[root@kaze r14]# ls -l
total 7513916
-rwxrwxrwx. 1 kaze kaze  178708944 Mar  6 22:59 22338618_QWORDS.bin
-rw-r--r--. 1 root root          0 Mar 13 22:53 22338618_QWORDS.bin.sorted
-rwxrwxrwx. 1 kaze kaze       1063 Mar 13 21:43 bench_gcc32GB.sh
-rwxrwxrwx. 1 kaze kaze        222 Mar 13 18:38 bench_gcc64GB.sh
-rwxrwxrwx. 1 kaze kaze       9327 Mar 13 18:28 crumsort.c
-rwxrwxrwx. 1 kaze kaze      10704 Mar 13 18:24 crumsort.h
-rwxrwxrwx. 1 kaze kaze 3803483832 Nov 29 02:06 Fedora-Workstation-35-1.2.aarch64.raw.xz
-rw-r--r--. 1 root root          0 Mar 13 20:59 Fedora-Workstation-35-1.2.aarch64.raw.xz.sorted
-rwxrwxrwx. 1 kaze kaze 2009333760 Nov 28 23:21 Fedora-Workstation-Live-x86_64-35-1.2.iso
-rw-r--r--. 1 root root          0 Mar 13 20:53 Fedora-Workstation-Live-x86_64-35-1.2.iso.sorted
-rwxrwxrwx. 1 kaze kaze 1137582080 Mar  1 19:08 linux-5.15.25.tar
-rw-r--r--. 1 root root          0 Mar 13 21:42 linux-5.15.25.tar.sorted
-rwxrwxrwx. 1 kaze kaze      19115 Mar  8 23:32 Magnetica_v12.h
-rwxrwxrwx. 1 kaze kaze      63531 Mar 10 23:55 Magnetica_v13.h
-rwxrwxrwx. 1 kaze kaze      94030 Mar 13 22:46 Magnetica_v14.h
-rwxrwxrwx. 1 kaze kaze        657 Mar 13 18:36 make_elf14.sh
-rwxrwxrwx. 1 kaze kaze   24823016 Mar  6 22:59 mobythesaurus.txt
-rw-r--r--. 1 root root          0 Mar 13 22:49 mobythesaurus.txt.sorted
-rwxrwxrwx. 1 kaze kaze     164095 Mar 13 22:01 QS_bench_r14.c
-rw-rw-r--. 1 kaze kaze     771431 Mar 13 22:52 QS_bench_r14.elf.asm
-rwxrwxr-x. 1 kaze kaze  270343816 Mar 13 22:52 QS_bench_r14_GCC11.2.1.elf
-rwxrwxr-x. 1 kaze kaze  268676136 Mar 13 22:52 QS_bench_r14_GCC11.2.1.exe
-rwxrwxrwx. 1 kaze kaze      23515 Mar 12 10:01 quadsort.c
-rwxrwxrwx. 1 kaze kaze      12100 Mar 13 18:31 quadsort.h
-rwxrwxrwx. 1 kaze kaze      70861 Mar 13 18:23 wolfsort-master.zip
[root@kaze r14]# echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
performance
[root@kaze r14]# sh bench_gcc32GB.sh 
Current priority is -20.
Allocating AUX-Buffer 21MB ...
Allocating Master-Buffer 17043MB ...
Sorting in single-thread 2233861800 elements...
Done in 385 seconds.
Sorting sorted elements...
Done in 342 seconds.
Checking whether sort went correct... OK. Unique keys = 10

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf qsort few':

        741,176.13 msec task-clock                #    1.000 CPUs utilized          
             9,131      context-switches          #   12.320 /sec                   
               419      cpu-migrations            #    0.565 /sec                   
         4,406,675      page-faults               #    5.946 K/sec                  
 2,282,977,109,087      cycles                    #    3.080 GHz                      (50.00%)
 6,448,450,744,497      instructions              #    2.82  insn per cycle           (62.50%)
 1,150,755,447,984      branches                  #    1.553 G/sec                    (62.50%)
     4,230,648,615      branch-misses             #    0.37% of all branches          (62.50%)
 1,450,135,698,847      L1-dcache-loads           #    1.957 G/sec                    (62.50%)
    13,376,561,911      L1-dcache-load-misses     #    0.92% of all L1-dcache accesses  (62.50%)
       882,666,046      LLC-loads                 #    1.191 M/sec                    (50.00%)
       183,275,336      LLC-load-misses           #   20.76% of all LL-cache accesses  (50.00%)

     741.396869717 seconds time elapsed

     731.397070000 seconds user
       5.245706000 seconds sys


Current priority is -20.
Allocating AUX-Buffer 21MB ...
Allocating Master-Buffer 17043MB ...
Sorting in single-thread 2233861800 elements...
Done in 29 seconds.
Sorting sorted elements...
Done in 6 seconds.
Checking whether sort went correct... OK. Unique keys = 10

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf Magnetica few':

         48,812.66 msec task-clock                #    1.000 CPUs utilized          
               622      context-switches          #   12.743 /sec                   
                49      cpu-migrations            #    1.004 /sec                   
         4,406,676      page-faults               #   90.277 K/sec                  
   150,249,961,844      cycles                    #    3.078 GHz                      (49.99%)
   171,452,642,615      instructions              #    1.14  insn per cycle           (62.50%)
    40,969,655,494      branches                  #  839.324 M/sec                    (62.49%)
     3,143,419,558      branch-misses             #    7.67% of all branches          (62.50%)
    28,323,570,933      L1-dcache-loads           #  580.250 M/sec                    (62.50%)
     3,166,487,955      L1-dcache-load-misses     #   11.18% of all L1-dcache accesses  (62.51%)
       398,800,860      LLC-loads                 #    8.170 M/sec                    (50.00%)
       234,611,263      LLC-load-misses           #   58.83% of all LL-cache accesses  (50.00%)

      48.821742330 seconds time elapsed

      43.312098000 seconds user
       5.150140000 seconds sys


Current priority is -20.
Allocating AUX-Buffer 21MB ...
Allocating Master-Buffer 17043MB ...
Sorting in single-thread 2233861800 elements...
Done in 38 seconds.
Sorting sorted elements...
Done in 13 seconds.
Checking whether sort went correct... OK. Unique keys = 10

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf BM few':

         65,090.69 msec task-clock                #    1.000 CPUs utilized          
               667      context-switches          #   10.247 /sec                   
                38      cpu-migrations            #    0.584 /sec                   
         4,406,674      page-faults               #   67.701 K/sec                  
   200,382,494,934      cycles                    #    3.079 GHz                      (50.00%)
   246,587,334,436      instructions              #    1.23  insn per cycle           (62.50%)
    50,900,521,440      branches                  #  781.994 M/sec                    (62.50%)
     2,979,113,705      branch-misses             #    5.85% of all branches          (62.50%)
    40,317,442,202      L1-dcache-loads           #  619.404 M/sec                    (62.50%)
     4,104,713,121      L1-dcache-load-misses     #   10.18% of all L1-dcache accesses  (62.50%)
       438,374,098      LLC-loads                 #    6.735 M/sec                    (50.00%)
       196,054,964      LLC-load-misses           #   44.72% of all LL-cache accesses  (50.00%)

      65.111262907 seconds time elapsed

      59.344413000 seconds user
       5.287248000 seconds sys


Current priority is -20.
Allocating AUX-Buffer 21MB ...
Allocating Master-Buffer 17043MB ...
Sorting in single-thread 2233861800 elements...
Done in 29 seconds.
Sorting sorted elements...
Done in 4 seconds.
Checking whether sort went correct... OK. Unique keys = 10

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf CS few':

         46,915.78 msec task-clock                #    1.000 CPUs utilized          
               771      context-switches          #   16.434 /sec                   
                50      cpu-migrations            #    1.066 /sec                   
         4,406,676      page-faults               #   93.927 K/sec                  
   144,478,573,987      cycles                    #    3.080 GHz                      (50.00%)
   351,332,884,902      instructions              #    2.43  insn per cycle           (62.50%)
    56,912,050,006      branches                  #    1.213 G/sec                    (62.50%)
        96,734,801      branch-misses             #    0.17% of all branches          (62.51%)
    78,229,007,507      L1-dcache-loads           #    1.667 G/sec                    (62.50%)
     2,838,213,026      L1-dcache-load-misses     #    3.63% of all L1-dcache accesses  (62.50%)
        80,097,493      LLC-loads                 #    1.707 M/sec                    (49.99%)
        50,451,503      LLC-load-misses           #   62.99% of all LL-cache accesses  (50.00%)

      46.926886620 seconds time elapsed

      41.451221000 seconds user
       5.154393000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 23MB ...
Allocating AUX-Buffer 189MB ...
Allocating Master-Buffer 18938MB ...
Sorting in single-thread 2482300900 elements...
Done in 527 seconds.
Sorting sorted elements...
Done in 234 seconds.
Checking whether sort went correct... OK. Unique keys = 2847531

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf qsort many':

        776,774.97 msec task-clock                #    1.000 CPUs utilized          
             9,109      context-switches          #   11.727 /sec                   
               446      cpu-migrations            #    0.574 /sec                   
         4,902,820      page-faults               #    6.312 K/sec                  
 2,392,351,852,804      cycles                    #    3.080 GHz                      (50.00%)
 4,921,980,445,033      instructions              #    2.06  insn per cycle           (62.50%)
   998,558,145,021      branches                  #    1.286 G/sec                    (62.50%)
    22,323,747,442      branch-misses             #    2.24% of all branches          (62.50%)
 1,141,624,230,258      L1-dcache-loads           #    1.470 G/sec                    (62.50%)
    15,644,921,235      L1-dcache-load-misses     #    1.37% of all L1-dcache accesses  (62.50%)
       513,061,373      LLC-loads                 #  660.502 K/sec                    (50.00%)
       228,259,488      LLC-load-misses           #   44.49% of all LL-cache accesses  (50.00%)

     777.040288815 seconds time elapsed

     766.133668000 seconds user
       5.840002000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 23MB ...
Allocating AUX-Buffer 189MB ...
Allocating Master-Buffer 18938MB ...
Sorting in single-thread 2482300900 elements...
Done in 198 seconds.
Sorting sorted elements...
Done in 47 seconds.
Checking whether sort went correct... OK. Unique keys = 2847531

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf Magnetica many':

        260,603.62 msec task-clock                #    1.000 CPUs utilized          
             3,146      context-switches          #   12.072 /sec                   
               158      cpu-migrations            #    0.606 /sec                   
         4,902,822      page-faults               #   18.813 K/sec                  
   802,093,619,954      cycles                    #    3.078 GHz                      (50.00%)
   936,751,248,598      instructions              #    1.17  insn per cycle           (62.50%)
   210,566,848,236      branches                  #  807.997 M/sec                    (62.50%)
    20,471,570,409      branch-misses             #    9.72% of all branches          (62.50%)
   168,928,902,470      L1-dcache-loads           #  648.222 M/sec                    (62.50%)
    16,002,393,914      L1-dcache-load-misses     #    9.47% of all L1-dcache accesses  (62.50%)
     2,782,766,631      LLC-loads                 #   10.678 M/sec                    (50.00%)
     1,499,655,659      LLC-load-misses           #   53.89% of all LL-cache accesses  (50.00%)

     260.685645075 seconds time elapsed

     252.857670000 seconds user
       5.838535000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 23MB ...
Allocating AUX-Buffer 189MB ...
Allocating Master-Buffer 18938MB ...
Sorting in single-thread 2482300900 elements...
Done in 223 seconds.
Sorting sorted elements...
Done in 47 seconds.
Checking whether sort went correct... OK. Unique keys = 2847531

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf BM many':

        286,287.34 msec task-clock                #    1.000 CPUs utilized          
             2,747      context-switches          #    9.595 /sec                   
               179      cpu-migrations            #    0.625 /sec                   
         4,902,819      page-faults               #   17.126 K/sec                  
   881,236,797,987      cycles                    #    3.078 GHz                      (50.00%)
 1,105,253,285,645      instructions              #    1.25  insn per cycle           (62.50%)
   272,772,199,608      branches                  #  952.792 M/sec                    (62.50%)
    18,453,665,676      branch-misses             #    6.77% of all branches          (62.50%)
   148,659,786,306      L1-dcache-loads           #  519.268 M/sec                    (62.50%)
    15,355,339,255      L1-dcache-load-misses     #   10.33% of all L1-dcache accesses  (62.50%)
       606,646,863      LLC-loads                 #    2.119 M/sec                    (50.00%)
       435,415,907      LLC-load-misses           #   71.77% of all LL-cache accesses  (50.00%)

     286.334426406 seconds time elapsed

     278.513610000 seconds user
       5.741575000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 23MB ...
Allocating AUX-Buffer 189MB ...
Allocating Master-Buffer 18938MB ...
Sorting in single-thread 2482300900 elements...
Done in 129 seconds.
Sorting sorted elements...
Done in 4 seconds.
Checking whether sort went correct... OK. Unique keys = 2847531

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf CS many':

        148,763.84 msec task-clock                #    1.000 CPUs utilized          
             1,634      context-switches          #   10.984 /sec                   
                64      cpu-migrations            #    0.430 /sec                   
         4,902,821      page-faults               #   32.957 K/sec                  
   458,077,528,982      cycles                    #    3.079 GHz                      (50.00%)
 1,284,147,329,900      instructions              #    2.80  insn per cycle           (62.50%)
   191,345,711,696      branches                  #    1.286 G/sec                    (62.50%)
       622,988,523      branch-misses             #    0.33% of all branches          (62.50%)
   302,236,346,094      L1-dcache-loads           #    2.032 G/sec                    (62.50%)
     7,916,476,379      L1-dcache-load-misses     #    2.62% of all L1-dcache accesses  (62.50%)
       182,495,043      LLC-loads                 #    1.227 M/sec                    (50.00%)
       109,006,042      LLC-load-misses           #   59.73% of all LL-cache accesses  (50.00%)

     148.806697173 seconds time elapsed

     142.016658000 seconds user
       5.766153000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1084MB ...
Allocating Master-Buffer 8679MB ...
Sorting in single-thread 1137582073 elements...
Done in 165 seconds.
Sorting sorted elements...
Done in 55 seconds.
Checking whether sort went correct... OK. Unique keys = 77275994

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf qsort manyC':

        229,007.91 msec task-clock                #    0.998 CPUs utilized          
             3,722      context-switches          #   16.253 /sec                   
               134      cpu-migrations            #    0.585 /sec                   
         5,832,362      page-faults               #   25.468 K/sec                  
   704,876,530,801      cycles                    #    3.078 GHz                      (50.00%)
 1,369,822,972,984      instructions              #    1.94  insn per cycle           (62.50%)
   326,383,470,566      branches                  #    1.425 G/sec                    (62.50%)
     7,220,886,293      branch-misses             #    2.21% of all branches          (62.50%)
   325,386,845,311      L1-dcache-loads           #    1.421 G/sec                    (62.50%)
    14,417,830,783      L1-dcache-load-misses     #    4.43% of all L1-dcache accesses  (62.50%)
       639,196,876      LLC-loads                 #    2.791 M/sec                    (50.00%)
       226,156,830      LLC-load-misses           #   35.38% of all LL-cache accesses  (50.00%)

     229.493279473 seconds time elapsed

     220.241849000 seconds user
       7.116753000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1084MB ...
Allocating Master-Buffer 8679MB ...
Sorting in single-thread 1137582073 elements...
Done in 86 seconds.
Sorting sorted elements...
Done in 22 seconds.
Checking whether sort went correct... OK. Unique keys = 77275994

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf Magnetica manyC':

        115,352.20 msec task-clock                #    1.000 CPUs utilized          
             1,199      context-switches          #   10.394 /sec                   
                79      cpu-migrations            #    0.685 /sec                   
         2,499,605      page-faults               #   21.669 K/sec                  
   354,970,198,697      cycles                    #    3.077 GHz                      (49.99%)
   443,844,553,192      instructions              #    1.25  insn per cycle           (62.50%)
    97,156,441,844      branches                  #  842.259 M/sec                    (62.50%)
     8,951,913,406      branch-misses             #    9.21% of all branches          (62.50%)
    78,557,775,541      L1-dcache-loads           #  681.025 M/sec                    (62.50%)
     6,028,568,093      L1-dcache-load-misses     #    7.67% of all L1-dcache accesses  (62.51%)
     1,033,708,338      LLC-loads                 #    8.961 M/sec                    (50.00%)
       546,965,854      LLC-load-misses           #   52.91% of all LL-cache accesses  (50.00%)

     115.376479128 seconds time elapsed

     111.478665000 seconds user
       3.008494000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1084MB ...
Allocating Master-Buffer 8679MB ...
Sorting in single-thread 1137582073 elements...
Done in 100 seconds.
Sorting sorted elements...
Done in 26 seconds.
Checking whether sort went correct... OK. Unique keys = 77275994

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf BM manyC':

        134,149.00 msec task-clock                #    1.000 CPUs utilized          
             1,378      context-switches          #   10.272 /sec                   
                81      cpu-migrations            #    0.604 /sec                   
         2,499,602      page-faults               #   18.633 K/sec                  
   412,850,788,936      cycles                    #    3.078 GHz                      (50.00%)
   507,140,963,617      instructions              #    1.23  insn per cycle           (62.50%)
   124,964,628,101      branches                  #  931.536 M/sec                    (62.50%)
     8,908,865,606      branch-misses             #    7.13% of all branches          (62.50%)
    70,369,183,706      L1-dcache-loads           #  524.560 M/sec                    (62.50%)
     5,938,371,053      L1-dcache-load-misses     #    8.44% of all L1-dcache accesses  (62.50%)
       258,728,599      LLC-loads                 #    1.929 M/sec                    (50.00%)
       170,359,231      LLC-load-misses           #   65.84% of all LL-cache accesses  (50.00%)

     134.183238731 seconds time elapsed

     130.144098000 seconds user
       3.014209000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1084MB ...
Allocating Master-Buffer 8679MB ...
Sorting in single-thread 1137582073 elements...
Done in 61 seconds.
Sorting sorted elements...
Done in 2 seconds.
Checking whether sort went correct... OK. Unique keys = 77275994

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf CS manyC':

         70,754.35 msec task-clock                #    1.000 CPUs utilized          
               851      context-switches          #   12.028 /sec                   
                56      cpu-migrations            #    0.791 /sec                   
         2,499,604      page-faults               #   35.328 K/sec                  
   217,810,654,072      cycles                    #    3.078 GHz                      (49.99%)
   603,065,127,518      instructions              #    2.77  insn per cycle           (62.50%)
    89,276,865,285      branches                  #    1.262 G/sec                    (62.50%)
       463,546,632      branch-misses             #    0.52% of all branches          (62.50%)
   141,013,572,873      L1-dcache-loads           #    1.993 G/sec                    (62.50%)
     3,102,962,136      L1-dcache-load-misses     #    2.20% of all L1-dcache accesses  (62.50%)
        78,996,768      LLC-loads                 #    1.116 M/sec                    (50.00%)
        46,820,775      LLC-load-misses           #   59.27% of all LL-cache accesses  (50.00%)

      70.765982083 seconds time elapsed

      67.332424000 seconds user
       2.928503000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1916MB ...
Allocating AUX-Buffer 15329MB ...
Allocating Master-Buffer 15329MB ...
Sorting in single-thread 2009333753 elements...
Done in 516 seconds.
Sorting sorted elements...
Done in 128 seconds.
Checking whether sort went correct... OK. Unique keys = 1912608132

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf qsort ALL':

        666,887.14 msec task-clock                #    0.997 CPUs utilized          
            17,173      context-switches          #   25.751 /sec                   
               488      cpu-migrations            #    0.732 /sec                   
         8,339,553      page-faults               #   12.505 K/sec                  
 2,053,471,385,498      cycles                    #    3.079 GHz                      (50.00%)
 3,250,596,357,540      instructions              #    1.58  insn per cycle           (62.50%)
   725,714,710,076      branches                  #    1.088 G/sec                    (62.50%)
    27,725,038,851      branch-misses             #    3.82% of all branches          (62.50%)
   763,847,707,475      L1-dcache-loads           #    1.145 G/sec                    (62.50%)
    13,182,340,804      L1-dcache-load-misses     #    1.73% of all L1-dcache accesses  (62.50%)
       451,075,991      LLC-loads                 #  676.390 K/sec                    (50.00%)
       194,868,222      LLC-load-misses           #   43.20% of all LL-cache accesses  (50.00%)

     668.793142197 seconds time elapsed

     650.689221000 seconds user
      11.992086000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1916MB ...
Allocating AUX-Buffer 15329MB ...
Allocating Master-Buffer 15329MB ...
Sorting in single-thread 2009333753 elements...
Done in 241 seconds.
Sorting sorted elements...
Done in 66 seconds.
Checking whether sort went correct... OK. Unique keys = 1912608132

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf Magnetica ALL':

        329,071.15 msec task-clock                #    0.995 CPUs utilized          
             5,740      context-switches          #   17.443 /sec                   
               185      cpu-migrations            #    0.562 /sec                   
         8,339,555      page-faults               #   25.343 K/sec                  
 1,012,531,312,853      cycles                    #    3.077 GHz                      (50.00%)
 1,291,624,832,269      instructions              #    1.28  insn per cycle           (62.50%)
   259,778,748,631      branches                  #  789.430 M/sec                    (62.50%)
    25,278,559,690      branch-misses             #    9.73% of all branches          (62.50%)
   222,539,768,208      L1-dcache-loads           #  676.266 M/sec                    (62.50%)
    13,653,065,150      L1-dcache-load-misses     #    6.14% of all L1-dcache accesses  (62.50%)
     2,192,397,791      LLC-loads                 #    6.662 M/sec                    (50.00%)
     1,097,375,480      LLC-load-misses           #   50.05% of all LL-cache accesses  (50.00%)

     330.699343682 seconds time elapsed

     315.480316000 seconds user
      11.296764000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1916MB ...
Allocating AUX-Buffer 15329MB ...
Allocating Master-Buffer 15329MB ...
Sorting in single-thread 2009333753 elements...
Done in 304 seconds.
Sorting sorted elements...
Done in 65 seconds.
Checking whether sort went correct... OK. Unique keys = 1912608132

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf BM ALL':

        389,600.48 msec task-clock                #    1.000 CPUs utilized          
             4,868      context-switches          #   12.495 /sec                   
               349      cpu-migrations            #    0.896 /sec                   
         8,339,556      page-faults               #   21.405 K/sec                  
 1,199,296,651,931      cycles                    #    3.078 GHz                      (50.00%)
 1,460,132,564,676      instructions              #    1.22  insn per cycle           (62.50%)
   358,765,130,483      branches                  #  920.854 M/sec                    (62.50%)
    25,947,160,599      branch-misses             #    7.23% of all branches          (62.50%)
   208,310,484,069      L1-dcache-loads           #  534.677 M/sec                    (62.50%)
    13,544,068,269      L1-dcache-load-misses     #    6.50% of all L1-dcache accesses  (62.50%)
       510,462,905      LLC-loads                 #    1.310 M/sec                    (50.00%)
       359,045,897      LLC-load-misses           #   70.34% of all LL-cache accesses  (50.00%)

     389.715860036 seconds time elapsed

     376.913075000 seconds user
       9.975587000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 1916MB ...
Allocating AUX-Buffer 15329MB ...
Allocating Master-Buffer 15329MB ...
Sorting in single-thread 2009333753 elements...
Done in 173 seconds.
Sorting sorted elements...
Done in 3 seconds.
Checking whether sort went correct... OK. Unique keys = 1912608132

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf CS ALL':

        197,263.15 msec task-clock                #    0.999 CPUs utilized          
             5,205      context-switches          #   26.386 /sec                   
               124      cpu-migrations            #    0.629 /sec                   
         8,339,554      page-faults               #   42.276 K/sec                  
   607,345,573,486      cycles                    #    3.079 GHz                      (50.00%)
 1,605,371,408,284      instructions              #    2.64  insn per cycle           (62.50%)
   229,123,071,463      branches                  #    1.162 G/sec                    (62.50%)
     1,615,672,906      branch-misses             #    0.71% of all branches          (62.50%)
   378,860,890,134      L1-dcache-loads           #    1.921 G/sec                    (62.50%)
     7,009,483,703      L1-dcache-load-misses     #    1.85% of all L1-dcache accesses  (62.51%)
       189,366,238      LLC-loads                 #  959.968 K/sec                    (50.00%)
       101,094,643      LLC-load-misses           #   53.39% of all LL-cache accesses  (50.00%)

     197.425433206 seconds time elapsed

     185.483587000 seconds user
      10.439897000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 3627MB ...
Allocating Master-Buffer 29018MB ...
Sorting in single-thread 3803483825 elements...
Done in 999 seconds.
Sorting sorted elements...
Done in 252 seconds.
Checking whether sort went correct... OK. Unique keys = 3346259533

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf qsort ALLmore':

      1,274,260.71 msec task-clock                #    0.995 CPUs utilized          
            19,189      context-switches          #   15.059 /sec                   
               855      cpu-migrations            #    0.671 /sec                   
         8,357,296      page-faults               #    6.559 K/sec                  
 3,924,149,682,152      cycles                    #    3.080 GHz                      (50.00%)
 6,250,299,799,611      instructions              #    1.59  insn per cycle           (62.50%)
 1,396,475,831,498      branches                  #    1.096 G/sec                    (62.50%)
    53,746,876,296      branch-misses             #    3.85% of all branches          (62.50%)
 1,467,716,577,883      L1-dcache-loads           #    1.152 G/sec                    (62.50%)
    24,533,499,860      L1-dcache-load-misses     #    1.67% of all L1-dcache accesses  (62.50%)
       785,095,426      LLC-loads                 #  616.118 K/sec                    (50.00%)
       378,625,583      LLC-load-misses           #   48.23% of all LL-cache accesses  (50.00%)

    1280.346914719 seconds time elapsed

    1255.634703000 seconds user
      10.612325000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 3627MB ...
Allocating Master-Buffer 29018MB ...
Sorting in single-thread 3803483825 elements...
Done in 472 seconds.
Sorting sorted elements...
Done in 134 seconds.
Checking whether sort went correct... OK. Unique keys = 3346259533

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf Magnetica ALLmore':

        634,811.66 msec task-clock                #    0.994 CPUs utilized          
            24,293      context-switches          #   38.268 /sec                   
               554      cpu-migrations            #    0.873 /sec                   
         8,357,323      page-faults               #   13.165 K/sec                  
 1,953,442,190,369      cycles                    #    3.077 GHz                      (50.00%)
 2,503,942,225,085      instructions              #    1.28  insn per cycle           (62.50%)
   504,388,086,433      branches                  #  794.548 M/sec                    (62.50%)
    49,686,992,111      branch-misses             #    9.85% of all branches          (62.50%)
   428,919,234,339      L1-dcache-loads           #  675.664 M/sec                    (62.50%)
    26,287,500,541      L1-dcache-load-misses     #    6.13% of all L1-dcache accesses  (62.50%)
     4,582,675,882      LLC-loads                 #    7.219 M/sec                    (50.00%)
     2,330,147,507      LLC-load-misses           #   50.85% of all LL-cache accesses  (50.00%)

     638.388911150 seconds time elapsed

     614.736052000 seconds user
      15.354805000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 3627MB ...
Allocating Master-Buffer 29018MB ...
Sorting in single-thread 3803483825 elements...
Done in 597 seconds.
Sorting sorted elements...
Done in 139 seconds.
Checking whether sort went correct... OK. Unique keys = 3346259533

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf BM ALLmore':

        760,701.91 msec task-clock                #    0.998 CPUs utilized          
            14,274      context-switches          #   18.764 /sec                   
               527      cpu-migrations            #    0.693 /sec                   
         8,357,297      page-faults               #   10.986 K/sec                  
 2,341,245,478,965      cycles                    #    3.078 GHz                      (50.00%)
 2,848,210,143,410      instructions              #    1.22  insn per cycle           (62.50%)
   697,981,168,200      branches                  #  917.549 M/sec                    (62.50%)
    52,575,388,329      branch-misses             #    7.53% of all branches          (62.50%)
   399,594,878,710      L1-dcache-loads           #  525.298 M/sec                    (62.50%)
    25,691,363,700      L1-dcache-load-misses     #    6.43% of all L1-dcache accesses  (62.50%)
       999,974,393      LLC-loads                 #    1.315 M/sec                    (50.00%)
       728,263,085      LLC-load-misses           #   72.83% of all LL-cache accesses  (50.00%)

     762.247038059 seconds time elapsed

     743.987373000 seconds user
      11.417382000 seconds sys


Current priority is -20.
Allocating FILE-Buffer 3627MB ...
Allocating Master-Buffer 29018MB ...
Sorting in single-thread 3803483825 elements...
Done in 339 seconds.
Sorting sorted elements...
Done in 7 seconds.
Checking whether sort went correct... OK. Unique keys = 3346259533

 Performance counter stats for './QS_bench_r14_GCC11.2.1.elf CS ALLmore':

        371,414.00 msec task-clock                #    0.996 CPUs utilized          
            13,157      context-switches          #   35.424 /sec                   
               292      cpu-migrations            #    0.786 /sec                   
         8,357,301      page-faults               #   22.501 K/sec                  
 1,143,342,186,618      cycles                    #    3.078 GHz                      (50.00%)
 3,102,283,088,926      instructions              #    2.71  insn per cycle           (62.50%)
   441,240,536,936      branches                  #    1.188 G/sec                    (62.50%)
     3,106,936,874      branch-misses             #    0.70% of all branches          (62.50%)
   730,732,887,523      L1-dcache-loads           #    1.967 G/sec                    (62.50%)
    12,751,353,710      L1-dcache-load-misses     #    1.75% of all L1-dcache accesses  (62.50%)
       334,565,245      LLC-loads                 #  900.788 K/sec                    (50.00%)
       180,333,837      LLC-load-misses           #   53.90% of all LL-cache accesses  (50.00%)

     372.788505783 seconds time elapsed

     356.818094000 seconds user
      12.021176000 seconds sys


[root@kaze r14]# 

