Function: hypre_BoomerAMGCoarsenPMIS.extracted | Module: exec | Source: par_coarsen.c:2516-2576 [...] | Coverage: 0.12% |
---|
Function: hypre_BoomerAMGCoarsenPMIS.extracted | Module: exec | Source: par_coarsen.c:2516-2576 [...] | Coverage: 0.12% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c: 2516 - 2576 |
-------------------------------------------------------------------------------- |
2516: #pragma omp parallel private(ig,i) |
[...] |
2523: hypre_GetSimpleThreadPartition(&ig_begin, &ig_end, graph_size); |
2524: |
2525: HYPRE_Int ig_offd_begin, ig_offd_end; |
2526: hypre_GetSimpleThreadPartition(&ig_offd_begin, &ig_offd_end, graph_offd_size); |
2527: |
2528: for (ig = ig_begin; ig < ig_end; ig++) |
2529: { |
2530: i = graph_array[ig]; |
2531: |
2532: if (CF_marker[i]!=0) /* C or F point */ |
2533: { |
2534: /* the independent set subroutine needs measure 0 for |
2535: removed nodes */ |
2536: measure_array[i] = 0; |
2537: } |
2538: else |
2539: { |
2540: private_graph_size_cnt++; |
2541: } |
2542: } |
2543: |
2544: for (ig = ig_offd_begin; ig < ig_offd_end; ig++) |
2545: { |
2546: i = graph_array_offd[ig]; |
2547: |
2548: if (CF_marker_offd[i]!=0) /* C of F point */ |
2549: { |
2550: /* the independent set subroutine needs measure 0 for |
2551: removed nodes */ |
2552: measure_array[i + num_variables] = 0; |
2553: } |
2554: else |
2555: { |
2556: private_graph_offd_size_cnt++; |
2557: } |
2558: } |
2559: |
2560: hypre_prefix_sum_pair(&private_graph_size_cnt, &graph_size, &private_graph_offd_size_cnt, &graph_offd_size, prefix_sum_workspace); |
2561: |
2562: for (ig = ig_begin; ig < ig_end; ig++) |
2563: { |
2564: i = graph_array[ig]; |
2565: if (CF_marker[i]==0) |
2566: { |
2567: graph_array2[private_graph_size_cnt++] = i; |
2568: } |
2569: } |
2570: |
2571: for (ig = ig_offd_begin; ig < ig_offd_end; ig++) |
2572: { |
2573: i = graph_array_offd[ig]; |
2574: if (CF_marker_offd[i]==0) |
2575: { |
2576: graph_array_offd2[private_graph_offd_size_cnt++] = i; |
0x428570 PUSH %RBP |
0x428571 MOV %RSP,%RBP |
0x428574 PUSH %R15 |
0x428576 PUSH %R14 |
0x428578 PUSH %R13 |
0x42857a PUSH %R12 |
0x42857c PUSH %RBX |
0x42857d SUB $0x38,%RSP |
0x428581 MOV %R9,%RBX |
0x428584 MOV %R8,%R14 |
0x428587 MOV %RCX,%R13 |
0x42858a MOV %RDX,%R15 |
0x42858d MOV 0x28(%RBP),%R12 |
0x428591 MOV 0x20(%RBP),%RAX |
0x428595 MOV (%RAX),%RDX |
0x428598 LEA -0x40(%RBP),%RDI |
0x42859c LEA -0x48(%RBP),%RSI |
0x4285a0 CALL 4f6110 <hypre_GetSimpleThreadPartition> |
0x4285a5 MOV (%R12),%RDX |
0x4285a9 LEA -0x50(%RBP),%RDI |
0x4285ad LEA -0x58(%RBP),%RSI |
0x4285b1 CALL 4f6110 <hypre_GetSimpleThreadPartition> |
0x4285b6 MOV -0x40(%RBP),%R8 |
0x4285ba MOV -0x48(%RBP),%R10 |
0x4285be MOV %R10,%R9 |
0x4285c1 SUB %R8,%R9 |
0x4285c4 JLE 428660 |
0x4285ca MOV %R9,%RCX |
0x4285cd AND $-0x4,%RCX |
0x4285d1 JE 428a60 |
0x4285d7 LEA -0x1(%RCX),%RSI |
0x4285db MOV 0x10(%RBP),%RAX |
0x4285df LEA (%RAX,%R8,8),%RDX |
0x4285e3 VXORPD %XMM0,%XMM0,%XMM0 |
0x4285e7 XOR %EDI,%EDI |
0x4285e9 VPCMPEQD %YMM2,%YMM2,%YMM2 |
0x4285ed VPXOR %XMM1,%XMM1,%XMM1 |
0x4285f1 NOPW %CS:(%RAX,%RAX,1) |
(262) 0x428600 VMOVDQU (%RDX,%RDI,8),%YMM3 |
(262) 0x428605 KXNORW %K0,%K0,%K1 |
(262) 0x428609 VPXOR %XMM4,%XMM4,%XMM4 |
(262) 0x42860d VPGATHERQQ (%R13,%YMM3,8),%YMM4{%K1} |
(262) 0x428615 VPTESTMQ %YMM4,%YMM4,%K1 |
(262) 0x42861b VSCATTERQPD %YMM0,(%RBX,%YMM3,8){%K1} |
(262) 0x428622 VPTESTNMQ %YMM4,%YMM4,%K1 |
(262) 0x428628 VPSUBQ %YMM2,%YMM1,%YMM1{%K1} |
(262) 0x42862e ADD $0x4,%RDI |
(262) 0x428632 CMP %RSI,%RDI |
(262) 0x428635 JBE 428600 |
0x428637 VEXTRACTI128 $0x1,%YMM1,%XMM0 |
0x42863d VPADDQ %XMM0,%XMM1,%XMM0 |
0x428641 VPSHUFD $-0x12,%XMM0,%XMM1 |
0x428646 VPADDQ %XMM1,%XMM0,%XMM0 |
0x42864a VMOVQ %XMM0,%RSI |
0x42864f CMP %RCX,%R9 |
0x428652 JE 428662 |
0x428654 JMP 428a68 |
0x428659 NOPL (%RAX) |
0x428660 XOR %ESI,%ESI |
0x428662 MOV 0x30(%RBP),%R8 |
0x428666 MOV 0x18(%RBP),%R12 |
0x42866a MOV %RSI,-0x30(%RBP) |
0x42866e MOV -0x50(%RBP),%R9 |
0x428672 MOV -0x58(%RBP),%RAX |
0x428676 MOV %RAX,%R10 |
0x428679 SUB %R9,%R10 |
0x42867c JLE 428760 |
0x428682 MOV %R10,%RCX |
0x428685 AND $-0x8,%RCX |
0x428689 JE 428ac0 |
0x42868f LEA -0x1(%RCX),%RDI |
0x428693 VPBROADCASTQ %R15,%YMM0 |
0x428699 LEA (%R12,%R9,8),%RDX |
0x42869d VPXOR %XMM1,%XMM1,%XMM1 |
0x4286a1 XOR %ESI,%ESI |
0x4286a3 VPCMPEQD %YMM3,%YMM3,%YMM3 |
0x4286a7 VPXOR %XMM2,%XMM2,%XMM2 |
0x4286ab VPXOR %XMM4,%XMM4,%XMM4 |
0x4286af NOP |
(260) 0x4286b0 VMOVDQU (%RDX,%RSI,8),%YMM5 |
(260) 0x4286b5 VMOVDQU 0x20(%RDX,%RSI,8),%YMM6 |
(260) 0x4286bb KXNORW %K0,%K0,%K1 |
(260) 0x4286bf VPXOR %XMM7,%XMM7,%XMM7 |
(260) 0x4286c3 VPGATHERQQ (%R14,%YMM6,8),%YMM7{%K1} |
(260) 0x4286ca KXNORW %K0,%K0,%K1 |
(260) 0x4286ce VPXOR %XMM8,%XMM8,%XMM8 |
(260) 0x4286d3 VPGATHERQQ (%R14,%YMM5,8),%YMM8{%K1} |
(260) 0x4286da VPTESTMQ %YMM7,%YMM7,%K1 |
(260) 0x4286e0 VPTESTMQ %YMM8,%YMM8,%K2 |
(260) 0x4286e6 VPADDQ %YMM5,%YMM0,%YMM5 |
(260) 0x4286ea VSCATTERQPD %YMM1,(%RBX,%YMM5,8){%K2} |
(260) 0x4286f1 VPADDQ %YMM6,%YMM0,%YMM5 |
(260) 0x4286f5 VSCATTERQPD %YMM1,(%RBX,%YMM5,8){%K1} |
(260) 0x4286fc VPTESTNMQ %YMM8,%YMM8,%K1 |
(260) 0x428702 VPTESTNMQ %YMM7,%YMM7,%K2 |
(260) 0x428708 VPSUBQ %YMM3,%YMM4,%YMM4{%K2} |
(260) 0x42870e VPSUBQ %YMM3,%YMM2,%YMM2{%K1} |
(260) 0x428714 ADD $0x8,%RSI |
(260) 0x428718 CMP %RDI,%RSI |
(260) 0x42871b JBE 4286b0 |
0x42871d VPADDQ %YMM4,%YMM2,%YMM0 |
0x428721 VEXTRACTI128 $0x1,%YMM0,%XMM1 |
0x428727 VPADDQ %XMM1,%XMM0,%XMM0 |
0x42872b VPSHUFD $-0x12,%XMM0,%XMM1 |
0x428730 VPADDQ %XMM1,%XMM0,%XMM0 |
0x428734 VMOVQ %XMM0,%RDI |
0x428739 CMP %RCX,%R10 |
0x42873c JE 428762 |
0x42873e JMP 428ac4 |
0x428743 NOPW %CS:(%RAX,%RAX,1) |
0x428752 NOPW %CS:(%RAX,%RAX,1) |
0x428760 XOR %EDI,%EDI |
0x428762 MOV %RDI,-0x38(%RBP) |
0x428766 LEA -0x30(%RBP),%RDI |
0x42876a LEA -0x38(%RBP),%RDX |
0x42876e MOV 0x20(%RBP),%RSI |
0x428772 MOV 0x28(%RBP),%RCX |
0x428776 VZEROUPPER |
0x428779 CALL 4f6500 <hypre_prefix_sum_pair> |
0x42877e MOV -0x40(%RBP),%RAX |
0x428782 MOV -0x48(%RBP),%R10 |
0x428786 MOV %R10,%R8 |
0x428789 SUB %RAX,%R8 |
0x42878c MOV 0x10(%RBP),%R11 |
0x428790 JLE 428800 |
0x428792 MOV 0x38(%RBP),%R9 |
0x428796 CMP $0x4,%R8 |
0x42879a JAE 4288a0 |
0x4287a0 MOV %R8,%RSI |
0x4287a3 AND $-0x4,%RSI |
0x4287a7 CMP %R8,%RSI |
0x4287aa JAE 428800 |
0x4287ac ADD %RSI,%RAX |
0x4287af JMP 4287c8 |
0x4287b1 NOPW %CS:(%RAX,%RAX,1) |
(257) 0x4287c0 INC %RAX |
(257) 0x4287c3 CMP %RAX,%R10 |
(257) 0x4287c6 JE 428800 |
(257) 0x4287c8 MOV (%R11,%RAX,8),%RSI |
(257) 0x4287cc CMPQ $0,(%R13,%RSI,8) |
(257) 0x4287d2 JNE 4287c0 |
(257) 0x4287d4 MOV -0x30(%RBP),%RCX |
(257) 0x4287d8 LEA 0x1(%RCX),%RDX |
(257) 0x4287dc MOV %RDX,-0x30(%RBP) |
(257) 0x4287e0 MOV %RSI,(%R9,%RCX,8) |
(257) 0x4287e4 JMP 4287c0 |
0x4287e6 NOPW %CS:(%RAX,%RAX,1) |
0x4287f5 NOPW %CS:(%RAX,%RAX,1) |
0x428800 MOV -0x50(%RBP),%RAX |
0x428804 MOV -0x58(%RBP),%R10 |
0x428808 MOV %R10,%R8 |
0x42880b SUB %RAX,%R8 |
0x42880e JLE 428880 |
0x428810 MOV 0x40(%RBP),%R9 |
0x428814 CMP $0x4,%R8 |
0x428818 JAE 428980 |
0x42881e MOV %R8,%RSI |
0x428821 AND $-0x4,%RSI |
0x428825 CMP %R8,%RSI |
0x428828 JAE 428880 |
0x42882a ADD %RSI,%RAX |
0x42882d JMP 428848 |
0x42882f NOPW %CS:(%RAX,%RAX,1) |
0x42883e XCHG %AX,%AX |
(255) 0x428840 INC %RAX |
(255) 0x428843 CMP %RAX,%R10 |
(255) 0x428846 JE 428880 |
(255) 0x428848 MOV (%R12,%RAX,8),%RSI |
(255) 0x42884c CMPQ $0,(%R14,%RSI,8) |
(255) 0x428851 JNE 428840 |
(255) 0x428853 MOV -0x38(%RBP),%RCX |
(255) 0x428857 LEA 0x1(%RCX),%RDX |
(255) 0x42885b MOV %RDX,-0x38(%RBP) |
(255) 0x42885f MOV %RSI,(%R9,%RCX,8) |
(255) 0x428863 JMP 428840 |
0x428865 NOPW %CS:(%RAX,%RAX,1) |
0x428874 NOPW %CS:(%RAX,%RAX,1) |
0x428880 ADD $0x38,%RSP |
0x428884 POP %RBX |
0x428885 POP %R12 |
0x428887 POP %R13 |
0x428889 POP %R14 |
0x42888b POP %R15 |
0x42888d POP %RBP |
0x42888e RET |
0x42888f NOPW %CS:(%RAX,%RAX,1) |
0x42889e XCHG %AX,%AX |
0x4288a0 MOV %R8,%RDI |
0x4288a3 SHR $0x2,%RDI |
0x4288a7 LEA (%R11,%RAX,8),%RBX |
0x4288ab ADD $0x18,%RBX |
0x4288af JMP 4288cd |
0x4288b1 NOPW %CS:(%RAX,%RAX,1) |
(258) 0x4288c0 ADD $0x20,%RBX |
(258) 0x4288c4 DEC %RDI |
(258) 0x4288c7 JE 4287a0 |
(258) 0x4288cd MOV -0x18(%RBX),%RSI |
(258) 0x4288d1 CMPQ $0,(%R13,%RSI,8) |
(258) 0x4288d7 JE 428900 |
(258) 0x4288d9 MOV -0x10(%RBX),%RSI |
(258) 0x4288dd CMPQ $0,(%R13,%RSI,8) |
(258) 0x4288e3 JE 42891c |
(258) 0x4288e5 MOV -0x8(%RBX),%RSI |
(258) 0x4288e9 CMPQ $0,(%R13,%RSI,8) |
(258) 0x4288ef JE 428938 |
(258) 0x4288f1 MOV (%RBX),%RSI |
(258) 0x4288f4 CMPQ $0,(%R13,%RSI,8) |
(258) 0x4288fa JNE 4288c0 |
(258) 0x4288fc JMP 428957 |
0x4288fe XCHG %AX,%AX |
(258) 0x428900 MOV -0x30(%RBP),%RDX |
(258) 0x428904 LEA 0x1(%RDX),%RCX |
(258) 0x428908 MOV %RCX,-0x30(%RBP) |
(258) 0x42890c MOV %RSI,(%R9,%RDX,8) |
(258) 0x428910 MOV -0x10(%RBX),%RSI |
(258) 0x428914 CMPQ $0,(%R13,%RSI,8) |
(258) 0x42891a JNE 4288e5 |
(258) 0x42891c MOV -0x30(%RBP),%RCX |
(258) 0x428920 LEA 0x1(%RCX),%RDX |
(258) 0x428924 MOV %RDX,-0x30(%RBP) |
(258) 0x428928 MOV %RSI,(%R9,%RCX,8) |
(258) 0x42892c MOV -0x8(%RBX),%RSI |
(258) 0x428930 CMPQ $0,(%R13,%RSI,8) |
(258) 0x428936 JNE 4288f1 |
(258) 0x428938 MOV -0x30(%RBP),%RCX |
(258) 0x42893c LEA 0x1(%RCX),%RDX |
(258) 0x428940 MOV %RDX,-0x30(%RBP) |
(258) 0x428944 MOV %RSI,(%R9,%RCX,8) |
(258) 0x428948 MOV (%RBX),%RSI |
(258) 0x42894b CMPQ $0,(%R13,%RSI,8) |
(258) 0x428951 JNE 4288c0 |
(258) 0x428957 MOV -0x30(%RBP),%RCX |
(258) 0x42895b LEA 0x1(%RCX),%RDX |
(258) 0x42895f MOV %RDX,-0x30(%RBP) |
(258) 0x428963 MOV %RSI,(%R9,%RCX,8) |
(258) 0x428967 JMP 4288c0 |
0x42896c NOPW %CS:(%RAX,%RAX,1) |
0x42897b NOPL (%RAX,%RAX,1) |
0x428980 MOV %R8,%RDI |
0x428983 SHR $0x2,%RDI |
0x428987 LEA (%R12,%RAX,8),%RBX |
0x42898b ADD $0x18,%RBX |
0x42898f JMP 4289ad |
0x428991 NOPW %CS:(%RAX,%RAX,1) |
(256) 0x4289a0 ADD $0x20,%RBX |
(256) 0x4289a4 DEC %RDI |
(256) 0x4289a7 JE 42881e |
(256) 0x4289ad MOV -0x18(%RBX),%RSI |
(256) 0x4289b1 CMPQ $0,(%R14,%RSI,8) |
(256) 0x4289b6 JE 4289e0 |
(256) 0x4289b8 MOV -0x10(%RBX),%RSI |
(256) 0x4289bc CMPQ $0,(%R14,%RSI,8) |
(256) 0x4289c1 JE 4289fb |
(256) 0x4289c3 MOV -0x8(%RBX),%RSI |
(256) 0x4289c7 CMPQ $0,(%R14,%RSI,8) |
(256) 0x4289cc JE 428a16 |
(256) 0x4289ce MOV (%RBX),%RSI |
(256) 0x4289d1 CMPQ $0,(%R14,%RSI,8) |
(256) 0x4289d6 JNE 4289a0 |
(256) 0x4289d8 JMP 428a34 |
0x4289da NOPW (%RAX,%RAX,1) |
(256) 0x4289e0 MOV -0x38(%RBP),%RDX |
(256) 0x4289e4 LEA 0x1(%RDX),%RCX |
(256) 0x4289e8 MOV %RCX,-0x38(%RBP) |
(256) 0x4289ec MOV %RSI,(%R9,%RDX,8) |
(256) 0x4289f0 MOV -0x10(%RBX),%RSI |
(256) 0x4289f4 CMPQ $0,(%R14,%RSI,8) |
(256) 0x4289f9 JNE 4289c3 |
(256) 0x4289fb MOV -0x38(%RBP),%RCX |
(256) 0x4289ff LEA 0x1(%RCX),%RDX |
(256) 0x428a03 MOV %RDX,-0x38(%RBP) |
(256) 0x428a07 MOV %RSI,(%R9,%RCX,8) |
(256) 0x428a0b MOV -0x8(%RBX),%RSI |
(256) 0x428a0f CMPQ $0,(%R14,%RSI,8) |
(256) 0x428a14 JNE 4289ce |
(256) 0x428a16 MOV -0x38(%RBP),%RCX |
(256) 0x428a1a LEA 0x1(%RCX),%RDX |
(256) 0x428a1e MOV %RDX,-0x38(%RBP) |
(256) 0x428a22 MOV %RSI,(%R9,%RCX,8) |
(256) 0x428a26 MOV (%RBX),%RSI |
(256) 0x428a29 CMPQ $0,(%R14,%RSI,8) |
(256) 0x428a2e JNE 4289a0 |
(256) 0x428a34 MOV -0x38(%RBP),%RCX |
(256) 0x428a38 LEA 0x1(%RCX),%RDX |
(256) 0x428a3c MOV %RDX,-0x38(%RBP) |
(256) 0x428a40 MOV %RSI,(%R9,%RCX,8) |
(256) 0x428a44 JMP 4289a0 |
0x428a49 NOPW %CS:(%RAX,%RAX,1) |
0x428a58 NOPL (%RAX,%RAX,1) |
0x428a60 XOR %ECX,%ECX |
0x428a62 XOR %ESI,%ESI |
0x428a64 MOV 0x10(%RBP),%RAX |
0x428a68 ADD %R8,%RCX |
0x428a6b JMP 428a94 |
0x428a6d NOPW %CS:(%RAX,%RAX,1) |
0x428a7c NOPL (%RAX) |
(261) 0x428a80 MOVQ $0,(%RBX,%RDX,8) |
(261) 0x428a88 INC %RCX |
(261) 0x428a8b CMP %RCX,%R10 |
(261) 0x428a8e JE 428662 |
(261) 0x428a94 MOV (%RAX,%RCX,8),%RDX |
(261) 0x428a98 CMPQ $0,(%R13,%RDX,8) |
(261) 0x428a9e JNE 428a80 |
(261) 0x428aa0 INC %RSI |
(261) 0x428aa3 INC %RCX |
(261) 0x428aa6 CMP %RCX,%R10 |
(261) 0x428aa9 JNE 428a94 |
0x428aab JMP 428662 |
0x428ab0 NOPW %CS:(%RAX,%RAX,1) |
0x428abf NOP |
0x428ac0 XOR %EDI,%EDI |
0x428ac2 XOR %ECX,%ECX |
0x428ac4 ADD %R9,%RCX |
0x428ac7 JMP 428af7 |
0x428ac9 NOPW %CS:(%RAX,%RAX,1) |
0x428ad8 NOPL (%RAX,%RAX,1) |
(259) 0x428ae0 ADD %R15,%RDX |
(259) 0x428ae3 MOVQ $0,(%RBX,%RDX,8) |
(259) 0x428aeb INC %RCX |
(259) 0x428aee CMP %RCX,%RAX |
(259) 0x428af1 JE 428762 |
(259) 0x428af7 MOV (%R12,%RCX,8),%RDX |
(259) 0x428afb CMPQ $0,(%R14,%RDX,8) |
(259) 0x428b00 JNE 428ae0 |
(259) 0x428b02 INC %RDI |
(259) 0x428b05 INC %RCX |
(259) 0x428b08 CMP %RCX,%RAX |
(259) 0x428b0b JNE 428af7 |
0x428b0d JMP 428762 |
0x428b12 NOPW %CS:(%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►88.89+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGCoarsenPMIS | par_coarsen.c:2516 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:601 | exec |
○ | hypre_PCGSetup | pcg.c:234 | exec |
○ | main | amg.c:398 | exec |
○ | __libc_init_first | libc.so.6 | |
►11.11+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGCoarsenPMIS | par_coarsen.c:2516 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:626 | exec |
○ | hypre_PCGSetup | pcg.c:234 | exec |
○ | main | amg.c:398 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | par_coarsen.c:2516-2576 |
Module | exec |
nb instructions | 169 |
nb uops | 175 |
loop length | 796 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 5 |
used zmm registers | 0 |
nb stack references | 13 |
micro-operation queue | 43.75 cycles |
front end | 43.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 19.00 | 18.92 | 13.50 | 13.50 | 11.00 | 19.08 | 19.00 | 12.00 |
cycles | 19.00 | 18.92 | 13.50 | 13.50 | 11.00 | 19.08 | 19.00 | 12.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 42.38 |
Stall cycles | 0.00 |
Front-end | 43.75 |
Dispatch | 19.08 |
Overall L1 | 43.75 |
all | 28% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 28% |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
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 | 100% |
all | 29% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 30% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 21% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
all | 25% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
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 | 25% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 21% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
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 $0x38,%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,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x28(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x40(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x48(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 4f6110 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV (%R12),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x50(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x58(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 4f6110 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x40(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 428660 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,%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 428a60 | 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 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%R8,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VXORPD %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 |
VPCMPEQD %YMM2,%YMM2,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM1,%XMM1,%XMM1 | 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 |
VEXTRACTI128 $0x1,%YMM1,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM0,%XMM1,%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,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 428662 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 428a68 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 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 0x30(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x50(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R9,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 428760 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R10,%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 |
JE 428ac0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBROADCASTQ %R15,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R12,%R9,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM1,%XMM1,%XMM1 | 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 |
VPCMPEQD %YMM3,%YMM3,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPXOR %XMM4,%XMM4,%XMM4 | 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 |
VPADDQ %YMM4,%YMM2,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
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,%RDI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
CMP %RCX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 428762 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 428ac4 | 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 |
NOPW %CS:(%RAX,%RAX,1) | 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 |
MOV %RDI,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x30(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x38(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x20(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x28(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4f6500 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x10(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 428800 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x38(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 4288a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 428800 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 4287c8 | 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 |
NOPW %CS:(%RAX,%RAX,1) | 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 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 428880 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x40(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 428980 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 428880 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 428848 | 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 |
XCHG %AX,%AX | 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 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x38,%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 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R11,%RAX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 4288cd | 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 |
XCHG %AX,%AX | 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 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R12,%RAX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 4289ad | 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 |
NOPW (%RAX,%RAX,1) | 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 |
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 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 428a94 | 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 |
JMP 428662 | 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 |
NOP | 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 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R9,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 428af7 | 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,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 428762 | 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 |
Source file and lines | par_coarsen.c:2516-2576 |
Module | exec |
nb instructions | 169 |
nb uops | 175 |
loop length | 796 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 5 |
used zmm registers | 0 |
nb stack references | 13 |
micro-operation queue | 43.75 cycles |
front end | 43.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 19.00 | 18.92 | 13.50 | 13.50 | 11.00 | 19.08 | 19.00 | 12.00 |
cycles | 19.00 | 18.92 | 13.50 | 13.50 | 11.00 | 19.08 | 19.00 | 12.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 42.38 |
Stall cycles | 0.00 |
Front-end | 43.75 |
Dispatch | 19.08 |
Overall L1 | 43.75 |
all | 28% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 28% |
all | 100% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
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 | 100% |
all | 29% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 30% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 21% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
all | 25% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
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 | 25% |
all | 16% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 21% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
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 $0x38,%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,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x28(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x40(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x48(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 4f6110 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV (%R12),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x50(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x58(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 4f6110 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x40(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 428660 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,%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 428a60 | 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 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%R8,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VXORPD %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 |
VPCMPEQD %YMM2,%YMM2,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM1,%XMM1,%XMM1 | 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 |
VEXTRACTI128 $0x1,%YMM1,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VPADDQ %XMM0,%XMM1,%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,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 428662 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 428a68 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 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 0x30(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x50(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R9,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 428760 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R10,%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 |
JE 428ac0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPBROADCASTQ %R15,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R12,%R9,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM1,%XMM1,%XMM1 | 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 |
VPCMPEQD %YMM3,%YMM3,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPXOR %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPXOR %XMM4,%XMM4,%XMM4 | 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 |
VPADDQ %YMM4,%YMM2,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
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,%RDI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
CMP %RCX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 428762 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 428ac4 | 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 |
NOPW %CS:(%RAX,%RAX,1) | 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 |
MOV %RDI,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x30(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x38(%RBP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x20(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x28(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4f6500 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x10(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 428800 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x38(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 4288a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 428800 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 4287c8 | 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 |
NOPW %CS:(%RAX,%RAX,1) | 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 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 428880 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x40(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 428980 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 428880 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 428848 | 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 |
XCHG %AX,%AX | 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 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x38,%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 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R11,%RAX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 4288cd | 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 |
XCHG %AX,%AX | 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 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R12,%RAX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 4289ad | 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 |
NOPW (%RAX,%RAX,1) | 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 |
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 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 428a94 | 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 |
JMP 428662 | 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 |
NOP | 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 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R9,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 428af7 | 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,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 428762 | 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 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_BoomerAMGCoarsenPMIS.extracted– | 0.12 | 0.05 |
○Loop 258 - par_coarsen.c:2562-2567 - exec | 0.07 | 0.02 |
○Loop 262 - par_coarsen.c:2528-2536 - exec | 0.05 | 0.02 |
○Loop 261 - par_coarsen.c:2528-2540 - exec | 0 | 0 |
○Loop 256 - par_coarsen.c:2571-2576 - exec | 0 | 0 |
○Loop 259 - par_coarsen.c:2544-2556 - exec | 0 | 0 |
○Loop 260 - par_coarsen.c:2528-2552 - exec | 0 | 0 |
○Loop 257 - par_coarsen.c:2562-2567 - exec | 0 | 0 |
○Loop 255 - par_coarsen.c:2571-2576 - exec | 0 | 0 |