Loop Id: 852 | Module: exec | Source: par_multi_interp.c:1585-1660 [...] | Coverage: 0.16% |
---|
Loop Id: 852 | Module: exec | Source: par_multi_interp.c:1585-1660 [...] | Coverage: 0.16% |
---|
0x447e40 MOV -0x58(%RBP),%RDX |
0x447e44 INC %RDX |
0x447e47 CMP -0x38(%RBP),%RDX |
0x447e4b MOV -0x50(%RBP),%R8 |
0x447e4f MOV -0x48(%RBP),%R9 |
0x447e53 JGE 448340 |
0x447e59 MOV -0xd8(%RBP),%RAX |
0x447e60 MOV %RDX,-0x58(%RBP) |
0x447e64 MOV (%RAX,%RDX,8),%RAX |
0x447e68 MOV -0xe0(%RBP),%RCX |
0x447e6f MOV (%RCX,%RAX,8),%RDX |
0x447e73 MOV -0x60(%RBP),%RCX |
0x447e77 MOV (%RCX,%RAX,8),%RSI |
0x447e7b MOV 0x8(%RCX,%RAX,8),%RCX |
0x447e80 LEA (%RCX,%RDX,1),%RDI |
0x447e84 SUB %RSI,%RDI |
0x447e87 CMP %RDI,%RDX |
0x447e8a JGE 447f55 |
0x447e90 MOV -0xc0(%RBP),%RDI |
0x447e97 MOV 0x8(%RDI),%R10 |
0x447e9b SUB %RSI,%RCX |
0x447e9e CMP $0x8,%RCX |
0x447ea2 JB 447f30 |
0x447ea8 MOV %RCX,%RDI |
0x447eab SHR $0x3,%RDI |
0x447eaf LEA (%R10,%RDX,8),%RSI |
0x447eb3 ADD $0x38,%RSI |
0x447eb7 NOPW (%RAX,%RAX,1) |
(862) 0x447ec0 MOV -0x38(%RSI),%RBX |
(862) 0x447ec4 MOV (%R12,%RBX,8),%RBX |
(862) 0x447ec8 MOV %RAX,(%R13,%RBX,8) |
(862) 0x447ecd MOV -0x30(%RSI),%RBX |
(862) 0x447ed1 MOV (%R12,%RBX,8),%RBX |
(862) 0x447ed5 MOV %RAX,(%R13,%RBX,8) |
(862) 0x447eda MOV -0x28(%RSI),%RBX |
(862) 0x447ede MOV (%R12,%RBX,8),%RBX |
(862) 0x447ee2 MOV %RAX,(%R13,%RBX,8) |
(862) 0x447ee7 MOV -0x20(%RSI),%RBX |
(862) 0x447eeb MOV (%R12,%RBX,8),%RBX |
(862) 0x447eef MOV %RAX,(%R13,%RBX,8) |
(862) 0x447ef4 MOV -0x18(%RSI),%RBX |
(862) 0x447ef8 MOV (%R12,%RBX,8),%RBX |
(862) 0x447efc MOV %RAX,(%R13,%RBX,8) |
(862) 0x447f01 MOV -0x10(%RSI),%RBX |
(862) 0x447f05 MOV (%R12,%RBX,8),%RBX |
(862) 0x447f09 MOV %RAX,(%R13,%RBX,8) |
(862) 0x447f0e MOV -0x8(%RSI),%RBX |
(862) 0x447f12 MOV (%R12,%RBX,8),%RBX |
(862) 0x447f16 MOV %RAX,(%R13,%RBX,8) |
(862) 0x447f1b MOV (%RSI),%RBX |
(862) 0x447f1e MOV (%R12,%RBX,8),%RBX |
(862) 0x447f22 MOV %RAX,(%R13,%RBX,8) |
(862) 0x447f27 ADD $0x40,%RSI |
(862) 0x447f2b DEC %RDI |
(862) 0x447f2e JNE 447ec0 |
0x447f30 MOV %RCX,%RSI |
0x447f33 AND $-0x8,%RSI |
0x447f37 CMP %RCX,%RSI |
0x447f3a JAE 447f55 |
0x447f3c LEA (%R10,%RDX,8),%RDX |
(861) 0x447f40 MOV (%RDX,%RSI,8),%RDI |
(861) 0x447f44 MOV (%R12,%RDI,8),%RDI |
(861) 0x447f48 MOV %RAX,(%R13,%RDI,8) |
(861) 0x447f4d INC %RSI |
(861) 0x447f50 CMP %RSI,%RCX |
(861) 0x447f53 JNE 447f40 |
0x447f55 MOV -0x60(%RBP),%RCX |
0x447f59 MOV (%RCX,%RAX,8),%RSI |
0x447f5d MOV -0x80(%RBP),%RDX |
0x447f61 MOV (%RDX,%RAX,8),%RCX |
0x447f65 MOV 0x8(%RDX,%RAX,8),%RDX |
0x447f6a INC %RCX |
0x447f6d VXORPD %XMM4,%XMM4,%XMM4 |
0x447f71 CMP %RDX,%RCX |
0x447f74 MOV %RSI,-0x30(%RBP) |
0x447f78 VXORPD %XMM3,%XMM3,%XMM3 |
0x447f7c JGE 448020 |
0x447f82 VXORPD %XMM4,%XMM4,%XMM4 |
0x447f86 MOV -0x88(%RBP),%RDI |
0x447f8d MOV -0x70(%RBP),%R10 |
0x447f91 JMP 447fa8 |
(860) 0x447fa0 INC %RCX |
(860) 0x447fa3 CMP %RDX,%RCX |
(860) 0x447fa6 JGE 448024 |
(860) 0x447fa8 MOV (%RDI,%RCX,8),%RSI |
(860) 0x447fac CMPQ $-0x3,(%R8,%RSI,8) |
(860) 0x447fb1 JE 447fd4 |
(860) 0x447fb3 CMPQ $0x1,-0xb0(%RBP) |
(860) 0x447fbb JE 447fce |
(860) 0x447fbd MOV (%R11,%RAX,8),%RDI |
(860) 0x447fc1 CMP (%R11,%RSI,8),%RDI |
(860) 0x447fc5 MOV -0x88(%RBP),%RDI |
(860) 0x447fcc JNE 447fd4 |
(860) 0x447fce VADDSD (%R10,%RCX,8),%XMM3,%XMM3 |
(860) 0x447fd4 CMP $-0x1,%RSI |
(860) 0x447fd8 JE 447fa0 |
(860) 0x447fda CMP %RAX,(%R13,%RSI,8) |
(860) 0x447fdf JNE 447fa0 |
(860) 0x447fe1 VMOVSD (%R10,%RCX,8),%XMM5 |
(860) 0x447fe7 MOV -0x78(%RBP),%RDX |
(860) 0x447feb MOV -0x30(%RBP),%RBX |
(860) 0x447fef VMOVSD %XMM5,(%RDX,%RBX,8) |
(860) 0x447ff4 MOV (%R9,%RSI,8),%RDX |
(860) 0x447ff8 MOV -0xf8(%RBP),%RSI |
(860) 0x447fff MOV %RDX,(%RSI,%RBX,8) |
(860) 0x448003 INC %RBX |
(860) 0x448006 MOV %RBX,-0x30(%RBP) |
(860) 0x44800a VADDSD (%R10,%RCX,8),%XMM4,%XMM4 |
(860) 0x448010 MOV -0x80(%RBP),%RDX |
(860) 0x448014 MOV 0x8(%RDX,%RAX,8),%RDX |
(860) 0x448019 JMP 447fa0 |
0x448020 MOV -0x70(%RBP),%R10 |
0x448024 MOV -0xe8(%RBP),%RCX |
0x44802b MOV (%RCX,%RAX,8),%RDX |
0x44802f MOV -0x68(%RBP),%RCX |
0x448033 MOV (%RCX,%RAX,8),%RSI |
0x448037 MOV 0x8(%RCX,%RAX,8),%RCX |
0x44803c LEA (%RCX,%RDX,1),%RDI |
0x448040 SUB %RSI,%RDI |
0x448043 CMP %RDI,%RDX |
0x448046 JGE 448104 |
0x44804c MOV -0xc8(%RBP),%RDI |
0x448053 MOV 0x8(%RDI),%R11 |
0x448057 SUB %RSI,%RCX |
0x44805a CMP $0x8,%RCX |
0x44805e JB 4480d8 |
0x448060 MOV %RCX,%RDI |
0x448063 SHR $0x3,%RDI |
0x448067 LEA (%R11,%RDX,8),%RSI |
0x44806b ADD $0x38,%RSI |
0x44806f NOP |
(859) 0x448070 MOV -0x38(%RSI),%RBX |
(859) 0x448074 MOV (%R15,%RBX,8),%RBX |
(859) 0x448078 MOV %RAX,(%R14,%RBX,8) |
(859) 0x44807c MOV -0x30(%RSI),%RBX |
(859) 0x448080 MOV (%R15,%RBX,8),%RBX |
(859) 0x448084 MOV %RAX,(%R14,%RBX,8) |
(859) 0x448088 MOV -0x28(%RSI),%RBX |
(859) 0x44808c MOV (%R15,%RBX,8),%RBX |
(859) 0x448090 MOV %RAX,(%R14,%RBX,8) |
(859) 0x448094 MOV -0x20(%RSI),%RBX |
(859) 0x448098 MOV (%R15,%RBX,8),%RBX |
(859) 0x44809c MOV %RAX,(%R14,%RBX,8) |
(859) 0x4480a0 MOV -0x18(%RSI),%RBX |
(859) 0x4480a4 MOV (%R15,%RBX,8),%RBX |
(859) 0x4480a8 MOV %RAX,(%R14,%RBX,8) |
(859) 0x4480ac MOV -0x10(%RSI),%RBX |
(859) 0x4480b0 MOV (%R15,%RBX,8),%RBX |
(859) 0x4480b4 MOV %RAX,(%R14,%RBX,8) |
(859) 0x4480b8 MOV -0x8(%RSI),%RBX |
(859) 0x4480bc MOV (%R15,%RBX,8),%RBX |
(859) 0x4480c0 MOV %RAX,(%R14,%RBX,8) |
(859) 0x4480c4 MOV (%RSI),%RBX |
(859) 0x4480c7 MOV (%R15,%RBX,8),%RBX |
(859) 0x4480cb MOV %RAX,(%R14,%RBX,8) |
(859) 0x4480cf ADD $0x40,%RSI |
(859) 0x4480d3 DEC %RDI |
(859) 0x4480d6 JNE 448070 |
0x4480d8 MOV %RCX,%RSI |
0x4480db AND $-0x8,%RSI |
0x4480df CMP %RCX,%RSI |
0x4480e2 JAE 448104 |
0x4480e4 LEA (%R11,%RDX,8),%RDX |
0x4480e8 NOPL (%RAX,%RAX,1) |
(858) 0x4480f0 MOV (%RDX,%RSI,8),%RDI |
(858) 0x4480f4 MOV (%R15,%RDI,8),%RDI |
(858) 0x4480f8 MOV %RAX,(%R14,%RDI,8) |
(858) 0x4480fc INC %RSI |
(858) 0x4480ff CMP %RSI,%RCX |
(858) 0x448102 JNE 4480f0 |
0x448104 MOV -0x68(%RBP),%RCX |
0x448108 MOV (%RCX,%RAX,8),%R9 |
0x44810c MOV -0x98(%RBP),%RCX |
0x448113 MOV (%RCX,%RAX,8),%RSI |
0x448117 MOV 0x8(%RCX,%RAX,8),%RCX |
0x44811c CMP %RCX,%RSI |
0x44811f JGE 448200 |
0x448125 MOV -0xb8(%RBP),%RDX |
0x44812c LEA (%RDX,%RSI,8),%RDI |
0x448130 MOV -0xd0(%RBP),%R8 |
0x448137 MOV -0x90(%RBP),%R11 |
0x44813e JMP 448150 |
(857) 0x448140 INC %RSI |
(857) 0x448143 ADD $0x8,%RDI |
(857) 0x448147 CMP %RCX,%RSI |
(857) 0x44814a JGE 448200 |
(857) 0x448150 MOV %RDI,%RDX |
(857) 0x448153 TEST %R8,%R8 |
(857) 0x448156 JE 448166 |
(857) 0x448158 MOV (%RDI),%RDX |
(857) 0x44815b MOV -0x110(%RBP),%RBX |
(857) 0x448162 LEA (%RBX,%RDX,8),%RDX |
(857) 0x448166 MOV (%RDX),%RBX |
(857) 0x448169 CMPQ $-0x3,(%R11,%RBX,8) |
(857) 0x44816e JE 4481a2 |
(857) 0x448170 CMPQ $0x1,-0xb0(%RBP) |
(857) 0x448178 JE 448196 |
(857) 0x44817a MOV -0x40(%RBP),%RDX |
(857) 0x44817e MOV (%RDX,%RAX,8),%RDX |
(857) 0x448182 MOV -0xf0(%RBP),%R11 |
(857) 0x448189 CMP (%R11,%RBX,8),%RDX |
(857) 0x44818d MOV -0x90(%RBP),%R11 |
(857) 0x448194 JNE 4481a2 |
(857) 0x448196 MOV -0xa8(%RBP),%RDX |
(857) 0x44819d VADDSD (%RDX,%RSI,8),%XMM3,%XMM3 |
(857) 0x4481a2 CMP $-0x1,%RBX |
(857) 0x4481a6 JE 448140 |
(857) 0x4481a8 CMP %RAX,(%R14,%RBX,8) |
(857) 0x4481ac JNE 448140 |
(857) 0x4481ae MOV -0xa8(%RBP),%R10 |
(857) 0x4481b5 VMOVSD (%R10,%RSI,8),%XMM5 |
(857) 0x4481bb MOV -0xa0(%RBP),%RCX |
(857) 0x4481c2 VMOVSD %XMM5,(%RCX,%R9,8) |
(857) 0x4481c8 MOV -0x108(%RBP),%RCX |
(857) 0x4481cf MOV (%RCX,%RBX,8),%RCX |
(857) 0x4481d3 MOV -0x100(%RBP),%RDX |
(857) 0x4481da MOV %RCX,(%RDX,%R9,8) |
(857) 0x4481de INC %R9 |
(857) 0x4481e1 VADDSD (%R10,%RSI,8),%XMM4,%XMM4 |
(857) 0x4481e7 MOV -0x70(%RBP),%R10 |
(857) 0x4481eb MOV -0x98(%RBP),%RCX |
(857) 0x4481f2 MOV 0x8(%RCX,%RAX,8),%RCX |
(857) 0x4481f7 JMP 448140 |
0x448200 MOV -0x80(%RBP),%RCX |
0x448204 MOV (%RCX,%RAX,8),%RCX |
0x448208 VMULSD (%R10,%RCX,8),%XMM4,%XMM4 |
0x44820e VUCOMISD %XMM1,%XMM4 |
0x448212 JE 44821c |
0x448214 VXORPD %XMM0,%XMM3,%XMM2 |
0x448218 VDIVSD %XMM4,%XMM2,%XMM2 |
0x44821c MOV -0x60(%RBP),%RCX |
0x448220 MOV (%RCX,%RAX,8),%R11 |
0x448224 MOV -0x30(%RBP),%RSI |
0x448228 MOV %RSI,%R10 |
0x44822b SUB %R11,%R10 |
0x44822e MOV -0xa0(%RBP),%RDI |
0x448235 MOV -0x78(%RBP),%RDX |
0x448239 JLE 4482a2 |
0x44823b MOV %R10,%RCX |
0x44823e AND $-0x4,%RCX |
0x448242 JE 448280 |
0x448244 LEA -0x1(%RCX),%RBX |
0x448248 VBROADCASTSD %XMM2,%YMM3 |
0x44824d LEA (%RDX,%R11,8),%RDX |
0x448251 XOR %R8D,%R8D |
0x448254 NOPW %CS:(%RAX,%RAX,1) |
(856) 0x448260 VMULPD (%RDX,%R8,8),%YMM3,%YMM4 |
(856) 0x448266 VMOVUPD %YMM4,(%RDX,%R8,8) |
(856) 0x44826c ADD $0x4,%R8 |
(856) 0x448270 CMP %RBX,%R8 |
(856) 0x448273 JBE 448260 |
0x448275 CMP %RCX,%R10 |
0x448278 MOV -0x78(%RBP),%RDX |
0x44827c JNE 448282 |
0x44827e JMP 4482a2 |
0x448280 XOR %ECX,%ECX |
0x448282 ADD %R11,%RCX |
0x448285 NOPW %CS:(%RAX,%RAX,1) |
(855) 0x448290 VMULSD (%RDX,%RCX,8),%XMM2,%XMM3 |
(855) 0x448295 VMOVSD %XMM3,(%RDX,%RCX,8) |
(855) 0x44829a INC %RCX |
(855) 0x44829d CMP %RCX,%RSI |
(855) 0x4482a0 JNE 448290 |
0x4482a2 MOV -0x68(%RBP),%RCX |
0x4482a6 MOV (%RCX,%RAX,8),%R8 |
0x4482aa MOV %R9,%RDX |
0x4482ad SUB %R8,%RDX |
0x4482b0 MOV -0x40(%RBP),%R11 |
0x4482b4 JLE 447e40 |
0x4482ba MOV %RDX,%RAX |
0x4482bd AND $-0x4,%RAX |
0x4482c1 JE 448300 |
0x4482c3 LEA -0x1(%RAX),%RSI |
0x4482c7 VBROADCASTSD %XMM2,%YMM3 |
0x4482cc LEA (%RDI,%R8,8),%RBX |
0x4482d0 XOR %ECX,%ECX |
0x4482d2 NOPW %CS:(%RAX,%RAX,1) |
(854) 0x4482e0 VMULPD (%RBX,%RCX,8),%YMM3,%YMM4 |
(854) 0x4482e5 VMOVUPD %YMM4,(%RBX,%RCX,8) |
(854) 0x4482ea ADD $0x4,%RCX |
(854) 0x4482ee CMP %RSI,%RCX |
(854) 0x4482f1 JBE 4482e0 |
0x4482f3 CMP %RAX,%RDX |
0x4482f6 JE 447e40 |
0x4482fc JMP 448302 |
0x448300 XOR %EAX,%EAX |
0x448302 ADD %R8,%RAX |
0x448305 NOPW %CS:(%RAX,%RAX,1) |
(853) 0x448310 VMULSD (%RDI,%RAX,8),%XMM2,%XMM3 |
(853) 0x448315 VMOVSD %XMM3,(%RDI,%RAX,8) |
(853) 0x44831a INC %RAX |
(853) 0x44831d CMP %RAX,%R9 |
(853) 0x448320 JNE 448310 |
0x448322 JMP 447e40 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 1585 - 1660 |
-------------------------------------------------------------------------------- |
1585: if (n_fine) |
[...] |
1598: thread_start = pass_pointer[1] + (pass_length/num_threads)*my_thread_num; |
[...] |
1605: for (i=thread_start; i < thread_stop; i++) |
1606: { |
1607: i1 = pass_array[i]; |
1608: sum_C = 0; |
1609: sum_N = 0; |
1610: j_start = P_diag_start[i1]; |
1611: j_end = j_start+P_diag_i[i1+1]-P_diag_i[i1]; |
1612: for (j=j_start; j < j_end; j++) |
1613: { |
1614: k1 = P_diag_pass[1][j]; |
1615: tmp_marker[C_array[k1]] = i1; |
1616: } |
1617: cnt = P_diag_i[i1]; |
1618: for (j=A_diag_i[i1]+1; j < A_diag_i[i1+1]; j++) |
1619: { |
1620: j1 = A_diag_j[j]; |
1621: if (CF_marker[j1] != -3 && |
1622: (num_functions == 1 || dof_func[i1] == dof_func[j1])) |
1623: sum_N += A_diag_data[j]; |
1624: if (j1 != -1 && tmp_marker[j1] == i1) |
1625: { |
1626: P_diag_data[cnt] = A_diag_data[j]; |
1627: P_diag_j[cnt++] = fine_to_coarse[j1]; |
1628: sum_C += A_diag_data[j]; |
1629: } |
1630: } |
1631: j_start = P_offd_start[i1]; |
1632: j_end = j_start+P_offd_i[i1+1]-P_offd_i[i1]; |
1633: for (j=j_start; j < j_end; j++) |
1634: { |
1635: k1 = P_offd_pass[1][j]; |
1636: tmp_marker_offd[C_array_offd[k1]] = i1; |
1637: } |
1638: cnt_offd = P_offd_i[i1]; |
1639: for (j=A_offd_i[i1]; j < A_offd_i[i1+1]; j++) |
1640: { |
1641: if (col_offd_S_to_A) |
1642: j1 = map_A_to_S[A_offd_j[j]]; |
1643: else |
1644: j1 = A_offd_j[j]; |
1645: if (CF_marker_offd[j1] != -3 && |
1646: (num_functions == 1 || dof_func[i1] == dof_func_offd[j1])) |
1647: sum_N += A_offd_data[j]; |
1648: if (j1 != -1 && tmp_marker_offd[j1] == i1) |
1649: { |
1650: P_offd_data[cnt_offd] = A_offd_data[j]; |
1651: P_offd_j[cnt_offd++] = map_S_to_new[j1]; |
1652: sum_C += A_offd_data[j]; |
1653: } |
1654: } |
1655: diagonal = A_diag_data[A_diag_i[i1]]; |
1656: if (sum_C*diagonal) alfa = -sum_N/(sum_C*diagonal); |
1657: for (j=P_diag_i[i1]; j < cnt; j++) |
1658: P_diag_data[j] *= alfa; |
1659: for (j=P_offd_i[i1]; j < cnt_offd; j++) |
1660: P_offd_data[j] *= alfa; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGBuildMultipass | par_multi_interp.c:1575 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:737 | exec |
○ | hypre_PCGSetup | pcg.c:234 | exec |
○ | main | amg.c:398 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.83 |
CQA speedup if FP arith vectorized | 4.11 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.44 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass.extracted.27 |
Source | par_multi_interp.c:1585-1660 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 34.50 |
CQA cycles if no scalar integer | 9.00 |
CQA cycles if FP arith vectorized | 8.39 |
CQA cycles if fully vectorized | 4.31 |
Front-end cycles | 34.50 |
DIV/SQRT cycles | 16.75 |
P0 cycles | 16.67 |
P1 cycles | 24.00 |
P2 cycles | 24.00 |
P3 cycles | 2.00 |
P4 cycles | 16.83 |
P5 cycles | 16.75 |
P6 cycles | 2.00 |
P7 cycles | 4.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 34.87 - 34.88 |
Stall cycles (UFS) | 0.00 |
Nb insns | 137.00 |
Nb uops | 137.00 |
Nb loads | 48.00 |
Nb stores | 2.00 |
Nb stack references | 22.00 |
FLOP/cycle | 0.06 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 1.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 11.59 |
Bytes prefetched | 0.00 |
Bytes loaded | 384.00 |
Bytes stored | 16.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 16.67 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 22.22 |
Vector-efficiency ratio all | 14.58 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | 15.28 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.83 |
CQA speedup if FP arith vectorized | 4.11 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.44 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass.extracted.27 |
Source | par_multi_interp.c:1585-1660 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 34.50 |
CQA cycles if no scalar integer | 9.00 |
CQA cycles if FP arith vectorized | 8.39 |
CQA cycles if fully vectorized | 4.31 |
Front-end cycles | 34.50 |
DIV/SQRT cycles | 16.75 |
P0 cycles | 16.67 |
P1 cycles | 24.00 |
P2 cycles | 24.00 |
P3 cycles | 2.00 |
P4 cycles | 16.83 |
P5 cycles | 16.75 |
P6 cycles | 2.00 |
P7 cycles | 4.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 34.87 - 34.88 |
Stall cycles (UFS) | 0.00 |
Nb insns | 137.00 |
Nb uops | 137.00 |
Nb loads | 48.00 |
Nb stores | 2.00 |
Nb stack references | 22.00 |
FLOP/cycle | 0.06 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 1.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 11.59 |
Bytes prefetched | 0.00 |
Bytes loaded | 384.00 |
Bytes stored | 16.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 16.67 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 22.22 |
Vector-efficiency ratio all | 14.58 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | 15.28 |
Path / |
Function | hypre_BoomerAMGBuildMultipass.extracted.27 |
Source file and lines | par_multi_interp.c:1585-1660 |
Module | exec |
nb instructions | 137 |
nb uops | 137 |
loop length | 587 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 22 |
micro-operation queue | 34.50 cycles |
front end | 34.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.75 | 16.67 | 24.00 | 24.00 | 2.00 | 16.83 | 16.75 | 2.00 |
cycles | 16.75 | 16.67 | 24.00 | 24.00 | 2.00 | 16.83 | 16.75 | 2.00 |
Cycles executing div or sqrt instructions | 4.00 |
FE+BE cycles | 34.87-34.88 |
Stall cycles | 0.00 |
Front-end | 34.50 |
Dispatch | 24.00 |
DIV/SQRT | 4.00 |
Overall L1 | 34.50 |
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) |
other | 0% |
all | 44% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 57% |
all | 16% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 22% |
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) |
other | 12% |
all | 18% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 19% |
all | 14% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x38(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 448340 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RAX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xe0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 447f55 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xc0(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 447f30 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R10,%RDX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 447f55 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R10,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDX,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM3,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JGE 448020 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x88(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 447fa8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x70(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xe8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448104 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xc8(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4480d8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R11,%RDX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RSI | 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 %RCX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 448104 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R11,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x98(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448200 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xb8(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RSI,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0xd0(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x90(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 448150 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x80(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%R10,%RCX,8),%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM1,%XMM4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 44821c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM0,%XMM3,%XMM2 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VDIVSD %XMM4,%XMM2,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R11,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xa0(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 4482a2 | 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 $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 448280 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM2,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%RDX,%R11,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %R8D,%R8D | 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 |
CMP %RCX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 448282 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4482a2 | 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 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 447e40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 448300 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RAX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM2,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%RDI,%R8,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ECX,%ECX | 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 |
CMP %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447e40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 448302 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 447e40 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGBuildMultipass.extracted.27 |
Source file and lines | par_multi_interp.c:1585-1660 |
Module | exec |
nb instructions | 137 |
nb uops | 137 |
loop length | 587 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 22 |
micro-operation queue | 34.50 cycles |
front end | 34.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.75 | 16.67 | 24.00 | 24.00 | 2.00 | 16.83 | 16.75 | 2.00 |
cycles | 16.75 | 16.67 | 24.00 | 24.00 | 2.00 | 16.83 | 16.75 | 2.00 |
Cycles executing div or sqrt instructions | 4.00 |
FE+BE cycles | 34.87-34.88 |
Stall cycles | 0.00 |
Front-end | 34.50 |
Dispatch | 24.00 |
DIV/SQRT | 4.00 |
Overall L1 | 34.50 |
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) |
other | 0% |
all | 44% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 57% |
all | 16% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 22% |
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) |
other | 12% |
all | 18% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 19% |
all | 14% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x38(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 448340 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RAX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xe0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 447f55 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xc0(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 447f30 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R10,%RDX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 447f55 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R10,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDX,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM3,%XMM3,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JGE 448020 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x88(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 447fa8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x70(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xe8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448104 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xc8(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4480d8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R11,%RDX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RSI | 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 %RCX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 448104 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R11,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x98(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448200 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xb8(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RSI,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0xd0(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x90(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 448150 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x80(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%R10,%RCX,8),%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM1,%XMM4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 44821c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM0,%XMM3,%XMM2 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VDIVSD %XMM4,%XMM2,%XMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R11,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xa0(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 4482a2 | 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 $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 448280 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM2,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%RDX,%R11,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %R8D,%R8D | 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 |
CMP %RCX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 448282 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4482a2 | 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 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 447e40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 448300 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RAX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM2,%YMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%RDI,%R8,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ECX,%ECX | 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 |
CMP %RAX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 447e40 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 448302 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 447e40 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |