Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ... | Module: libqmcwfs.so | Source: einspline_spo_ref.hpp:203-230 [...] | Coverage: 1.47% |
---|
Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ... | Module: libqmcwfs.so | Source: einspline_spo_ref.hpp:203-230 [...] | Coverage: 1.47% |
---|
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 217 - 217 |
-------------------------------------------------------------------------------- |
217: inline const PosType& activeR(int iat) const { return (activePtcl == iat) ? activePos : R[iat]; } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 146 - 146 |
-------------------------------------------------------------------------------- |
146: X[i] = base[i * offset]; |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 183 - 183 |
-------------------------------------------------------------------------------- |
183: return (const_cast<T1&>(a) = b); |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 203 - 241 |
-------------------------------------------------------------------------------- |
203: const Type_t operator[](size_t i) const { return Type_t(myData + i, nGhosts); } |
[...] |
237: T* data() { return myData; } |
238: ///return the base |
239: const T* data() const { return myData; } |
240: ///return the pointer of the i-th components |
241: T* restrict data(size_t i) { return myData + i * nGhosts; } |
/usr/include/c++/13.1.1/bits/stl_vector.h: 1126 - 1258 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
[...] |
1258: { return _M_data_ptr(this->_M_impl._M_start); } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 229 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
[...] |
229: return X[i]; |
/usr/include/c++/13.1.1/bits/stl_algobase.h: 238 - 238 |
-------------------------------------------------------------------------------- |
238: if (__b < __a) |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp: 203 - 230 |
-------------------------------------------------------------------------------- |
203: ScopedTimer local_timer(timer); |
204: |
205: auto u = Lattice.toUnit_floor(P.activeR(iat)); |
206: for (int i = 0; i < nBlocks; ++i) |
207: MultiBsplineEvalRef::evaluate_vgh(einsplines[i], u[0], u[1], u[2], psi[i].data(), grad[i].data(), hess[i].data(), |
208: nSplinesPerBlock); |
209: } |
210: |
211: inline void evaluate(const ParticleSet& P, |
[...] |
219: for (int i = 0; i < nBlocks; ++i) |
220: { |
221: // in real simulation, phase needs to be applied. Here just fake computation |
222: const int first = i * nBlocks; |
223: for (int j = first; j < std::min((i + 1) * nSplinesPerBlock, OrbitalSetSize); j++) |
224: { |
225: psi_v[j] = psi[i][j - first]; |
226: dpsi_v[j] = grad[i][j - first]; |
227: d2psi_v[j] = hess[i].data(0)[j - first]; |
228: } |
229: } |
230: } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249 |
-------------------------------------------------------------------------------- |
242: ScopeGuard(TIMER& t) : timer(t) { timer.start(); } |
[...] |
249: ~ScopeGuard() { timer.stop(); } |
0x51950 PUSH %RBP |
0x51951 MOV %RSP,%RBP |
0x51954 PUSH %R15 |
0x51956 PUSH %R14 |
0x51958 PUSH %R13 |
0x5195a MOVSXD %EDX,%R13 |
0x5195d PUSH %R12 |
0x5195f MOV %RSI,%R12 |
0x51962 PUSH %RBX |
0x51963 MOV %RDI,%RBX |
0x51966 SUB $0x88,%RSP |
0x5196d MOV %RCX,-0x98(%RBP) |
0x51974 MOV %R8,-0xa0(%RBP) |
0x5197b MOV 0x348(%RDI),%R15 |
0x51982 MOV %R9,-0xa8(%RBP) |
0x51989 MOV %R15,%RDI |
0x5198c MOV %FS:0x28,%RAX |
0x51995 MOV %RAX,-0x38(%RBP) |
0x51999 XOR %EAX,%EAX |
0x5199b CALL 8460 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> |
0x519a0 LEA 0x48(%RBX),%RSI |
0x519a4 LEA 0x988(%R12),%RDX |
0x519ac CMP 0x984(%R12),%R13D |
0x519b4 JE 519c7 |
0x519b6 MOV 0x5e8(%R12),%RAX |
0x519be LEA (%R13,%R13,2),%RDX |
0x519c3 LEA (%RAX,%RDX,8),%RDX |
0x519c7 LEA -0x50(%RBP),%RDI |
0x519cb CALL 123c0 <_ZNK11qmcplusplus14CrystalLatticeIdLj3ELb0EE12toUnit_floorIdEENS_10TinyVectorIdLj3EEERKNS3_IT_Lj3EEE> |
0x519d0 MOV 0x30(%RBX),%R9D |
0x519d4 TEST %R9D,%R9D |
0x519d7 JLE 51ad8 |
0x519dd MOV -0x40(%RBP),%R14 |
0x519e1 MOV -0x48(%RBP),%RCX |
0x519e5 XOR %R12D,%R12D |
0x519e8 VMOVSD -0x50(%RBP),%XMM3 |
0x519ed VMOVQ %R14,%XMM2 |
0x519f2 VMOVQ %RCX,%XMM1 |
0x519f7 VMOVSD %XMM3,-0x58(%RBP) |
(564) 0x519fc MOV 0x300(%RBX),%R11 |
(564) 0x51a03 MOV 0x330(%RBX),%RDI |
(564) 0x51a0a LEA (%R12,%R12,2),%R10 |
(564) 0x51a0e LEA (%R12,%R12,4),%RSI |
(564) 0x51a12 MOV 0x318(%RBX),%R8 |
(564) 0x51a19 MOV 0x2e8(%RBX),%RAX |
(564) 0x51a20 SAL $0x3,%RSI |
(564) 0x51a24 LEA 0x1(%R12),%R14 |
(564) 0x51a29 LEA (%R11,%R10,8),%R13 |
(564) 0x51a2d MOV 0x18(%RDI,%RSI,1),%RCX |
(564) 0x51a32 VMOVSD -0x58(%RBP),%XMM0 |
(564) 0x51a37 VMOVSD %XMM2,-0x68(%RBP) |
(564) 0x51a3c MOV 0x18(%R8,%RSI,1),%RDX |
(564) 0x51a41 MOV (%RAX,%R12,8),%RDI |
(564) 0x51a45 VMOVSD %XMM1,-0x60(%RBP) |
(564) 0x51a4a MOV (%R13),%RSI |
(564) 0x51a4e MOVSXD 0x40(%RBX),%R8 |
(564) 0x51a52 CALL 50370 <_ZN16miniqmcreference19MultiBsplineEvalRef12evaluate_vghIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_S9_S9_m> |
(564) 0x51a57 CMP %R14D,0x30(%RBX) |
(564) 0x51a5b VMOVSD -0x60(%RBP),%XMM1 |
(564) 0x51a60 VMOVSD -0x68(%RBP),%XMM2 |
(564) 0x51a65 JLE 51ad8 |
(564) 0x51a67 MOV 0x318(%RBX),%RSI |
(564) 0x51a6e MOV 0x300(%RBX),%RDI |
(564) 0x51a75 LEA (%R14,%R14,4),%RDX |
(564) 0x51a79 LEA (%R14,%R14,2),%R8 |
(564) 0x51a7d SAL $0x3,%RDX |
(564) 0x51a81 MOV 0x330(%RBX),%R9 |
(564) 0x51a88 MOV 0x2e8(%RBX),%R13 |
(564) 0x51a8f ADD $0x2,%R12 |
(564) 0x51a93 LEA (%RDI,%R8,8),%R11 |
(564) 0x51a97 MOV 0x18(%RSI,%RDX,1),%R10 |
(564) 0x51a9c MOVSXD 0x40(%RBX),%R8 |
(564) 0x51aa0 VMOVSD %XMM2,-0x68(%RBP) |
(564) 0x51aa5 MOV 0x18(%R9,%RDX,1),%RCX |
(564) 0x51aaa MOV (%R11),%RSI |
(564) 0x51aad VMOVSD %XMM1,-0x60(%RBP) |
(564) 0x51ab2 MOV (%R13,%R14,8),%RDI |
(564) 0x51ab7 VMOVSD -0x58(%RBP),%XMM0 |
(564) 0x51abc MOV %R10,%RDX |
(564) 0x51abf CALL 50370 <_ZN16miniqmcreference19MultiBsplineEvalRef12evaluate_vghIdEEvPKN11qmcplusplus14bspline_traitsIT_Lj3EE10SplineTypeES4_S4_S4_PS4_S9_S9_m> |
(564) 0x51ac4 CMP %R12D,0x30(%RBX) |
(564) 0x51ac8 VMOVSD -0x60(%RBP),%XMM1 |
(564) 0x51acd VMOVSD -0x68(%RBP),%XMM2 |
(564) 0x51ad2 JG 519fc |
0x51ad8 MOV %R15,%RDI |
0x51adb CALL 8420 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> |
0x51ae0 MOV 0x30(%RBX),%R15D |
0x51ae4 MOV %R15D,-0x74(%RBP) |
0x51ae8 TEST %R15D,%R15D |
0x51aeb JLE 51dc5 |
0x51af1 MOVSXD -0x74(%RBP),%RAX |
0x51af5 MOV 0x40(%RBX),%R12D |
0x51af9 MOVQ $0,-0x70(%RBP) |
0x51b01 XOR %R15D,%R15D |
0x51b04 MOV 0x8(%RBX),%ECX |
0x51b07 MOVQ $0,-0x58(%RBP) |
0x51b0f LEA (%RAX,%RAX,2),%RDX |
0x51b13 MOV %R12D,-0x7c(%RBP) |
0x51b17 LEA (,%RAX,8),%R14 |
0x51b1f SAL $0x3,%RDX |
0x51b23 MOV %ECX,-0x78(%RBP) |
0x51b26 MOV %RDX,-0x90(%RBP) |
0x51b2d MOV %R12D,-0x68(%RBP) |
0x51b31 MOVL $0,-0x60(%RBP) |
0x51b38 MOV %R14,-0x88(%RBP) |
0x51b3f XOR %R14D,%R14D |
0x51b42 NOPW (%RAX,%RAX,1) |
(562) 0x51b48 MOV -0x68(%RBP),%R9D |
(562) 0x51b4c MOV -0x78(%RBP),%R12D |
(562) 0x51b50 CMP %R12D,%R9D |
(562) 0x51b53 CMOVLE %R9D,%R12D |
(562) 0x51b57 CMP %R12D,-0x60(%RBP) |
(562) 0x51b5b JGE 51d8a |
(562) 0x51b61 MOV 0x318(%RBX),%R13 |
(562) 0x51b68 MOV -0xa0(%RBP),%RCX |
(562) 0x51b6f MOV -0x60(%RBP),%EAX |
(562) 0x51b72 MOV -0x70(%RBP),%RDX |
(562) 0x51b76 ADD %R15,%R13 |
(562) 0x51b79 MOV 0x300(%RBX),%R10 |
(562) 0x51b80 MOV -0x58(%RBP),%R8 |
(562) 0x51b84 MOV 0x18(%R13),%RSI |
(562) 0x51b88 MOV 0x330(%RBX),%RDI |
(562) 0x51b8f SUB %EAX,%R12D |
(562) 0x51b92 XOR %EAX,%EAX |
(562) 0x51b94 ADD 0x18(%RCX),%RDX |
(562) 0x51b98 MOVSXD 0x8(%R13),%RCX |
(562) 0x51b9c SAL $0x3,%R12 |
(562) 0x51ba0 MOV -0xa8(%RBP),%R13 |
(562) 0x51ba7 MOV (%R10,%R8,1),%R11 |
(562) 0x51bab MOV -0x98(%RBP),%R10 |
(562) 0x51bb2 MOV 0x18(%RDI,%R15,1),%R8 |
(562) 0x51bb7 LEA (%RSI,%RCX,8),%R9 |
(562) 0x51bbb SAL $0x4,%RCX |
(562) 0x51bbf MOV 0x18(%R13),%RDI |
(562) 0x51bc3 LEA -0x8(%R12),%R13 |
(562) 0x51bc8 ADD %RSI,%RCX |
(562) 0x51bcb MOV 0x18(%R10),%R10 |
(562) 0x51bcf SHR $0x3,%R13 |
(562) 0x51bd3 INC %R13 |
(562) 0x51bd6 ADD %R14,%RDI |
(562) 0x51bd9 ADD %R14,%R10 |
(562) 0x51bdc AND $0x3,%R13D |
(562) 0x51be0 JE 51ca0 |
(562) 0x51be6 CMP $0x1,%R13 |
(562) 0x51bea JE 51c5e |
(562) 0x51bec CMP $0x2,%R13 |
(562) 0x51bf0 JE 51c25 |
(562) 0x51bf2 VMOVSD (%R11),%XMM0 |
(562) 0x51bf7 ADD $0x18,%RDX |
(562) 0x51bfb MOV $0x8,%EAX |
(562) 0x51c00 VMOVSD %XMM0,(%R10) |
(562) 0x51c05 VMOVSD (%RSI),%XMM2 |
(562) 0x51c09 VMOVSD (%RCX),%XMM1 |
(562) 0x51c0d VMOVHPD (%R9),%XMM2,%XMM4 |
(562) 0x51c12 VMOVSD %XMM1,-0x8(%RDX) |
(562) 0x51c17 VMOVUPD %XMM4,-0x18(%RDX) |
(562) 0x51c1c VMOVSD (%R8),%XMM5 |
(562) 0x51c21 VMOVSD %XMM5,(%RDI) |
(562) 0x51c25 VMOVSD (%R11,%RAX,1),%XMM6 |
(562) 0x51c2b ADD $0x18,%RDX |
(562) 0x51c2f VMOVSD %XMM6,(%R10,%RAX,1) |
(562) 0x51c35 VMOVSD (%RSI,%RAX,1),%XMM8 |
(562) 0x51c3a VMOVSD (%RCX,%RAX,1),%XMM7 |
(562) 0x51c3f VMOVHPD (%R9,%RAX,1),%XMM8,%XMM9 |
(562) 0x51c45 VMOVSD %XMM7,-0x8(%RDX) |
(562) 0x51c4a VMOVUPD %XMM9,-0x18(%RDX) |
(562) 0x51c4f VMOVSD (%R8,%RAX,1),%XMM10 |
(562) 0x51c55 VMOVSD %XMM10,(%RDI,%RAX,1) |
(562) 0x51c5a ADD $0x8,%RAX |
(562) 0x51c5e VMOVSD (%R11,%RAX,1),%XMM11 |
(562) 0x51c64 ADD $0x18,%RDX |
(562) 0x51c68 VMOVSD %XMM11,(%R10,%RAX,1) |
(562) 0x51c6e VMOVSD (%RSI,%RAX,1),%XMM13 |
(562) 0x51c73 VMOVSD (%RCX,%RAX,1),%XMM12 |
(562) 0x51c78 VMOVHPD (%R9,%RAX,1),%XMM13,%XMM14 |
(562) 0x51c7e VMOVSD %XMM12,-0x8(%RDX) |
(562) 0x51c83 VMOVUPD %XMM14,-0x18(%RDX) |
(562) 0x51c88 VMOVSD (%R8,%RAX,1),%XMM15 |
(562) 0x51c8e VMOVSD %XMM15,(%RDI,%RAX,1) |
(562) 0x51c93 ADD $0x8,%RAX |
(562) 0x51c97 CMP %RAX,%R12 |
(562) 0x51c9a JE 51d8a |
(563) 0x51ca0 VMOVSD (%R11,%RAX,1),%XMM3 |
(563) 0x51ca6 ADD $0x60,%RDX |
(563) 0x51caa VMOVSD %XMM3,(%R10,%RAX,1) |
(563) 0x51cb0 VMOVSD (%RSI,%RAX,1),%XMM0 |
(563) 0x51cb5 VMOVSD (%RCX,%RAX,1),%XMM1 |
(563) 0x51cba VMOVHPD (%R9,%RAX,1),%XMM0,%XMM2 |
(563) 0x51cc0 VMOVSD %XMM1,-0x50(%RDX) |
(563) 0x51cc5 VMOVUPD %XMM2,-0x60(%RDX) |
(563) 0x51cca VMOVSD (%R8,%RAX,1),%XMM4 |
(563) 0x51cd0 VMOVSD %XMM4,(%RDI,%RAX,1) |
(563) 0x51cd5 VMOVSD 0x8(%R11,%RAX,1),%XMM5 |
(563) 0x51cdc VMOVSD %XMM5,0x8(%RAX,%R10,1) |
(563) 0x51ce3 VMOVSD 0x8(%RSI,%RAX,1),%XMM7 |
(563) 0x51ce9 VMOVSD 0x8(%RCX,%RAX,1),%XMM6 |
(563) 0x51cef VMOVHPD 0x8(%R9,%RAX,1),%XMM7,%XMM8 |
(563) 0x51cf6 VMOVSD %XMM6,-0x38(%RDX) |
(563) 0x51cfb VMOVUPD %XMM8,-0x48(%RDX) |
(563) 0x51d00 VMOVSD 0x8(%R8,%RAX,1),%XMM9 |
(563) 0x51d07 VMOVSD %XMM9,0x8(%RAX,%RDI,1) |
(563) 0x51d0d VMOVSD 0x10(%R11,%RAX,1),%XMM10 |
(563) 0x51d14 VMOVSD %XMM10,0x10(%RAX,%R10,1) |
(563) 0x51d1b VMOVSD 0x10(%RSI,%RAX,1),%XMM12 |
(563) 0x51d21 VMOVSD 0x10(%RCX,%RAX,1),%XMM11 |
(563) 0x51d27 VMOVHPD 0x10(%R9,%RAX,1),%XMM12,%XMM13 |
(563) 0x51d2e VMOVSD %XMM11,-0x20(%RDX) |
(563) 0x51d33 VMOVUPD %XMM13,-0x30(%RDX) |
(563) 0x51d38 VMOVSD 0x10(%R8,%RAX,1),%XMM14 |
(563) 0x51d3f VMOVSD %XMM14,0x10(%RAX,%RDI,1) |
(563) 0x51d45 VMOVSD 0x18(%R11,%RAX,1),%XMM15 |
(563) 0x51d4c VMOVSD %XMM15,0x18(%RAX,%R10,1) |
(563) 0x51d53 VMOVSD 0x18(%RSI,%RAX,1),%XMM1 |
(563) 0x51d59 VMOVSD 0x18(%RCX,%RAX,1),%XMM3 |
(563) 0x51d5f VMOVHPD 0x18(%R9,%RAX,1),%XMM1,%XMM0 |
(563) 0x51d66 VMOVUPD %XMM0,-0x18(%RDX) |
(563) 0x51d6b VMOVSD %XMM3,-0x8(%RDX) |
(563) 0x51d70 VMOVSD 0x18(%R8,%RAX,1),%XMM2 |
(563) 0x51d77 ADD $0x20,%RAX |
(563) 0x51d7b VMOVSD %XMM2,-0x8(%RAX,%RDI,1) |
(563) 0x51d81 CMP %RAX,%R12 |
(563) 0x51d84 JNE 51ca0 |
(562) 0x51d8a ADDQ $0x18,-0x58(%RBP) |
(562) 0x51d8f MOV -0x7c(%RBP),%R12D |
(562) 0x51d93 ADD $0x28,%R15 |
(562) 0x51d97 MOV -0x74(%RBP),%R11D |
(562) 0x51d9b MOV -0x88(%RBP),%RSI |
(562) 0x51da2 MOV -0x90(%RBP),%RDX |
(562) 0x51da9 ADD %R12D,-0x68(%RBP) |
(562) 0x51dad ADD %R11D,-0x60(%RBP) |
(562) 0x51db1 ADD %RSI,%R14 |
(562) 0x51db4 MOV -0x58(%RBP),%R8 |
(562) 0x51db8 ADD %RDX,-0x70(%RBP) |
(562) 0x51dbc CMP %RDX,%R8 |
(562) 0x51dbf JNE 51b48 |
0x51dc5 MOV -0x38(%RBP),%RAX |
0x51dc9 SUB %FS:0x28,%RAX |
0x51dd2 JNE 51de6 |
0x51dd4 ADD $0x88,%RSP |
0x51ddb POP %RBX |
0x51ddc POP %R12 |
0x51dde POP %R13 |
0x51de0 POP %R14 |
0x51de2 POP %R15 |
0x51de4 POP %RBP |
0x51de5 RET |
0x51de6 CALL 80d0 <__stack_chk_fail@plt> |
0x51deb NOP |
0x51dec NOPL (%RAX) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►50.00+ | qmcplusplus::SPOSet::evaluate_[...] | OhmmsVector.h:144 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:263 | libqmcwfs.so |
○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:238 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:177 | libqmcwfs.so |
○ | main._omp_fn.0 | miniqmc.cpp:390 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►25.00+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:100 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:202 | libqmcwfs.so |
○ | main._omp_fn.1 | stl_vector.h:1123 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►25.00+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:100 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:202 | libqmcwfs.so |
○ | main._omp_fn.1 | stl_vector.h:1123 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | einspline_spo_ref.hpp:203-230 |
Module | libqmcwfs.so |
nb instructions | 76 |
nb uops | 80 |
loop length | 327 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 16 |
micro-operation queue | 20.00 cycles |
front end | 20.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.50 | 6.50 | 15.00 | 15.00 | 24.00 | 6.50 | 6.50 | 15.00 |
cycles | 6.50 | 6.50 | 15.00 | 15.00 | 24.00 | 6.50 | 6.50 | 15.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 20.12 |
Stall cycles | 0.64 |
SB full (events) | 1.91 |
Front-end | 20.00 |
Dispatch | 24.00 |
Overall L1 | 24.00 |
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 | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 8% |
load | 8% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 8% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 9% |
load | 9% |
store | 9% |
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 | 8% |
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 |
MOVSXD %EDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB $0x88,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x348(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %FS:0x28,%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 8460 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
LEA 0x48(%RBX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x988(%R12),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP 0x984(%R12),%R13D | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 519c7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5e8(%R12),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R13,%R13,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RAX,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x50(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 123c0 <_ZNK11qmcplusplus14CrystalLatticeIdLj3ELb0EE12toUnit_floorIdEENS_10TinyVectorIdLj3EEERKNS3_IT_Lj3EEE> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x30(%RBX),%R9D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R9D,%R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 51ad8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x40(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD -0x50(%RBP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVQ %R14,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVQ %RCX,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVSD %XMM3,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 8420 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x30(%RBX),%R15D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15D,-0x74(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
TEST %R15D,%R15D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 51dc5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD -0x74(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x40(%RBX),%R12D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
XOR %R15D,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x8(%RBX),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
LEA (%RAX,%RAX,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R12D,-0x7c(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (,%RAX,8),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x3,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %ECX,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12D,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVL $0,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %R14,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %R14D,%R14D | 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 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %FS:0x28,%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 51de6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD $0x88,%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 |
CALL 80d0 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | einspline_spo_ref.hpp:203-230 |
Module | libqmcwfs.so |
nb instructions | 76 |
nb uops | 80 |
loop length | 327 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 16 |
micro-operation queue | 20.00 cycles |
front end | 20.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.50 | 6.50 | 15.00 | 15.00 | 24.00 | 6.50 | 6.50 | 15.00 |
cycles | 6.50 | 6.50 | 15.00 | 15.00 | 24.00 | 6.50 | 6.50 | 15.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 20.12 |
Stall cycles | 0.64 |
SB full (events) | 1.91 |
Front-end | 20.00 |
Dispatch | 24.00 |
Overall L1 | 24.00 |
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 | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 8% |
load | 8% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 8% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 9% |
load | 9% |
store | 9% |
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 | 8% |
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 |
MOVSXD %EDX,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB $0x88,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x348(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %FS:0x28,%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 8460 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
LEA 0x48(%RBX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x988(%R12),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP 0x984(%R12),%R13D | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 519c7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5e8(%R12),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R13,%R13,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RAX,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x50(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 123c0 <_ZNK11qmcplusplus14CrystalLatticeIdLj3ELb0EE12toUnit_floorIdEENS_10TinyVectorIdLj3EEERKNS3_IT_Lj3EEE> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x30(%RBX),%R9D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R9D,%R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 51ad8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x40(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD -0x50(%RBP),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVQ %R14,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVQ %RCX,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VMOVSD %XMM3,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 8420 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x30(%RBX),%R15D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15D,-0x74(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
TEST %R15D,%R15D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 51dc5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD -0x74(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x40(%RBX),%R12D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
XOR %R15D,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x8(%RBX),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
LEA (%RAX,%RAX,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R12D,-0x7c(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (,%RAX,8),%R14 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x3,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %ECX,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12D,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVL $0,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %R14,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %R14D,%R14D | 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 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %FS:0x28,%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 51de6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD $0x88,%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 |
CALL 80d0 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::einspline_spo_ref | 1.47 | 0.02 |
○Loop 564 - einspline_spo_ref.hpp:206-207 - libqmcwfs.so | 0 | 0 |
▼Loop 562 - einspline_spo_ref.hpp:219-227 - libqmcwfs.so– | 0 | 0 |
○Loop 563 - einspline_spo_ref.hpp:223-227 - libqmcwfs.so | 1.47 | 0.02 |