Function: hypre_IJMatrixSetValuesOMPParCSR.extracted.28 | Module: exec | Source: IJMatrix_parcsr.c:3240-3484 [...] | Coverage: 1.12% |
---|
Function: hypre_IJMatrixSetValuesOMPParCSR.extracted.28 | Module: exec | Source: IJMatrix_parcsr.c:3240-3484 [...] | Coverage: 1.12% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/IJ_mv/IJMatrix_parcsr.c: 3240 - 3484 |
-------------------------------------------------------------------------------- |
3240: #pragma omp parallel |
[...] |
3256: num_threads = hypre_NumActiveThreads(); |
3257: my_thread_num = hypre_GetThreadNum(); |
3258: |
3259: len = nrows/num_threads; |
3260: rest = nrows - len*num_threads; |
3261: |
3262: if (my_thread_num < rest) |
3263: { |
3264: ns = my_thread_num*(len+1); |
3265: ne = (my_thread_num+1)*(len+1); |
3266: } |
3267: else |
3268: { |
3269: ns = my_thread_num*len+rest; |
3270: ne = (my_thread_num+1)*len+rest; |
3271: } |
3272: |
3273: value_start[my_thread_num] = 0; |
3274: for (ii=ns; ii < ne; ii++) |
3275: value_start[my_thread_num] += ncols[ii]; |
3276: |
3277: #ifdef HYPRE_USING_OPENMP |
3278: #pragma omp barrier |
3279: #endif |
3280: if (my_thread_num == 0) |
3281: { |
3282: for (i=0; i < max_num_threads; i++) |
3283: value_start[i+1] += value_start[i]; |
[...] |
3289: if (my_thread_num) |
3290: indx = value_start[my_thread_num-1]; |
3291: for (ii=ns; ii < ne; ii++) |
3292: { |
3293: row = rows[ii]; |
3294: n = ncols[ii]; |
3295: /* processor owns the row */ |
3296: if (row >= row_partitioning[pstart] && row < row_partitioning[pstart+1]) |
3297: { |
3298: row_local = row - row_partitioning[pstart]; |
3299: /* compute local row number */ |
3300: if (need_aux) |
3301: { |
3302: local_j = aux_j[row_local]; |
3303: local_data = aux_data[row_local]; |
3304: space = row_space[row_local]; |
3305: old_size = row_length[row_local]; |
3306: size = space - old_size; |
3307: if (size < n) |
3308: { |
3309: size = n - size; |
3310: tmp_j = hypre_CTAlloc(HYPRE_Int,size); |
3311: tmp_data = hypre_CTAlloc(HYPRE_Complex,size); |
3312: } |
3313: tmp_indx = 0; |
3314: not_found = 1; |
3315: size = old_size; |
3316: for (i=0; i < n; i++) |
3317: { |
3318: for (j=0; j < old_size; j++) |
3319: { |
3320: if (local_j[j] == cols[indx]) |
3321: { |
3322: local_data[j] = values[indx]; |
[...] |
3329: if (size < space) |
3330: { |
3331: local_j[size] = cols[indx]; |
3332: local_data[size++] = values[indx]; |
3333: } |
3334: else |
3335: { |
3336: tmp_j[tmp_indx] = cols[indx]; |
3337: tmp_data[tmp_indx++] = values[indx]; |
3338: } |
3339: } |
3340: not_found = 1; |
3341: indx++; |
3342: } |
3343: |
3344: row_length[row_local] = size+tmp_indx; |
3345: |
3346: if (tmp_indx) |
3347: { |
3348: aux_j[row_local] = hypre_TReAlloc(aux_j[row_local],HYPRE_Int, |
3349: size+tmp_indx); |
3350: aux_data[row_local] = hypre_TReAlloc(aux_data[row_local], |
3351: HYPRE_Complex,size+tmp_indx); |
3352: row_space[row_local] = size+tmp_indx; |
3353: local_j = aux_j[row_local]; |
[...] |
3359: for (i=0; i < tmp_indx; i++) |
3360: { |
3361: local_j[cnt] = tmp_j[i]; |
3362: local_data[cnt++] = tmp_data[i]; |
3363: } |
3364: |
3365: if (tmp_j) |
3366: { |
3367: hypre_TFree(tmp_j); |
3368: hypre_TFree(tmp_data); |
[...] |
3376: offd_indx = hypre_AuxParCSRMatrixIndxOffd(aux_matrix)[row_local]; |
3377: diag_indx = hypre_AuxParCSRMatrixIndxDiag(aux_matrix)[row_local]; |
3378: cnt_diag = diag_indx; |
3379: cnt_offd = offd_indx; |
3380: diag_space = diag_i[row_local+1]; |
3381: offd_space = offd_i[row_local+1]; |
3382: not_found = 1; |
3383: for (i=0; i < n; i++) |
3384: { |
3385: if (cols[indx] < col_0 || cols[indx] > col_n) |
3386: /* insert into offd */ |
3387: { |
3388: for (j=offd_i[row_local]; j < offd_indx; j++) |
3389: { |
3390: if (offd_j[j] == cols[indx]) |
3391: { |
3392: offd_data[j] = values[indx]; |
[...] |
3399: if (cnt_offd < offd_space) |
3400: { |
3401: offd_j[cnt_offd] = cols[indx]; |
3402: offd_data[cnt_offd++] = values[indx]; |
3403: } |
3404: else |
3405: { |
3406: hypre_error(HYPRE_ERROR_GENERIC); |
3407: #ifdef HYPRE_USING_OPENMP |
3408: #pragma omp atomic |
3409: #endif |
3410: error_flag++; |
[...] |
3422: for (j=diag_i[row_local]; j < diag_indx; j++) |
3423: { |
3424: if (diag_j[j] == cols[indx]) |
3425: { |
3426: diag_data[j] = values[indx]; |
[...] |
3433: if (cnt_diag < diag_space) |
3434: { |
3435: diag_j[cnt_diag] = cols[indx]; |
3436: diag_data[cnt_diag++] = values[indx]; |
3437: } |
3438: else |
3439: { |
3440: hypre_error(HYPRE_ERROR_GENERIC); |
3441: #ifdef HYPRE_USING_OPENMP |
3442: #pragma omp atomic |
3443: #endif |
3444: error_flag++; |
3445: if (print_level) |
[...] |
3454: indx++; |
3455: } |
3456: |
3457: hypre_AuxParCSRMatrixIndxDiag(aux_matrix)[row_local] = cnt_diag; |
3458: hypre_AuxParCSRMatrixIndxOffd(aux_matrix)[row_local] = cnt_offd; |
[...] |
3466: indx += n; |
3467: if (aux_matrix) |
3468: { |
3469: col_indx = 0; |
3470: for (i=0; i < off_proc_i_indx; i=i+2) |
3471: { |
3472: row_len = off_proc_i[i+1]; |
3473: if (off_proc_i[i] == row) |
3474: { |
3475: for (j=0; j < n; j++) |
3476: { |
3477: cnt1 = col_indx; |
3478: for (k=0; k < row_len; k++) |
3479: { |
3480: if (off_proc_j[cnt1] == cols[j]) |
3481: { |
3482: off_proc_j[cnt1++] = -1; |
3483: /*cancel_indx++;*/ |
3484: offproc_cnt[my_thread_num]++; |
0x4caee0 PUSH %RBP |
0x4caee1 MOV %RSP,%RBP |
0x4caee4 PUSH %R15 |
0x4caee6 PUSH %R14 |
0x4caee8 PUSH %R13 |
0x4caeea PUSH %R12 |
0x4caeec PUSH %RBX |
0x4caeed SUB $0x78,%RSP |
0x4caef1 MOV %R9,%RBX |
0x4caef4 MOV %R8,-0x60(%RBP) |
0x4caef8 MOV %RCX,-0x58(%RBP) |
0x4caefc MOV %RDX,%R14 |
0x4caeff MOV %RDI,-0x98(%RBP) |
0x4caf06 CALL 4df9c0 <hypre_NumActiveThreads> |
0x4caf0b MOV %RAX,%R15 |
0x4caf0e CALL 4df9d0 <hypre_GetThreadNum> |
0x4caf13 MOV %RAX,%R13 |
0x4caf16 MOV %R15,%RAX |
0x4caf19 OR %R14,%RAX |
0x4caf1c SHR $0x20,%RAX |
0x4caf20 JE 4caf5f |
0x4caf22 MOV %R14,%RAX |
0x4caf25 CQTO |
0x4caf27 IDIV %R15 |
0x4caf2a MOV 0xb8(%RBP),%R14 |
0x4caf31 LEA 0x1(%R13),%RCX |
0x4caf35 CMP %RDX,%R13 |
0x4caf38 JGE 4caf77 |
0x4caf3a LEA 0x1(%RAX),%R10 |
0x4caf3e MOV %R10,%R15 |
0x4caf41 IMUL %R13,%R15 |
0x4caf45 IMUL %RCX,%R10 |
0x4caf49 MOVQ $0,(%R14,%R13,8) |
0x4caf51 CMP %R10,%R15 |
0x4caf54 MOV %RBX,-0x38(%RBP) |
0x4caf58 JL 4cafa0 |
0x4caf5a JMP 4cb020 |
0x4caf5f MOV %R14D,%EAX |
0x4caf62 XOR %EDX,%EDX |
0x4caf64 DIV %R15D |
0x4caf67 MOV 0xb8(%RBP),%R14 |
0x4caf6e LEA 0x1(%R13),%RCX |
0x4caf72 CMP %RDX,%R13 |
0x4caf75 JL 4caf3a |
0x4caf77 MOV %RAX,%R15 |
0x4caf7a IMUL %R13,%R15 |
0x4caf7e ADD %RDX,%R15 |
0x4caf81 IMUL %RAX,%RCX |
0x4caf85 ADD %RDX,%RCX |
0x4caf88 MOV %RCX,%R10 |
0x4caf8b MOVQ $0,(%R14,%R13,8) |
0x4caf93 CMP %R10,%R15 |
0x4caf96 MOV %RBX,-0x38(%RBP) |
0x4caf9a JGE 4cb020 |
0x4cafa0 CMP %RDX,%R13 |
0x4cafa3 CMOVL %R13,%RDX |
0x4cafa7 IMUL %R13,%RAX |
0x4cafab MOV %R10,%R8 |
0x4cafae SUB %RDX,%R8 |
0x4cafb1 SUB %RAX,%R8 |
0x4cafb4 MOV %R8,%RCX |
0x4cafb7 AND $-0x4,%RCX |
0x4cafbb JE 4cb001 |
0x4cafbd LEA -0x1(%RCX),%RSI |
0x4cafc1 MOV -0x58(%RBP),%R9 |
0x4cafc5 LEA (%R9,%R15,8),%RBX |
0x4cafc9 VPXOR %XMM0,%XMM0,%XMM0 |
0x4cafcd XOR %EDI,%EDI |
0x4cafcf NOP |
(3743) 0x4cafd0 VPADDQ (%RBX,%RDI,8),%YMM0,%YMM0 |
(3743) 0x4cafd5 ADD $0x4,%RDI |
(3743) 0x4cafd9 CMP %RSI,%RDI |
(3743) 0x4cafdc JBE 4cafd0 |
0x4cafde VEXTRACTI128 $0x1,%YMM0,%XMM1 |
0x4cafe4 VPADDQ %XMM1,%XMM0,%XMM0 |
0x4cafe8 VPSHUFD $-0x12,%XMM0,%XMM1 |
0x4cafed VPADDQ %XMM1,%XMM0,%XMM0 |
0x4caff1 VMOVQ %XMM0,%RSI |
0x4caff6 CMP %RCX,%R8 |
0x4caff9 MOV -0x38(%RBP),%RBX |
0x4caffd JNE 4cb009 |
0x4cafff JMP 4cb01c |
0x4cb001 XOR %ECX,%ECX |
0x4cb003 XOR %ESI,%ESI |
0x4cb005 MOV -0x58(%RBP),%R9 |
0x4cb009 ADD %RDX,%RCX |
0x4cb00c ADD %RAX,%RCX |
0x4cb00f NOP |
(3725) 0x4cb010 ADD (%R9,%RCX,8),%RSI |
(3725) 0x4cb014 INC %RCX |
(3725) 0x4cb017 CMP %RCX,%R10 |
(3725) 0x4cb01a JNE 4cb010 |
0x4cb01c MOV %RSI,(%R14,%R13,8) |
0x4cb020 MOV %R10,-0x68(%RBP) |
0x4cb024 MOV -0x98(%RBP),%RAX |
0x4cb02b MOV (%RAX),%ESI |
0x4cb02d MOV $0x52b530,%EDI |
0x4cb032 VZEROUPPER |
0x4cb035 CALL 410560 <__kmpc_barrier@plt> |
0x4cb03a TEST %R13,%R13 |
0x4cb03d JNE 4cb0e6 |
0x4cb043 MOV 0xc8(%RBP),%RAX |
0x4cb04a TEST %RAX,%RAX |
0x4cb04d JLE 4cb0e6 |
0x4cb053 CMP $0x8,%RAX |
0x4cb057 JB 4cb0b7 |
0x4cb059 MOV %RAX,%RCX |
0x4cb05c SHR $0x3,%RCX |
0x4cb060 MOV (%R14),%RDX |
0x4cb063 LEA 0x40(%R14),%RSI |
0x4cb067 NOPW (%RAX,%RAX,1) |
(3742) 0x4cb070 ADD -0x38(%RSI),%RDX |
(3742) 0x4cb074 MOV %RDX,-0x38(%RSI) |
(3742) 0x4cb078 ADD -0x30(%RSI),%RDX |
(3742) 0x4cb07c MOV %RDX,-0x30(%RSI) |
(3742) 0x4cb080 ADD -0x28(%RSI),%RDX |
(3742) 0x4cb084 MOV %RDX,-0x28(%RSI) |
(3742) 0x4cb088 ADD -0x20(%RSI),%RDX |
(3742) 0x4cb08c MOV %RDX,-0x20(%RSI) |
(3742) 0x4cb090 ADD -0x18(%RSI),%RDX |
(3742) 0x4cb094 MOV %RDX,-0x18(%RSI) |
(3742) 0x4cb098 ADD -0x10(%RSI),%RDX |
(3742) 0x4cb09c MOV %RDX,-0x10(%RSI) |
(3742) 0x4cb0a0 ADD -0x8(%RSI),%RDX |
(3742) 0x4cb0a4 MOV %RDX,-0x8(%RSI) |
(3742) 0x4cb0a8 ADD (%RSI),%RDX |
(3742) 0x4cb0ab MOV %RDX,(%RSI) |
(3742) 0x4cb0ae ADD $0x40,%RSI |
(3742) 0x4cb0b2 DEC %RCX |
(3742) 0x4cb0b5 JNE 4cb070 |
0x4cb0b7 MOV %RAX,%RCX |
0x4cb0ba AND $-0x8,%RCX |
0x4cb0be CMP %RAX,%RCX |
0x4cb0c1 JAE 4cb0e6 |
0x4cb0c3 MOV (%R14,%RCX,8),%RDX |
0x4cb0c7 NOPW (%RAX,%RAX,1) |
(3741) 0x4cb0d0 ADD 0x8(%R14,%RCX,8),%RDX |
(3741) 0x4cb0d5 MOV %RDX,0x8(%R14,%RCX,8) |
(3741) 0x4cb0da LEA 0x1(%RCX),%RSI |
(3741) 0x4cb0de MOV %RSI,%RCX |
(3741) 0x4cb0e1 CMP %RSI,%RAX |
(3741) 0x4cb0e4 JNE 4cb0d0 |
0x4cb0e6 MOV -0x98(%RBP),%RAX |
0x4cb0ed MOV (%RAX),%ESI |
0x4cb0ef MOV $0x52b550,%EDI |
0x4cb0f4 CALL 410560 <__kmpc_barrier@plt> |
0x4cb0f9 TEST %R13,%R13 |
0x4cb0fc JE 4cb105 |
0x4cb0fe MOV -0x8(%R14,%R13,8),%RDX |
0x4cb103 JMP 4cb107 |
0x4cb105 XOR %EDX,%EDX |
0x4cb107 MOV -0x58(%RBP),%RDI |
0x4cb10b MOV %R15,%R8 |
0x4cb10e MOV -0x68(%RBP),%R12 |
0x4cb112 CMP %R12,%R15 |
0x4cb115 JGE 4cb967 |
0x4cb11b MOV 0xb0(%RBP),%RAX |
0x4cb122 MOV 0xa8(%RBP),%R9 |
0x4cb129 MOV 0x98(%RBP),%RSI |
0x4cb130 CMPQ $0,0x18(%RBP) |
0x4cb135 LEA (%RAX,%R13,8),%R15 |
0x4cb139 SETE %AL |
0x4cb13c TEST %RSI,%RSI |
0x4cb13f SETLE %CL |
0x4cb142 OR %AL,%CL |
0x4cb144 MOV %CL,-0x39(%RBP) |
0x4cb147 MOV -0x60(%RBP),%RCX |
0x4cb14b DEC %RSI |
0x4cb14e SHR $0x1,%RSI |
0x4cb151 MOV %RSI,-0x98(%RBP) |
0x4cb158 MOV 0x20(%RBP),%RSI |
0x4cb15c LEA 0x18(%R9),%RAX |
0x4cb160 MOV %RAX,-0xa0(%RBP) |
0x4cb167 XOR %EAX,%EAX |
0x4cb169 MOV %RAX,-0x80(%RBP) |
0x4cb16d JMP 4cb197 |
0x4cb16f NOP |
(3726) 0x4cb170 MOV -0x60(%RBP),%RCX |
(3726) 0x4cb174 MOV -0x58(%RBP),%RDI |
(3726) 0x4cb178 MOV -0x88(%RBP),%R8 |
(3726) 0x4cb17f MOV -0x68(%RBP),%R12 |
(3726) 0x4cb183 MOV -0x30(%RBP),%RDX |
(3726) 0x4cb187 MOV 0x20(%RBP),%RSI |
(3726) 0x4cb18b INC %R8 |
(3726) 0x4cb18e CMP %R12,%R8 |
(3726) 0x4cb191 JGE 4cb967 |
(3726) 0x4cb197 MOV (%RCX,%R8,8),%R13 |
(3726) 0x4cb19b MOV (%RDI,%R8,8),%R14 |
(3726) 0x4cb19f MOV %R13,%R10 |
(3726) 0x4cb1a2 SUB (%RSI),%R10 |
(3726) 0x4cb1a5 JL 4cb270 |
(3726) 0x4cb1ab CMP 0x8(%RSI),%R13 |
(3726) 0x4cb1af JGE 4cb270 |
(3726) 0x4cb1b5 CMPQ $0,0x58(%RBP) |
(3726) 0x4cb1ba JE 4cb428 |
(3726) 0x4cb1c0 MOV 0x38(%RBP),%RAX |
(3726) 0x4cb1c4 MOV (%RAX,%R10,8),%R12 |
(3726) 0x4cb1c8 MOV 0x40(%RBP),%RAX |
(3726) 0x4cb1cc MOV (%RAX,%R10,8),%RAX |
(3726) 0x4cb1d0 MOV %RAX,-0x90(%RBP) |
(3726) 0x4cb1d7 MOV 0x50(%RBP),%RAX |
(3726) 0x4cb1db MOV (%RAX,%R10,8),%RCX |
(3726) 0x4cb1df MOV 0x48(%RBP),%RAX |
(3726) 0x4cb1e3 MOV (%RAX,%R10,8),%R13 |
(3726) 0x4cb1e7 MOV %RCX,-0x70(%RBP) |
(3726) 0x4cb1eb MOV %RCX,%RAX |
(3726) 0x4cb1ee SUB %R13,%RAX |
(3726) 0x4cb1f1 MOV %R14,%RDI |
(3726) 0x4cb1f4 SUB %RAX,%RDI |
(3726) 0x4cb1f7 MOV %R8,-0x88(%RBP) |
(3726) 0x4cb1fe MOV %RDX,-0x30(%RBP) |
(3726) 0x4cb202 JLE 4cb5be |
(3726) 0x4cb208 MOV $0x8,%ESI |
(3726) 0x4cb20d MOV %R10,-0x50(%RBP) |
(3726) 0x4cb211 MOV %RDI,-0x48(%RBP) |
(3726) 0x4cb215 CALL 4dd8f0 <hypre_CAlloc> |
(3726) 0x4cb21a MOV %RAX,-0x78(%RBP) |
(3726) 0x4cb21e MOV $0x8,%ESI |
(3726) 0x4cb223 MOV -0x48(%RBP),%RDI |
(3726) 0x4cb227 CALL 4dd8f0 <hypre_CAlloc> |
(3726) 0x4cb22c MOV -0x78(%RBP),%R11 |
(3726) 0x4cb230 MOV -0x50(%RBP),%R10 |
(3726) 0x4cb234 MOV 0x10(%RBP),%R9 |
(3726) 0x4cb238 TEST %R14,%R14 |
(3726) 0x4cb23b MOV %RAX,%RCX |
(3726) 0x4cb23e MOV %RAX,-0x80(%RBP) |
(3726) 0x4cb242 JG 4cb5d9 |
(3726) 0x4cb248 MOV 0x48(%RBP),%RAX |
(3726) 0x4cb24c MOV %R13,(%RAX,%R10,8) |
(3726) 0x4cb250 MOV -0x60(%RBP),%RCX |
(3726) 0x4cb254 MOV -0x30(%RBP),%RDX |
(3726) 0x4cb258 TEST %R11,%R11 |
(3726) 0x4cb25b JNE 4cb7e4 |
(3726) 0x4cb261 JMP 4cb80a |
0x4cb266 NOPW %CS:(%RAX,%RAX,1) |
(3726) 0x4cb270 ADD %R14,%RDX |
(3726) 0x4cb273 CMPB $0,-0x39(%RBP) |
(3726) 0x4cb277 JNE 4cb18b |
(3726) 0x4cb27d TEST %R14,%R14 |
(3726) 0x4cb280 JLE 4cb18b |
(3726) 0x4cb286 MOV %RDX,-0x30(%RBP) |
(3726) 0x4cb28a MOV %R8,-0x88(%RBP) |
(3726) 0x4cb291 DEC %R14 |
(3726) 0x4cb294 XOR %R8D,%R8D |
(3726) 0x4cb297 XOR %R9D,%R9D |
(3726) 0x4cb29a JMP 4cb2b4 |
0x4cb29c NOPL (%RAX) |
(3727) 0x4cb2a0 LEA 0x1(%R9),%RAX |
(3727) 0x4cb2a4 CMP -0x98(%RBP),%R9 |
(3727) 0x4cb2ab MOV %RAX,%R9 |
(3727) 0x4cb2ae JE 4cb170 |
(3727) 0x4cb2b4 MOV %R8,%RAX |
(3727) 0x4cb2b7 MOV %R9,%RCX |
(3727) 0x4cb2ba SAL $0x4,%RCX |
(3727) 0x4cb2be MOV 0xa0(%RBP),%RSI |
(3727) 0x4cb2c5 MOV 0x8(%RSI,%RCX,1),%RDX |
(3727) 0x4cb2ca ADD %RDX,%R8 |
(3727) 0x4cb2cd CMP %R13,(%RSI,%RCX,1) |
(3727) 0x4cb2d1 JNE 4cb2a0 |
(3727) 0x4cb2d3 TEST %RDX,%RDX |
(3727) 0x4cb2d6 JLE 4cb2a0 |
(3727) 0x4cb2d8 MOV 0xa8(%RBP),%RSI |
(3727) 0x4cb2df LEA (%RSI,%R8,8),%RCX |
(3727) 0x4cb2e3 ADD $-0x8,%RCX |
(3727) 0x4cb2e7 LEA (%RSI,%RAX,8),%RSI |
(3727) 0x4cb2eb CMP %R15,%RCX |
(3727) 0x4cb2ee JB 4cb340 |
(3727) 0x4cb2f0 CMP %RSI,%R15 |
(3727) 0x4cb2f3 JB 4cb340 |
(3727) 0x4cb2f5 XOR %EAX,%EAX |
(3727) 0x4cb2f7 JMP 4cb30c |
0x4cb2f9 NOPL (%RAX) |
(3731) 0x4cb300 LEA 0x1(%RAX),%RCX |
(3731) 0x4cb304 CMP %R14,%RAX |
(3731) 0x4cb307 MOV %RCX,%RAX |
(3731) 0x4cb30a JE 4cb2a0 |
(3731) 0x4cb30c MOV (%RBX,%RAX,8),%RCX |
(3731) 0x4cb310 XOR %EDI,%EDI |
(3731) 0x4cb312 JMP 4cb328 |
0x4cb314 NOPW %CS:(%RAX,%RAX,1) |
(3732) 0x4cb320 INC %RDI |
(3732) 0x4cb323 CMP %RDI,%RDX |
(3732) 0x4cb326 JE 4cb300 |
(3732) 0x4cb328 CMP %RCX,(%RSI,%RDI,8) |
(3732) 0x4cb32c JNE 4cb320 |
(3732) 0x4cb32e MOVQ $-0x1,(%RSI,%RDI,8) |
(3732) 0x4cb336 INCQ (%R15) |
(3732) 0x4cb339 JMP 4cb320 |
0x4cb33b NOPL (%RAX,%RAX,1) |
(3727) 0x4cb340 MOV %RDX,%R11 |
(3727) 0x4cb343 SHR $0x2,%R11 |
(3727) 0x4cb347 MOV %RDX,%R12 |
(3727) 0x4cb34a AND $-0x4,%R12 |
(3727) 0x4cb34e MOV -0xa0(%RBP),%RCX |
(3727) 0x4cb355 LEA (%RCX,%RAX,8),%R10 |
(3727) 0x4cb359 XOR %EAX,%EAX |
(3727) 0x4cb35b JMP 4cb374 |
0x4cb35d NOPL (%RAX) |
(3728) 0x4cb360 LEA 0x1(%RAX),%RCX |
(3728) 0x4cb364 CMP %R14,%RAX |
(3728) 0x4cb367 MOV %RCX,%RAX |
(3728) 0x4cb36a MOV -0x38(%RBP),%RBX |
(3728) 0x4cb36e JE 4cb2a0 |
(3728) 0x4cb374 MOV (%RBX,%RAX,8),%RBX |
(3728) 0x4cb378 CMP $0x4,%RDX |
(3728) 0x4cb37c JAE 4cb3b0 |
(3728) 0x4cb37e CMP %RDX,%R12 |
(3728) 0x4cb381 JAE 4cb360 |
(3728) 0x4cb383 MOV %R12,%RCX |
(3728) 0x4cb386 JMP 4cb398 |
0x4cb388 NOPL (%RAX,%RAX,1) |
(3729) 0x4cb390 INC %RCX |
(3729) 0x4cb393 CMP %RCX,%RDX |
(3729) 0x4cb396 JE 4cb360 |
(3729) 0x4cb398 CMP %RBX,(%RSI,%RCX,8) |
(3729) 0x4cb39c JNE 4cb390 |
(3729) 0x4cb39e MOVQ $-0x1,(%RSI,%RCX,8) |
(3729) 0x4cb3a6 INCQ (%R15) |
(3729) 0x4cb3a9 JMP 4cb390 |
0x4cb3ab NOPL (%RAX,%RAX,1) |
(3728) 0x4cb3b0 MOV %R11,%RDI |
(3728) 0x4cb3b3 MOV %R10,%RCX |
(3728) 0x4cb3b6 JMP 4cb3c9 |
0x4cb3b8 NOPL (%RAX,%RAX,1) |
(3730) 0x4cb3c0 ADD $0x20,%RCX |
(3730) 0x4cb3c4 DEC %RDI |
(3730) 0x4cb3c7 JE 4cb37e |
(3730) 0x4cb3c9 CMP %RBX,-0x18(%RCX) |
(3730) 0x4cb3cd JNE 4cb400 |
(3730) 0x4cb3cf MOVQ $-0x1,-0x18(%RCX) |
(3730) 0x4cb3d7 INCQ (%R15) |
(3730) 0x4cb3da CMP %RBX,-0x10(%RCX) |
(3730) 0x4cb3de JE 4cb406 |
(3730) 0x4cb3e0 CMP %RBX,-0x8(%RCX) |
(3730) 0x4cb3e4 JNE 4cb417 |
(3730) 0x4cb3e6 MOVQ $-0x1,-0x8(%RCX) |
(3730) 0x4cb3ee INCQ (%R15) |
(3730) 0x4cb3f1 CMP %RBX,(%RCX) |
(3730) 0x4cb3f4 JNE 4cb3c0 |
(3730) 0x4cb3f6 JMP 4cb41c |
0x4cb3f8 NOPL (%RAX,%RAX,1) |
(3730) 0x4cb400 CMP %RBX,-0x10(%RCX) |
(3730) 0x4cb404 JNE 4cb3e0 |
(3730) 0x4cb406 MOVQ $-0x1,-0x10(%RCX) |
(3730) 0x4cb40e INCQ (%R15) |
(3730) 0x4cb411 CMP %RBX,-0x8(%RCX) |
(3730) 0x4cb415 JE 4cb3e6 |
(3730) 0x4cb417 CMP %RBX,(%RCX) |
(3730) 0x4cb41a JNE 4cb3c0 |
(3730) 0x4cb41c MOVQ $-0x1,(%RCX) |
(3730) 0x4cb423 INCQ (%R15) |
(3730) 0x4cb426 JMP 4cb3c0 |
(3726) 0x4cb428 MOV 0x18(%RBP),%RAX |
(3726) 0x4cb42c MOV 0x38(%RAX),%RCX |
(3726) 0x4cb430 MOV 0x40(%RAX),%RAX |
(3726) 0x4cb434 MOV (%RAX,%R10,8),%R9 |
(3726) 0x4cb438 MOV (%RCX,%R10,8),%R11 |
(3726) 0x4cb43c TEST %R14,%R14 |
(3726) 0x4cb43f JLE 4cb790 |
(3726) 0x4cb445 MOV 0x60(%RBP),%RAX |
(3726) 0x4cb449 MOV 0x8(%RAX,%R10,8),%RAX |
(3726) 0x4cb44e MOV %RAX,-0x90(%RBP) |
(3726) 0x4cb455 MOV 0x78(%RBP),%RAX |
(3726) 0x4cb459 MOV %R10,-0x50(%RBP) |
(3726) 0x4cb45d MOV 0x8(%RAX,%R10,8),%R10 |
(3726) 0x4cb462 MOV %RDX,%R12 |
(3726) 0x4cb465 LEA (%RDX,%R14,1),%RDI |
(3726) 0x4cb469 XOR %ESI,%ESI |
(3726) 0x4cb46b MOV %R9,-0x70(%RBP) |
(3726) 0x4cb46f MOV %R11,%RCX |
(3726) 0x4cb472 JMP 4cb49e |
(3733) 0x4cb474 MOV -0x30(%RBP),%R12 |
(3733) 0x4cb478 MOV 0x10(%RBP),%RAX |
(3733) 0x4cb47c VMOVQ (%RAX,%R12,8),%XMM0 |
(3733) 0x4cb482 MOV 0x70(%RBP),%RAX |
(3733) 0x4cb486 VMOVQ %XMM0,(%RAX,%RDX,8) |
(3733) 0x4cb48b MOV -0x38(%RBP),%RBX |
(3733) 0x4cb48f INC %R12 |
(3733) 0x4cb492 INC %RSI |
(3733) 0x4cb495 CMP %R14,%RSI |
(3733) 0x4cb498 JE 4cb59f |
(3733) 0x4cb49e MOV %R12,-0x30(%RBP) |
(3733) 0x4cb4a2 MOV (%RBX,%R12,8),%RBX |
(3733) 0x4cb4a6 CMP 0x28(%RBP),%RBX |
(3733) 0x4cb4aa JL 4cb510 |
(3733) 0x4cb4ac CMP 0x30(%RBP),%RBX |
(3733) 0x4cb4b0 JG 4cb510 |
(3733) 0x4cb4b2 MOV 0x60(%RBP),%RAX |
(3733) 0x4cb4b6 MOV -0x50(%RBP),%RDX |
(3733) 0x4cb4ba MOV (%RAX,%RDX,8),%RDX |
(3733) 0x4cb4be CMP %R11,%RDX |
(3733) 0x4cb4c1 MOV 0x68(%RBP),%RAX |
(3733) 0x4cb4c5 JGE 4cb4de |
(3733) 0x4cb4c7 NOPW (%RAX,%RAX,1) |
(3735) 0x4cb4d0 CMP %RBX,(%RAX,%RDX,8) |
(3735) 0x4cb4d4 JE 4cb474 |
(3735) 0x4cb4d6 INC %RDX |
(3735) 0x4cb4d9 CMP %RDX,%R11 |
(3735) 0x4cb4dc JNE 4cb4d0 |
(3733) 0x4cb4de CMP -0x90(%RBP),%RCX |
(3733) 0x4cb4e5 JGE 4cb81e |
(3733) 0x4cb4eb MOV %RBX,(%RAX,%RCX,8) |
(3733) 0x4cb4ef MOV -0x30(%RBP),%R12 |
(3733) 0x4cb4f3 MOV 0x10(%RBP),%RAX |
(3733) 0x4cb4f7 VMOVQ (%RAX,%R12,8),%XMM0 |
(3733) 0x4cb4fd MOV 0x70(%RBP),%RAX |
(3733) 0x4cb501 VMOVQ %XMM0,(%RAX,%RCX,8) |
(3733) 0x4cb506 INC %RCX |
(3733) 0x4cb509 JMP 4cb48b |
0x4cb50b NOPL (%RAX,%RAX,1) |
(3733) 0x4cb510 MOV %RCX,-0x48(%RBP) |
(3733) 0x4cb514 MOV 0x78(%RBP),%RAX |
(3733) 0x4cb518 MOV -0x50(%RBP),%RDX |
(3733) 0x4cb51c MOV (%RAX,%RDX,8),%RDX |
(3733) 0x4cb520 CMP %R9,%RDX |
(3733) 0x4cb523 MOV 0x80(%RBP),%RAX |
(3733) 0x4cb52a MOV -0x70(%RBP),%RCX |
(3733) 0x4cb52e JGE 4cb53e |
(3734) 0x4cb530 CMP %RBX,(%RAX,%RDX,8) |
(3734) 0x4cb534 JE 4cb56e |
(3734) 0x4cb536 INC %RDX |
(3734) 0x4cb539 CMP %RDX,%R9 |
(3734) 0x4cb53c JNE 4cb530 |
(3733) 0x4cb53e CMP %R10,%RCX |
(3733) 0x4cb541 JGE 4cb857 |
(3733) 0x4cb547 MOV %RBX,(%RAX,%RCX,8) |
(3733) 0x4cb54b MOV -0x30(%RBP),%R12 |
(3733) 0x4cb54f MOV 0x10(%RBP),%RAX |
(3733) 0x4cb553 VMOVQ (%RAX,%R12,8),%XMM0 |
(3733) 0x4cb559 MOV 0x88(%RBP),%RDX |
(3733) 0x4cb560 VMOVQ %XMM0,(%RDX,%RCX,8) |
(3733) 0x4cb565 INC %RCX |
(3733) 0x4cb568 MOV %RCX,-0x70(%RBP) |
(3733) 0x4cb56c JMP 4cb588 |
(3733) 0x4cb56e MOV -0x30(%RBP),%R12 |
(3733) 0x4cb572 MOV 0x10(%RBP),%RAX |
(3733) 0x4cb576 VMOVQ (%RAX,%R12,8),%XMM0 |
(3733) 0x4cb57c MOV 0x88(%RBP),%RBX |
(3733) 0x4cb583 VMOVQ %XMM0,(%RBX,%RDX,8) |
(3733) 0x4cb588 MOV -0x38(%RBP),%RBX |
(3733) 0x4cb58c MOV -0x48(%RBP),%RCX |
(3733) 0x4cb590 INC %R12 |
(3733) 0x4cb593 INC %RSI |
(3733) 0x4cb596 CMP %R14,%RSI |
(3733) 0x4cb599 JNE 4cb49e |
(3726) 0x4cb59f MOV %RDI,%RDX |
(3726) 0x4cb5a2 MOV -0x68(%RBP),%R12 |
(3726) 0x4cb5a6 MOV 0x20(%RBP),%RSI |
(3726) 0x4cb5aa MOV -0x50(%RBP),%R10 |
(3726) 0x4cb5ae MOV -0x70(%RBP),%R9 |
(3726) 0x4cb5b2 MOV -0x58(%RBP),%RDI |
(3726) 0x4cb5b6 MOV %RCX,%R11 |
(3726) 0x4cb5b9 JMP 4cb8b7 |
(3726) 0x4cb5be XOR %R11D,%R11D |
(3726) 0x4cb5c1 MOV 0x10(%RBP),%R9 |
(3726) 0x4cb5c5 MOV -0x80(%RBP),%RAX |
(3726) 0x4cb5c9 TEST %R14,%R14 |
(3726) 0x4cb5cc MOV %RAX,%RCX |
(3726) 0x4cb5cf MOV %RAX,-0x80(%RBP) |
(3726) 0x4cb5d3 JLE 4cb248 |
(3726) 0x4cb5d9 XOR %EDI,%EDI |
(3726) 0x4cb5db MOV %R13,-0x50(%RBP) |
(3726) 0x4cb5df MOV -0x30(%RBP),%RCX |
(3726) 0x4cb5e3 XOR %EDX,%EDX |
(3726) 0x4cb5e5 MOV %RDX,-0x48(%RBP) |
(3726) 0x4cb5e9 JMP 4cb60f |
0x4cb5eb NOPL (%RAX,%RAX,1) |
(3739) 0x4cb5f0 MOV -0x48(%RBP),%RSI |
(3739) 0x4cb5f4 MOV %RDX,(%R11,%RSI,8) |
(3739) 0x4cb5f8 VMOVQ %XMM0,(%RAX,%RSI,8) |
(3739) 0x4cb5fd INC %RSI |
(3739) 0x4cb600 MOV %RSI,-0x48(%RBP) |
(3739) 0x4cb604 INC %RCX |
(3739) 0x4cb607 INC %RDI |
(3739) 0x4cb60a CMP %R14,%RDI |
(3739) 0x4cb60d JE 4cb674 |
(3739) 0x4cb60f MOV (%RBX,%RCX,8),%RDX |
(3739) 0x4cb613 TEST %R13,%R13 |
(3739) 0x4cb616 JLE 4cb62e |
(3739) 0x4cb618 XOR %ESI,%ESI |
(3739) 0x4cb61a NOPW (%RAX,%RAX,1) |
(3740) 0x4cb620 CMP %RDX,(%R12,%RSI,8) |
(3740) 0x4cb624 JE 4cb660 |
(3740) 0x4cb626 INC %RSI |
(3740) 0x4cb629 CMP %RSI,%R13 |
(3740) 0x4cb62c JNE 4cb620 |
(3739) 0x4cb62e VMOVQ (%R9,%RCX,8),%XMM0 |
(3739) 0x4cb634 MOV -0x50(%RBP),%RSI |
(3739) 0x4cb638 CMP -0x70(%RBP),%RSI |
(3739) 0x4cb63c JGE 4cb5f0 |
(3739) 0x4cb63e MOV %RDX,(%R12,%RSI,8) |
(3739) 0x4cb642 MOV -0x90(%RBP),%RDX |
(3739) 0x4cb649 VMOVQ %XMM0,(%RDX,%RSI,8) |
(3739) 0x4cb64e INC %RSI |
(3739) 0x4cb651 MOV %RSI,-0x50(%RBP) |
(3739) 0x4cb655 JMP 4cb604 |
0x4cb657 NOPW (%RAX,%RAX,1) |
(3739) 0x4cb660 VMOVQ (%R9,%RCX,8),%XMM0 |
(3739) 0x4cb666 MOV -0x90(%RBP),%RDX |
(3739) 0x4cb66d VMOVQ %XMM0,(%RDX,%RSI,8) |
(3739) 0x4cb672 JMP 4cb604 |
(3726) 0x4cb674 MOV -0x30(%RBP),%RDX |
(3726) 0x4cb678 ADD %R14,%RDX |
(3726) 0x4cb67b MOV -0x48(%RBP),%RCX |
(3726) 0x4cb67f MOV -0x50(%RBP),%RAX |
(3726) 0x4cb683 LEA (%RAX,%RCX,1),%RBX |
(3726) 0x4cb687 MOV 0x48(%RBP),%RAX |
(3726) 0x4cb68b MOV %RBX,(%RAX,%R10,8) |
(3726) 0x4cb68f TEST %RCX,%RCX |
(3726) 0x4cb692 MOV -0x60(%RBP),%RCX |
(3726) 0x4cb696 JE 4cb785 |
(3726) 0x4cb69c MOV %R11,-0x78(%RBP) |
(3726) 0x4cb6a0 MOV %RDX,-0x30(%RBP) |
(3726) 0x4cb6a4 MOV 0x38(%RBP),%R13 |
(3726) 0x4cb6a8 MOV (%R13,%R10,8),%RDI |
(3726) 0x4cb6ad LEA (,%RBX,8),%R14 |
(3726) 0x4cb6b5 MOV %R14,%RSI |
(3726) 0x4cb6b8 MOV %R10,%R12 |
(3726) 0x4cb6bb CALL 4dd960 <hypre_ReAlloc> |
(3726) 0x4cb6c0 MOV %RAX,(%R13,%R12,8) |
(3726) 0x4cb6c5 MOV 0x40(%RBP),%R13 |
(3726) 0x4cb6c9 MOV (%R13,%R12,8),%RDI |
(3726) 0x4cb6ce MOV %R14,%RSI |
(3726) 0x4cb6d1 CALL 4dd960 <hypre_ReAlloc> |
(3726) 0x4cb6d6 MOV %RAX,(%R13,%R12,8) |
(3726) 0x4cb6db MOV -0x48(%RBP),%R13 |
(3726) 0x4cb6df MOV 0x50(%RBP),%RCX |
(3726) 0x4cb6e3 MOV %RBX,(%RCX,%R12,8) |
(3726) 0x4cb6e7 TEST %R13,%R13 |
(3726) 0x4cb6ea JLE 4cb799 |
(3726) 0x4cb6f0 MOV 0x38(%RBP),%RCX |
(3726) 0x4cb6f4 MOV (%RCX,%R12,8),%RCX |
(3726) 0x4cb6f8 MOV -0x78(%RBP),%R11 |
(3726) 0x4cb6fc LEA (%R11,%R13,8),%RDX |
(3726) 0x4cb700 ADD $-0x8,%RDX |
(3726) 0x4cb704 MOV -0x50(%RBP),%RBX |
(3726) 0x4cb708 LEA (%RCX,%RBX,8),%RDI |
(3726) 0x4cb70c CMP %RDI,%RDX |
(3726) 0x4cb70f SETAE %R8B |
(3726) 0x4cb713 LEA (%RBX,%R13,1),%RSI |
(3726) 0x4cb717 DEC %RSI |
(3726) 0x4cb71a LEA (%RCX,%RSI,8),%RCX |
(3726) 0x4cb71e CMP %R11,%RCX |
(3726) 0x4cb721 SETAE %DL |
(3726) 0x4cb724 MOV -0x80(%RBP),%R9 |
(3726) 0x4cb728 LEA (%R9,%R13,8),%RCX |
(3726) 0x4cb72c ADD $-0x8,%RCX |
(3726) 0x4cb730 LEA (%RAX,%RBX,8),%R14 |
(3726) 0x4cb734 CMP %R14,%RCX |
(3726) 0x4cb737 SETB %CL |
(3726) 0x4cb73a LEA (%RAX,%RSI,8),%RAX |
(3726) 0x4cb73e CMP %R9,%RAX |
(3726) 0x4cb741 SETB %AL |
(3726) 0x4cb744 TEST %DL,%R8B |
(3726) 0x4cb747 JNE 4cb7b0 |
(3726) 0x4cb749 OR %AL,%CL |
(3726) 0x4cb74b JE 4cb7b0 |
(3726) 0x4cb74d CMP $0xd,%R13 |
(3726) 0x4cb751 JB 4cb8d4 |
(3726) 0x4cb757 SAL $0x3,%R13 |
(3726) 0x4cb75b MOV %R11,%RSI |
(3726) 0x4cb75e MOV %R13,%RDX |
(3726) 0x4cb761 MOV %R9,%RBX |
(3726) 0x4cb764 CALL 4e5f20 <_intel_fast_memcpy> |
(3726) 0x4cb769 MOV %R14,%RDI |
(3726) 0x4cb76c MOV %RBX,%RSI |
(3726) 0x4cb76f MOV %R13,%RDX |
(3726) 0x4cb772 CALL 4e5f20 <_intel_fast_memcpy> |
(3726) 0x4cb777 MOV -0x78(%RBP),%R11 |
(3726) 0x4cb77b MOV -0x38(%RBP),%RBX |
(3726) 0x4cb77f MOV -0x30(%RBP),%RDX |
(3726) 0x4cb783 JMP 4cb7e0 |
(3726) 0x4cb785 MOV -0x38(%RBP),%RBX |
(3726) 0x4cb789 TEST %R11,%R11 |
(3726) 0x4cb78c JNE 4cb7e4 |
(3726) 0x4cb78e JMP 4cb80a |
(3726) 0x4cb790 MOV -0x58(%RBP),%RDI |
(3726) 0x4cb794 JMP 4cb8b7 |
(3726) 0x4cb799 MOV -0x38(%RBP),%RBX |
(3726) 0x4cb79d MOV -0x30(%RBP),%RDX |
(3726) 0x4cb7a1 MOV -0x60(%RBP),%RCX |
(3726) 0x4cb7a5 MOV -0x78(%RBP),%R11 |
(3726) 0x4cb7a9 TEST %R11,%R11 |
(3726) 0x4cb7ac JNE 4cb7e4 |
(3726) 0x4cb7ae JMP 4cb80a |
(3726) 0x4cb7b0 XOR %EAX,%EAX |
(3726) 0x4cb7b2 MOV -0x30(%RBP),%RDX |
(3726) 0x4cb7b6 NOPW %CS:(%RAX,%RAX,1) |
(3736) 0x4cb7c0 MOV (%R11,%RAX,8),%RCX |
(3736) 0x4cb7c4 MOV %RCX,(%RDI,%RAX,8) |
(3736) 0x4cb7c8 VMOVQ (%R9,%RAX,8),%XMM0 |
(3736) 0x4cb7ce VMOVQ %XMM0,(%R14,%RAX,8) |
(3736) 0x4cb7d4 INC %RAX |
(3736) 0x4cb7d7 CMP %RAX,%R13 |
(3736) 0x4cb7da JNE 4cb7c0 |
(3726) 0x4cb7dc MOV -0x38(%RBP),%RBX |
(3726) 0x4cb7e0 MOV -0x60(%RBP),%RCX |
(3726) 0x4cb7e4 MOV %R11,%RDI |
(3726) 0x4cb7e7 MOV %RDX,%R14 |
(3726) 0x4cb7ea MOV %RCX,%R12 |
(3726) 0x4cb7ed VZEROUPPER |
(3726) 0x4cb7f0 CALL 4dd9d0 <hypre_Free> |
(3726) 0x4cb7f5 MOV -0x80(%RBP),%RDI |
(3726) 0x4cb7f9 CALL 4dd9d0 <hypre_Free> |
(3726) 0x4cb7fe MOV %R12,%RCX |
(3726) 0x4cb801 MOV %R14,%RDX |
(3726) 0x4cb804 XOR %EAX,%EAX |
(3726) 0x4cb806 MOV %RAX,-0x80(%RBP) |
(3726) 0x4cb80a MOV -0x58(%RBP),%RDI |
(3726) 0x4cb80e MOV -0x88(%RBP),%R8 |
(3726) 0x4cb815 MOV -0x68(%RBP),%R12 |
(3726) 0x4cb819 JMP 4cb187 |
(3726) 0x4cb81e MOV %RCX,-0x48(%RBP) |
(3726) 0x4cb822 MOV %R8,%R14 |
(3726) 0x4cb825 MOV $0x5063ab,%EDI |
(3726) 0x4cb82a MOV $0xd70,%ESI |
(3726) 0x4cb82f MOV $0x1,%EDX |
(3726) 0x4cb834 XOR %ECX,%ECX |
(3726) 0x4cb836 CALL 4dfac0 <hypre_error_handler> |
(3726) 0x4cb83b MOV 0xd0(%RBP),%RAX |
(3726) 0x4cb842 LOCK INCQ (%RAX) |
(3726) 0x4cb846 MOV $0x50651f,%EDI |
(3726) 0x4cb84b CMPQ $0,0xc0(%RBP) |
(3726) 0x4cb853 JNE 4cb88a |
(3726) 0x4cb855 JMP 4cb894 |
(3726) 0x4cb857 MOV %R8,%R14 |
(3726) 0x4cb85a MOV $0x5063ab,%EDI |
(3726) 0x4cb85f MOV $0xd4e,%ESI |
(3726) 0x4cb864 MOV $0x1,%EDX |
(3726) 0x4cb869 XOR %ECX,%ECX |
(3726) 0x4cb86b CALL 4dfac0 <hypre_error_handler> |
(3726) 0x4cb870 MOV 0xd0(%RBP),%RAX |
(3726) 0x4cb877 LOCK INCQ (%RAX) |
(3726) 0x4cb87b MOV $0x5064f9,%EDI |
(3726) 0x4cb880 CMPQ $0,0xc0(%RBP) |
(3726) 0x4cb888 JE 4cb894 |
(3726) 0x4cb88a MOV %R13,%RSI |
(3726) 0x4cb88d XOR %EAX,%EAX |
(3726) 0x4cb88f CALL 4ddab0 <hypre_printf> |
(3726) 0x4cb894 MOV -0x38(%RBP),%RBX |
(3726) 0x4cb898 MOV -0x58(%RBP),%RDI |
(3726) 0x4cb89c MOV %R14,%R8 |
(3726) 0x4cb89f MOV -0x68(%RBP),%R12 |
(3726) 0x4cb8a3 MOV -0x30(%RBP),%RDX |
(3726) 0x4cb8a7 MOV 0x20(%RBP),%RSI |
(3726) 0x4cb8ab MOV -0x50(%RBP),%R10 |
(3726) 0x4cb8af MOV -0x70(%RBP),%R9 |
(3726) 0x4cb8b3 MOV -0x48(%RBP),%R11 |
(3726) 0x4cb8b7 MOV 0x18(%RBP),%RCX |
(3726) 0x4cb8bb MOV 0x38(%RCX),%RAX |
(3726) 0x4cb8bf MOV %R11,(%RAX,%R10,8) |
(3726) 0x4cb8c3 MOV 0x40(%RCX),%RAX |
(3726) 0x4cb8c7 MOV %R9,(%RAX,%R10,8) |
(3726) 0x4cb8cb MOV -0x60(%RBP),%RCX |
(3726) 0x4cb8cf JMP 4cb18b |
(3726) 0x4cb8d4 MOV %R13,%RAX |
(3726) 0x4cb8d7 AND $-0x4,%RAX |
(3726) 0x4cb8db MOV -0x30(%RBP),%RSI |
(3726) 0x4cb8df JE 4cb925 |
(3726) 0x4cb8e1 LEA -0x1(%RAX),%RCX |
(3726) 0x4cb8e5 XOR %EDX,%EDX |
(3726) 0x4cb8e7 NOPW (%RAX,%RAX,1) |
(3738) 0x4cb8f0 VMOVUPS (%R11,%RDX,8),%YMM0 |
(3738) 0x4cb8f6 VMOVUPS %YMM0,(%RDI,%RDX,8) |
(3738) 0x4cb8fb VMOVDQU (%R9,%RDX,8),%YMM0 |
(3738) 0x4cb901 VMOVDQU %YMM0,(%R14,%RDX,8) |
(3738) 0x4cb907 ADD $0x4,%RDX |
(3738) 0x4cb90b CMP %RCX,%RDX |
(3738) 0x4cb90e JLE 4cb8f0 |
(3726) 0x4cb910 CMP %RAX,%R13 |
(3726) 0x4cb913 MOV -0x38(%RBP),%RBX |
(3726) 0x4cb917 MOV -0x60(%RBP),%RCX |
(3726) 0x4cb91b JNE 4cb92f |
(3726) 0x4cb91d MOV %RSI,%RDX |
(3726) 0x4cb920 JMP 4cb7e4 |
(3726) 0x4cb925 XOR %EAX,%EAX |
(3726) 0x4cb927 MOV -0x38(%RBP),%RBX |
(3726) 0x4cb92b MOV -0x60(%RBP),%RCX |
(3726) 0x4cb92f MOV %RCX,%RDX |
(3726) 0x4cb932 NOPW %CS:(%RAX,%RAX,1) |
(3737) 0x4cb940 MOV (%R11,%RAX,8),%RCX |
(3737) 0x4cb944 MOV %RCX,(%RDI,%RAX,8) |
(3737) 0x4cb948 VMOVQ (%R9,%RAX,8),%XMM0 |
(3737) 0x4cb94e VMOVQ %XMM0,(%R14,%RAX,8) |
(3737) 0x4cb954 INC %RAX |
(3737) 0x4cb957 CMP %RAX,%R13 |
(3737) 0x4cb95a JNE 4cb940 |
(3726) 0x4cb95c MOV %RDX,%RCX |
(3726) 0x4cb95f MOV %RSI,%RDX |
(3726) 0x4cb962 JMP 4cb7e4 |
0x4cb967 ADD $0x78,%RSP |
0x4cb96b POP %RBX |
0x4cb96c POP %R12 |
0x4cb96e POP %R13 |
0x4cb970 POP %R14 |
0x4cb972 POP %R15 |
0x4cb974 POP %RBP |
0x4cb975 RET |
0x4cb976 NOPW %CS:(%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_IJMatrixSetValuesOMPParC[...] | IJMatrix_parcsr.c:3240 | exec |
○ | BuildIJLaplacian27pt | amg.c:2267 | exec |
○ | main | amg.c:274 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | IJMatrix_parcsr.c:3240-3484 |
Module | exec |
nb instructions | 166 |
nb uops | 238 |
loop length | 651 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 15 |
micro-operation queue | 59.50 cycles |
front end | 59.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 35.75 | 35.75 | 17.17 | 16.83 | 23.00 | 35.75 | 35.75 | 17.00 |
cycles | 35.75 | 35.75 | 17.17 | 16.83 | 23.00 | 35.75 | 35.75 | 17.00 |
Cycles executing div or sqrt instructions | 30.00-96.00 |
FE+BE cycles | 43.00-96.62 |
Stall cycles | 0.00-53.57 |
Front-end | 59.50 |
Dispatch | 35.75 |
DIV/SQRT | 30.00-96.00 |
Overall L1 | 59.50-96.00 |
all | 9% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 40% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 12% |
all | 12% |
load | 11% |
store | 11% |
mul | 12% |
add-sub | 17% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 9% |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x78,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 4df9c0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4df9d0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R15,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %R14,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x20,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
JE 4caf5f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %R15 | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
MOV 0xb8(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%R13),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 4caf77 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA 0x1(%RAX),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R10,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
IMUL %R13,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RCX,%R10 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVQ $0,(%R14,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
CMP %R10,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JL 4cafa0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4cb020 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R14D,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
DIV %R15D | 10 | 2.50 | 2.50 | 0 | 0 | 0 | 2.50 | 2.50 | 0 | 26 | 6 |
MOV 0xb8(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%R13),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JL 4caf3a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
IMUL %R13,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL %RAX,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVQ $0,(%R14,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
CMP %R10,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JGE 4cb020 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP %RDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVL %R13,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IMUL %R13,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R10,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RDX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4cb001 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x58(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R9,%R15,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VEXTRACTI128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM1,%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSHUFD $-0x12,%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM1,%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM0,%RSI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
CMP %RCX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4cb009 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4cb01c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x58(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,(%R14,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x98(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x52b530,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 410560 <__kmpc_barrier@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 4cb0e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4cb0e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4cb0b7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV (%R14),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x40(%R14),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 4cb0e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV (%R14,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x98(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x52b550,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CALL 410560 <__kmpc_barrier@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4cb105 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x8(%R14,%R13,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4cb107 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x58(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x68(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R12,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 4cb967 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xb0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa8(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x98(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,0x18(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
LEA (%RAX,%R13,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SETE %AL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST %RSI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETLE %CL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
OR %AL,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %CL,-0x39(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DEC %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x1,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RSI,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x18(%R9),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JMP 4cb197 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x78,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | IJMatrix_parcsr.c:3240-3484 |
Module | exec |
nb instructions | 166 |
nb uops | 238 |
loop length | 651 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 15 |
micro-operation queue | 59.50 cycles |
front end | 59.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 35.75 | 35.75 | 17.17 | 16.83 | 23.00 | 35.75 | 35.75 | 17.00 |
cycles | 35.75 | 35.75 | 17.17 | 16.83 | 23.00 | 35.75 | 35.75 | 17.00 |
Cycles executing div or sqrt instructions | 30.00-96.00 |
FE+BE cycles | 43.00-96.62 |
Stall cycles | 0.00-53.57 |
Front-end | 59.50 |
Dispatch | 35.75 |
DIV/SQRT | 30.00-96.00 |
Overall L1 | 59.50-96.00 |
all | 9% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 40% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 12% |
all | 12% |
load | 11% |
store | 11% |
mul | 12% |
add-sub | 17% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 9% |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x78,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 4df9c0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4df9d0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R15,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %R14,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x20,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
JE 4caf5f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %R15 | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
MOV 0xb8(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%R13),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 4caf77 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA 0x1(%RAX),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R10,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
IMUL %R13,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
IMUL %RCX,%R10 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVQ $0,(%R14,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
CMP %R10,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JL 4cafa0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4cb020 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R14D,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
DIV %R15D | 10 | 2.50 | 2.50 | 0 | 0 | 0 | 2.50 | 2.50 | 0 | 26 | 6 |
MOV 0xb8(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%R13),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JL 4caf3a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
IMUL %R13,%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL %RAX,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVQ $0,(%R14,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
CMP %R10,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JGE 4cb020 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP %RDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVL %R13,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IMUL %R13,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R10,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RDX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4cb001 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x58(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R9,%R15,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VEXTRACTI128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM1,%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VPSHUFD $-0x12,%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ %XMM1,%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM0,%RSI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
CMP %RCX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4cb009 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4cb01c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x58(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,(%R14,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x98(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x52b530,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 410560 <__kmpc_barrier@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 4cb0e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4cb0e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4cb0b7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV (%R14),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x40(%R14),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 4cb0e6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV (%R14,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x98(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x52b550,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CALL 410560 <__kmpc_barrier@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4cb105 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x8(%R14,%R13,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4cb107 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x58(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x68(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R12,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 4cb967 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xb0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa8(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x98(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,0x18(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
LEA (%RAX,%R13,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SETE %AL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST %RSI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETLE %CL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
OR %AL,%CL | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %CL,-0x39(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DEC %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x1,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RSI,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x18(%R9),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RAX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JMP 4cb197 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x78,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_IJMatrixSetValuesOMPParCSR.extracted.28– | 1.12 | 0.41 |
▼Loop 3726 - IJMatrix_parcsr.c:3262-3484 - exec– | 0.07 | 0.02 |
▼Loop 3733 - IJMatrix_parcsr.c:3383-3454 - exec– | 1.04 | 0.38 |
○Loop 3735 - IJMatrix_parcsr.c:3422-3424 - exec | 0 | 0 |
○Loop 3734 - IJMatrix_parcsr.c:3388-3390 - exec | 0 | 0 |
▼Loop 3727 - IJMatrix_parcsr.c:3262-3484 - exec– | 0 | 0 |
▼Loop 3731 - IJMatrix_parcsr.c:3475-3484 - exec– | 0 | 0 |
○Loop 3732 - IJMatrix_parcsr.c:3478-3484 - exec | 0 | 0 |
▼Loop 3728 - IJMatrix_parcsr.c:3473-3484 - exec– | 0 | 0 |
○Loop 3729 - IJMatrix_parcsr.c:3478-3484 - exec | 0 | 0 |
○Loop 3730 - IJMatrix_parcsr.c:3478-3484 - exec | 0 | 0 |
○Loop 3737 - IJMatrix_parcsr.c:3359-3362 - exec | 0 | 0 |
○Loop 3738 - IJMatrix_parcsr.c:3359-3362 - exec | 0 | 0 |
▼Loop 3739 - IJMatrix_parcsr.c:3316-3341 - exec– | 0 | 0 |
○Loop 3740 - IJMatrix_parcsr.c:3318-3320 - exec | 0 | 0 |
○Loop 3736 - IJMatrix_parcsr.c:3359-3362 - exec | 0 | 0 |
○Loop 3743 - IJMatrix_parcsr.c:3274-3275 - exec | 0.01 | 0 |
○Loop 3742 - IJMatrix_parcsr.c:3282-3283 - exec | 0 | 0 |
○Loop 3725 - IJMatrix_parcsr.c:3274-3275 - exec | 0 | 0 |
○Loop 3741 - IJMatrix_parcsr.c:3282-3283 - exec | 0 | 0 |