Function: hypre_ParMatmul._omp_fn.3 | Module: exec | Source: par_csr_matop.c:829-995 [...] | Coverage: 4.65% |
---|
Function: hypre_ParMatmul._omp_fn.3 | Module: exec | Source: par_csr_matop.c:829-995 [...] | Coverage: 4.65% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 829 - 995 |
-------------------------------------------------------------------------------- |
829: #pragma omp parallel |
830: #endif |
831: { |
832: HYPRE_Int *B_marker = NULL; |
[...] |
840: ii = hypre_GetThreadNum(); |
841: num_threads = hypre_NumActiveThreads(); |
842: size = num_rows_diag_A/num_threads; |
843: rest = num_rows_diag_A - size*num_threads; |
844: if (ii < rest) |
845: { |
846: ns = ii*size+ii; |
847: ne = (ii+1)*size+ii+1; |
848: } |
849: else |
850: { |
851: ns = ii*size+rest; |
852: ne = (ii+1)*size+rest; |
853: } |
854: jj_count_diag = C_diag_i[ns]; |
855: jj_count_offd = C_offd_i[ns]; |
856: if (num_cols_diag_B || num_cols_offd_C) |
857: B_marker = hypre_CTAlloc(HYPRE_Int, num_cols_diag_B+num_cols_offd_C); |
858: for (i1 = 0; i1 < num_cols_diag_B+num_cols_offd_C; i1++) |
859: B_marker[i1] = -1; |
[...] |
865: for (i1 = ns; i1 < ne; i1++) |
[...] |
874: if ( allsquare ) |
875: { |
876: B_marker[i1] = jj_count_diag; |
877: C_diag_data[jj_count_diag] = zero; |
878: C_diag_j[jj_count_diag] = i1; |
879: jj_count_diag++; |
[...] |
886: if (num_cols_offd_A) |
887: { |
888: for (jj2 = A_offd_i[i1]; jj2 < A_offd_i[i1+1]; jj2++) |
889: { |
890: i2 = A_offd_j[jj2]; |
891: a_entry = A_offd_data[jj2]; |
[...] |
897: for (jj3 = B_ext_offd_i[i2]; jj3 < B_ext_offd_i[i2+1]; jj3++) |
898: { |
899: i3 = num_cols_diag_B+B_ext_offd_j[jj3]; |
[...] |
907: if (B_marker[i3] < jj_row_begin_offd) |
908: { |
909: B_marker[i3] = jj_count_offd; |
910: C_offd_data[jj_count_offd] = a_entry*B_ext_offd_data[jj3]; |
911: C_offd_j[jj_count_offd] = i3-num_cols_diag_B; |
912: jj_count_offd++; |
913: } |
914: else |
915: C_offd_data[B_marker[i3]] += a_entry*B_ext_offd_data[jj3]; |
916: } |
917: for (jj3 = B_ext_diag_i[i2]; jj3 < B_ext_diag_i[i2+1]; jj3++) |
918: { |
919: i3 = B_ext_diag_j[jj3]; |
920: if (B_marker[i3] < jj_row_begin_diag) |
921: { |
922: B_marker[i3] = jj_count_diag; |
923: C_diag_data[jj_count_diag] = a_entry*B_ext_diag_data[jj3]; |
924: C_diag_j[jj_count_diag] = i3; |
925: jj_count_diag++; |
926: } |
927: else |
928: C_diag_data[B_marker[i3]] += a_entry*B_ext_diag_data[jj3]; |
[...] |
937: for (jj2 = A_diag_i[i1]; jj2 < A_diag_i[i1+1]; jj2++) |
938: { |
939: i2 = A_diag_j[jj2]; |
940: a_entry = A_diag_data[jj2]; |
[...] |
946: for (jj3 = B_diag_i[i2]; jj3 < B_diag_i[i2+1]; jj3++) |
947: { |
948: i3 = B_diag_j[jj3]; |
[...] |
956: if (B_marker[i3] < jj_row_begin_diag) |
957: { |
958: B_marker[i3] = jj_count_diag; |
959: C_diag_data[jj_count_diag] = a_entry*B_diag_data[jj3]; |
960: C_diag_j[jj_count_diag] = i3; |
961: jj_count_diag++; |
962: } |
963: else |
964: { |
965: C_diag_data[B_marker[i3]] += a_entry*B_diag_data[jj3]; |
966: } |
967: } |
968: if (num_cols_offd_B) |
969: { |
970: for (jj3 = B_offd_i[i2]; jj3 < B_offd_i[i2+1]; jj3++) |
971: { |
972: i3 = num_cols_diag_B+map_B_to_C[B_offd_j[jj3]]; |
[...] |
980: if (B_marker[i3] < jj_row_begin_offd) |
981: { |
982: B_marker[i3] = jj_count_offd; |
983: C_offd_data[jj_count_offd] = a_entry*B_offd_data[jj3]; |
984: C_offd_j[jj_count_offd] = i3-num_cols_diag_B; |
985: jj_count_offd++; |
986: } |
987: else |
988: { |
989: C_offd_data[B_marker[i3]] += a_entry*B_offd_data[jj3]; |
[...] |
995: hypre_TFree(B_marker); |
0x55a060 PUSH %RBP |
0x55a061 MOV %RSP,%RBP |
0x55a064 PUSH %R15 |
0x55a066 PUSH %R14 |
0x55a068 PUSH %R13 |
0x55a06a MOV %RDI,%R13 |
0x55a06d PUSH %R12 |
0x55a06f PUSH %RBX |
0x55a070 SUB $0x108,%RSP |
0x55a077 VMOVSD 0xf8(%RDI),%XMM0 |
0x55a07f MOV 0xf0(%RDI),%RAX |
0x55a086 MOV 0xe8(%RDI),%RDX |
0x55a08d MOV 0xe0(%RDI),%RCX |
0x55a094 MOV 0xd8(%RDI),%RBX |
0x55a09b MOV 0xd0(%RDI),%RSI |
0x55a0a2 VMOVSD %XMM0,-0x58(%RBP) |
0x55a0a7 MOV 0xc8(%RDI),%R8 |
0x55a0ae MOV 0xc0(%RDI),%R9 |
0x55a0b5 MOV %RAX,-0x110(%RBP) |
0x55a0bc MOV 0xb0(%RDI),%R10 |
0x55a0c3 MOV 0xa0(%RDI),%R11 |
0x55a0ca MOV %RDX,-0x60(%RBP) |
0x55a0ce MOV 0x98(%RDI),%R12 |
0x55a0d5 MOV 0x80(%RDI),%R14 |
0x55a0dc MOV %RCX,-0xe8(%RBP) |
0x55a0e3 MOV %RBX,-0x68(%RBP) |
0x55a0e7 MOV 0x88(%RDI),%RBX |
0x55a0ee MOV %RSI,-0x70(%RBP) |
0x55a0f2 MOV %R8,-0xf0(%RBP) |
0x55a0f9 MOV %R9,-0x78(%RBP) |
0x55a0fd MOV %R10,-0x80(%RBP) |
0x55a101 MOV %R11,-0x50(%RBP) |
0x55a105 MOV %R12,-0x48(%RBP) |
0x55a109 MOV %R14,-0x88(%RBP) |
0x55a110 MOV 0x78(%RDI),%R15 |
0x55a114 MOV 0x70(%RDI),%RAX |
0x55a118 MOV 0x68(%RDI),%RDX |
0x55a11c MOV 0x60(%RDI),%RCX |
0x55a120 MOV 0x58(%RDI),%RSI |
0x55a124 MOV %R15,-0xb8(%RBP) |
0x55a12b MOV 0x50(%RDI),%R8 |
0x55a12f MOV 0x48(%RDI),%R9 |
0x55a133 MOV %RAX,-0x40(%RBP) |
0x55a137 MOV 0x40(%RDI),%R10 |
0x55a13b MOV 0x38(%RDI),%R11 |
0x55a13f MOV %RDX,-0x90(%RBP) |
0x55a146 MOV 0x30(%RDI),%R12 |
0x55a14a MOV 0x10(%RDI),%RDX |
0x55a14e MOV %RCX,-0xf8(%RBP) |
0x55a155 MOV 0x28(%RDI),%R14 |
0x55a159 MOV 0x8(%RDI),%RCX |
0x55a15d MOV %RSI,-0x98(%RBP) |
0x55a164 MOV 0x20(%RDI),%R15 |
0x55a168 MOV 0x18(%RDI),%RAX |
0x55a16c MOV %R8,-0x128(%RBP) |
0x55a173 MOV (%RDI),%RDI |
0x55a176 MOV %R9,-0xc0(%RBP) |
0x55a17d MOV %R10,-0x130(%RBP) |
0x55a184 MOV %R11,-0x118(%RBP) |
0x55a18b MOV %RDX,-0xc8(%RBP) |
0x55a192 MOV %RCX,-0xb0(%RBP) |
0x55a199 MOV %RDI,-0xd0(%RBP) |
0x55a1a0 MOV %R14,-0x100(%RBP) |
0x55a1a7 MOV %R15,-0xe0(%RBP) |
0x55a1ae MOV %RAX,-0x108(%RBP) |
0x55a1b5 CALL 5b5180 <hypre_GetThreadNum> |
0x55a1ba MOV %RAX,-0x38(%RBP) |
0x55a1be CALL 5b5170 <hypre_NumActiveThreads> |
0x55a1c3 MOV -0x38(%RBP),%R8 |
0x55a1c7 MOV -0x40(%RBP),%R11 |
0x55a1cb MOV %RAX,%RSI |
0x55a1ce MOV %R12,%RAX |
0x55a1d1 MOV -0x48(%RBP),%R10 |
0x55a1d5 MOV -0x50(%RBP),%R9 |
0x55a1d9 CQTO |
0x55a1db VMOVSD -0x58(%RBP),%XMM3 |
0x55a1e0 IDIV %RSI |
0x55a1e3 CMP %R8,%RDX |
0x55a1e6 JLE 55a6d4 |
0x55a1ec MOV %R8,%R14 |
0x55a1ef IMUL %RAX,%R14 |
0x55a1f3 LEA (%R8,%R14,1),%RDX |
0x55a1f7 ADD %R14,%RAX |
0x55a1fa MOV %RDX,-0xa0(%RBP) |
0x55a201 LEA 0x1(%R8,%RAX,1),%R15 |
0x55a206 MOV 0x90(%R13),%RCX |
0x55a20d MOV 0xa8(%R13),%RSI |
0x55a214 MOV 0xb8(%R13),%R14 |
0x55a21b MOV (%RCX),%RDI |
0x55a21e MOV (%RSI),%RAX |
0x55a221 MOV (%R14),%RCX |
0x55a224 MOV (%RAX,%RDX,8),%R8 |
0x55a228 MOV (%RDI,%RDX,8),%R12 |
0x55a22c MOV %R11,%RDX |
0x55a22f OR %RCX,%RDX |
0x55a232 MOV %R8,-0x40(%RBP) |
0x55a236 JNE 55a668 |
0x55a23c XOR %R8D,%R8D |
0x55a23f CMP %R15,-0xa0(%RBP) |
0x55a246 JGE 55a64f |
0x55a24c CMPQ $0,-0x110(%RBP) |
0x55a254 MOV %R15,-0x120(%RBP) |
0x55a25b MOV %R9,-0x50(%RBP) |
0x55a25f MOV %R10,-0x38(%RBP) |
0x55a263 MOV %R11,-0x58(%RBP) |
0x55a267 JNE 55a395 |
(2474) 0x55a26d CMPQ $0,-0x118(%RBP) |
(2474) 0x55a275 MOV -0x40(%RBP),%RSI |
(2474) 0x55a279 MOV %R12,%RDX |
(2474) 0x55a27c JNE 55a3c5 |
(2474) 0x55a282 MOV -0xb0(%RBP),%R11 |
(2474) 0x55a289 MOV -0xa0(%RBP),%R14 |
(2474) 0x55a290 MOV (%R11,%R14,8),%RDI |
(2474) 0x55a294 CMP %RDI,0x8(%R11,%R14,8) |
(2474) 0x55a299 JLE 55a365 |
(2474) 0x55a29f MOV -0x128(%RBP),%R11 |
(2474) 0x55a2a6 MOV -0x130(%RBP),%R13 |
(2474) 0x55a2ad MOV %RSI,-0xa8(%RBP) |
(2474) 0x55a2b4 MOV %RDI,-0x48(%RBP) |
(2474) 0x55a2b8 NOPL (%RAX,%RAX,1) |
(2479) 0x55a2c0 MOV -0x48(%RBP),%R9 |
(2479) 0x55a2c4 MOV -0xc8(%RBP),%RCX |
(2479) 0x55a2cb MOV -0xd0(%RBP),%RSI |
(2479) 0x55a2d2 MOV -0xc0(%RBP),%R10 |
(2479) 0x55a2d9 MOV (%RCX,%R9,8),%RDI |
(2479) 0x55a2dd VMOVSD (%RSI,%R9,8),%XMM7 |
(2479) 0x55a2e3 LEA 0x8(,%RDI,8),%R9 |
(2479) 0x55a2eb MOV (%R10,%RDI,8),%RAX |
(2479) 0x55a2ef LEA (%R10,%R9,1),%R14 |
(2479) 0x55a2f3 MOV (%R14),%R10 |
(2479) 0x55a2f6 CMP %R10,%RAX |
(2479) 0x55a2f9 JGE 55a32f |
(2479) 0x55a2fb NOPL (%RAX,%RAX,1) |
(2481) 0x55a300 MOV (%R11,%RAX,8),%RCX |
(2481) 0x55a304 VMULSD (%R13,%RAX,8),%XMM7,%XMM8 |
(2481) 0x55a30b LEA (%R8,%RCX,8),%RSI |
(2481) 0x55a30f MOV (%RSI),%R15 |
(2481) 0x55a312 CMP %R15,%R12 |
(2481) 0x55a315 JG 55a500 |
(2481) 0x55a31b LEA (%RBX,%R15,8),%RCX |
(2481) 0x55a31f INC %RAX |
(2481) 0x55a322 VADDSD (%RCX),%XMM8,%XMM9 |
(2481) 0x55a326 VMOVSD %XMM9,(%RCX) |
(2481) 0x55a32a CMP %R10,%RAX |
(2481) 0x55a32d JL 55a300 |
(2479) 0x55a32f CMPQ $0,-0xb8(%RBP) |
(2479) 0x55a337 JNE 55a530 |
(2479) 0x55a33d INCQ -0x48(%RBP) |
(2479) 0x55a341 MOV -0xb0(%RBP),%R14 |
(2479) 0x55a348 MOV -0xa0(%RBP),%RSI |
(2479) 0x55a34f MOV -0x48(%RBP),%RAX |
(2479) 0x55a353 CMP %RAX,0x8(%R14,%RSI,8) |
(2479) 0x55a358 JG 55a2c0 |
(2474) 0x55a35e MOV -0xa8(%RBP),%RSI |
(2474) 0x55a365 INCQ -0xa0(%RBP) |
(2474) 0x55a36c MOV -0xa0(%RBP),%R12 |
(2474) 0x55a373 CMP %R12,-0x120(%RBP) |
(2474) 0x55a37a JE 55a64f |
(2474) 0x55a380 CMPQ $0,-0x110(%RBP) |
(2474) 0x55a388 MOV %RSI,-0x40(%RBP) |
(2474) 0x55a38c MOV %RDX,%R12 |
(2474) 0x55a38f JE 55a26d |
(2478) 0x55a395 MOV -0xa0(%RBP),%R11 |
(2478) 0x55a39c MOV -0x38(%RBP),%R9 |
(2478) 0x55a3a0 LEA 0x1(%R12),%RDX |
(2478) 0x55a3a5 CMPQ $0,-0x118(%RBP) |
(2478) 0x55a3ad MOV -0x40(%RBP),%RSI |
(2478) 0x55a3b1 MOV %R12,(%R8,%R11,8) |
(2478) 0x55a3b5 VMOVSD %XMM3,(%RBX,%R12,8) |
(2478) 0x55a3bb MOV %R11,(%R9,%R12,8) |
(2478) 0x55a3bf JE 55a282 |
(2474) 0x55a3c5 MOV -0xe0(%RBP),%R15 |
(2474) 0x55a3cc MOV -0xa0(%RBP),%RAX |
(2474) 0x55a3d3 MOV (%R15,%RAX,8),%R14 |
(2474) 0x55a3d7 CMP 0x8(%R15,%RAX,8),%R14 |
(2474) 0x55a3dc JGE 55a282 |
(2474) 0x55a3e2 MOV %R12,-0x48(%RBP) |
(2474) 0x55a3e6 MOV -0x50(%RBP),%R11 |
(2474) 0x55a3ea MOV %R14,%RDI |
(2474) 0x55a3ed MOV -0x58(%RBP),%R12 |
(2474) 0x55a3f1 NOPL (%RAX) |
(2475) 0x55a3f8 MOV -0x100(%RBP),%R13 |
(2475) 0x55a3ff MOV -0xe8(%RBP),%R10 |
(2475) 0x55a406 MOV -0x108(%RBP),%RCX |
(2475) 0x55a40d MOV (%R13,%RDI,8),%R14 |
(2475) 0x55a412 VMOVSD (%RCX,%RDI,8),%XMM2 |
(2475) 0x55a417 LEA 0x8(,%R14,8),%R13 |
(2475) 0x55a41f MOV (%R10,%R14,8),%RAX |
(2475) 0x55a423 ADD %R13,%R10 |
(2475) 0x55a426 MOV %R10,-0xa8(%RBP) |
(2475) 0x55a42d MOV (%R10),%R10 |
(2475) 0x55a430 CMP %R10,%RAX |
(2475) 0x55a433 JGE 55a481 |
(2475) 0x55a435 MOV %RDX,-0xd8(%RBP) |
(2475) 0x55a43c NOPL (%RAX) |
(2477) 0x55a440 MOV -0x60(%RBP),%R9 |
(2477) 0x55a444 MOV (%R9,%RAX,8),%RCX |
(2477) 0x55a448 LEA (%R12,%RCX,1),%RDX |
(2477) 0x55a44c LEA (%R8,%RDX,8),%R9 |
(2477) 0x55a450 MOV -0x68(%RBP),%RDX |
(2477) 0x55a454 MOV (%R9),%R15 |
(2477) 0x55a457 VMULSD (%RDX,%RAX,8),%XMM2,%XMM1 |
(2477) 0x55a45c CMP %R15,-0x40(%RBP) |
(2477) 0x55a460 JG 55a620 |
(2477) 0x55a466 LEA (%R11,%R15,8),%RCX |
(2477) 0x55a46a INC %RAX |
(2477) 0x55a46d VADDSD (%RCX),%XMM1,%XMM4 |
(2477) 0x55a471 VMOVSD %XMM4,(%RCX) |
(2477) 0x55a475 CMP %R10,%RAX |
(2477) 0x55a478 JL 55a440 |
(2475) 0x55a47a MOV -0xd8(%RBP),%RDX |
(2475) 0x55a481 MOV -0xf0(%RBP),%RCX |
(2475) 0x55a488 MOV (%RCX,%R14,8),%RAX |
(2475) 0x55a48c ADD %R13,%RCX |
(2475) 0x55a48f MOV (%RCX),%R13 |
(2475) 0x55a492 MOV %RCX,%R15 |
(2475) 0x55a495 CMP %R13,%RAX |
(2475) 0x55a498 JGE 55a4d7 |
(2475) 0x55a49a NOPW (%RAX,%RAX,1) |
(2476) 0x55a4a0 MOV -0x70(%RBP),%R14 |
(2476) 0x55a4a4 MOV -0x78(%RBP),%R9 |
(2476) 0x55a4a8 MOV (%R14,%RAX,8),%RCX |
(2476) 0x55a4ac VMULSD (%R9,%RAX,8),%XMM2,%XMM5 |
(2476) 0x55a4b2 LEA (%R8,%RCX,8),%R10 |
(2476) 0x55a4b6 MOV (%R10),%R14 |
(2476) 0x55a4b9 CMP %R14,-0x48(%RBP) |
(2476) 0x55a4bd JG 55a5f0 |
(2476) 0x55a4c3 LEA (%RBX,%R14,8),%RCX |
(2476) 0x55a4c7 INC %RAX |
(2476) 0x55a4ca VADDSD (%RCX),%XMM5,%XMM6 |
(2476) 0x55a4ce VMOVSD %XMM6,(%RCX) |
(2476) 0x55a4d2 CMP %R13,%RAX |
(2476) 0x55a4d5 JL 55a4a0 |
(2475) 0x55a4d7 MOV -0xe0(%RBP),%RAX |
(2475) 0x55a4de MOV -0xa0(%RBP),%R15 |
(2475) 0x55a4e5 INC %RDI |
(2475) 0x55a4e8 CMP %RDI,0x8(%RAX,%R15,8) |
(2475) 0x55a4ed JG 55a3f8 |
(2474) 0x55a4f3 MOV -0x48(%RBP),%R12 |
(2474) 0x55a4f7 JMP 55a282 |
0x55a4fc NOPL (%RAX) |
(2481) 0x55a500 MOV -0x38(%RBP),%R10 |
(2481) 0x55a504 MOV %RDX,(%RSI) |
(2481) 0x55a507 INC %RAX |
(2481) 0x55a50a VMOVSD %XMM8,(%RBX,%RDX,8) |
(2481) 0x55a50f MOV %RCX,(%R10,%RDX,8) |
(2481) 0x55a513 INC %RDX |
(2481) 0x55a516 MOV (%R14),%R10 |
(2481) 0x55a519 CMP %RAX,%R10 |
(2481) 0x55a51c JG 55a300 |
(2479) 0x55a522 CMPQ $0,-0xb8(%RBP) |
(2479) 0x55a52a JE 55a33d |
(2479) 0x55a530 MOV -0xf8(%RBP),%R14 |
(2479) 0x55a537 MOV (%R14,%RDI,8),%RAX |
(2479) 0x55a53b LEA (%R14,%R9,1),%R14 |
(2479) 0x55a53f MOV (%R14),%R10 |
(2479) 0x55a542 CMP %R10,%RAX |
(2479) 0x55a545 JGE 55a33d |
(2479) 0x55a54b MOV -0xa8(%RBP),%RSI |
(2479) 0x55a552 NOPW (%RAX,%RAX,1) |
(2480) 0x55a558 MOV -0x90(%RBP),%RDI |
(2480) 0x55a55f MOV -0x88(%RBP),%R15 |
(2480) 0x55a566 MOV (%RDI,%RAX,8),%R9 |
(2480) 0x55a56a MOV -0x58(%RBP),%RDI |
(2480) 0x55a56e MOV (%R15,%R9,8),%RCX |
(2480) 0x55a572 MOV -0x98(%RBP),%R15 |
(2480) 0x55a579 VMULSD (%R15,%RAX,8),%XMM7,%XMM10 |
(2480) 0x55a57f ADD %RCX,%RDI |
(2480) 0x55a582 LEA (%R8,%RDI,8),%RDI |
(2480) 0x55a586 MOV (%RDI),%R9 |
(2480) 0x55a589 CMP %R9,-0x40(%RBP) |
(2480) 0x55a58d JG 55a5b8 |
(2480) 0x55a58f MOV -0x50(%RBP),%RCX |
(2480) 0x55a593 INC %RAX |
(2480) 0x55a596 LEA (%RCX,%R9,8),%RDI |
(2480) 0x55a59a VADDSD (%RDI),%XMM10,%XMM11 |
(2480) 0x55a59e VMOVSD %XMM11,(%RDI) |
(2480) 0x55a5a2 CMP %R10,%RAX |
(2480) 0x55a5a5 JL 55a558 |
(2479) 0x55a5a7 MOV %RSI,-0xa8(%RBP) |
(2479) 0x55a5ae JMP 55a33d |
0x55a5b3 NOPL (%RAX,%RAX,1) |
(2480) 0x55a5b8 MOV -0x50(%RBP),%R10 |
(2480) 0x55a5bc MOV -0x80(%RBP),%R9 |
(2480) 0x55a5c0 MOV %RSI,(%RDI) |
(2480) 0x55a5c3 INC %RAX |
(2480) 0x55a5c6 VMOVSD %XMM10,(%R10,%RSI,8) |
(2480) 0x55a5cc MOV %RCX,(%R9,%RSI,8) |
(2480) 0x55a5d0 INC %RSI |
(2480) 0x55a5d3 MOV (%R14),%R10 |
(2480) 0x55a5d6 CMP %RAX,%R10 |
(2480) 0x55a5d9 JG 55a558 |
(2479) 0x55a5df MOV %RSI,-0xa8(%RBP) |
(2479) 0x55a5e6 JMP 55a33d |
0x55a5eb NOPL (%RAX,%RAX,1) |
(2476) 0x55a5f0 MOV -0x38(%RBP),%R13 |
(2476) 0x55a5f4 MOV %RDX,(%R10) |
(2476) 0x55a5f7 INC %RAX |
(2476) 0x55a5fa VMOVSD %XMM5,(%RBX,%RDX,8) |
(2476) 0x55a5ff MOV %RCX,(%R13,%RDX,8) |
(2476) 0x55a604 INC %RDX |
(2476) 0x55a607 MOV (%R15),%R13 |
(2476) 0x55a60a CMP %RAX,%R13 |
(2476) 0x55a60d JG 55a4a0 |
(2475) 0x55a613 JMP 55a4d7 |
0x55a618 NOPL (%RAX,%RAX,1) |
(2477) 0x55a620 MOV -0x80(%RBP),%R10 |
(2477) 0x55a624 MOV %RSI,(%R9) |
(2477) 0x55a627 INC %RAX |
(2477) 0x55a62a VMOVSD %XMM1,(%R11,%RSI,8) |
(2477) 0x55a630 MOV -0xa8(%RBP),%R9 |
(2477) 0x55a637 MOV %RCX,(%R10,%RSI,8) |
(2477) 0x55a63b INC %RSI |
(2477) 0x55a63e MOV (%R9),%R10 |
(2477) 0x55a641 CMP %R10,%RAX |
(2477) 0x55a644 JL 55a440 |
(2475) 0x55a64a JMP 55a47a |
0x55a64f ADD $0x108,%RSP |
0x55a656 MOV %R8,%RDI |
0x55a659 POP %RBX |
0x55a65a POP %R12 |
0x55a65c POP %R13 |
0x55a65e POP %R14 |
0x55a660 POP %R15 |
0x55a662 POP %RBP |
0x55a663 JMP 5b1eb0 |
0x55a668 LEA (%R11,%RCX,1),%RDI |
0x55a66c MOV $0x8,%ESI |
0x55a671 MOV %R10,-0x58(%RBP) |
0x55a675 MOV %R9,-0x50(%RBP) |
0x55a679 MOV %R11,-0x38(%RBP) |
0x55a67d VMOVSD %XMM3,-0x48(%RBP) |
0x55a682 CALL 5b1df0 <hypre_CAlloc> |
0x55a687 MOV 0xb8(%R13),%R13 |
0x55a68e MOV -0x38(%RBP),%R11 |
0x55a692 VMOVSD -0x48(%RBP),%XMM3 |
0x55a697 MOV -0x50(%RBP),%R9 |
0x55a69b MOV %RAX,%R8 |
0x55a69e MOV (%R13),%R10 |
0x55a6a2 ADD %R11,%R10 |
0x55a6a5 TEST %R10,%R10 |
0x55a6a8 MOV -0x58(%RBP),%R10 |
0x55a6ac JLE 55a23f |
0x55a6b2 XOR %EDI,%EDI |
0x55a6b4 NOPL (%RAX) |
(2482) 0x55a6b8 MOVQ $-0x1,(%R8,%RDI,8) |
(2482) 0x55a6c0 INC %RDI |
(2482) 0x55a6c3 MOV (%R13),%RSI |
(2482) 0x55a6c7 ADD %R11,%RSI |
(2482) 0x55a6ca CMP %RDI,%RSI |
(2482) 0x55a6cd JG 55a6b8 |
0x55a6cf JMP 55a23f |
0x55a6d4 IMUL %RAX,%R8 |
0x55a6d8 LEA (%RDX,%R8,1),%R12 |
0x55a6dc ADD %RAX,%R8 |
0x55a6df LEA (%R8,%RDX,1),%R15 |
0x55a6e3 MOV %R12,-0xa0(%RBP) |
0x55a6ea MOV %R12,%RDX |
0x55a6ed JMP 55a206 |
0x55a6f2 NOPW %CS:(%RAX,%RAX,1) |
0x55a6fd NOPL (%RAX) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | par_csr_matop.c:829-995 |
Module | exec |
nb instructions | 148 |
nb uops | 207 |
loop length | 701 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 30 |
micro-operation queue | 51.75 cycles |
front end | 51.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 21.75 | 21.75 | 34.67 | 34.67 | 48.00 | 21.75 | 21.75 | 34.67 |
cycles | 21.75 | 22.00 | 34.67 | 34.67 | 48.00 | 21.75 | 21.75 | 34.67 |
Cycles executing div or sqrt instructions | 24.00-90.00 |
FE+BE cycles | 45.16-90.48 |
Stall cycles | 7.22-52.54 |
SB full (events) | 11.56-57.01 |
Front-end | 51.75 |
Dispatch | 48.00 |
DIV/SQRT | 24.00-90.00 |
Overall L1 | 51.75-90.00 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 0% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
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 |
MOV %RDI,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
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 $0x108,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0xf8(%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xf0(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xe8(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xe0(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xd8(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xd0(%RDI),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xc8(%RDI),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xc0(%RDI),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xb0(%RDI),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa0(%RDI),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x98(%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x80(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xe8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x88(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0xf0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x78(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x70(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x68(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x60(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x58(%RDI),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15,-0xb8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x50(%RDI),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x48(%RDI),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x40(%RDI),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x38(%RDI),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x30(%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xf8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x28(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x128(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,-0xc0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x118(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,-0xc8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,-0xd0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,-0x100(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,-0xe0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,-0x108(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 5b5180 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 5b5170 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x38(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMOVSD -0x58(%RBP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IDIV %RSI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
CMP %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 55a6d4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
IMUL %RAX,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%R8,%R14,1),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %R14,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RDX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R8,%RAX,1),%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x90(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa8(%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xb8(%R13),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R14),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDI,%RDX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R11,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JNE 55a668 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R15,-0xa0(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 55a64f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMPQ $0,-0x110(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %R15,-0x120(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JNE 55a395 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
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 |
ADD $0x108,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 |
JMP 5b1eb0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
LEA (%R11,%RCX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x8,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R10,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM3,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 5b1df0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0xb8(%R13),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x48(%RBP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%R13),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST %R10,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 55a23f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDI,%EDI | 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 |
JMP 55a23f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
IMUL %RAX,%R8 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%RDX,%R8,1),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%RDX,1),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R12,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 55a206 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
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 |
Source file and lines | par_csr_matop.c:829-995 |
Module | exec |
nb instructions | 148 |
nb uops | 207 |
loop length | 701 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 30 |
micro-operation queue | 51.75 cycles |
front end | 51.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 21.75 | 21.75 | 34.67 | 34.67 | 48.00 | 21.75 | 21.75 | 34.67 |
cycles | 21.75 | 22.00 | 34.67 | 34.67 | 48.00 | 21.75 | 21.75 | 34.67 |
Cycles executing div or sqrt instructions | 24.00-90.00 |
FE+BE cycles | 45.16-90.48 |
Stall cycles | 7.22-52.54 |
SB full (events) | 11.56-57.01 |
Front-end | 51.75 |
Dispatch | 48.00 |
DIV/SQRT | 24.00-90.00 |
Overall L1 | 51.75-90.00 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 0% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
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 |
MOV %RDI,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
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 $0x108,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0xf8(%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xf0(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xe8(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xe0(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xd8(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xd0(%RDI),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xc8(%RDI),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xc0(%RDI),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xb0(%RDI),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa0(%RDI),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x98(%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x80(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xe8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x88(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0xf0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x78(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x70(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x68(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x60(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x58(%RDI),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15,-0xb8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x50(%RDI),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x48(%RDI),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x40(%RDI),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x38(%RDI),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x30(%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xf8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x28(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x128(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,-0xc0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x118(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,-0xc8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,-0xd0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,-0x100(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,-0xe0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,-0x108(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 5b5180 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 5b5170 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x38(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMOVSD -0x58(%RBP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IDIV %RSI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
CMP %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 55a6d4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
IMUL %RAX,%R14 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%R8,%R14,1),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %R14,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RDX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R8,%RAX,1),%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x90(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa8(%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xb8(%R13),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R14),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDI,%RDX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R11,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JNE 55a668 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R15,-0xa0(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 55a64f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMPQ $0,-0x110(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %R15,-0x120(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JNE 55a395 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
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 |
ADD $0x108,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 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 |
JMP 5b1eb0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
LEA (%R11,%RCX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x8,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R10,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM3,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 5b1df0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0xb8(%R13),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x48(%RBP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x50(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%R13),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST %R10,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 55a23f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDI,%EDI | 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 |
JMP 55a23f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
IMUL %RAX,%R8 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%RDX,%R8,1),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%RDX,1),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R12,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 55a206 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
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 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_ParMatmul._omp_fn.3– | 4.65 | 1.71 |
▼Loop 2478 - par_csr_matop.c:865-989 - exec– | 0 | 0 |
▼Loop 2474 - par_csr_matop.c:865-989 - exec– | 0.05 | 0.02 |
▼Loop 2479 - par_csr_matop.c:937-989 - exec– | 1.6 | 0.59 |
○Loop 2481 - par_csr_matop.c:946-965 - exec | 3 | 1.1 |
○Loop 2480 - par_csr_matop.c:970-989 - exec | 0 | 0 |
▼Loop 2475 - par_csr_matop.c:888-928 - exec– | 0 | 0 |
○Loop 2476 - par_csr_matop.c:917-928 - exec | 0 | 0 |
○Loop 2477 - par_csr_matop.c:897-915 - exec | 0 | 0 |
○Loop 2482 - par_csr_matop.c:858-859 - exec | 0 | 0 |