Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcp ... | Module: exec | Source: OneBodyJastrowRef.h:112-198 [...] | Coverage: 0.01% |
---|
Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcp ... | Module: exec | Source: OneBodyJastrowRef.h:112-198 [...] | Coverage: 0.01% |
---|
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_iterator.h: 1077 - 1244 |
-------------------------------------------------------------------------------- |
1077: : _M_current(__i) { } |
[...] |
1244: { return __lhs.base() != __rhs.base(); } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h: 49 - 49 |
-------------------------------------------------------------------------------- |
49: for (unsigned d = 0; d < D; ++d) |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h: 214 - 214 |
-------------------------------------------------------------------------------- |
214: inline const Type_t* operator[](size_type i) const { return X.data() + i * D2; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94 |
-------------------------------------------------------------------------------- |
94: (const_cast<T1&>(a) += b); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 242 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
[...] |
242: inline iterator begin() { return X; } |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_numeric.h: 140 - 141 |
-------------------------------------------------------------------------------- |
140: for (; __first != __last; ++__first) |
141: __init = _GLIBCXX_MOVE_IF_20(__init) + *__first; |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 112 - 198 |
-------------------------------------------------------------------------------- |
112: const DistanceTableData& d_ie(*(P.DistTables[myTableID])); |
113: for (int iat = 0; iat < Nelec; ++iat) |
114: { |
115: computeU3(P, iat, d_ie.Distances[iat]); |
116: Vat[iat] = std::accumulate(U.begin(), U.begin() + Nions, valT()); |
117: Lap[iat] = accumulateGL(dU.data(), d2U.data(), d_ie.Displacements[iat], Grad[iat]); |
[...] |
169: { |
170: if (fromscratch) |
171: recompute(P); |
172: |
173: for (size_t iat = 0; iat < Nelec; ++iat) |
174: G[iat] += Grad[iat]; |
175: for (size_t iat = 0; iat < Nelec; ++iat) |
176: L[iat] -= Lap[iat]; |
177: LogValue = -std::accumulate(Vat.begin(), Vat.begin() + Nelec, valT()); |
178: } |
[...] |
190: for (int jat = 0; jat < Nions; ++jat) |
191: lap += d2u[jat] + lapfac * du[jat]; |
192: for (int idim = 0; idim < OHMMS_DIM; ++idim) |
193: { |
194: const valT* restrict dX = displ.data(idim); |
195: valT s = valT(); |
196: for (int jat = 0; jat < Nions; ++jat) |
197: s += du[jat] * dX[jat]; |
198: grad[idim] = s; |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 176 - 177 |
-------------------------------------------------------------------------------- |
176: inline Type_t& operator[](unsigned int i) { return X[i]; } |
177: inline const Type_t& operator[](unsigned int i) const { return X[i]; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 243 - 243 |
-------------------------------------------------------------------------------- |
243: const T* restrict data(size_t i) const { return myData + i * nGhosts; } |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_vector.h: 1126 - 1258 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
[...] |
1145: return *(this->_M_impl._M_start + __n); |
[...] |
1258: { return _M_data_ptr(this->_M_impl._M_start); } |
0x41b7d0 PUSH %RBP |
0x41b7d1 MOV %RSP,%RBP |
0x41b7d4 PUSH %R15 |
0x41b7d6 PUSH %R14 |
0x41b7d8 PUSH %R13 |
0x41b7da PUSH %R12 |
0x41b7dc PUSH %RBX |
0x41b7dd SUB $0x18,%RSP |
0x41b7e1 MOV %RSI,-0x30(%RBP) |
0x41b7e5 MOV %RDI,%R13 |
0x41b7e8 MOV $0x3ffffffffffffffc,%R14 |
0x41b7f2 MOV 0x98(%RDI),%EAX |
0x41b7f8 TEST %R8B,%R8B |
0x41b7fb JE 41bb97 |
0x41b801 TEST %EAX,%EAX |
0x41b803 JLE 41bb97 |
0x41b809 MOV %RDX,-0x38(%RBP) |
0x41b80d MOV %RCX,-0x40(%RBP) |
0x41b811 MOV -0x30(%RBP),%RAX |
0x41b815 MOV 0xa10(%RAX),%RAX |
0x41b81c MOVSXD 0x90(%R13),%RCX |
0x41b823 MOV (%RAX,%RCX,8),%R15 |
0x41b827 XOR %R12D,%R12D |
0x41b82a JMP 41b86b |
0x41b82c NOPL (%RAX) |
(262) 0x41b830 LEA (%R12,%R12,2),%RAX |
(262) 0x41b834 VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b838 VMOVUPD %XMM0,(%R8,%RAX,8) |
(262) 0x41b83e MOVQ $0,0x10(%R8,%RAX,8) |
(262) 0x41b847 VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b84b MOV 0x1b0(%R13),%RAX |
(262) 0x41b852 VMOVSD %XMM0,(%RAX,%R12,8) |
(262) 0x41b858 INC %R12 |
(262) 0x41b85b MOVSXD 0x98(%R13),%RAX |
(262) 0x41b862 CMP %RAX,%R12 |
(262) 0x41b865 JGE 41bb8f |
(262) 0x41b86b MOV 0x18(%R15),%RCX |
(262) 0x41b86f IMUL %R12,%RCX |
(262) 0x41b873 SAL $0x3,%RCX |
(262) 0x41b877 ADD 0x40(%R15),%RCX |
(262) 0x41b87b MOV %R13,%RDI |
(262) 0x41b87e MOV -0x30(%RBP),%RSI |
(262) 0x41b882 MOV %R12D,%EDX |
(262) 0x41b885 VZEROUPPER |
(262) 0x41b888 CALL 41d810 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd> |
(262) 0x41b88d MOVSXD 0x94(%R13),%RBX |
(262) 0x41b894 TEST %RBX,%RBX |
(262) 0x41b897 JE 41b910 |
(262) 0x41b899 MOV 0xf8(%R13),%RCX |
(262) 0x41b8a0 MOV $0x1fffffffffffffff,%RAX |
(262) 0x41b8aa LEA (%RBX,%RAX,1),%RDX |
(262) 0x41b8ae AND %RAX,%RDX |
(262) 0x41b8b1 INC %RDX |
(262) 0x41b8b4 MOV %RDX,%RSI |
(262) 0x41b8b7 AND %R14,%RSI |
(262) 0x41b8ba JE 41b930 |
(262) 0x41b8bc VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b8c0 XOR %EAX,%EAX |
(262) 0x41b8c2 NOPW %CS:(%RAX,%RAX,1) |
(272) 0x41b8d0 VADDPD (%RCX,%RAX,8),%YMM0,%YMM0 |
(272) 0x41b8d5 ADD $0x4,%RAX |
(272) 0x41b8d9 CMP %RSI,%RAX |
(272) 0x41b8dc JB 41b8d0 |
(262) 0x41b8de VEXTRACTF128 $0x1,%YMM0,%XMM1 |
(262) 0x41b8e4 VADDPD %XMM1,%XMM0,%XMM0 |
(262) 0x41b8e8 VPERMILPD $0x1,%XMM0,%XMM1 |
(262) 0x41b8ee VADDSD %XMM1,%XMM0,%XMM0 |
(262) 0x41b8f2 CMP %RSI,%RDX |
(262) 0x41b8f5 VMOVSD 0x7c80b(%RIP),%XMM2 |
(262) 0x41b8fd VBROADCASTSD 0x7c802(%RIP),%YMM1 |
(262) 0x41b906 JNE 41b950 |
(262) 0x41b908 JMP 41b95d |
0x41b90a NOPW (%RAX,%RAX,1) |
(262) 0x41b910 VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b914 VMOVSD 0x7c7ec(%RIP),%XMM2 |
(262) 0x41b91c VBROADCASTSD 0x7c7e3(%RIP),%YMM1 |
(262) 0x41b925 JMP 41b95d |
0x41b927 NOPW (%RAX,%RAX,1) |
(262) 0x41b930 VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b934 XOR %ESI,%ESI |
(262) 0x41b936 VMOVSD 0x7c7ca(%RIP),%XMM2 |
(262) 0x41b93e VBROADCASTSD 0x7c7c1(%RIP),%YMM1 |
(262) 0x41b947 NOPW (%RAX,%RAX,1) |
(271) 0x41b950 VADDSD (%RCX,%RSI,8),%XMM0,%XMM0 |
(271) 0x41b955 INC %RSI |
(271) 0x41b958 CMP %RSI,%RDX |
(271) 0x41b95b JNE 41b950 |
(262) 0x41b95d MOV 0xe8(%R13),%RAX |
(262) 0x41b964 VMOVSD %XMM0,(%RAX,%R12,8) |
(262) 0x41b96a MOV 0x188(%R13),%R8 |
(262) 0x41b971 TEST %EBX,%EBX |
(262) 0x41b973 JLE 41b830 |
(262) 0x41b979 MOV 0x110(%R13),%RDX |
(262) 0x41b980 MOV 0x128(%R13),%RCX |
(262) 0x41b987 MOV %RBX,%RAX |
(262) 0x41b98a AND $-0x4,%RAX |
(262) 0x41b98e JE 41b9e0 |
(262) 0x41b990 VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b994 XOR %ESI,%ESI |
(262) 0x41b996 NOPW %CS:(%RAX,%RAX,1) |
(270) 0x41b9a0 VADDPD (%RCX,%RSI,8),%YMM0,%YMM0 |
(270) 0x41b9a5 VFMADD231PD (%RDX,%RSI,8),%YMM1,%YMM0 |
(270) 0x41b9ab ADD $0x4,%RSI |
(270) 0x41b9af CMP %RAX,%RSI |
(270) 0x41b9b2 JL 41b9a0 |
(262) 0x41b9b4 VEXTRACTF128 $0x1,%YMM0,%XMM1 |
(262) 0x41b9ba VADDPD %XMM1,%XMM0,%XMM0 |
(262) 0x41b9be VPERMILPD $0x1,%XMM0,%XMM1 |
(262) 0x41b9c4 VADDSD %XMM1,%XMM0,%XMM0 |
(262) 0x41b9c8 MOV %RAX,%RDI |
(262) 0x41b9cb CMP %RBX,%RAX |
(262) 0x41b9ce JNE 41b9f0 |
(262) 0x41b9d0 JMP 41ba03 |
0x41b9d2 NOPW %CS:(%RAX,%RAX,1) |
(262) 0x41b9e0 VXORPD %XMM0,%XMM0,%XMM0 |
(262) 0x41b9e4 XOR %EDI,%EDI |
(262) 0x41b9e6 NOPW %CS:(%RAX,%RAX,1) |
(263) 0x41b9f0 VADDSD (%RCX,%RDI,8),%XMM0,%XMM0 |
(263) 0x41b9f5 VFMADD231SD (%RDX,%RDI,8),%XMM2,%XMM0 |
(263) 0x41b9fb INC %RDI |
(263) 0x41b9fe CMP %RDI,%RBX |
(263) 0x41ba01 JNE 41b9f0 |
(262) 0x41ba03 MOV 0x50(%R15),%R9 |
(262) 0x41ba07 LEA (%R12,%R12,4),%RCX |
(262) 0x41ba0b MOV 0x18(%R9,%RCX,8),%RDI |
(262) 0x41ba10 TEST %RAX,%RAX |
(262) 0x41ba13 JE 41ba60 |
(262) 0x41ba15 VXORPD %XMM1,%XMM1,%XMM1 |
(262) 0x41ba19 XOR %ESI,%ESI |
(262) 0x41ba1b NOPL (%RAX,%RAX,1) |
(269) 0x41ba20 VMOVUPD (%RDI,%RSI,8),%YMM2 |
(269) 0x41ba25 VFMADD231PD (%RDX,%RSI,8),%YMM2,%YMM1 |
(269) 0x41ba2b ADD $0x4,%RSI |
(269) 0x41ba2f CMP %RAX,%RSI |
(269) 0x41ba32 JL 41ba20 |
(262) 0x41ba34 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(262) 0x41ba3a VADDPD %XMM2,%XMM1,%XMM1 |
(262) 0x41ba3e VPERMILPD $0x1,%XMM1,%XMM2 |
(262) 0x41ba44 VADDSD %XMM2,%XMM1,%XMM1 |
(262) 0x41ba48 MOV %RAX,%RSI |
(262) 0x41ba4b CMP %RBX,%RAX |
(262) 0x41ba4e JNE 41ba70 |
(262) 0x41ba50 JMP 41ba83 |
0x41ba52 NOPW %CS:(%RAX,%RAX,1) |
(262) 0x41ba60 VXORPD %XMM1,%XMM1,%XMM1 |
(262) 0x41ba64 XOR %ESI,%ESI |
(262) 0x41ba66 NOPW %CS:(%RAX,%RAX,1) |
(264) 0x41ba70 VMOVSD (%RDI,%RSI,8),%XMM2 |
(264) 0x41ba75 VFMADD231SD (%RDX,%RSI,8),%XMM2,%XMM1 |
(264) 0x41ba7b INC %RSI |
(264) 0x41ba7e CMP %RSI,%RBX |
(264) 0x41ba81 JNE 41ba70 |
(262) 0x41ba83 MOV 0x8(%R9,%RCX,8),%R10 |
(262) 0x41ba88 LEA (%R12,%R12,2),%R9 |
(262) 0x41ba8c VMOVSD %XMM1,(%R8,%R9,8) |
(262) 0x41ba92 TEST %RAX,%RAX |
(262) 0x41ba95 JE 41baf0 |
(262) 0x41ba97 LEA (%RDI,%R10,8),%RSI |
(262) 0x41ba9b VXORPD %XMM1,%XMM1,%XMM1 |
(262) 0x41ba9f XOR %ECX,%ECX |
(262) 0x41baa1 NOPW %CS:(%RAX,%RAX,1) |
(268) 0x41bab0 VMOVUPD (%RSI,%RCX,8),%YMM2 |
(268) 0x41bab5 VFMADD231PD (%RDX,%RCX,8),%YMM2,%YMM1 |
(268) 0x41babb ADD $0x4,%RCX |
(268) 0x41babf CMP %RAX,%RCX |
(268) 0x41bac2 JL 41bab0 |
(262) 0x41bac4 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(262) 0x41baca VADDPD %XMM2,%XMM1,%XMM1 |
(262) 0x41bace VPERMILPD $0x1,%XMM1,%XMM2 |
(262) 0x41bad4 VADDSD %XMM2,%XMM1,%XMM1 |
(262) 0x41bad8 MOV %RAX,%RSI |
(262) 0x41badb CMP %RBX,%RAX |
(262) 0x41bade JNE 41baf6 |
(262) 0x41bae0 JMP 41bb13 |
0x41bae2 NOPW %CS:(%RAX,%RAX,1) |
(262) 0x41baf0 VXORPD %XMM1,%XMM1,%XMM1 |
(262) 0x41baf4 XOR %ESI,%ESI |
(262) 0x41baf6 LEA (%RDI,%R10,8),%RCX |
(262) 0x41bafa NOPW (%RAX,%RAX,1) |
(265) 0x41bb00 VMOVSD (%RCX,%RSI,8),%XMM2 |
(265) 0x41bb05 VFMADD231SD (%RDX,%RSI,8),%XMM2,%XMM1 |
(265) 0x41bb0b INC %RSI |
(265) 0x41bb0e CMP %RSI,%RBX |
(265) 0x41bb11 JNE 41bb00 |
(262) 0x41bb13 VMOVSD %XMM1,0x8(%R8,%R9,8) |
(262) 0x41bb1a TEST %RAX,%RAX |
(262) 0x41bb1d JE 41bb60 |
(262) 0x41bb1f MOV %R10,%RSI |
(262) 0x41bb22 SAL $0x4,%RSI |
(262) 0x41bb26 ADD %RDI,%RSI |
(262) 0x41bb29 VXORPD %XMM1,%XMM1,%XMM1 |
(262) 0x41bb2d XOR %ECX,%ECX |
(262) 0x41bb2f NOP |
(267) 0x41bb30 VMOVUPD (%RSI,%RCX,8),%YMM2 |
(267) 0x41bb35 VFMADD231PD (%RDX,%RCX,8),%YMM2,%YMM1 |
(267) 0x41bb3b ADD $0x4,%RCX |
(267) 0x41bb3f CMP %RAX,%RCX |
(267) 0x41bb42 JL 41bb30 |
(262) 0x41bb44 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
(262) 0x41bb4a VADDPD %XMM2,%XMM1,%XMM1 |
(262) 0x41bb4e VPERMILPD $0x1,%XMM1,%XMM2 |
(262) 0x41bb54 VADDSD %XMM2,%XMM1,%XMM1 |
(262) 0x41bb58 CMP %RBX,%RAX |
(262) 0x41bb5b JNE 41bb66 |
(262) 0x41bb5d JMP 41bb83 |
0x41bb5f NOP |
(262) 0x41bb60 VXORPD %XMM1,%XMM1,%XMM1 |
(262) 0x41bb64 XOR %EAX,%EAX |
(262) 0x41bb66 SAL $0x4,%R10 |
(262) 0x41bb6a ADD %R10,%RDI |
(262) 0x41bb6d NOPL (%RAX) |
(266) 0x41bb70 VMOVSD (%RDI,%RAX,8),%XMM2 |
(266) 0x41bb75 VFMADD231SD (%RDX,%RAX,8),%XMM2,%XMM1 |
(266) 0x41bb7b INC %RAX |
(266) 0x41bb7e CMP %RAX,%RBX |
(266) 0x41bb81 JNE 41bb70 |
(262) 0x41bb83 VMOVSD %XMM1,0x10(%R8,%R9,8) |
(262) 0x41bb8a JMP 41b84b |
0x41bb8f MOV -0x40(%RBP),%RCX |
0x41bb93 MOV -0x38(%RBP),%RDX |
0x41bb97 TEST %EAX,%EAX |
0x41bb99 JE 41bc31 |
0x41bb9f MOVSXD %EAX,%R8 |
0x41bba2 MOV 0x188(%R13),%RSI |
0x41bba9 MOV 0x18(%RDX),%RDI |
0x41bbad CMP $0x2,%R8 |
0x41bbb1 MOV $0x1,%R10D |
0x41bbb7 CMOVAE %R8,%R10 |
0x41bbbb LEA -0x1(%R10),%R9 |
0x41bbbf LEA -0x8(,%R10,8),%RAX |
0x41bbc7 LEA (%RAX,%RAX,2),%RAX |
0x41bbcb LEA (%RDI,%RAX,1),%RDX |
0x41bbcf ADD $0x10,%RDX |
0x41bbd3 CMP %RSI,%RDX |
0x41bbd6 JB 41bc3a |
0x41bbd8 ADD %RSI,%RAX |
0x41bbdb ADD $0x10,%RAX |
0x41bbdf CMP %RDI,%RAX |
0x41bbe2 JB 41bc3a |
0x41bbe4 XOR %EAX,%EAX |
0x41bbe6 NOPW %CS:(%RAX,%RAX,1) |
(261) 0x41bbf0 XOR %EDX,%EDX |
(261) 0x41bbf2 NOPW %CS:(%RAX,%RAX,1) |
(260) 0x41bc00 VMOVSD (%RDI,%RDX,8),%XMM0 |
(260) 0x41bc05 VADDSD (%RSI,%RDX,8),%XMM0,%XMM0 |
(260) 0x41bc0a VMOVSD %XMM0,(%RDI,%RDX,8) |
(260) 0x41bc0f INC %RDX |
(260) 0x41bc12 CMP $0x3,%RDX |
(260) 0x41bc16 JNE 41bc00 |
(261) 0x41bc18 LEA 0x1(%RAX),%RDX |
(261) 0x41bc1c ADD $0x18,%RSI |
(261) 0x41bc20 ADD $0x18,%RDI |
(261) 0x41bc24 CMP %R9,%RAX |
(261) 0x41bc27 MOV %RDX,%RAX |
(261) 0x41bc2a JNE 41bbf0 |
0x41bc2c JMP 41bce1 |
0x41bc31 VXORPD %XMM0,%XMM0,%XMM0 |
0x41bc35 JMP 41bdd9 |
0x41bc3a TEST %R9,%R9 |
0x41bc3d JE 41bd4a |
0x41bc43 MOV %R10,%RAX |
0x41bc46 AND $-0x2,%RAX |
0x41bc4a MOV $0x28,%EDX |
0x41bc4f XOR %EBX,%EBX |
0x41bc51 NOPW %CS:(%RAX,%RAX,1) |
(259) 0x41bc60 VMOVUPD -0x28(%RDI,%RDX,1),%XMM0 |
(259) 0x41bc66 VADDPD -0x28(%RSI,%RDX,1),%XMM0,%XMM0 |
(259) 0x41bc6c VMOVUPD %XMM0,-0x28(%RDI,%RDX,1) |
(259) 0x41bc72 VMOVSD -0x18(%RDI,%RDX,1),%XMM0 |
(259) 0x41bc78 VADDSD -0x18(%RSI,%RDX,1),%XMM0,%XMM0 |
(259) 0x41bc7e VMOVSD %XMM0,-0x18(%RDI,%RDX,1) |
(259) 0x41bc84 VMOVUPD -0x10(%RDI,%RDX,1),%XMM0 |
(259) 0x41bc8a VADDPD -0x10(%RSI,%RDX,1),%XMM0,%XMM0 |
(259) 0x41bc90 VMOVUPD %XMM0,-0x10(%RDI,%RDX,1) |
(259) 0x41bc96 VMOVSD (%RDI,%RDX,1),%XMM0 |
(259) 0x41bc9b VADDSD (%RSI,%RDX,1),%XMM0,%XMM0 |
(259) 0x41bca0 VMOVSD %XMM0,(%RDI,%RDX,1) |
(259) 0x41bca5 ADD $0x2,%RBX |
(259) 0x41bca9 ADD $0x30,%RDX |
(259) 0x41bcad CMP %RBX,%RAX |
(259) 0x41bcb0 JNE 41bc60 |
0x41bcb2 TEST $0x1,%R10B |
0x41bcb6 JE 41bce1 |
0x41bcb8 SAL $0x3,%RBX |
0x41bcbc LEA (%RBX,%RBX,2),%RAX |
0x41bcc0 VMOVUPD (%RDI,%RAX,1),%XMM0 |
0x41bcc5 VADDPD (%RSI,%RAX,1),%XMM0,%XMM0 |
0x41bcca VMOVUPD %XMM0,(%RDI,%RAX,1) |
0x41bccf VMOVSD 0x10(%RDI,%RAX,1),%XMM0 |
0x41bcd5 VADDSD 0x10(%RSI,%RAX,1),%XMM0,%XMM0 |
0x41bcdb VMOVSD %XMM0,0x10(%RDI,%RAX,1) |
0x41bce1 MOV 0x1b0(%R13),%RSI |
0x41bce8 MOV 0x18(%RCX),%RDI |
0x41bcec LEA (%RDI,%R9,8),%RCX |
0x41bcf0 CMP %RSI,%RCX |
0x41bcf3 JB 41bd19 |
0x41bcf5 LEA (%RSI,%R9,8),%RCX |
0x41bcf9 CMP %RDI,%RCX |
0x41bcfc JB 41bd19 |
0x41bcfe XOR %ECX,%ECX |
(258) 0x41bd00 VMOVSD (%RDI,%RCX,8),%XMM0 |
(258) 0x41bd05 VSUBSD (%RSI,%RCX,8),%XMM0,%XMM0 |
(258) 0x41bd0a VMOVSD %XMM0,(%RDI,%RCX,8) |
(258) 0x41bd0f INC %RCX |
(258) 0x41bd12 CMP %RCX,%R10 |
(258) 0x41bd15 JNE 41bd00 |
0x41bd17 JMP 41bd71 |
0x41bd19 MOV %R10,%RDX |
0x41bd1c AND $-0x4,%RDX |
0x41bd20 JE 41bd58 |
0x41bd22 LEA -0x1(%RDX),%RCX |
0x41bd26 XOR %EBX,%EBX |
0x41bd28 NOPL (%RAX,%RAX,1) |
(257) 0x41bd30 VMOVUPD (%RDI,%RBX,8),%YMM0 |
(257) 0x41bd35 VSUBPD (%RSI,%RBX,8),%YMM0,%YMM0 |
(257) 0x41bd3a VMOVUPD %YMM0,(%RDI,%RBX,8) |
(257) 0x41bd3f ADD $0x4,%RBX |
(257) 0x41bd43 CMP %RCX,%RBX |
(257) 0x41bd46 JBE 41bd30 |
0x41bd48 JMP 41bd6c |
0x41bd4a XOR %EBX,%EBX |
0x41bd4c TEST $0x1,%R10B |
0x41bd50 JNE 41bcb8 |
0x41bd56 JMP 41bce1 |
0x41bd58 XOR %EDX,%EDX |
(254) 0x41bd5a VMOVSD (%RDI,%RDX,8),%XMM0 |
(254) 0x41bd5f VSUBSD (%RSI,%RDX,8),%XMM0,%XMM0 |
(254) 0x41bd64 VMOVSD %XMM0,(%RDI,%RDX,8) |
(254) 0x41bd69 INC %RDX |
(254) 0x41bd6c CMP %RDX,%R10 |
(254) 0x41bd6f JNE 41bd5a |
0x41bd71 MOV 0xe8(%R13),%RCX |
0x41bd78 MOV $0x1fffffffffffffff,%RAX |
0x41bd82 ADD %RAX,%R8 |
0x41bd85 AND %RAX,%R8 |
0x41bd88 INC %R8 |
0x41bd8b AND %R8,%R14 |
0x41bd8e JE 41bdc4 |
0x41bd90 VXORPD %XMM0,%XMM0,%XMM0 |
0x41bd94 XOR %EAX,%EAX |
0x41bd96 NOPW %CS:(%RAX,%RAX,1) |
(256) 0x41bda0 VADDPD (%RCX,%RAX,8),%YMM0,%YMM0 |
(256) 0x41bda5 ADD $0x4,%RAX |
(256) 0x41bda9 CMP %R14,%RAX |
(256) 0x41bdac JB 41bda0 |
0x41bdae VEXTRACTF128 $0x1,%YMM0,%XMM1 |
0x41bdb4 VADDPD %XMM1,%XMM0,%XMM0 |
0x41bdb8 VPERMILPD $0x1,%XMM0,%XMM1 |
0x41bdbe VADDSD %XMM1,%XMM0,%XMM0 |
0x41bdc2 JMP 41bdd4 |
0x41bdc4 XOR %R14D,%R14D |
0x41bdc7 VXORPD %XMM0,%XMM0,%XMM0 |
(255) 0x41bdcb VADDSD (%RCX,%R14,8),%XMM0,%XMM0 |
(255) 0x41bdd1 INC %R14 |
(255) 0x41bdd4 CMP %R14,%R8 |
(255) 0x41bdd7 JNE 41bdcb |
0x41bdd9 VXORPD 0x7a29d(%RIP){1to2},%XMM0,%XMM0 |
0x41bde3 VMOVLPD %XMM0,0x10(%R13) |
0x41bde9 ADD $0x18,%RSP |
0x41bded POP %RBX |
0x41bdee POP %R12 |
0x41bdf0 POP %R13 |
0x41bdf2 POP %R14 |
0x41bdf4 POP %R15 |
0x41bdf6 POP %RBP |
0x41bdf7 VZEROUPPER |
0x41bdfa RET |
0x41bdfb NOPL (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | miniqmcreference::OneBodyJastr[...] | OneBodyJastrowRef.h:126 | exec |
○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:181 | exec |
○ | main.extracted.107 | miniqmc.cpp:375 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:374 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | OneBodyJastrowRef.h:112-198 |
Module | exec |
nb instructions | 125 |
nb uops | 128 |
loop length | 539 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 32.50 cycles |
front end | 32.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.00 | 16.00 | 12.17 | 11.83 | 12.00 | 16.00 | 16.00 | 12.00 |
cycles | 16.00 | 16.00 | 12.17 | 11.83 | 12.00 | 16.00 | 16.00 | 12.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 31.97 |
Stall cycles | 0.00 |
Front-end | 32.50 |
Dispatch | 16.00 |
Overall L1 | 32.50 |
all | 4% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 66% |
load | 60% |
store | 33% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 30% |
load | 50% |
store | 16% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
all | 11% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 20% |
load | 20% |
store | 16% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 15% |
load | 18% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x18,%RSP | 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 |
MOV %RDI,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x3ffffffffffffffc,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x98(%RDI),%EAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R8B,%R8B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bb97 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 41bb97 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa10(%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD 0x90(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R15 | 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 |
JMP 41b86b | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bc31 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %EAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x188(%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RDX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x2,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%R10D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVAE %R8,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA -0x1(%R10),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x8(,%R10,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RAX,%RAX,2),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RDI,%RAX,1),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x10,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RSI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bc3a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bc3a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EAX,%EAX | 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 |
JMP 41bce1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 41bdd9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
TEST %R9,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bd4a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x2,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x28,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EBX,%EBX | 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 |
TEST $0x1,%R10B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bce1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SAL $0x3,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%RBX,%RBX,2),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPD (%RDI,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDPD (%RSI,%RAX,1),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %XMM0,(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RDI,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x10(%RSI,%RAX,1),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,0x10(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x1b0(%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RCX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDI,%R9,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bd19 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RSI,%R9,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bd19 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 41bd71 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R10,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bd58 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RDX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 41bd6c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $0x1,%R10B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 41bcb8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 41bce1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xe8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x1fffffffffffffff,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND %R8,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bdc4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EAX,%EAX | 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 |
VEXTRACTF128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 41bdd4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %R14D,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD 0x7a29d(%RIP){1to2},%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VMOVLPD %XMM0,0x10(%R13) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x18,%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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | OneBodyJastrowRef.h:112-198 |
Module | exec |
nb instructions | 125 |
nb uops | 128 |
loop length | 539 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 32.50 cycles |
front end | 32.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.00 | 16.00 | 12.17 | 11.83 | 12.00 | 16.00 | 16.00 | 12.00 |
cycles | 16.00 | 16.00 | 12.17 | 11.83 | 12.00 | 16.00 | 16.00 | 12.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 31.97 |
Stall cycles | 0.00 |
Front-end | 32.50 |
Dispatch | 16.00 |
Overall L1 | 32.50 |
all | 4% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 66% |
load | 60% |
store | 33% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 30% |
load | 50% |
store | 16% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
all | 11% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 20% |
load | 20% |
store | 16% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 15% |
load | 18% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x18,%RSP | 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 |
MOV %RDI,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x3ffffffffffffffc,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x98(%RDI),%EAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R8B,%R8B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bb97 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 41bb97 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa10(%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD 0x90(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R15 | 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 |
JMP 41b86b | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bc31 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %EAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x188(%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RDX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x2,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x1,%R10D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVAE %R8,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA -0x1(%R10),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x8(,%R10,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RAX,%RAX,2),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RDI,%RAX,1),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x10,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RSI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bc3a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bc3a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EAX,%EAX | 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 |
JMP 41bce1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 41bdd9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
TEST %R9,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bd4a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x2,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x28,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EBX,%EBX | 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 |
TEST $0x1,%R10B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bce1 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SAL $0x3,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%RBX,%RBX,2),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPD (%RDI,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDPD (%RSI,%RAX,1),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %XMM0,(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD 0x10(%RDI,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD 0x10(%RSI,%RAX,1),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM0,0x10(%RDI,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x1b0(%R13),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RCX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDI,%R9,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bd19 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RSI,%R9,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 41bd19 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 41bd71 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R10,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bd58 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RDX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 41bd6c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $0x1,%R10B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 41bcb8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 41bce1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xe8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x1fffffffffffffff,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
INC %R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND %R8,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 41bdc4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EAX,%EAX | 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 |
VEXTRACTF128 $0x1,%YMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM1,%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
JMP 41bdd4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %R14D,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD 0x7a29d(%RIP){1to2},%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VMOVLPD %XMM0,0x10(%R13) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x18,%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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::OneBodyJastrowRef | 0.01 | 0.01 |
▼Loop 261 - OneBodyJastrowRef.h:173-173 - exec– | 0 | 0 |
○Loop 260 - TinyVectorOps.h:49-49 - exec | 0 | 0 |
○Loop 255 - OneBodyJastrowRef.h:0-0 - exec | 0 | 0 |
○Loop 258 - OneBodyJastrowRef.h:175-176 - exec | 0 | 0 |
○Loop 257 - OneBodyJastrowRef.h:175-176 - exec | 0 | 0 |
○Loop 256 - stl_numeric.h:140-141 - exec | 0 | 0 |
▼Loop 262 - OneBodyJastrowRef.h:113-198 - exec– | 0 | 0 |
○Loop 269 - OneBodyJastrowRef.h:196-197 - exec | 0.01 | 0.01 |
○Loop 270 - OneBodyJastrowRef.h:190-191 - exec | 0 | 0 |
○Loop 264 - OneBodyJastrowRef.h:196-197 - exec | 0 | 0 |
○Loop 268 - OneBodyJastrowRef.h:196-197 - exec | 0 | 0 |
○Loop 271 - stl_numeric.h:140-141 - exec | 0 | 0 |
○Loop 272 - stl_numeric.h:140-141 - exec | 0 | 0 |
○Loop 265 - OneBodyJastrowRef.h:196-197 - exec | 0 | 0 |
○Loop 263 - OneBodyJastrowRef.h:190-191 - exec | 0 | 0 |
○Loop 267 - OneBodyJastrowRef.h:196-197 - exec | 0 | 0 |
○Loop 266 - OneBodyJastrowRef.h:196-197 - exec | 0 | 0 |
○Loop 259 - OneBodyJastrowRef.h:173-173 - exec | 0 | 0 |
○Loop 254 - OneBodyJastrowRef.h:175-176 - exec | 0 | 0 |