: 0
REUNITARIZE: time = 2.512101e+00
Reunitarized for double precision. Max deviation 0.00e+00 changed to 0.00e+00
Time to check unitarity = 2.593245e+00
"Fat 7 (level 1)"
path coefficients: npath path_coeff
0 1.250000e-01
1 -6.250000e-02
2 1.562500e-02
3 -2.604167e-03
Unitarization method = UNITARIZE_ANALYTIC
Unitarizaton group = U(3)
"Fat7 + 2xLepage"
path coefficients: npath path_coeff
0 1.000000e+00
1 -4.166667e-02
2 -6.250000e-02
3 1.562500e-02
4 -2.604167e-03
5 -1.250000e-01
"1-link + Naik"
path coefficients: npath path_coeff
0 1.250000e-01
1 -4.166667e-02
MAKING PATH TABLES
Combined fattening and long-link calculation time: 0.259860
Combined fattening and long-link calculation time: 1.240873
FLTIME: time = 9.311223e+00 (HISQ QUDA D) mflops = 2.179357e+03
Symanzik 1x1 + 1x2 + 1x1x1 action with HISQ quark loops
gauge_action: total_dyn_flavors = 4
loop coefficients: nloop rep loop_coeff multiplicity
0 0 1.000000e+00 6
1 0 -2.486061e-02 12
2 0 4.078970e-03 16
WARMUPS COMPLETED
Omelyan integration, 3 gauge for one 1 fermion step, steps= 2 eps= 2.000000e-01 alpha= 1.000000e-01 beta= 1.000000e-01
GRSOURCE: sum = 2.3956085362e+05
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
PreTune N4quda19StaggeredDslashCudaI7double2S1_S1_dEE
Tuning N4quda19StaggeredDslashCudaI7double2S1_S1_dEE with policy,comm=0000,reconstruct=18,topo=1111 at vol=10x20x20x20x1
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(0,0,0)
block=(32,1,1), shared=0, aux=(0,0,0,0) gives 364.02 Gflop/s, 991.04 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(1,0,0)
block=(32,1,1), shared=0, aux=(1,0,0,0) gives 364.39 Gflop/s, 992.06 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(6,0,0)
block=(32,1,1), shared=0, aux=(6,0,0,0) gives 364.21 Gflop/s, 991.56 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(7,0,0)
block=(32,1,1), shared=0, aux=(7,0,0,0) gives 363.43 Gflop/s, 989.45 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(8,0,0)
block=(32,1,1), shared=0, aux=(8,0,0,0) gives 362.52 Gflop/s, 986.95 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(9,0,0)
block=(32,1,1), shared=0, aux=(9,0,0,0) gives 362.87 Gflop/s, 987.92 GB/s
Tuned block=(32,1,1), shared=0, aux=(1,0,0,0) giving 364.39 Gflop/s, 992.06 GB/s for N4quda19StaggeredDslashCudaI7double2S1_S1_dEE with policy,comm=0000,reconstruct=18,topo=1111
PostTune N4quda19StaggeredDslashCudaI7double2S1_S1_dEE
PreTune N4quda19StaggeredDslashCudaI7double2S1_S1_dEE
Tuning N4quda19StaggeredDslashCudaI7double2S1_S1_dEE with policy,comm=0000,reconstruct=18,Xpay,topo=1111 at vol=10x20x20x20x1
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(0,0,0)
block=(32,1,1), shared=0, aux=(0,0,0,0) gives 361.47 Gflop/s, 973.92 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(1,0,0)
block=(32,1,1), shared=0, aux=(1,0,0,0) gives 360.97 Gflop/s, 972.56 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(6,0,0)
block=(32,1,1), shared=0, aux=(6,0,0,0) gives 360.29 Gflop/s, 970.72 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(7,0,0)
block=(32,1,1), shared=0, aux=(7,0,0,0) gives 359.57 Gflop/s, 968.80 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(8,0,0)
block=(32,1,1), shared=0, aux=(8,0,0,0) gives 360.14 Gflop/s, 970.33 GB/s
About to call tunable.apply block=(32,1,1) grid=(1,1,1) shared_bytes=0 aux=(9,0,0)
block=(32,1,1), shared=0, aux=(9,0,0,0) gives 360.96 Gflop/s, 972.54 GB/s
Tuned block=(32,1,1), shared=0, aux=(0,0,0,0) giving 361.47 Gflop/s, 973.92 GB/s for N4quda19StaggeredDslashCudaI7double2S1_S1_dEE with policy,comm=0000,reconstruct=18,Xpay,topo=1111
PostTune N4quda19StaggeredDslashCudaI7double2S1_S1_dEE
MultiShift CG: Converged after 49 iterations
shift=0, 49 iterations, relative residual: iterated = 1.583502e-08, true = 1.583502e-08
shift=1, 49 iterations, relative residual: iterated = 1.573696e-08, true = 1.573696e-08
shift=2, 49 iterations, relative residual: iterated = 1.551453e-08, true = 1.551453e-08
shift=3, 49 iterations, relative residual: iterated = 1.506123e-08, true = 1.506123e-08
shift=4, 49 iterations, relative residual: iterated = 1.418507e-08, true = 1.418507e-08
shift=5, 49 iterations, relative residual: iterated = 1.260066e-08, true = 1.260066e-08
shift=6, 49 iterations, relative residual: iterated = 9.902723e-09, true = 9.902723e-09
shift=7, 49 iterations, relative residual: iterated = 6.758318e-09, true = 6.758318e-09
shift=8, 49 iterations, relative residual: iterated = 3.814897e-09, true = 3.814897e-09
shift=9, 49 iterations, relative residual: iterated = 1.942222e-09, true = 1.942222e-09
shift=10, 49 iterations, relative residual: iterated = 1.165993e-09, true = 1.165993e-09
Saving 1559 sets of cached parameters to /gpfs/alpinetds/csc190/scratch/gottlieb/run/tune/tunecache.tsv
CONGRAD5: time = 1.231061e+01 (multicg_offset_QUDA D) masses = 11 iters = 49 mflops = 8.724832e+02
OK converged final_rsq= 2.5e-16 (cf 4e-16) rel = 7.4e-15 (cf 0) restarts = 0 iters= 49
GRSOURCETIME: time = 4.268599e-02
GRSOURCE: sum = 2.3993655876e+05
MultiShift CG: Converged after 44 iterations
shift=0, 44 iterations, relative residual: iterated = 1.147350e-08, true = 1.147350e-08
shift=1, 44 iterations, relative residual: iterated = 2.508170e-09, true = 2.508170e-09
shift=2, 44 iterations, relative residual: iterated = 7.628297e-11, true = 7.628297e-11
shift=3, 44 iterations, relative residual: iterated = 7.650004e-14, true = 7.650325e-14
shift=4, 37 iterations, relative residual: iterated = 3.505303e-16, true = 5.517133e-16
shift=5, 25 iterations, relative residual: iterated = 8.453941e-16, true = 9.213981e-16
shift=6, 17 iterations, relative residual: iterated = 4.163180e-16, true = 4.873558e-16
shift=7, 11 iterations, relative residual: iterated = 9.384030e-16, true = 9.619013e-16
shift=8, 7 iterations, relative residual: iterated = 4.989710e-16, true = 5.221107e-16
Saving 1561 sets of cached parameters to /gpfs/alpinetds/csc190/scratch/gottlieb/run/tune/tunecache.tsv
CONGRAD5: time = 5.282975e+00 (multicg_offset_QUDA D) masses = 9 iters = 44 mflops = 1.785661e+03
OK converged final_rsq= 1.3e-16 (cf 4e-16) rel = 7.6e-15 (cf 0) restarts = 0 iters= 44
GRSOURCETIME: time = 4.071808e-02
GRSOURCE: sum = 2.3982668388e+05
MultiShift CG: Converged after 44 iterations
shift=0, 44 iterations, relative residual: iterated = 1.188005e-08, true = 1.188005e-08
shift=1, 44 iterations, relative residual: iterated = 2.590711e-09, true = 2.590711e-09
shift=2, 44 iterations, relative residual: iterated = 7.841279e-11, true = 7.841279e-11
shift=3, 44 iterations, relative residual: iterated = 7.812726e-14, true = 7.812799e-14
shift=4, 37 iterations, relative residual: iterated = 3.600522e-16, true = 5.591907e-16
shift=5, 25 iterations, relative residual: iterated = 8.475664e-16, true = 9.016234e-16
shift=6, 17 iterations, relative residual: iterated = 4.183393e-16, true = 4.762422e-16
shift=7, 11 iterations, relative residual: iterated = 9.508779e-16, true = 9.747225e-16
shift=8, 7 iterations, relative residual: iterated = 5.060587e-16, true = 5.288781e-16
CONGRAD5: time = 4.353690e-02 (multicg_offset_QUDA D) masses = 9 iters = 44 mflops = 2.166806e+05
OK converged final_rsq= 1.4e-16 (cf 4e-16) rel = 8.1e-15 (cf 0) restarts = 0 iters= 44
GRSOURCETIME: time = 3.893185e-02
GRSOURCE: sum = 2.3903259706e+05
MultiShift CG: Converged after 44 iterations
shift=0, 44 iterations, relative residual: iterated = 1.187413e-08, true = 1.187413e-08
shift=1, 44 iterations, relative residual: iterated = 2.588942e-09, true = 2.588942e-09
shift=2, 44 iterations, relative residual: iterated = 7.833153e-11, true = 7.833153e-11
shift=3, 44 iterations, relative residual: iterated = 7.801166e-14, true = 7.801338e-14
shift=4, 37 iterations, relative residual: iterated = 3.598643e-16, true = 5.486066e-16
shift=5, 25 iterations, relative residual: iterated = 8.437522e-16, true = 8.953807e-16
shift=6, 17 iterations, relative residual: iterated = 4.195124e-16, true = 4.852079e-16
shift=7, 11 iterations, relative residual: iterated = 9.662735e-16, true = 9.805650e-16
shift=8, 7 iterations, relative residual: iterated = 5.090767e-16, true = 5.324986e-16
CONGRAD5: time = 4.362822e-02 (multicg_offset_QUDA D) masses = 9 iters = 44 mflops = 2.162270e+05
OK converged final_rsq= 1.4e-16 (cf 4e-16) rel = 7.7e-15 (cf 0) restarts = 0 iters= 44
GRSOURCETIME: time = 3.729010e-02
GRSOURCE: sum = 2.3907899272e+05
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 25 iterations
shift=0, 25 iterations, relative residual: iterated = 8.022534e-10, true = 8.022534e-10
shift=1, 25 iterations, relative residual: iterated = 6.448291e-11, true = 6.448291e-11
shift=2, 25 iterations, relative residual: iterated = 5.837242e-13, true = 5.837238e-13
shift=3, 25 iterations, relative residual: iterated = 4.142970e-16, true = 5.105751e-16
shift=4, 20 iterations, relative residual: iterated = 2.045805e-16, true = 3.680485e-16
shift=5, 15 iterations, relative residual: iterated = 5.243314e-16, true = 5.713939e-16
shift=6, 12 iterations, relative residual: iterated = 1.032886e-16, true = 2.356475e-16
shift=7, 9 iterations, relative residual: iterated = 1.035064e-16, true = 1.819169e-16
shift=8, 6 iterations, relative residual: iterated = 3.588347e-16, true = 4.072394e-16
CONGRAD5: time = 8.337903e-02 (multicg_offset_QUDA D) masses = 9 iters = 25 mflops = 6.428475e+04
OK converged final_rsq= 6.4e-19 (cf 4e-18) rel = 1.1e-16 (cf 0) restarts = 0 iters= 25
GRSOURCETIME: time = 3.925800e-02
PLAQUETTE ACTION: -5.376000e+06
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 49 iterations
shift=0, 49 iterations, relative residual: iterated = 1.563278e-08, true = 1.563278e-08
shift=1, 49 iterations, relative residual: iterated = 1.555741e-08, true = 1.555741e-08
shift=2, 49 iterations, relative residual: iterated = 1.537589e-08, true = 1.537589e-08
shift=3, 49 iterations, relative residual: iterated = 1.499969e-08, true = 1.499969e-08
shift=4, 49 iterations, relative residual: iterated = 1.426296e-08, true = 1.426296e-08
shift=5, 49 iterations, relative residual: iterated = 1.290454e-08, true = 1.290454e-08
shift=6, 49 iterations, relative residual: iterated = 1.075005e-08, true = 1.075005e-08
shift=7, 49 iterations, relative residual: iterated = 7.868228e-09, true = 7.868228e-09
shift=8, 49 iterations, relative residual: iterated = 4.760513e-09, true = 4.760513e-09
shift=9, 49 iterations, relative residual: iterated = 2.465938e-09, true = 2.465938e-09
shift=10, 49 iterations, relative residual: iterated = 1.336245e-09, true = 1.336245e-09
CONGRAD5: time = 1.093042e-01 (multicg_offset_QUDA D) masses = 11 iters = 49 mflops = 9.826522e+04
OK converged final_rsq= 2.4e-16 (cf 4e-16) rel = 9.4e-15 (cf 0) restarts = 0 iters= 49
MultiShift CG: Converged after 44 iterations
shift=0, 44 iterations, relative residual: iterated = 1.122977e-08, true = 1.122977e-08
shift=1, 44 iterations, relative residual: iterated = 2.945656e-09, true = 2.945656e-09
shift=2, 44 iterations, relative residual: iterated = 1.229659e-10, true = 1.229659e-10
shift=3, 44 iterations, relative residual: iterated = 2.117178e-13, true = 2.117186e-13
shift=4, 38 iterations, relative residual: iterated = 5.654505e-16, true = 7.090131e-16
shift=5, 27 iterations, relative residual: iterated = 2.949037e-16, true = 4.372062e-16
shift=6, 18 iterations, relative residual: iterated = 3.184911e-16, true = 3.898895e-16
shift=7, 12 iterations, relative residual: iterated = 2.639295e-16, true = 3.248424e-16
shift=8, 8 iterations, relative residual: iterated = 4.704179e-17, true = 1.657731e-16
CONGRAD5: time = 4.459906e-02 (multicg_offset_QUDA D) masses = 9 iters = 44 mflops = 2.115202e+05
OK converged final_rsq= 1.3e-16 (cf 4e-16) rel = 9.5e-15 (cf 0) restarts = 0 iters= 44
MultiShift CG: Converged after 44 iterations
shift=0, 44 iterations, relative residual: iterated = 1.168162e-08, true = 1.168162e-08
shift=1, 44 iterations, relative residual: iterated = 3.056443e-09, true = 3.056443e-09
shift=2, 44 iterations, relative residual: iterated = 1.269166e-10, true = 1.269166e-10
shift=3, 44 iterations, relative residual: iterated = 2.168978e-13, true = 2.168973e-13
shift=4, 38 iterations, relative residual: iterated = 5.918377e-16, true = 7.255780e-16
shift=5, 27 iterations, relative residual: iterated = 2.972469e-16, true = 4.570892e-16
shift=6, 18 iterations, relative residual: iterated = 3.199629e-16, true = 3.929300e-16
shift=7, 12 iterations, relative residual: iterated = 2.675661e-16, true = 3.204748e-16
shift=8, 8 iterations, relative residual: iterated = 4.752218e-17, true = 1.502201e-16
CONGRAD5: time = 4.387307e-02 (multicg_offset_QUDA D) masses = 9 iters = 44 mflops = 2.150203e+05
OK converged final_rsq= 1.4e-16 (cf 4e-16) rel = 1e-14 (cf 0) restarts = 0 iters= 44
MultiShift CG: Converged after 44 iterations
shift=0, 44 iterations, relative residual: iterated = 1.167533e-08, true = 1.167533e-08
shift=1, 44 iterations, relative residual: iterated = 3.054204e-09, true = 3.054204e-09
shift=2, 44 iterations, relative residual: iterated = 1.267738e-10, true = 1.267738e-10
shift=3, 44 iterations, relative residual: iterated = 2.165425e-13, true = 2.165439e-13
shift=4, 38 iterations, relative residual: iterated = 5.939915e-16, true = 7.309323e-16
shift=5, 27 iterations, relative residual: iterated = 2.967168e-16, true = 4.277801e-16
shift=6, 18 iterations, relative residual: iterated = 3.215270e-16, true = 3.926853e-16
shift=7, 12 iterations, relative residual: iterated = 2.711535e-16, true = 3.440950e-16
shift=8, 8 iterations, relative residual: iterated = 4.802504e-17, true = 1.513293e-16
CONGRAD5: time = 4.378295e-02 (multicg_offset_QUDA D) masses = 9 iters = 44 mflops = 2.154629e+05
OK converged final_rsq= 1.4e-16 (cf 4e-16) rel = 1e-14 (cf 0) restarts = 0 iters= 44
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 25 iterations
shift=0, 25 iterations, relative residual: iterated = 9.066533e-10, true = 9.066533e-10
shift=1, 25 iterations, relative residual: iterated = 9.413413e-11, true = 9.413413e-11
shift=2, 25 iterations, relative residual: iterated = 1.147891e-12, true = 1.147891e-12
shift=3, 25 iterations, relative residual: iterated = 1.153804e-15, true = 1.192060e-15
shift=4, 20 iterations, relative residual: iterated = 6.291209e-16, true = 6.754000e-16
shift=5, 16 iterations, relative residual: iterated = 1.652084e-16, true = 2.655617e-16
shift=6, 12 iterations, relative residual: iterated = 3.403122e-16, true = 3.907636e-16
shift=7, 9 iterations, relative residual: iterated = 3.937105e-16, true = 4.226529e-16
shift=8, 7 iterations, relative residual: iterated = 9.974350e-18, true = 1.332118e-16
CONGRAD5: time = 8.360314e-02 (multicg_offset_QUDA D) masses = 9 iters = 25 mflops = 6.411242e+04
OK converged final_rsq= 8.2e-19 (cf 4e-18) rel = 1.4e-16 (cf 0) restarts = 0 iters= 25
ACTION: g,h,f = 0.00000000000000e+00 -7.51558724726046e+02 1.19743568603853e+06 1.19668412731381e+06
DG = 0.000000e+00, DH = -7.515587e+02, DF = 1.197436e+06, D = 1.196684e+06
ACTIONTIME: time = 3.453788e+00
LINK_UPDATE: time = 9.229770e-01 mflops = 9.735454e+02
GFTIME: time = 8.527547e+00 (Symanzik1_QUDA) mflops = 2.870772e+03
LINK_UPDATE: time = 8.436918e-03 mflops = 1.065033e+05
Combined fattening and long-link calculation time: 0.008092
Combined fattening and long-link calculation time: 0.019963
FLTIME: time = 2.778718e-01 (HISQ QUDA D) mflops = 7.302820e+04
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 76 iterations
shift=0, 76 iterations, relative residual: iterated = 2.021576e-08, true = 2.021576e-08
shift=1, 76 iterations, relative residual: iterated = 1.992781e-08, true = 1.992781e-08
shift=2, 76 iterations, relative residual: iterated = 1.915254e-08, true = 1.915254e-08
shift=3, 76 iterations, relative residual: iterated = 1.742670e-08, true = 1.742670e-08
shift=4, 76 iterations, relative residual: iterated = 1.408217e-08, true = 1.408217e-08
shift=5, 76 iterations, relative residual: iterated = 9.412576e-09, true = 9.412576e-09
shift=6, 76 iterations, relative residual: iterated = 4.013161e-09, true = 4.013161e-09
shift=7, 76 iterations, relative residual: iterated = 9.511337e-10, true = 9.511337e-10
shift=8, 76 iterations, relative residual: iterated = 1.723993e-10, true = 1.723993e-10
Saving 1567 sets of cached parameters to /gpfs/alpinetds/csc190/scratch/gottlieb/run/tune/tunecache.tsv
CONGRAD5: time = 1.300180e-01 (multicg_offset_QUDA D) masses = 9 iters = 76 mflops = 1.253242e+05
OK converged final_rsq= 4.1e-16 (cf 6.2e-16) rel = 1.5e-14 (cf 0) restarts = 0 iters= 76
MultiShift CG: Converged after 52 iterations
shift=0, 52 iterations, relative residual: iterated = 4.706224e-08, true = 4.706224e-08
shift=1, 52 iterations, relative residual: iterated = 2.248871e-09, true = 2.248871e-09
shift=2, 52 iterations, relative residual: iterated = 1.031205e-12, true = 1.031205e-12
shift=3, 42 iterations, relative residual: iterated = 7.615418e-16, true = 8.884097e-16
shift=4, 25 iterations, relative residual: iterated = 5.419404e-16, true = 6.183320e-16
shift=5, 15 iterations, relative residual: iterated = 3.485022e-16, true = 4.097942e-16
shift=6, 9 iterations, relative residual: iterated = 1.390685e-16, true = 2.050083e-16
CONGRAD5: time = 4.759502e-02 (multicg_offset_QUDA D) masses = 7 iters = 52 mflops = 2.289987e+05
OK converged final_rsq= 2.2e-15 (cf 2.5e-15) rel = 1.7e-13 (cf 0) restarts = 0 iters= 52
MultiShift CG: Converged after 52 iterations
shift=0, 52 iterations, relative residual: iterated = 4.822576e-08, true = 4.822576e-08
shift=1, 52 iterations, relative residual: iterated = 2.301762e-09, true = 2.301762e-09
shift=2, 52 iterations, relative residual: iterated = 1.053055e-12, true = 1.053055e-12
shift=3, 42 iterations, relative residual: iterated = 7.809641e-16, true = 9.156207e-16
shift=4, 25 iterations, relative residual: iterated = 5.442310e-16, true = 6.300574e-16
shift=5, 15 iterations, relative residual: iterated = 3.514921e-16, true = 4.046267e-16
shift=6, 9 iterations, relative residual: iterated = 1.405153e-16, true = 2.088271e-16
CONGRAD5: time = 4.782486e-02 (multicg_offset_QUDA D) masses = 7 iters = 52 mflops = 2.278982e+05
OK converged final_rsq= 2.3e-15 (cf 2.5e-15) rel = 1.7e-13 (cf 0) restarts = 0 iters= 52
MultiShift CG: Converged after 52 iterations
shift=0, 52 iterations, relative residual: iterated = 4.752638e-08, true = 4.752638e-08
shift=1, 52 iterations, relative residual: iterated = 2.269805e-09, true = 2.269805e-09
shift=2, 52 iterations, relative residual: iterated = 1.039887e-12, true = 1.039887e-12
shift=3, 42 iterations, relative residual: iterated = 7.988885e-16, true = 9.175270e-16
shift=4, 25 iterations, relative residual: iterated = 5.439127e-16, true = 6.215035e-16
shift=5, 15 iterations, relative residual: iterated = 3.544361e-16, true = 4.072759e-16
shift=6, 9 iterations, relative residual: iterated = 1.424956e-16, true = 2.314377e-16
CONGRAD5: time = 4.740596e-02 (multicg_offset_QUDA D) masses = 7 iters = 52 mflops = 2.299120e+05
OK converged final_rsq= 2.3e-15 (cf 2.5e-15) rel = 1.6e-13 (cf 0) restarts = 0 iters= 52
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 24 iterations
shift=0, 24 iterations, relative residual: iterated = 2.364558e-09, true = 2.364558e-09
shift=1, 24 iterations, relative residual: iterated = 8.370411e-11, true = 8.370411e-11
shift=2, 24 iterations, relative residual: iterated = 9.127935e-14, true = 9.127970e-14
shift=3, 21 iterations, relative residual: iterated = 2.475549e-16, true = 3.637033e-16
shift=4, 15 iterations, relative residual: iterated = 3.230745e-16, true = 3.922743e-16
shift=5, 11 iterations, relative residual: iterated = 1.009845e-16, true = 2.171125e-16
shift=6, 7 iterations, relative residual: iterated = 7.709456e-16, true = 7.834564e-16
CONGRAD5: time = 8.125687e-02 (multicg_offset_QUDA D) masses = 7 iters = 24 mflops = 6.190738e+04
OK converged final_rsq= 5.6e-18 (cf 2.5e-17) rel = 9.9e-16 (cf 0) restarts = 0 iters= 24
FFTIME: time = 2.497515e+01 (HISQ QUDA D) terms = 37 flops/site = 0 mflops = 0.000000e+00
LINK_UPDATE: time = 8.425951e-03 mflops = 1.066420e+05
GFTIME: time = 1.682210e-02 (Symanzik1_QUDA) mflops = 1.455267e+06
LINK_UPDATE: time = 8.478165e-03 mflops = 1.059852e+05
GFTIME: time = 1.680994e-02 (Symanzik1_QUDA) mflops = 1.456319e+06
LINK_UPDATE: time = 8.481979e-03 mflops = 1.059375e+05
GFTIME: time = 1.686311e-02 (Symanzik1_QUDA) mflops = 1.451728e+06
LINK_UPDATE: time = 8.466005e-03 mflops = 1.061374e+05
GFTIME: time = 1.679420e-02 (Symanzik1_QUDA) mflops = 1.457684e+06
LINK_UPDATE: time = 8.469105e-03 mflops = 1.060986e+05
Combined fattening and long-link calculation time: 0.008104
Combined fattening and long-link calculation time: 0.019970
FLTIME: time = 2.789850e-01 (HISQ QUDA D) mflops = 7.273681e+04
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 95 iterations
shift=0, 95 iterations, relative residual: iterated = 2.331713e-08, true = 2.331713e-08
shift=1, 95 iterations, relative residual: iterated = 2.285545e-08, true = 2.285545e-08
shift=2, 95 iterations, relative residual: iterated = 2.162586e-08, true = 2.162586e-08
shift=3, 95 iterations, relative residual: iterated = 1.896106e-08, true = 1.896106e-08
shift=4, 95 iterations, relative residual: iterated = 1.409934e-08, true = 1.409934e-08
shift=5, 95 iterations, relative residual: iterated = 8.066745e-09, true = 8.066745e-09
shift=6, 95 iterations, relative residual: iterated = 2.490810e-09, true = 2.490810e-09
shift=7, 95 iterations, relative residual: iterated = 3.476911e-10, true = 3.476911e-10
shift=8, 95 iterations, relative residual: iterated = 3.427215e-11, true = 3.427215e-11
Saving 1831 sets of cached parameters to /gpfs/alpinetds/csc190/scratch/gottlieb/run/tune/tunecache.tsv
CONGRAD5: time = 1.467640e-01 (multicg_offset_QUDA D) masses = 9 iters = 95 mflops = 1.387806e+05
OK converged final_rsq= 5.4e-16 (cf 6.2e-16) rel = 1.8e-14 (cf 0) restarts = 0 iters= 95
MultiShift CG: Converged after 57 iterations
shift=0, 57 iterations, relative residual: iterated = 4.180237e-08, true = 4.180237e-08
shift=1, 57 iterations, relative residual: iterated = 1.394096e-09, true = 1.394096e-09
shift=2, 57 iterations, relative residual: iterated = 2.502369e-13, true = 2.502387e-13
shift=3, 43 iterations, relative residual: iterated = 4.819548e-16, true = 6.685948e-16
shift=4, 25 iterations, relative residual: iterated = 5.142128e-16, true = 5.938002e-16
shift=5, 15 iterations, relative residual: iterated = 2.981804e-16, true = 3.657939e-16
shift=6, 9 iterations, relative residual: iterated = 1.249907e-16, true = 2.389302e-16
CONGRAD5: time = 5.000305e-02 (multicg_offset_QUDA D) masses = 7 iters = 57 mflops = 2.389294e+05
OK converged final_rsq= 1.7e-15 (cf 2.5e-15) rel = 1.2e-13 (cf 0) restarts = 0 iters= 57
MultiShift CG: Converged after 57 iterations
shift=0, 57 iterations, relative residual: iterated = 4.305819e-08, true = 4.305819e-08
shift=1, 57 iterations, relative residual: iterated = 1.431974e-09, true = 1.431974e-09
shift=2, 57 iterations, relative residual: iterated = 2.556347e-13, true = 2.556344e-13
shift=3, 43 iterations, relative residual: iterated = 4.944132e-16, true = 6.789685e-16
shift=4, 25 iterations, relative residual: iterated = 5.163982e-16, true = 5.984993e-16
shift=5, 15 iterations, relative residual: iterated = 3.024478e-16, true = 3.776876e-16
shift=6, 9 iterations, relative residual: iterated = 1.267542e-16, true = 1.968747e-16
CONGRAD5: time = 5.022001e-02 (multicg_offset_QUDA D) masses = 7 iters = 57 mflops = 2.378972e+05
OK converged final_rsq= 1.9e-15 (cf 2.5e-15) rel = 1.2e-13 (cf 0) restarts = 0 iters= 57
MultiShift CG: Converged after 58 iterations
shift=0, 58 iterations, relative residual: iterated = 4.917833e-08, true = 4.917833e-08
shift=1, 58 iterations, relative residual: iterated = 1.479684e-09, true = 1.479684e-09
shift=2, 58 iterations, relative residual: iterated = 2.073765e-13, true = 2.073778e-13
shift=3, 43 iterations, relative residual: iterated = 4.927973e-16, true = 7.038457e-16
shift=4, 25 iterations, relative residual: iterated = 5.133488e-16, true = 5.946719e-16
shift=5, 15 iterations, relative residual: iterated = 3.029045e-16, true = 3.629578e-16
shift=6, 9 iterations, relative residual: iterated = 1.271109e-16, true = 2.530356e-16
CONGRAD5: time = 5.057907e-02 (multicg_offset_QUDA D) masses = 7 iters = 58 mflops = 2.403524e+05
OK converged final_rsq= 2.4e-15 (cf 2.5e-15) rel = 1.6e-13 (cf 0) restarts = 0 iters= 58
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 24 iterations
shift=0, 24 iterations, relative residual: iterated = 2.545818e-09, true = 2.545818e-09
shift=1, 24 iterations, relative residual: iterated = 8.754166e-11, true = 8.754166e-11
shift=2, 24 iterations, relative residual: iterated = 9.113150e-14, true = 9.113207e-14
shift=3, 21 iterations, relative residual: iterated = 2.359381e-16, true = 3.534782e-16
shift=4, 15 iterations, relative residual: iterated = 2.767385e-16, true = 3.455814e-16
shift=5, 11 iterations, relative residual: iterated = 8.843093e-17, true = 1.887503e-16
shift=6, 7 iterations, relative residual: iterated = 7.182274e-16, true = 7.323282e-16
CONGRAD5: time = 8.056688e-02 (multicg_offset_QUDA D) masses = 7 iters = 24 mflops = 6.243757e+04
OK converged final_rsq= 6.5e-18 (cf 2.5e-17) rel = 1.1e-15 (cf 0) restarts = 0 iters= 24
FFTIME: time = 7.929149e-01 (HISQ QUDA D) terms = 37 flops/site = 0 mflops = 0.000000e+00
LINK_UPDATE: time = 8.450031e-03 mflops = 1.063381e+05
GFTIME: time = 1.688409e-02 (Symanzik1_QUDA) mflops = 1.449924e+06
LINK_UPDATE: time = 8.469105e-03 mflops = 1.060986e+05
REUNITARIZE: time = 6.437063e-03
PLAQUETTE ACTION: -3.666786e+06
Combined fattening and long-link calculation time: 0.008084
Combined fattening and long-link calculation time: 0.019989
FLTIME: time = 2.774181e-01 (HISQ QUDA D) mflops = 7.314763e+04
ks_multicg_offset_field_gpu: fn, notify: Signal QUDA to refresh links
ks_multicg_offset_field_gpu: naik_epsilon: Signal QUDA to refresh links
MultiShift CG: Converged after 98 iterations
shift=0, 98 iterations, relative residual: iterated = 1.921398e-08, true = 1.921398e-08
shift=1, 98 iterations, relative residual: iterated = 1.890918e-08, true = 1.890918e-08
shift=2, 98 iterations, relative residual: iterated = 1.818962e-08, true = 1.818962e-08
shift=3, 98 iterations, relative residual: iterated = 1.676203e-08, true = 1.676203e-08
shift=4, 98 iterations, relative residual: iterated = 1.420448e-08, true = 1.420448e-08
shift=5, 98 iterations, relative residual: iterated = 1.024653e-08, true = 1.024653e-08
shift=6, 98 iterations, relative residual: iterated = 5.689320e-09, true = 5.689320e-09
shift=7, 98 iterations, relative residual: iterated = 2.126702e-09, true = 2.126702e-09
shift=8, 98 iterations, relative residual: iterated = 4.577740e-10, true = 4.577740e-10
shift=9, 98 iterations, relative residual: iterated = 6.602792e-11, true = 6.602792e-11
shift=10, 98 iterations, relative residual: iterated = 1.156545e-11, true = 1.156545e-11
CONGRAD5: time = 1.485040e-01 (multicg_offset_QUDA D) masses = 11 iters = 98 mflops = 1.446533e+05
OK converged final_rsq= 3.7e-16 (cf 4e-16) rel = 1.2e-14 (cf 0) restarts = 0 iters= 98
MultiShift CG: Converged after 65 iterations
shift=0, 65 iterations, relative residual: iterated = 1.937263e-08, true = 1.937263e-08
shift=1, 65 iterations, relative residual: iterated = 1.511188e-09, true = 1.511188e-09
shift=2, 65 iterations, relative residual: iterated = 4.899673e-12, true = 4.899673e-12
shift=3, 61 iterations, relative residual: iterated = 8.644573e-16, true = 1.047507e-15
shift=4, 41 iterations, relative residual: iterated = 7.443824e-16, true = 8.687410e-16
shift=5, 27 iterations, relative residual: iterated = 4.236602e-16, true = 5.501619e-16
shift=6, 18 iterations, relative residual: iterated = 2.696841e-16, true = 3.621450e-16
shift=7, 12 iterations, relative residual: iterated = 2.262608e-16, true = 2.855223e-16
shift=8, 8 iterations, relative residual: iterated = 4.290331e-17, true = 1.745184e-16
CONGRAD5: time = 5.867004e-02 (multicg_offset_QUDA D) masses = 9 iters = 65 mflops = 2.375318e+05
OK converged final_rsq= 3.8e-16 (cf 4e-16) rel = 2.5e-14 (cf 0) restarts = 0 iters= 65
MultiShift CG: Converged after 66 iterations
shift=0, 66 iterations, relative residual: iterated = 1.749747e-08, true = 1.749747e-08
shift=1, 66 iterations, relative residual: iterated = 1.294698e-09, true = 1.294698e-09
shift=2, 66 iterations, relative residual: iterated = 3.752669e-12, true = 3.752669e-12
shift=3, 61 iterations, relative residual: iterated = 8.781894e-16, true = 1.056438e-15