Function: void RAJA::internal::StatementExecutor<RAJA::statement::Collapse<RAJA::omp_parallel_collap ... | Module: libkripke.so | Source: Collapse.hpp:81-81 [...] | Coverage: 12.44% |
---|
Function: void RAJA::internal::StatementExecutor<RAJA::statement::Collapse<RAJA::omp_parallel_collap ... | Module: libkripke.so | Source: Collapse.hpp:81-81 [...] | Coverage: 12.44% |
---|
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp: 120 - 120 |
-------------------------------------------------------------------------------- |
120: RAJA_HOST_DEVICE RAJA_INLINE ~TypedRangeSegment() {} |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp: 55 - 55 |
-------------------------------------------------------------------------------- |
55: return a * b; |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59 |
-------------------------------------------------------------------------------- |
59: for (decltype(distance_it) i = 0; i < distance_it; ++i) { |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 55 - 177 |
-------------------------------------------------------------------------------- |
55: : val(rhs.val) |
[...] |
142: return val - rhs.val; |
[...] |
177: return value_type(val + rhs); |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/src/Kripke/Kernel/LPlusTimes.cpp: 57 - 57 |
-------------------------------------------------------------------------------- |
57: rhs(d,g,z) += ell_plus(d, nm) * phi_out(nm, g, z); |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 81 - 81 |
-------------------------------------------------------------------------------- |
81: #pragma omp parallel for private(i0, i1) firstprivate(privatizer) \ |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/View.hpp: 79 - 110 |
-------------------------------------------------------------------------------- |
79: : layout(V.layout), data(V.data) |
[...] |
110: return data[idx]; |
0x4acd0 PUSH %RBP |
0x4acd1 MOV %RSP,%RBP |
0x4acd4 PUSH %R15 |
0x4acd6 PUSH %R14 |
0x4acd8 PUSH %R13 |
0x4acda PUSH %R12 |
0x4acdc PUSH %RBX |
0x4acdd AND $-0x20,%RSP |
0x4ace1 SUB $0xe0,%RSP |
0x4ace8 MOV 0x10(%RDI),%RAX |
0x4acec MOV (%RAX),%RBX |
0x4acef MOV 0x110(%RAX),%R13 |
0x4acf6 MOV 0x10(%RAX),%RDX |
0x4acfa MOV 0x18(%RAX),%RCX |
0x4acfe MOV 0x20(%RAX),%RSI |
0x4ad02 MOV 0x38(%RAX),%R8 |
0x4ad06 MOV %RBX,0x8(%RSP) |
0x4ad0b MOV 0x60(%RAX),%R9 |
0x4ad0f MOV 0x68(%RAX),%R10 |
0x4ad13 MOV %R13,0xd0(%RSP) |
0x4ad1b MOV 0xc0(%RAX),%R11 |
0x4ad22 MOV 0xf0(%RAX),%R12 |
0x4ad29 MOV %RDX,0x70(%RSP) |
0x4ad2e MOV 0x118(%RAX),%R14 |
0x4ad35 MOV 0x30(%RAX),%RBX |
0x4ad39 MOV %RCX,0x68(%RSP) |
0x4ad3e MOV 0xa8(%RAX),%R15 |
0x4ad45 MOV %RSI,0x40(%RSP) |
0x4ad4a MOV %R8,0x60(%RSP) |
0x4ad4f MOV %R9,0x30(%RSP) |
0x4ad54 MOV %R10,0x48(%RSP) |
0x4ad59 MOV %R11,0x58(%RSP) |
0x4ad5e MOV %R12,0x38(%RSP) |
0x4ad63 MOV %R14,0x50(%RSP) |
0x4ad68 MOV 0x158(%RAX),%R14 |
0x4ad6f MOV (%RDI),%R13 |
0x4ad72 MOV 0x8(%RDI),%RAX |
0x4ad76 TEST %R13,%R13 |
0x4ad79 JLE 4b217 |
0x4ad7f MOV %RAX,0x78(%RSP) |
0x4ad84 TEST %RAX,%RAX |
0x4ad87 JLE 4b217 |
0x4ad8d CALL 9760 <omp_get_num_threads@plt> |
0x4ad92 MOVSXD %EAX,%R12 |
0x4ad95 CALL 9650 <omp_get_thread_num@plt> |
0x4ad9a XOR %EDX,%EDX |
0x4ad9c MOVSXD %EAX,%RDI |
0x4ad9f MOV 0x78(%RSP),%RAX |
0x4ada4 IMUL %R13,%RAX |
0x4ada8 DIV %R12 |
0x4adab MOV %RAX,%RCX |
0x4adae CMP %RDX,%RDI |
0x4adb1 JB 4b43d |
0x4adb7 IMUL %RCX,%RDI |
0x4adbb LEA (%RDI,%RDX,1),%RAX |
0x4adbf LEA (%RCX,%RAX,1),%RSI |
0x4adc3 CMP %RSI,%RAX |
0x4adc6 JAE 4b217 |
0x4adcc XOR %EDX,%EDX |
0x4adce MOV 0x60(%RSP),%R12 |
0x4add3 MOV 0x70(%RSP),%R9 |
0x4add8 DIVQ 0x78(%RSP) |
0x4addd SUB %RBX,%R12 |
0x4ade0 MOV %RAX,0x10(%RSP) |
0x4ade5 MOV %RDX,%R8 |
0x4ade8 CMP %R9,0x68(%RSP) |
0x4aded JLE 4b217 |
0x4adf3 TEST %R12,%R12 |
0x4adf6 JLE 4b217 |
0x4adfc MOV 0xd0(%RSP),%R11 |
0x4ae04 LEA -0x1(%RCX),%R10 |
0x4ae08 MOV 0x10(%RSP),%RSI |
0x4ae0d MOV %R12,%RCX |
0x4ae10 MOV 0x8(%RSP),%RDX |
0x4ae15 MOV %R10,0x20(%RSP) |
0x4ae1a SHR $0x2,%RCX |
0x4ae1e MOV %R12,%RAX |
0x4ae21 MOV %R11,%R13 |
0x4ae24 MOV %R12,%R10 |
0x4ae27 LEA -0x1(%R12),%RDI |
0x4ae2c SAL $0x5,%RCX |
0x4ae30 IMUL %R9,%R13 |
0x4ae34 MOV %R12,%R9 |
0x4ae37 AND $-0x4,%RAX |
0x4ae3b ADD %RDX,%RSI |
0x4ae3e AND $0x3,%R9D |
0x4ae42 AND $0x3,%R10D |
0x4ae46 MOV %RDI,0xa8(%RSP) |
0x4ae4e SAL $0x3,%R11 |
0x4ae52 MOV %RCX,0xc8(%RSP) |
0x4ae5a MOV %R13,0x18(%RSP) |
0x4ae5f MOV %RAX,0x98(%RSP) |
0x4ae67 MOV %RSI,0x28(%RSP) |
0x4ae6c MOV %R9,0xa0(%RSP) |
0x4ae74 MOV %R10,0x90(%RSP) |
0x4ae7c MOV %R11,0xc0(%RSP) |
0x4ae84 XOR %R11D,%R11D |
0x4ae87 NOPW (%RAX,%RAX,1) |
(429) 0x4ae90 MOV 0x40(%RSP),%R13 |
(429) 0x4ae95 MOV 0x28(%RSP),%RCX |
(429) 0x4ae9a MOV %R8,0x88(%RSP) |
(429) 0x4aea2 MOV 0x48(%RSP),%R10 |
(429) 0x4aea7 MOV 0x30(%RSP),%RSI |
(429) 0x4aeac MOV %R11,0x80(%RSP) |
(429) 0x4aeb4 LEA (%R8,%R13,1),%RDI |
(429) 0x4aeb8 MOV 0x58(%RSP),%RAX |
(429) 0x4aebd MOV 0x70(%RSP),%RDX |
(429) 0x4aec2 IMUL %RCX,%RSI |
(429) 0x4aec6 MOV 0x38(%RSP),%R9 |
(429) 0x4aecb IMUL %RDI,%R10 |
(429) 0x4aecf IMUL %RCX,%RAX |
(429) 0x4aed3 ADD %RSI,%R10 |
(429) 0x4aed6 MOV 0x50(%RSP),%RSI |
(429) 0x4aedb LEA (%RAX,%RDX,1),%R13 |
(429) 0x4aedf MOV 0x18(%RSP),%RDX |
(429) 0x4aee4 IMUL %RSI,%RDI |
(429) 0x4aee8 LEA (%R9,%R13,8),%RCX |
(429) 0x4aeec ADD %RDX,%RDI |
(429) 0x4aeef MOV 0x68(%RSP),%RDX |
(429) 0x4aef4 LEA (%RBX,%RDI,1),%R13 |
(429) 0x4aef8 ADD %RDX,%RAX |
(429) 0x4aefb LEA (%R14,%R13,8),%RSI |
(429) 0x4aeff MOV 0x60(%RSP),%R13 |
(429) 0x4af04 LEA (%R9,%RAX,8),%RAX |
(429) 0x4af08 LEA (%R10,%RBX,1),%R9 |
(429) 0x4af0c MOV %R9,0xb8(%RSP) |
(429) 0x4af14 ADD %R10,%R13 |
(429) 0x4af17 MOV %RAX,0xd8(%RSP) |
(429) 0x4af1f LEA (%R15,%R13,8),%R13 |
(429) 0x4af23 LEA (%R15,%R9,8),%RAX |
(429) 0x4af27 NOPW (%RAX,%RAX,1) |
(428) 0x4af30 CMP $0x1,%R12 |
(428) 0x4af34 JE 4b3e0 |
(428) 0x4af3a LEA 0x8(%RCX),%R9 |
(428) 0x4af3e CMP %R9,%RAX |
(428) 0x4af41 SETAE %R8B |
(428) 0x4af45 CMP %R13,%RCX |
(428) 0x4af48 SETAE %R11B |
(428) 0x4af4c OR %R8B,%R11B |
(428) 0x4af4f JE 4b230 |
(428) 0x4af55 LEA 0x8(%RSI),%R8 |
(428) 0x4af59 MOV %RAX,%RDX |
(428) 0x4af5c SUB %R8,%RDX |
(428) 0x4af5f CMP $0x10,%RDX |
(428) 0x4af63 JBE 4b230 |
(428) 0x4af69 CMPQ $0x2,0xa8(%RSP) |
(428) 0x4af72 JBE 4b3fa |
(428) 0x4af78 MOV 0xc8(%RSP),%R11 |
(428) 0x4af80 VBROADCASTSD (%RCX),%YMM2 |
(428) 0x4af85 XOR %EDX,%EDX |
(428) 0x4af87 LEA -0x20(%R11),%R8 |
(428) 0x4af8b SHR $0x5,%R8 |
(428) 0x4af8f INC %R8 |
(428) 0x4af92 AND $0x7,%R8D |
(428) 0x4af96 JE 4b05c |
(428) 0x4af9c CMP $0x1,%R8 |
(428) 0x4afa0 JE 4b03a |
(428) 0x4afa6 CMP $0x2,%R8 |
(428) 0x4afaa JE 4b026 |
(428) 0x4afac CMP $0x3,%R8 |
(428) 0x4afb0 JE 4b012 |
(428) 0x4afb2 CMP $0x4,%R8 |
(428) 0x4afb6 JE 4affe |
(428) 0x4afb8 CMP $0x5,%R8 |
(428) 0x4afbc JE 4afea |
(428) 0x4afbe CMP $0x6,%R8 |
(428) 0x4afc2 JE 4afd6 |
(428) 0x4afc4 VMOVUPD (%RSI),%YMM1 |
(428) 0x4afc8 VFMADD213PD (%RAX),%YMM2,%YMM1 |
(428) 0x4afcd MOV $0x20,%EDX |
(428) 0x4afd2 VMOVUPD %YMM1,(%RAX) |
(428) 0x4afd6 VMOVUPD (%RSI,%RDX,1),%YMM3 |
(428) 0x4afdb VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM3 |
(428) 0x4afe1 VMOVUPD %YMM3,(%RAX,%RDX,1) |
(428) 0x4afe6 ADD $0x20,%RDX |
(428) 0x4afea VMOVUPD (%RSI,%RDX,1),%YMM5 |
(428) 0x4afef VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM5 |
(428) 0x4aff5 VMOVUPD %YMM5,(%RAX,%RDX,1) |
(428) 0x4affa ADD $0x20,%RDX |
(428) 0x4affe VMOVUPD (%RSI,%RDX,1),%YMM6 |
(428) 0x4b003 VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM6 |
(428) 0x4b009 VMOVUPD %YMM6,(%RAX,%RDX,1) |
(428) 0x4b00e ADD $0x20,%RDX |
(428) 0x4b012 VMOVUPD (%RSI,%RDX,1),%YMM7 |
(428) 0x4b017 VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM7 |
(428) 0x4b01d VMOVUPD %YMM7,(%RAX,%RDX,1) |
(428) 0x4b022 ADD $0x20,%RDX |
(428) 0x4b026 VMOVUPD (%RSI,%RDX,1),%YMM8 |
(428) 0x4b02b VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM8 |
(428) 0x4b031 VMOVUPD %YMM8,(%RAX,%RDX,1) |
(428) 0x4b036 ADD $0x20,%RDX |
(428) 0x4b03a VMOVUPD (%RSI,%RDX,1),%YMM9 |
(428) 0x4b03f VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM9 |
(428) 0x4b045 VMOVUPD %YMM9,(%RAX,%RDX,1) |
(428) 0x4b04a ADD $0x20,%RDX |
(428) 0x4b04e CMP %RDX,0xc8(%RSP) |
(428) 0x4b056 JE 4b12a |
(431) 0x4b05c VMOVUPD (%RSI,%RDX,1),%YMM10 |
(431) 0x4b061 VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM10 |
(431) 0x4b067 VMOVUPD %YMM10,(%RAX,%RDX,1) |
(431) 0x4b06c VMOVUPD 0x20(%RDX,%RSI,1),%YMM11 |
(431) 0x4b072 VFMADD213PD 0x20(%RAX,%RDX,1),%YMM2,%YMM11 |
(431) 0x4b079 VMOVUPD %YMM11,0x20(%RAX,%RDX,1) |
(431) 0x4b07f VMOVUPD 0x40(%RDX,%RSI,1),%YMM12 |
(431) 0x4b085 VFMADD213PD 0x40(%RAX,%RDX,1),%YMM2,%YMM12 |
(431) 0x4b08c VMOVUPD %YMM12,0x40(%RAX,%RDX,1) |
(431) 0x4b092 VMOVUPD 0x60(%RDX,%RSI,1),%YMM13 |
(431) 0x4b098 VFMADD213PD 0x60(%RAX,%RDX,1),%YMM2,%YMM13 |
(431) 0x4b09f VMOVUPD %YMM13,0x60(%RAX,%RDX,1) |
(431) 0x4b0a5 VMOVUPD 0x80(%RDX,%RSI,1),%YMM14 |
(431) 0x4b0ae VFMADD213PD 0x80(%RAX,%RDX,1),%YMM2,%YMM14 |
(431) 0x4b0b8 VMOVUPD %YMM14,0x80(%RAX,%RDX,1) |
(431) 0x4b0c1 VMOVUPD 0xa0(%RDX,%RSI,1),%YMM15 |
(431) 0x4b0ca VFMADD213PD 0xa0(%RAX,%RDX,1),%YMM2,%YMM15 |
(431) 0x4b0d4 VMOVUPD %YMM15,0xa0(%RAX,%RDX,1) |
(431) 0x4b0dd VMOVUPD 0xc0(%RDX,%RSI,1),%YMM0 |
(431) 0x4b0e6 VFMADD213PD 0xc0(%RAX,%RDX,1),%YMM2,%YMM0 |
(431) 0x4b0f0 VMOVUPD %YMM0,0xc0(%RAX,%RDX,1) |
(431) 0x4b0f9 VMOVUPD 0xe0(%RDX,%RSI,1),%YMM4 |
(431) 0x4b102 VFMADD213PD 0xe0(%RAX,%RDX,1),%YMM2,%YMM4 |
(431) 0x4b10c VMOVUPD %YMM4,0xe0(%RAX,%RDX,1) |
(431) 0x4b115 ADD $0x100,%RDX |
(431) 0x4b11c CMP %RDX,0xc8(%RSP) |
(431) 0x4b124 JNE 4b05c |
(428) 0x4b12a CMPQ $0,0xa0(%RSP) |
(428) 0x4b133 JE 4b1bd |
(428) 0x4b139 MOV 0x90(%RSP),%R11 |
(428) 0x4b141 MOV %R11,%RDX |
(428) 0x4b144 CMP $0x1,%R11 |
(428) 0x4b148 JE 4b411 |
(428) 0x4b14e MOV 0x98(%RSP),%R8 |
(428) 0x4b156 MOV %R8,0xb0(%RSP) |
(428) 0x4b15e MOV 0xb8(%RSP),%R11 |
(428) 0x4b166 VMOVDDUP (%RCX),%XMM2 |
(428) 0x4b16a ADD %R8,%R11 |
(428) 0x4b16d ADD %RBX,%R8 |
(428) 0x4b170 LEA (%R15,%R11,8),%R11 |
(428) 0x4b174 ADD %RDI,%R8 |
(428) 0x4b177 VMOVUPD (%R11),%XMM1 |
(428) 0x4b17c VFMADD132PD (%R14,%R8,8),%XMM1,%XMM2 |
(428) 0x4b182 VMOVUPD %XMM2,(%R11) |
(428) 0x4b187 TEST $0x1,%DL |
(428) 0x4b18a JE 4b1bd |
(428) 0x4b18c MOV 0xb0(%RSP),%R8 |
(428) 0x4b194 AND $-0x2,%RDX |
(428) 0x4b198 ADD %R8,%RDX |
(428) 0x4b19b ADD %RBX,%RDX |
(428) 0x4b19e VMOVSD (%RCX),%XMM3 |
(428) 0x4b1a2 LEA (%R10,%RDX,1),%R11 |
(428) 0x4b1a6 ADD %RDI,%RDX |
(428) 0x4b1a9 LEA (%R15,%R11,8),%R8 |
(428) 0x4b1ad VMOVSD (%R8),%XMM5 |
(428) 0x4b1b2 VFMADD132SD (%R14,%RDX,8),%XMM5,%XMM3 |
(428) 0x4b1b8 VMOVSD %XMM3,(%R8) |
(428) 0x4b1bd MOV 0xc0(%RSP),%R8 |
(428) 0x4b1c5 MOV %R9,%RCX |
(428) 0x4b1c8 MOV 0xd8(%RSP),%R11 |
(428) 0x4b1d0 MOV 0xd0(%RSP),%R9 |
(428) 0x4b1d8 ADD %R8,%RSI |
(428) 0x4b1db ADD %R9,%RDI |
(428) 0x4b1de CMP %R11,%RCX |
(428) 0x4b1e1 JNE 4af30 |
(429) 0x4b1e7 MOV 0x88(%RSP),%R8 |
(429) 0x4b1ef MOV 0x80(%RSP),%R11 |
(429) 0x4b1f7 CMP %R11,0x20(%RSP) |
(429) 0x4b1fc JE 4b214 |
(429) 0x4b1fe INC %R8 |
(429) 0x4b201 CMP %R8,0x78(%RSP) |
(429) 0x4b206 JLE 4b41e |
(429) 0x4b20c INC %R11 |
(429) 0x4b20f JMP 4ae90 |
0x4b214 VZEROUPPER |
0x4b217 LEA -0x28(%RBP),%RSP |
0x4b21b POP %RBX |
0x4b21c POP %R12 |
0x4b21e POP %R13 |
0x4b220 POP %R14 |
0x4b222 POP %R15 |
0x4b224 POP %RBP |
0x4b225 RET |
0x4b226 NOPW %CS:(%RAX,%RAX,1) |
(428) 0x4b230 MOV %R12,%R11 |
(428) 0x4b233 XOR %EDX,%EDX |
(428) 0x4b235 AND $0x7,%R11D |
(428) 0x4b239 JE 4b314 |
(428) 0x4b23f CMP $0x1,%R11 |
(428) 0x4b243 JE 4b2f4 |
(428) 0x4b249 CMP $0x2,%R11 |
(428) 0x4b24d JE 4b2dd |
(428) 0x4b253 CMP $0x3,%R11 |
(428) 0x4b257 JE 4b2c6 |
(428) 0x4b259 CMP $0x4,%R11 |
(428) 0x4b25d JE 4b2af |
(428) 0x4b25f CMP $0x5,%R11 |
(428) 0x4b263 JE 4b298 |
(428) 0x4b265 CMP $0x6,%R11 |
(428) 0x4b269 JE 4b281 |
(428) 0x4b26b VMOVSD (%RSI),%XMM7 |
(428) 0x4b26f VMOVSD (%RAX),%XMM6 |
(428) 0x4b273 MOV $0x1,%EDX |
(428) 0x4b278 VFMADD132SD (%RCX),%XMM6,%XMM7 |
(428) 0x4b27d VMOVSD %XMM7,(%RAX) |
(428) 0x4b281 VMOVSD (%RSI,%RDX,8),%XMM8 |
(428) 0x4b286 VMOVSD (%RAX,%RDX,8),%XMM9 |
(428) 0x4b28b VFMADD132SD (%RCX),%XMM9,%XMM8 |
(428) 0x4b290 VMOVSD %XMM8,(%RAX,%RDX,8) |
(428) 0x4b295 INC %RDX |
(428) 0x4b298 VMOVSD (%RSI,%RDX,8),%XMM10 |
(428) 0x4b29d VMOVSD (%RAX,%RDX,8),%XMM11 |
(428) 0x4b2a2 VFMADD132SD (%RCX),%XMM11,%XMM10 |
(428) 0x4b2a7 VMOVSD %XMM10,(%RAX,%RDX,8) |
(428) 0x4b2ac INC %RDX |
(428) 0x4b2af VMOVSD (%RSI,%RDX,8),%XMM12 |
(428) 0x4b2b4 VMOVSD (%RAX,%RDX,8),%XMM13 |
(428) 0x4b2b9 VFMADD132SD (%RCX),%XMM13,%XMM12 |
(428) 0x4b2be VMOVSD %XMM12,(%RAX,%RDX,8) |
(428) 0x4b2c3 INC %RDX |
(428) 0x4b2c6 VMOVSD (%RSI,%RDX,8),%XMM14 |
(428) 0x4b2cb VMOVSD (%RAX,%RDX,8),%XMM15 |
(428) 0x4b2d0 VFMADD132SD (%RCX),%XMM15,%XMM14 |
(428) 0x4b2d5 VMOVSD %XMM14,(%RAX,%RDX,8) |
(428) 0x4b2da INC %RDX |
(428) 0x4b2dd VMOVSD (%RSI,%RDX,8),%XMM0 |
(428) 0x4b2e2 VMOVSD (%RAX,%RDX,8),%XMM4 |
(428) 0x4b2e7 VFMADD132SD (%RCX),%XMM4,%XMM0 |
(428) 0x4b2ec VMOVSD %XMM0,(%RAX,%RDX,8) |
(428) 0x4b2f1 INC %RDX |
(428) 0x4b2f4 VMOVSD (%RSI,%RDX,8),%XMM2 |
(428) 0x4b2f9 VMOVSD (%RAX,%RDX,8),%XMM1 |
(428) 0x4b2fe VFMADD132SD (%RCX),%XMM1,%XMM2 |
(428) 0x4b303 VMOVSD %XMM2,(%RAX,%RDX,8) |
(428) 0x4b308 INC %RDX |
(428) 0x4b30b CMP %RDX,%R12 |
(428) 0x4b30e JE 4b1bd |
(430) 0x4b314 VMOVSD (%RSI,%RDX,8),%XMM3 |
(430) 0x4b319 VMOVSD (%RAX,%RDX,8),%XMM5 |
(430) 0x4b31e VFMADD132SD (%RCX),%XMM5,%XMM3 |
(430) 0x4b323 VMOVSD 0x8(%RAX,%RDX,8),%XMM6 |
(430) 0x4b329 VMOVSD 0x10(%RAX,%RDX,8),%XMM9 |
(430) 0x4b32f VMOVSD 0x18(%RAX,%RDX,8),%XMM11 |
(430) 0x4b335 VMOVSD 0x20(%RAX,%RDX,8),%XMM13 |
(430) 0x4b33b VMOVSD 0x28(%RAX,%RDX,8),%XMM15 |
(430) 0x4b341 VMOVSD 0x30(%RAX,%RDX,8),%XMM4 |
(430) 0x4b347 VMOVSD 0x38(%RAX,%RDX,8),%XMM1 |
(430) 0x4b34d VMOVSD %XMM3,(%RAX,%RDX,8) |
(430) 0x4b352 VMOVSD 0x8(%RSI,%RDX,8),%XMM7 |
(430) 0x4b358 VFMADD132SD (%RCX),%XMM6,%XMM7 |
(430) 0x4b35d VMOVSD %XMM7,0x8(%RAX,%RDX,8) |
(430) 0x4b363 VMOVSD 0x10(%RSI,%RDX,8),%XMM8 |
(430) 0x4b369 VFMADD132SD (%RCX),%XMM9,%XMM8 |
(430) 0x4b36e VMOVSD %XMM8,0x10(%RAX,%RDX,8) |
(430) 0x4b374 VMOVSD 0x18(%RSI,%RDX,8),%XMM10 |
(430) 0x4b37a VFMADD132SD (%RCX),%XMM11,%XMM10 |
(430) 0x4b37f VMOVSD %XMM10,0x18(%RAX,%RDX,8) |
(430) 0x4b385 VMOVSD 0x20(%RSI,%RDX,8),%XMM12 |
(430) 0x4b38b VFMADD132SD (%RCX),%XMM13,%XMM12 |
(430) 0x4b390 VMOVSD %XMM12,0x20(%RAX,%RDX,8) |
(430) 0x4b396 VMOVSD 0x28(%RSI,%RDX,8),%XMM14 |
(430) 0x4b39c VFMADD132SD (%RCX),%XMM15,%XMM14 |
(430) 0x4b3a1 VMOVSD %XMM14,0x28(%RAX,%RDX,8) |
(430) 0x4b3a7 VMOVSD 0x30(%RSI,%RDX,8),%XMM0 |
(430) 0x4b3ad VFMADD132SD (%RCX),%XMM4,%XMM0 |
(430) 0x4b3b2 VMOVSD %XMM0,0x30(%RAX,%RDX,8) |
(430) 0x4b3b8 VMOVSD 0x38(%RSI,%RDX,8),%XMM2 |
(430) 0x4b3be VFMADD132SD (%RCX),%XMM1,%XMM2 |
(430) 0x4b3c3 VMOVSD %XMM2,0x38(%RAX,%RDX,8) |
(430) 0x4b3c9 ADD $0x8,%RDX |
(430) 0x4b3cd CMP %RDX,%R12 |
(430) 0x4b3d0 JNE 4b314 |
(428) 0x4b3d6 JMP 4b1bd |
0x4b3db NOPL (%RAX,%RAX,1) |
(428) 0x4b3e0 VMOVSD (%RCX),%XMM0 |
(428) 0x4b3e4 VMOVSD (%RAX),%XMM4 |
(428) 0x4b3e8 LEA 0x8(%RCX),%R9 |
(428) 0x4b3ec VFMADD132SD (%RSI),%XMM4,%XMM0 |
(428) 0x4b3f1 VMOVSD %XMM0,(%RAX) |
(428) 0x4b3f5 JMP 4b1bd |
(428) 0x4b3fa MOVQ $0,0xb0(%RSP) |
(428) 0x4b406 MOV %R12,%RDX |
(428) 0x4b409 XOR %R8D,%R8D |
(428) 0x4b40c JMP 4b15e |
(428) 0x4b411 MOV 0x98(%RSP),%RDX |
(428) 0x4b419 JMP 4b19b |
(429) 0x4b41e INCQ 0x10(%RSP) |
(429) 0x4b423 MOV 0x8(%RSP),%RDI |
(429) 0x4b428 XOR %R8D,%R8D |
(429) 0x4b42b MOV 0x10(%RSP),%R10 |
(429) 0x4b430 ADD %RDI,%R10 |
(429) 0x4b433 MOV %R10,0x28(%RSP) |
(429) 0x4b438 JMP 4b20c |
0x4b43d INC %RCX |
0x4b440 XOR %EDX,%EDX |
0x4b442 JMP 4adb7 |
0x4b447 NOPW (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | Collapse.hpp:81-81 |
Module | libkripke.so |
nb instructions | 113 |
nb uops | 188 |
loop length | 500 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 23 |
micro-operation queue | 47.00 cycles |
front end | 47.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 27.00 | 27.00 | 20.83 | 20.50 | 30.00 | 27.00 | 27.00 | 20.67 |
cycles | 27.00 | 27.25 | 20.83 | 20.50 | 30.00 | 27.00 | 27.00 | 20.67 |
Cycles executing div or sqrt instructions | 42.00-166.00 |
FE+BE cycles | 42.02 |
Stall cycles | 12.22 |
ROB full (events) | 12.47 |
Front-end | 47.00 |
Dispatch | 30.00 |
DIV/SQRT | 42.00-166.00 |
Overall L1 | 47.00-166.00 |
all | 1% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 6% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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 |
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 |
AND $-0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0xe0,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x10(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x110(%RAX),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RAX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x38(%RAX),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,0x8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x60(%RAX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x68(%RAX),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R13,0xd0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xc0(%RAX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xf0(%RAX),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,0x70(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x118(%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x30(%RAX),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,0x68(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa8(%RAX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,0x40(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,0x60(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,0x48(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,0x58(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,0x38(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,0x50(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x158(%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDI),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,0x78(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CALL 9760 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD %EAX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CALL 9650 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVSXD %EAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x78(%RSP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R13,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
DIV %R12 | 36 | 9 | 9 | 0 | 0 | 0 | 9 | 9 | 0 | 34 | 21-83 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RDX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4b43d <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x76d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
IMUL %RCX,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%RDI,%RDX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RCX,%RAX,1),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x60(%RSP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x70(%RSP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DIVQ 0x78(%RSP) | 36 | 8.75 | 8.75 | 0.50 | 0.50 | 0 | 8.75 | 8.75 | 0 | 34 | 21-83 |
SUB %RBX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,0x10(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R9,0x68(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %R12,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xd0(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x1(%RCX),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x10(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x8(%RSP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,0x20(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SHR $0x2,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R12,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R11,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x1(%R12),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x5,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IMUL %R9,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R12,%R9 | 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 |
ADD %RDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%R10D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RDI,0xa8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SAL $0x3,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RCX,0xc8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R13,0x18(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,0x98(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,0x28(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,0xa0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,0x90(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,0xc0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %R11D,%R11D | 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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
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 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4adb7 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0xe7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | Collapse.hpp:81-81 |
Module | libkripke.so |
nb instructions | 113 |
nb uops | 188 |
loop length | 500 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 23 |
micro-operation queue | 47.00 cycles |
front end | 47.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 27.00 | 27.00 | 20.83 | 20.50 | 30.00 | 27.00 | 27.00 | 20.67 |
cycles | 27.00 | 27.25 | 20.83 | 20.50 | 30.00 | 27.00 | 27.00 | 20.67 |
Cycles executing div or sqrt instructions | 42.00-166.00 |
FE+BE cycles | 42.02 |
Stall cycles | 12.22 |
ROB full (events) | 12.47 |
Front-end | 47.00 |
Dispatch | 30.00 |
DIV/SQRT | 42.00-166.00 |
Overall L1 | 47.00-166.00 |
all | 1% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 6% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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 |
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 |
AND $-0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0xe0,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x10(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x110(%RAX),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RAX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x38(%RAX),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,0x8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x60(%RAX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x68(%RAX),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R13,0xd0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xc0(%RAX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xf0(%RAX),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,0x70(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x118(%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x30(%RAX),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,0x68(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa8(%RAX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,0x40(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,0x60(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,0x48(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,0x58(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,0x38(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,0x50(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x158(%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDI),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R13,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,0x78(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CALL 9760 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD %EAX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CALL 9650 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVSXD %EAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x78(%RSP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R13,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
DIV %R12 | 36 | 9 | 9 | 0 | 0 | 0 | 9 | 9 | 0 | 34 | 21-83 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RDX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4b43d <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x76d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
IMUL %RCX,%RDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%RDI,%RDX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RCX,%RAX,1),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x60(%RSP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x70(%RSP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DIVQ 0x78(%RSP) | 36 | 8.75 | 8.75 | 0.50 | 0.50 | 0 | 8.75 | 8.75 | 0 | 34 | 21-83 |
SUB %RBX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,0x10(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R9,0x68(%RSP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %R12,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4b217 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x547> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xd0(%RSP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x1(%RCX),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x10(%RSP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x8(%RSP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R10,0x20(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SHR $0x2,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R12,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R11,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x1(%R12),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x5,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IMUL %R9,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R12,%R9 | 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 |
ADD %RDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%R10D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RDI,0xa8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SAL $0x3,%R11 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RCX,0xc8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R13,0x18(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,0x98(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,0x28(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,0xa0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R10,0x90(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,0xc0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %R11D,%R11D | 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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
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 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4adb7 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EESS_EENSO_INSQ_INSR_6MomentElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK14LPlusTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0xe7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼void RAJA::internal::StatementExecutor | 12.44 | 3.85 |
▼Loop 429 - RangeSegment.hpp:120-120 - libkripke.so– | 0 | 0 |
▼Loop 428 - forall.hpp:59-59 - libkripke.so– | 0 | 0 |
○Loop 431 - forall.hpp:59-59 - libkripke.so | 12.44 | 3.85 |
○Loop 430 - forall.hpp:59-59 - libkripke.so | 0 | 0 |