API tools faq
paste
Advertisement
Guest User

o3_native

a guest
Mar 8th, 2025
32
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
C 23.18 KB | None | 0 0
raw download clone embed print report
  1.     .file   "galsim.c"
  2. # GNU C17 (Debian 12.2.0-14) version 12.2.0 (x86_64-linux-gnu)
  3. #   compiled by GNU C version 12.2.0, GMP version 6.2.1, MPFR version 4.1.1-p1, MPC version 1.3.1, isl version isl-0.25-GMP
  4.  
  5. # warning: MPFR header version 4.1.1-p1 differs from library version 4.2.0.
  6. # GGC heuristics: --param ggc-min-expand=100 --param ggc-min-heapsize=131072
  7. # options passed: -march=znver3 -mmmx -mpopcnt -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mavx -mavx2 -msse4a -mno-fma4 -mno-xop -mfma -mno-avx512f -mbmi -mbmi2 -maes -mpclmul -mno-avx512vl -mno-avx512bw -mno-avx512dq -mno-avx512cd -mno-avx512er -mno-avx512pf -mno-avx512vbmi -mno-avx512ifma -mno-avx5124vnniw -mno-avx5124fmaps -mno-avx512vpopcntdq -mno-avx512vbmi2 -mno-gfni -mvpclmulqdq -mno-avx512vnni -mno-avx512bitalg -mno-avx512bf16 -mno-avx512vp2intersect -mno-3dnow -madx -mabm -mno-cldemote -mclflushopt -mclwb -mclzero -mcx16 -mno-enqcmd -mf16c -mfsgsbase -mfxsr -mno-hle -msahf -mno-lwp -mlzcnt -mmovbe -mno-movdir64b -mno-movdiri -mno-mwaitx -mno-pconfig -mno-pku -mno-prefetchwt1 -mprfchw -mno-ptwrite -mrdpid -mrdrnd -mrdseed -mno-rtm -mno-serialize -mno-sgx -msha -mshstk -mno-tbm -mno-tsxldtrk -mvaes -mno-waitpkg -mno-wbnoinvd -mxsave -mxsavec -mxsaveopt -mxsaves -mno-amx-tile -mno-amx-int8 -mno-amx-bf16 -mno-uintr -mno-hreset -mno-kl -mno-widekl -mno-avxvnni -mno-avx512fp16 --param=l1-cache-size=32 --param=l1-cache-line-size=64 --param=l2-cache-size=512 -mtune=znver3 -O3 -fasynchronous-unwind-tables
  8.     .text
  9.     .section    .rodata.str1.8,"aMS",@progbits,1
  10.     .align 8
  11. .LC1:
  12.     .string "Correct Format: %s N inputfile timesteps deltaT graphics\n"
  13.     .section    .rodata.str1.1,"aMS",@progbits,1
  14. .LC2:
  15.     .string "Memory allocation error!"
  16. .LC3:
  17.     .string "File open error!"
  18. .LC5:
  19.     .string "Time for File to DS(s): %lf\n"
  20. .LC8:
  21.     .string "Time for Processing(s): %lf\n"
  22. .LC9:
  23.     .string "result.gal"
  24. .LC10:
  25.     .string "File create error!"
  26. .LC11:
  27.     .string "Time for DS to File(s): %lf\n"
  28.     .section    .text.startup,"ax",@progbits
  29.     .p2align 4
  30.     .globl  main
  31.     .type   main, @function
  32. main:
  33. .LFB22:
  34.     .cfi_startproc
  35.     pushq   %r15    #
  36.     .cfi_def_cfa_offset 16
  37.     .cfi_offset 15, -16
  38.     pushq   %r14    #
  39.     .cfi_def_cfa_offset 24
  40.     .cfi_offset 14, -24
  41.     pushq   %r13    #
  42.     .cfi_def_cfa_offset 32
  43.     .cfi_offset 13, -32
  44.     pushq   %r12    #
  45.     .cfi_def_cfa_offset 40
  46.     .cfi_offset 12, -40
  47.     pushq   %rbp    #
  48.     .cfi_def_cfa_offset 48
  49.     .cfi_offset 6, -48
  50.     pushq   %rbx    #
  51.     .cfi_def_cfa_offset 56
  52.     .cfi_offset 3, -56
  53.     movq    %rsi, %rbx  # tmp230, av
  54.     subq    $136, %rsp  #,
  55.     .cfi_def_cfa_offset 192
  56. # galsim.c:16:     if(ac != 6){
  57.     cmpl    $6, %edi    #, tmp229
  58.     je  .L2 #,
  59. # galsim.c:17:         printf("Correct Format: %s N inputfile timesteps deltaT graphics\n", av[0]);
  60.     movq    (%rsi), %rsi    # *av_77(D),
  61.     leaq    .LC1(%rip), %rdi    #, tmp169
  62.     xorl    %eax, %eax  #
  63.     call    printf@PLT  #
  64. .L3:
  65. # galsim.c:18:         return 1;
  66.     movl    $1, %eax    #, <retval>
  67. .L1:
  68. # galsim.c:126: }
  69.     addq    $136, %rsp  #,
  70.     .cfi_remember_state
  71.     .cfi_def_cfa_offset 56
  72.     popq    %rbx    #
  73.     .cfi_def_cfa_offset 48
  74.     popq    %rbp    #
  75.     .cfi_def_cfa_offset 40
  76.     popq    %r12    #
  77.     .cfi_def_cfa_offset 32
  78.     popq    %r13    #
  79.     .cfi_def_cfa_offset 24
  80.     popq    %r14    #
  81.     .cfi_def_cfa_offset 16
  82.     popq    %r15    #
  83.     .cfi_def_cfa_offset 8
  84.     ret
  85. .L2:
  86.     .cfi_restore_state
  87. # /usr/include/stdlib.h:364:   return (int) strtol (__nptr, (char **) NULL, 10);
  88.     movq    8(%rsi), %rdi   # MEM[(char * *)av_77(D) + 8B], MEM[(char * *)av_77(D) + 8B]
  89.     movl    $10, %edx   #,
  90.     xorl    %esi, %esi  #
  91.     call    strtol@PLT  #
  92.     movq    24(%rbx), %rdi  # MEM[(char * *)av_77(D) + 24B], MEM[(char * *)av_77(D) + 24B]
  93.     movl    $10, %edx   #,
  94.     xorl    %esi, %esi  #
  95. # galsim.c:23:     const char *inputfile = av[2];
  96.     movq    16(%rbx), %r15  # MEM[(char * *)av_77(D) + 16B], inputfile
  97. # /usr/include/stdlib.h:364:   return (int) strtol (__nptr, (char **) NULL, 10);
  98.     movq    %rax, %r14  # tmp231, _151
  99. # /usr/include/stdlib.h:364:   return (int) strtol (__nptr, (char **) NULL, 10);
  100.     movl    %eax, 32(%rsp)  # _152, %sfp
  101. # /usr/include/stdlib.h:364:   return (int) strtol (__nptr, (char **) NULL, 10);
  102.     call    strtol@PLT  #
  103. # /usr/include/x86_64-linux-gnu/bits/stdlib-float.h:27:   return strtod (__nptr, (char **) NULL);
  104.     movq    32(%rbx), %rdi  # MEM[(char * *)av_77(D) + 32B], MEM[(char * *)av_77(D) + 32B]
  105.     xorl    %esi, %esi  #
  106. # /usr/include/stdlib.h:364:   return (int) strtol (__nptr, (char **) NULL, 10);
  107.     movq    %rax, 48(%rsp)  # _149, %sfp
  108. # /usr/include/stdlib.h:364:   return (int) strtol (__nptr, (char **) NULL, 10);
  109.     movl    %eax, 24(%rsp)  # _150, %sfp
  110. # /usr/include/x86_64-linux-gnu/bits/stdlib-float.h:27:   return strtod (__nptr, (char **) NULL);
  111.     call    strtod@PLT  #
  112.     vmovsd  %xmm0, 16(%rsp) # _148, %sfp
  113. # galsim.c:28:     start = clock();
  114.     call    clock@PLT   #
  115.     movq    %rax, 40(%rsp)  # tmp234, %sfp
  116. # galsim.c:32:     particles.x = (double *) malloc(N * sizeof(double));
  117.     movslq  %r14d, %rax # _151, _152
  118.     leaq    0(,%rax,8), %r13    #, _8
  119.     movq    %r13, %rdi  # _8,
  120.     call    malloc@PLT  #
  121. # galsim.c:33:     particles.y = (double *) malloc(N * sizeof(double));
  122.     movq    %r13, %rdi  # _8,
  123. # galsim.c:32:     particles.x = (double *) malloc(N * sizeof(double));
  124.     movq    %rax, 8(%rsp)   # _9, %sfp
  125. # galsim.c:33:     particles.y = (double *) malloc(N * sizeof(double));
  126.     call    malloc@PLT  #
  127. # galsim.c:34:     particles.mass = (double *) malloc(N * sizeof(double));
  128.     movq    %r13, %rdi  # _8,
  129. # galsim.c:33:     particles.y = (double *) malloc(N * sizeof(double));
  130.     movq    %rax, (%rsp)    # _12, %sfp
  131. # galsim.c:34:     particles.mass = (double *) malloc(N * sizeof(double));
  132.     call    malloc@PLT  #
  133. # galsim.c:35:     particles.vx = (double *) malloc(N * sizeof(double));
  134.     movq    %r13, %rdi  # _8,
  135. # galsim.c:34:     particles.mass = (double *) malloc(N * sizeof(double));
  136.     movq    %rax, %r12  # tmp237, _13
  137. # galsim.c:35:     particles.vx = (double *) malloc(N * sizeof(double));
  138.     call    malloc@PLT  #
  139. # galsim.c:36:     particles.vy = (double *) malloc(N * sizeof(double));
  140.     movq    %r13, %rdi  # _8,
  141. # galsim.c:35:     particles.vx = (double *) malloc(N * sizeof(double));
  142.     movq    %rax, %rbp  # tmp238, _14
  143. # galsim.c:36:     particles.vy = (double *) malloc(N * sizeof(double));
  144.     call    malloc@PLT  #
  145. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  146.     movq    8(%rsp), %r8    # %sfp, _9
  147. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  148.     movq    (%rsp), %rcx    # %sfp, _12
  149. # galsim.c:36:     particles.vy = (double *) malloc(N * sizeof(double));
  150.     movq    %rax, %rbx  # tmp239, _15
  151. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  152.     testq   %r8, %r8    # _9
  153.     sete    %al #, tmp180
  154. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  155.     testq   %rcx, %rcx  # _12
  156.     sete    %dl #, tmp182
  157. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  158.     orl %edx, %eax  # tmp182, tmp183
  159. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  160.     testq   %rbp, %rbp  # _14
  161.     sete    %dl #, tmp185
  162. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  163.     testq   %r12, %r12  # _13
  164.     sete    %sil    #, tmp187
  165. # galsim.c:38:     if (!particles.x || !particles.y || !particles.mass || !particles.vx || !particles.vy) {
  166.     orl %esi, %edx  # tmp187, tmp188
  167.     orb %dl, %al    # tmp188, tmp253
  168.     jne .L19    #,
  169.     testq   %rbx, %rbx  # _15
  170.     vmovsd  16(%rsp), %xmm9 # %sfp, _148
  171.     movl    24(%rsp), %r11d # %sfp, _150
  172.     movl    32(%rsp), %r10d # %sfp, _152
  173.     je  .L19    #,
  174. # galsim.c:43:     int inputfd = open(inputfile, O_RDONLY);
  175.     xorl    %esi, %esi  #
  176.     movq    %r15, %rdi  # inputfile,
  177.     xorl    %eax, %eax  #
  178.     movl    %r10d, 32(%rsp) # _152, %sfp
  179.     movl    %r11d, 24(%rsp) # _150, %sfp
  180.     vmovsd  %xmm9, 16(%rsp) # _148, %sfp
  181.     movq    %rcx, 8(%rsp)   # _12, %sfp
  182.     movq    %r8, (%rsp) # _9, %sfp
  183.     call    open@PLT    #
  184. # galsim.c:44:     if(inputfd == -1) {
  185.     cmpl    $-1, %eax   #, inputfd
  186.     vmovsd  16(%rsp), %xmm9 # %sfp, _148
  187.     movq    (%rsp), %r8 # %sfp, _9
  188. # galsim.c:43:     int inputfd = open(inputfile, O_RDONLY);
  189.     movl    %eax, %r15d # tmp240, inputfd
  190. # galsim.c:44:     if(inputfd == -1) {
  191.     movq    8(%rsp), %rcx   # %sfp, _12
  192.     movl    24(%rsp), %r11d # %sfp, _150
  193.     movl    32(%rsp), %r10d # %sfp, _152
  194.     je  .L28    #,
  195. # galsim.c:49:     read(inputfd, particles.x, N * sizeof(double));
  196.     movq    %r8, %rsi   # _9,
  197.     movq    %r13, %rdx  # _8,
  198.     movl    %eax, %edi  # inputfd,
  199.     movq    %r8, 16(%rsp)   # _9, %sfp
  200.     movl    %r10d, 56(%rsp) # _152, %sfp
  201.     movl    %r11d, 32(%rsp) # _150, %sfp
  202.     vmovsd  %xmm9, 24(%rsp) # _148, %sfp
  203.     movq    %rcx, (%rsp)    # _12, %sfp
  204.     call    read@PLT    #
  205. # galsim.c:50:     read(inputfd, particles.y, N * sizeof(double));
  206.     movq    %r13, %rdx  # _8,
  207.     movl    %r15d, %edi # inputfd,
  208.     movq    (%rsp), %rcx    # %sfp, _12
  209.     movq    %rcx, %rsi  # _12,
  210.     movq    %rcx, 8(%rsp)   # _12, %sfp
  211.     call    read@PLT    #
  212. # galsim.c:51:     read(inputfd, particles.mass, N * sizeof(double));
  213.     movq    %r13, %rdx  # _8,
  214.     movq    %r12, %rsi  # _13,
  215.     movl    %r15d, %edi # inputfd,
  216.     call    read@PLT    #
  217. # galsim.c:52:     read(inputfd, particles.vx, N * sizeof(double));
  218.     movq    %r13, %rdx  # _8,
  219.     movq    %rbp, %rsi  # _14,
  220.     movl    %r15d, %edi # inputfd,
  221.     call    read@PLT    #
  222. # galsim.c:53:     read(inputfd, particles.vy, N * sizeof(double));
  223.     movq    %r13, %rdx  # _8,
  224.     movq    %rbx, %rsi  # _15,
  225.     movl    %r15d, %edi # inputfd,
  226.     call    read@PLT    #
  227. # galsim.c:55:     close(inputfd);
  228.     movl    %r15d, %edi # inputfd,
  229.     call    close@PLT   #
  230. # galsim.c:57:     printf("Time for File to DS(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  231.     call    clock@PLT   #
  232. # galsim.c:57:     printf("Time for File to DS(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  233.     vxorpd  %xmm7, %xmm7, %xmm7 # tmp296
  234. # galsim.c:57:     printf("Time for File to DS(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  235.     movq    40(%rsp), %rdi  # %sfp, start
  236.     subq    %rdi, %rax  # start, tmp194
  237. # galsim.c:57:     printf("Time for File to DS(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  238.     leaq    .LC5(%rip), %rdi    #, tmp198
  239. # galsim.c:57:     printf("Time for File to DS(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  240.     vcvtsi2sdq  %rax, %xmm7, %xmm0  # tmp194, tmp296, tmp249
  241. # galsim.c:57:     printf("Time for File to DS(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  242.     vdivsd  .LC4(%rip), %xmm0, %xmm0    #, tmp195, tmp196
  243.     movl    $1, %eax    #,
  244.     call    printf@PLT  #
  245. # galsim.c:58:     start = clock();
  246.     call    clock@PLT   #
  247. # galsim.c:62:     while (instant < timesteps) {
  248.     cmpl    $0, 48(%rsp)    #, %sfp
  249.     movq    8(%rsp), %rcx   # %sfp, _12
  250. # galsim.c:58:     start = clock();
  251.     movq    %rax, (%rsp)    # tmp242, %sfp
  252. # galsim.c:62:     while (instant < timesteps) {
  253.     movq    16(%rsp), %r8   # %sfp, _9
  254.     jle .L8 #,
  255. # galsim.c:22:     const double G = 100.0 / N;
  256.     vmovsd  .LC6(%rip), %xmm6   #, tmp200
  257. # galsim.c:22:     const double G = 100.0 / N;
  258.     vxorpd  %xmm7, %xmm7, %xmm7 # tmp297
  259. # galsim.c:61:     int instant = 0, i = 0, j = 0;
  260.     xorl    %r15d, %r15d    # instant
  261.     leal    -1(%r14), %eax  #,
  262. # galsim.c:22:     const double G = 100.0 / N;
  263.     vcvtsi2sdl  %r14d, %xmm7, %xmm0 # _151, tmp297, tmp250
  264. # galsim.c:22:     const double G = 100.0 / N;
  265.     vdivsd  %xmm0, %xmm6, %xmm6 # tmp199, tmp200, G
  266.     testl   %r14d, %r14d    # _151
  267.     jle .L8 #,
  268.     vmovsd  .LC7(%rip), %xmm8   #, tmp226
  269.     vmovsd  24(%rsp), %xmm9 # %sfp, _148
  270.     movl    %r15d, %edi # instant, instant
  271.     movq    %r13, %r14  # _8, _8
  272.     movl    32(%rsp), %r11d # %sfp, _150
  273.     movl    56(%rsp), %r10d # %sfp, _152
  274.     movq    %rcx, %r15  # _12, _12
  275.     addq    $2, %rax    #, _279
  276.     vxorpd  %xmm7, %xmm7, %xmm7 # tmp228
  277.     movq    %r8, %r13   # _9, _9
  278.     movq    %r12, %rdx  # _13, _13
  279.     movl    %edi, %ecx  # instant, instant
  280.     .p2align 4
  281.     .p2align 3
  282. .L9:
  283. # galsim.c:15: int main(int ac, char *av[]) {
  284.     movl    $1, %r12d   #, ivtmp.31
  285.     .p2align 4
  286.     .p2align 3
  287. .L15:
  288. # galsim.c:65:             double dmi = deltaT * mi;
  289.     vmulsd  -8(%rdx,%r12,8), %xmm9, %xmm12  # MEM[(double *)_13 + -8B + ivtmp.31_271 * 8], _148, dmi
  290. # galsim.c:66:             double x = particles.x[i], y = particles.y[i];
  291.     vmovsd  -8(%r13,%r12,8), %xmm10 # MEM[(double *)_9 + -8B + ivtmp.31_271 * 8], x
  292. # galsim.c:66:             double x = particles.x[i], y = particles.y[i];
  293.     vmovsd  -8(%r15,%r12,8), %xmm5  # MEM[(double *)_12 + -8B + ivtmp.31_271 * 8], y
  294. # galsim.c:69:             for (j = i + 1; j < N; j++) {
  295.     cmpl    %r12d, %r10d    # ivtmp.31, _152
  296.     jle .L18    #,
  297. # galsim.c:67:             double a_x = 0.0, a_y = 0.0;
  298.     vxorpd  %xmm4, %xmm4, %xmm4 # a_y
  299. # galsim.c:69:             for (j = i + 1; j < N; j++) {
  300.     movq    %r12, %rsi  # ivtmp.31, ivtmp.18
  301. # galsim.c:67:             double a_x = 0.0, a_y = 0.0;
  302.     vmovsd  %xmm4, %xmm4, %xmm11    #, a_x
  303.     .p2align 4
  304.     .p2align 3
  305. .L14:
  306. # galsim.c:72:                 double dy = particles.y[j] - y;
  307.     vmovsd  (%r15,%rsi,8), %xmm1    # MEM[(double *)_12 + ivtmp.18_266 * 8], MEM[(double *)_12 + ivtmp.18_266 * 8]
  308. # galsim.c:71:                 double dx = particles.x[j] - x;
  309.     vmovsd  0(%r13,%rsi,8), %xmm2   # MEM[(double *)_9 + ivtmp.18_266 * 8], MEM[(double *)_9 + ivtmp.18_266 * 8]
  310. # galsim.c:70:                 double mj = particles.mass[j];
  311.     vmovsd  (%rdx,%rsi,8), %xmm3    # MEM[(double *)_13 + ivtmp.18_266 * 8], mj
  312. # galsim.c:72:                 double dy = particles.y[j] - y;
  313.     vsubsd  %xmm5, %xmm1, %xmm1 # y, MEM[(double *)_12 + ivtmp.18_266 * 8], dy
  314. # galsim.c:71:                 double dx = particles.x[j] - x;
  315.     vsubsd  %xmm10, %xmm2, %xmm2    # x, MEM[(double *)_9 + ivtmp.18_266 * 8], dx
  316. # galsim.c:73:                 double rij2 = dx * dx + dy * dy;
  317.     vmulsd  %xmm1, %xmm1, %xmm0 # dy, dy, tmp203
  318. # galsim.c:73:                 double rij2 = dx * dx + dy * dy;
  319.     vfmadd231sd %xmm2, %xmm2, %xmm0 # dx, dx, rij2
  320.     vucomisd    %xmm0, %xmm7    # rij2, tmp228
  321.     ja  .L24    #,
  322. # galsim.c:74:                 double radius = (__builtin_sqrt(rij2) + eps);
  323.     vsqrtsd %xmm0, %xmm0, %xmm0 # rij2, _34
  324. .L13:
  325. # galsim.c:74:                 double radius = (__builtin_sqrt(rij2) + eps);
  326.     vaddsd  %xmm8, %xmm0, %xmm0 # tmp226, _34, radius
  327. # galsim.c:75:                 double radius_cubed = radius * radius * radius;
  328.     vmulsd  %xmm0, %xmm0, %xmm13    # radius, radius, tmp206
  329. # galsim.c:75:                 double radius_cubed = radius * radius * radius;
  330.     vmulsd  %xmm0, %xmm13, %xmm0    # radius, tmp206, radius_cubed
  331. # galsim.c:76:                 double force = G / radius_cubed;
  332.     vdivsd  %xmm0, %xmm6, %xmm0 # radius_cubed, G, force
  333. # galsim.c:78:                 double fx = force * dx;
  334.     vmulsd  %xmm0, %xmm2, %xmm2 # force, dx, fx
  335. # galsim.c:79:                 double fy = force * dy;
  336.     vmulsd  %xmm0, %xmm1, %xmm1 # force, dy, fy
  337. # galsim.c:82:                 a_x += fx * mj;
  338.     vfmadd231sd %xmm2, %xmm3, %xmm11    # fx, mj, a_x
  339. # galsim.c:83:                 a_y += fy * mj;
  340.     vfmadd231sd %xmm1, %xmm3, %xmm4 # fy, mj, a_y
  341. # galsim.c:86:                 particles.vx[j] -= dmi * fx;
  342.     vfnmadd213sd    0(%rbp,%rsi,8), %xmm12, %xmm2   # MEM[(double *)_14 + ivtmp.18_266 * 8], dmi, _41
  343. # galsim.c:87:                 particles.vy[j] -= dmi * fy;
  344.     vfnmadd213sd    (%rbx,%rsi,8), %xmm12, %xmm1    # MEM[(double *)_15 + ivtmp.18_266 * 8], dmi, _45
  345. # galsim.c:86:                 particles.vx[j] -= dmi * fx;
  346.     vmovsd  %xmm2, 0(%rbp,%rsi,8)   # _41, MEM[(double *)_14 + ivtmp.18_266 * 8]
  347. # galsim.c:87:                 particles.vy[j] -= dmi * fy;
  348.     vmovsd  %xmm1, (%rbx,%rsi,8)    # _45, MEM[(double *)_15 + ivtmp.18_266 * 8]
  349. # galsim.c:69:             for (j = i + 1; j < N; j++) {
  350.     incq    %rsi    # ivtmp.18
  351.     cmpl    %esi, %r10d # ivtmp.18, _152
  352.     jg  .L14    #,
  353. .L10:
  354. # galsim.c:91:             particles.vx[i] += deltaT * a_x;
  355.     vfmadd213sd -8(%rbp,%r12,8), %xmm9, %xmm11  # MEM[(double *)_14 + -8B + ivtmp.31_271 * 8], _148, _49
  356. # galsim.c:92:             particles.vy[i] += deltaT * a_y;
  357.     vfmadd213sd -8(%rbx,%r12,8), %xmm9, %xmm4   # MEM[(double *)_15 + -8B + ivtmp.31_271 * 8], _148, _53
  358. # galsim.c:91:             particles.vx[i] += deltaT * a_x;
  359.     vmovsd  %xmm11, -8(%rbp,%r12,8) # _49, MEM[(double *)_14 + -8B + ivtmp.31_271 * 8]
  360. # galsim.c:93:             particles.x[i] += deltaT * particles.vx[i];
  361.     vfmadd132sd %xmm9, %xmm10, %xmm11   # _148, x, _55
  362. # galsim.c:92:             particles.vy[i] += deltaT * a_y;
  363.     vmovsd  %xmm4, -8(%rbx,%r12,8)  # _53, MEM[(double *)_15 + -8B + ivtmp.31_271 * 8]
  364. # galsim.c:94:             particles.y[i] += deltaT * particles.vy[i];
  365.     vfmadd132sd %xmm9, %xmm5, %xmm4 # _148, y, _57
  366. # galsim.c:93:             particles.x[i] += deltaT * particles.vx[i];
  367.     vmovsd  %xmm11, -8(%r13,%r12,8) # _55, MEM[(double *)_9 + -8B + ivtmp.31_271 * 8]
  368. # galsim.c:94:             particles.y[i] += deltaT * particles.vy[i];
  369.     vmovsd  %xmm4, -8(%r15,%r12,8)  # _57, MEM[(double *)_12 + -8B + ivtmp.31_271 * 8]
  370. # galsim.c:63:         for (i = 0; i < N; i++) {
  371.     incq    %r12    # ivtmp.31
  372.     cmpq    %rax, %r12  # _279, ivtmp.31
  373.     jne .L15    #,
  374. # galsim.c:96:         instant++;
  375.     incl    %ecx    # instant
  376. # galsim.c:62:     while (instant < timesteps) {
  377.     cmpl    %r11d, %ecx # _150, instant
  378.     jne .L9 #,
  379.     movq    %r13, %r8   # _9, _9
  380.     movq    %r15, %rcx  # _12, _12
  381.     movq    %r14, %r13  # _8, _8
  382.     movq    %rdx, %r12  # _13, _13
  383. .L8:
  384.     movq    %rcx, 16(%rsp)  # _12, %sfp
  385.     movq    %r8, 8(%rsp)    # _9, %sfp
  386. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  387.     call    clock@PLT   #
  388. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  389.     movq    (%rsp), %rdi    # %sfp, start
  390. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  391.     vxorpd  %xmm7, %xmm7, %xmm7 # tmp299
  392. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  393.     subq    %rdi, %rax  # start, tmp210
  394. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  395.     leaq    .LC8(%rip), %rdi    #, tmp214
  396. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  397.     vcvtsi2sdq  %rax, %xmm7, %xmm0  # tmp210, tmp299, tmp251
  398. # galsim.c:99:     printf("Time for Processing(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  399.     vdivsd  .LC4(%rip), %xmm0, %xmm0    #, tmp211, tmp212
  400.     movl    $1, %eax    #,
  401.     call    printf@PLT  #
  402. # galsim.c:100:     start = clock();
  403.     call    clock@PLT   #
  404. # galsim.c:103:     int outputfd = open("result.gal", O_RDWR | O_CREAT, 0666);
  405.     movl    $438, %edx  #,
  406.     movl    $66, %esi   #,
  407. # galsim.c:100:     start = clock();
  408.     movq    %rax, %r15  # tmp245, start
  409. # galsim.c:103:     int outputfd = open("result.gal", O_RDWR | O_CREAT, 0666);
  410.     leaq    .LC9(%rip), %rdi    #, tmp215
  411.     xorl    %eax, %eax  #
  412.     call    open@PLT    #
  413. # galsim.c:104:     if(outputfd == -1) {
  414.     movq    8(%rsp), %r8    # %sfp, _9
  415.     cmpl    $-1, %eax   #, outputfd
  416.     movq    16(%rsp), %rcx  # %sfp, _12
  417. # galsim.c:103:     int outputfd = open("result.gal", O_RDWR | O_CREAT, 0666);
  418.     movl    %eax, %r14d # tmp246, outputfd
  419. # galsim.c:104:     if(outputfd == -1) {
  420.     je  .L29    #,
  421. # galsim.c:109:     write(outputfd, particles.x, N * sizeof(double));
  422.     movq    %r8, %rsi   # _9,
  423.     movq    %r13, %rdx  # _8,
  424.     movl    %eax, %edi  # outputfd,
  425.     movq    %rcx, (%rsp)    # _12, %sfp
  426.     movq    %r8, 8(%rsp)    # _9, %sfp
  427.     call    write@PLT   #
  428. # galsim.c:110:     write(outputfd, particles.y, N * sizeof(double));
  429.     movq    %r13, %rdx  # _8,
  430.     movl    %r14d, %edi # outputfd,
  431.     movq    (%rsp), %rsi    # %sfp,
  432.     call    write@PLT   #
  433. # galsim.c:111:     write(outputfd, particles.mass, N * sizeof(double));
  434.     movq    %r13, %rdx  # _8,
  435.     movq    %r12, %rsi  # _13,
  436.     movl    %r14d, %edi # outputfd,
  437.     call    write@PLT   #
  438. # galsim.c:112:     write(outputfd, particles.vx, N * sizeof(double));
  439.     movq    %r13, %rdx  # _8,
  440.     movq    %rbp, %rsi  # _14,
  441.     movl    %r14d, %edi # outputfd,
  442.     call    write@PLT   #
  443. # galsim.c:113:     write(outputfd, particles.vy, N * sizeof(double));
  444.     movq    %r13, %rdx  # _8,
  445.     movq    %rbx, %rsi  # _15,
  446.     movl    %r14d, %edi # outputfd,
  447.     call    write@PLT   #
  448. # galsim.c:115:     close(outputfd);
  449.     movl    %r14d, %edi # outputfd,
  450.     call    close@PLT   #
  451. # galsim.c:117:     free(particles.x);
  452.     movq    8(%rsp), %rdi   # %sfp,
  453.     call    free@PLT    #
  454. # galsim.c:118:     free(particles.y);
  455.     movq    (%rsp), %rdi    # %sfp,
  456.     call    free@PLT    #
  457. # galsim.c:119:     free(particles.mass);
  458.     movq    %r12, %rdi  # _13,
  459.     call    free@PLT    #
  460. # galsim.c:120:     free(particles.vx);
  461.     movq    %rbp, %rdi  # _14,
  462.     call    free@PLT    #
  463. # galsim.c:121:     free(particles.vy);
  464.     movq    %rbx, %rdi  # _15,
  465.     call    free@PLT    #
  466. # galsim.c:123:     printf("Time for DS to File(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  467.     call    clock@PLT   #
  468. # galsim.c:123:     printf("Time for DS to File(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  469.     vxorpd  %xmm7, %xmm7, %xmm7 # tmp300
  470. # galsim.c:123:     printf("Time for DS to File(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  471.     leaq    .LC11(%rip), %rdi   #, tmp221
  472. # galsim.c:123:     printf("Time for DS to File(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  473.     subq    %r15, %rax  # start, tmp217
  474. # galsim.c:123:     printf("Time for DS to File(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  475.     vcvtsi2sdq  %rax, %xmm7, %xmm0  # tmp217, tmp300, tmp252
  476. # galsim.c:123:     printf("Time for DS to File(s): %lf\n", (double) (clock() - start) / CLOCKS_PER_SEC);
  477.     vdivsd  .LC4(%rip), %xmm0, %xmm0    #, tmp218, tmp219
  478.     movl    $1, %eax    #,
  479.     call    printf@PLT  #
  480. # galsim.c:125:     return 0;
  481.     xorl    %eax, %eax  # <retval>
  482.     jmp .L1 #
  483.     .p2align 4
  484.     .p2align 3
  485. .L18:
  486. # galsim.c:67:             double a_x = 0.0, a_y = 0.0;
  487.     vxorpd  %xmm4, %xmm4, %xmm4 # a_y
  488. # galsim.c:67:             double a_x = 0.0, a_y = 0.0;
  489.     vmovsd  %xmm4, %xmm4, %xmm11    #, a_x
  490.     jmp .L10    #
  491. .L28:
  492. # galsim.c:45:         printf("File open error!\n");
  493.     leaq    .LC3(%rip), %rdi    #, tmp193
  494.     call    puts@PLT    #
  495. # galsim.c:46:         return 1;
  496.     jmp .L3 #
  497. .L29:
  498. # galsim.c:105:         printf("File create error!\n");
  499.     leaq    .LC10(%rip), %rdi   #, tmp216
  500.     call    puts@PLT    #
  501. # galsim.c:106:         return 1;
  502.     jmp .L3 #
  503. .L24:
  504.     movq    %rax, 120(%rsp) # _279, %sfp
  505.     movq    %rsi, 112(%rsp) # ivtmp.18, %sfp
  506.     movl    %r10d, 108(%rsp)    # _152, %sfp
  507.     movl    %r11d, 104(%rsp)    # _150, %sfp
  508.     vmovsd  %xmm4, 96(%rsp) # a_y, %sfp
  509.     vmovsd  %xmm11, 88(%rsp)    # a_x, %sfp
  510.     vmovsd  %xmm12, 80(%rsp)    # dmi, %sfp
  511.     movl    %ecx, 76(%rsp)  # instant, %sfp
  512.     vmovsd  %xmm6, 64(%rsp) # G, %sfp
  513.     movq    %rdx, 56(%rsp)  # _13, %sfp
  514.     vmovsd  %xmm9, 48(%rsp) # _148, %sfp
  515.     vmovsd  %xmm1, 40(%rsp) # dy, %sfp
  516.     vmovsd  %xmm2, 32(%rsp) # dx, %sfp
  517.     vmovsd  %xmm3, 24(%rsp) # mj, %sfp
  518.     vmovsd  %xmm5, 16(%rsp) # y, %sfp
  519.     vmovsd  %xmm10, 8(%rsp) # x, %sfp
  520. # galsim.c:74:                 double radius = (__builtin_sqrt(rij2) + eps);
  521.     call    sqrt@PLT    #
  522.     vxorpd  %xmm7, %xmm7, %xmm7 # tmp228
  523.     movq    .LC7(%rip), %rdi    #, tmp343
  524.     vmovsd  96(%rsp), %xmm4 # %sfp, a_y
  525.     vmovsd  88(%rsp), %xmm11    # %sfp, a_x
  526.     vmovsd  80(%rsp), %xmm12    # %sfp, dmi
  527.     vmovsd  64(%rsp), %xmm6 # %sfp, G
  528.     vmovsd  48(%rsp), %xmm9 # %sfp, _148
  529.     vmovsd  40(%rsp), %xmm1 # %sfp, dy
  530.     vmovsd  32(%rsp), %xmm2 # %sfp, dx
  531.     vmovsd  24(%rsp), %xmm3 # %sfp, mj
  532.     vmovsd  16(%rsp), %xmm5 # %sfp, y
  533.     vmovq   %rdi, %xmm8 # tmp343, tmp226
  534.     vmovsd  8(%rsp), %xmm10 # %sfp, x
  535.     movq    120(%rsp), %rax # %sfp, _279
  536.     movq    112(%rsp), %rsi # %sfp, ivtmp.18
  537.     movl    108(%rsp), %r10d    # %sfp, _152
  538.     movl    104(%rsp), %r11d    # %sfp, _150
  539.     movl    76(%rsp), %ecx  # %sfp, instant
  540.     movq    56(%rsp), %rdx  # %sfp, _13
  541.     jmp .L13    #
  542. .L19:
  543. # galsim.c:39:         printf("Memory allocation error!\n");
  544.     leaq    .LC2(%rip), %rdi    #, tmp192
  545.     call    puts@PLT    #
  546. # galsim.c:40:         return 1;
  547.     jmp .L3 #
  548.     .cfi_endproc
  549. .LFE22:
  550.     .size   main, .-main
  551.     .section    .rodata.cst8,"aM",@progbits,8
  552.     .align 8
  553. .LC4:
  554.     .long   0
  555.     .long   1093567616
  556.     .align 8
  557. .LC6:
  558.     .long   0
  559.     .long   1079574528
  560.     .align 8
  561. .LC7:
  562.     .long   -755914244
  563.     .long   1062232653
  564.     .ident  "GCC: (Debian 12.2.0-14) 12.2.0"
  565.     .section    .note.GNU-stack,"",@progbits
  566.  
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!