Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratio(qmcpluspl ... | Module: exec | Source: OneBodyJastrowRef.h:129-159 [...] | Coverage: 0.01% |
---|
Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratio(qmcpluspl ... | Module: exec | Source: OneBodyJastrowRef.h:129-159 [...] | Coverage: 0.01% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 164 - 182 |
-------------------------------------------------------------------------------- |
164: inline real_type evaluate(real_type r) |
165: { |
166: if (r >= cutoff_radius) |
167: return 0.0; |
168: r *= DeltaRInv; |
169: real_type ipart, t; |
170: t = std::modf(r, &ipart); |
171: int i = (int)ipart; |
172: real_type tp[4]; |
173: tp[0] = t * t * t; |
[...] |
179: (SplineCoefs[i+0]*(A[ 0]*tp[0] + A[ 1]*tp[1] + A[ 2]*tp[2] + A[ 3]*tp[3])+ |
180: SplineCoefs[i+1]*(A[ 4]*tp[0] + A[ 5]*tp[1] + A[ 6]*tp[2] + A[ 7]*tp[3])+ |
181: SplineCoefs[i+2]*(A[ 8]*tp[0] + A[ 9]*tp[1] + A[10]*tp[2] + A[11]*tp[3])+ |
182: SplineCoefs[i+3]*(A[12]*tp[0] + A[13]*tp[1] + A[14]*tp[2] + A[15]*tp[3])); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229 |
-------------------------------------------------------------------------------- |
229: return X[i]; |
/usr/include/c++/13.1.1/bits/stl_vector.h: 1123 - 1258 |
-------------------------------------------------------------------------------- |
1123: operator[](size_type __n) _GLIBCXX_NOEXCEPT |
1124: { |
1125: __glibcxx_requires_subscript(__n); |
1126: return *(this->_M_impl._M_start + __n); |
[...] |
1258: { return _M_data_ptr(this->_M_impl._M_start); } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 129 - 159 |
-------------------------------------------------------------------------------- |
129: ValueType ratio(ParticleSet& P, int iat) |
130: { |
131: UpdateMode = ORB_PBYP_RATIO; |
132: curAt = computeU(P.DistTables[myTableID]->Temp_r.data()); |
133: return std::exp(Vat[iat] - curAt); |
134: } |
[...] |
144: valT curVat(0); |
145: if (NumGroups > 0) |
146: { |
147: for (int jg = 0; jg < NumGroups; ++jg) |
148: { |
149: if (F[jg] != nullptr) |
150: curVat += F[jg]->evaluateV(-1, Ions.first(jg), Ions.last(jg), dist, DistCompressed.data()); |
151: } |
152: } |
153: else |
154: { |
155: for (int c = 0; c < Nions; ++c) |
156: { |
157: int gid = Ions.GroupID[c]; |
158: if (F[gid] != nullptr) |
159: curVat += F[gid]->evaluate(dist[c]); |
0x44e6f0 PUSH %RBP |
0x44e6f1 MOV %RSP,%RBP |
0x44e6f4 PUSH %R15 |
0x44e6f6 PUSH %R14 |
0x44e6f8 PUSH %R13 |
0x44e6fa MOVSXD %EDX,%R13 |
0x44e6fd PUSH %R12 |
0x44e6ff PUSH %RBX |
0x44e700 MOV %RDI,%RBX |
0x44e703 SUB $0x48,%RSP |
0x44e707 MOV %FS:0x28,%RAX |
0x44e710 MOV %RAX,-0x38(%RBP) |
0x44e714 XOR %EAX,%EAX |
0x44e716 MOVSXD 0x90(%RDI),%RDX |
0x44e71d MOV 0xa10(%RSI),%RAX |
0x44e724 MOVL $0,0xc(%RDI) |
0x44e72b MOVSXD 0x9c(%RDI),%R12 |
0x44e732 MOV (%RAX,%RDX,8),%RCX |
0x44e736 MOV 0x68(%RCX),%R8 |
0x44e73a TEST %R12D,%R12D |
0x44e73d JLE 44e9d0 |
0x44e743 SAL $0x2,%R12 |
0x44e747 MOV 0x1c0(%RDI),%R14 |
0x44e74e XOR %R15D,%R15D |
0x44e751 VXORPD %XMM7,%XMM7,%XMM7 |
0x44e755 LEA -0x4(%R12),%RDI |
0x44e75a SHR $0x2,%RDI |
0x44e75e INC %RDI |
0x44e761 AND $0x3,%EDI |
0x44e764 JE 44e859 |
0x44e76a CMP $0x1,%RDI |
0x44e76e JE 44e805 |
0x44e774 CMP $0x2,%RDI |
0x44e778 JE 44e7ba |
0x44e77a MOV (%R14),%RDI |
0x44e77d TEST %RDI,%RDI |
0x44e780 JE 44e7b4 |
0x44e782 MOV 0xa0(%RBX),%R9 |
0x44e789 MOV $-0x1,%ESI |
0x44e78e MOV %R8,-0x48(%RBP) |
0x44e792 MOV 0xa98(%R9),%R10 |
0x44e799 MOV 0x140(%RBX),%R9 |
0x44e7a0 MOV 0x4(%R10),%ECX |
0x44e7a4 MOV (%R10),%EDX |
0x44e7a7 CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
0x44e7ac MOV -0x48(%RBP),%R8 |
0x44e7b0 VMOVSD %XMM0,%XMM0,%XMM7 |
0x44e7b4 MOV $0x4,%R15D |
0x44e7ba MOV (%R14,%R15,2),%RDI |
0x44e7be TEST %RDI,%RDI |
0x44e7c1 JE 44e801 |
0x44e7c3 MOV 0xa0(%RBX),%R11 |
0x44e7ca MOV 0x140(%RBX),%R9 |
0x44e7d1 MOV $-0x1,%ESI |
0x44e7d6 MOV %R8,-0x48(%RBP) |
0x44e7da VMOVSD %XMM7,-0x50(%RBP) |
0x44e7df MOV 0xa98(%R11),%RDX |
0x44e7e6 MOV 0x4(%RDX,%R15,1),%ECX |
0x44e7eb MOV (%RDX,%R15,1),%EDX |
0x44e7ef CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
0x44e7f4 VMOVSD -0x50(%RBP),%XMM5 |
0x44e7f9 MOV -0x48(%RBP),%R8 |
0x44e7fd VADDSD %XMM0,%XMM5,%XMM7 |
0x44e801 ADD $0x4,%R15 |
0x44e805 MOV (%R14,%R15,2),%RDI |
0x44e809 TEST %RDI,%RDI |
0x44e80c JE 44e84c |
0x44e80e MOV 0xa0(%RBX),%RAX |
0x44e815 MOV 0x140(%RBX),%R9 |
0x44e81c MOV %R8,-0x48(%RBP) |
0x44e820 VMOVSD %XMM7,-0x50(%RBP) |
0x44e825 MOV 0xa98(%RAX),%RSI |
0x44e82c MOV 0x4(%RSI,%R15,1),%ECX |
0x44e831 MOV (%RSI,%R15,1),%EDX |
0x44e835 MOV $-0x1,%ESI |
0x44e83a CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
0x44e83f VMOVSD -0x50(%RBP),%XMM9 |
0x44e844 MOV -0x48(%RBP),%R8 |
0x44e848 VADDSD %XMM0,%XMM9,%XMM7 |
0x44e84c ADD $0x4,%R15 |
0x44e850 CMP %R15,%R12 |
0x44e853 JE 44e98d |
0x44e859 MOV %R12,-0x50(%RBP) |
0x44e85d MOV %R15,%R10 |
0x44e860 MOV %R8,%R15 |
0x44e863 VMOVSD %XMM7,-0x48(%RBP) |
(647) 0x44e868 MOV (%R14,%R10,2),%RDI |
(647) 0x44e86c TEST %RDI,%RDI |
(647) 0x44e86f JE 44e8ae |
(647) 0x44e871 MOV 0xa0(%RBX),%R8 |
(647) 0x44e878 MOV 0x140(%RBX),%R9 |
(647) 0x44e87f MOV $-0x1,%ESI |
(647) 0x44e884 MOV %R10,-0x58(%RBP) |
(647) 0x44e888 MOV 0xa98(%R8),%R12 |
(647) 0x44e88f MOV %R15,%R8 |
(647) 0x44e892 MOV 0x4(%R12,%R10,1),%ECX |
(647) 0x44e897 MOV (%R12,%R10,1),%EDX |
(647) 0x44e89b CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
(647) 0x44e8a0 MOV -0x58(%RBP),%R10 |
(647) 0x44e8a4 VADDSD -0x48(%RBP),%XMM0,%XMM10 |
(647) 0x44e8a9 VMOVSD %XMM10,-0x48(%RBP) |
(647) 0x44e8ae LEA 0x4(%R10),%R12 |
(647) 0x44e8b2 MOV (%R14,%R12,2),%RDI |
(647) 0x44e8b6 TEST %RDI,%RDI |
(647) 0x44e8b9 JE 44e8f1 |
(647) 0x44e8bb MOV 0xa0(%RBX),%RCX |
(647) 0x44e8c2 MOV %R15,%R8 |
(647) 0x44e8c5 MOV $-0x1,%ESI |
(647) 0x44e8ca MOV 0xa98(%RCX),%R9 |
(647) 0x44e8d1 MOV 0x4(%R9,%R12,1),%ECX |
(647) 0x44e8d6 MOV 0x4(%R9,%R10,1),%EDX |
(647) 0x44e8db MOV 0x140(%RBX),%R9 |
(647) 0x44e8e2 CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
(647) 0x44e8e7 VADDSD -0x48(%RBP),%XMM0,%XMM11 |
(647) 0x44e8ec VMOVSD %XMM11,-0x48(%RBP) |
(647) 0x44e8f1 LEA 0x4(%R12),%RDI |
(647) 0x44e8f6 MOV (%R14,%RDI,2),%RDI |
(647) 0x44e8fa TEST %RDI,%RDI |
(647) 0x44e8fd JE 44e935 |
(647) 0x44e8ff MOV 0xa0(%RBX),%R10 |
(647) 0x44e906 MOV 0x140(%RBX),%R9 |
(647) 0x44e90d MOV %R15,%R8 |
(647) 0x44e910 MOV $-0x1,%ESI |
(647) 0x44e915 MOV 0xa98(%R10),%R11 |
(647) 0x44e91c MOV 0x8(%R11,%R12,1),%ECX |
(647) 0x44e921 MOV 0x4(%R11,%R12,1),%EDX |
(647) 0x44e926 CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
(647) 0x44e92b VADDSD -0x48(%RBP),%XMM0,%XMM12 |
(647) 0x44e930 VMOVSD %XMM12,-0x48(%RBP) |
(647) 0x44e935 LEA 0x8(%R12),%RDX |
(647) 0x44e93a MOV (%R14,%RDX,2),%RDI |
(647) 0x44e93e TEST %RDI,%RDI |
(647) 0x44e941 JE 44e979 |
(647) 0x44e943 MOV 0xa0(%RBX),%RAX |
(647) 0x44e94a MOV 0x140(%RBX),%R9 |
(647) 0x44e951 MOV %R15,%R8 |
(647) 0x44e954 MOV 0xa98(%RAX),%RSI |
(647) 0x44e95b MOV 0xc(%RSI,%R12,1),%ECX |
(647) 0x44e960 MOV 0x8(%RSI,%R12,1),%EDX |
(647) 0x44e965 MOV $-0x1,%ESI |
(647) 0x44e96a CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
(647) 0x44e96f VADDSD -0x48(%RBP),%XMM0,%XMM13 |
(647) 0x44e974 VMOVSD %XMM13,-0x48(%RBP) |
(647) 0x44e979 LEA 0xc(%R12),%R10 |
(647) 0x44e97e CMP %R10,-0x50(%RBP) |
(647) 0x44e982 JNE 44e868 |
0x44e988 VMOVSD -0x48(%RBP),%XMM7 |
0x44e98d VMOVSD %XMM7,0xa8(%RBX) |
0x44e995 MOV -0x38(%RBP),%RAX |
0x44e999 SUB %FS:0x28,%RAX |
0x44e9a2 JNE 44ed94 |
0x44e9a8 MOV 0xe8(%RBX),%RBX |
0x44e9af VMOVSD (%RBX,%R13,8),%XMM14 |
0x44e9b5 ADD $0x48,%RSP |
0x44e9b9 POP %RBX |
0x44e9ba POP %R12 |
0x44e9bc VSUBSD %XMM7,%XMM14,%XMM0 |
0x44e9c0 POP %R13 |
0x44e9c2 POP %R14 |
0x44e9c4 POP %R15 |
0x44e9c6 POP %RBP |
0x44e9c7 JMP 4040a0 |
0x44e9cc NOPL (%RAX) |
0x44e9d0 MOV 0x94(%RDI),%ESI |
0x44e9d6 VXORPD %XMM7,%XMM7,%XMM7 |
0x44e9da TEST %ESI,%ESI |
0x44e9dc JLE 44e98d |
0x44e9de MOV 0x1c0(%RDI),%R14 |
0x44e9e5 MOV 0xa0(%RDI),%RDI |
0x44e9ec MOVSXD %ESI,%R9 |
0x44e9ef LEA -0x40(%RBP),%R10 |
0x44e9f3 MOV %R10,-0x48(%RBP) |
0x44e9f7 VXORPD %XMM7,%XMM7,%XMM7 |
0x44e9fb MOV 0x5c0(%RDI),%R15 |
0x44ea02 MOV %R8,%RDI |
0x44ea05 LEA (%R15,%R9,4),%RSI |
0x44ea09 AND $0x1,%R9D |
0x44ea0d JNE 44ec70 |
0x44ea13 MOV %RBX,-0x68(%RBP) |
0x44ea17 MOV %R14,%RBX |
0x44ea1a MOV %RSI,%R14 |
0x44ea1d MOV %R13D,-0x6c(%RBP) |
0x44ea21 MOV %RDI,%R13 |
(646) 0x44ea24 MOVSXD (%R15),%R9 |
(646) 0x44ea27 MOV (%RBX,%R9,8),%R12 |
(646) 0x44ea2b TEST %R12,%R12 |
(646) 0x44ea2e JE 44eb2a |
(646) 0x44ea34 VMOVSD (%R13),%XMM2 |
(646) 0x44ea3a VCOMISD 0x8(%R12),%XMM2 |
(646) 0x44ea41 JAE 44eb2a |
(646) 0x44ea47 VMULSD 0x238(%R12),%XMM2,%XMM0 |
(646) 0x44ea51 MOV -0x48(%RBP),%RDI |
(646) 0x44ea55 VMOVSD %XMM7,-0x50(%RBP) |
(646) 0x44ea5a CALL 4042f0 <modf@plt> |
(646) 0x44ea5f VMOVSD 0x28(%R12),%XMM6 |
(646) 0x44ea66 VMOVSD 0x48(%R12),%XMM5 |
(646) 0x44ea6d VMULSD %XMM0,%XMM0,%XMM3 |
(646) 0x44ea71 VMOVSD 0x68(%R12),%XMM12 |
(646) 0x44ea78 VMOVSD 0x90(%R12),%XMM15 |
(646) 0x44ea82 VFMADD213SD 0x30(%R12),%XMM0,%XMM6 |
(646) 0x44ea89 VFMADD213SD 0x50(%R12),%XMM0,%XMM5 |
(646) 0x44ea90 VFMADD213SD 0x70(%R12),%XMM0,%XMM12 |
(646) 0x44ea97 VCVTTSD2SI -0x40(%RBP),%R11D |
(646) 0x44ea9c MOV 0x218(%R12),%R10 |
(646) 0x44eaa4 VMULSD %XMM3,%XMM0,%XMM4 |
(646) 0x44eaa8 VFMADD132SD 0x88(%R12),%XMM15,%XMM0 |
(646) 0x44eab2 VMULSD 0x20(%R12),%XMM3,%XMM1 |
(646) 0x44eab9 MOVSXD %R11D,%R8 |
(646) 0x44eabc VMULSD 0x40(%R12),%XMM3,%XMM7 |
(646) 0x44eac3 VMULSD 0x60(%R12),%XMM3,%XMM11 |
(646) 0x44eaca VMULSD 0x80(%R12),%XMM3,%XMM14 |
(646) 0x44ead4 VFMADD231SD 0x18(%R12),%XMM4,%XMM1 |
(646) 0x44eadb VFMADD231SD 0x38(%R12),%XMM4,%XMM7 |
(646) 0x44eae2 VFMADD231SD 0x58(%R12),%XMM4,%XMM11 |
(646) 0x44eae9 VFMADD132SD 0x78(%R12),%XMM14,%XMM4 |
(646) 0x44eaf0 VADDSD %XMM1,%XMM6,%XMM8 |
(646) 0x44eaf4 VADDSD %XMM7,%XMM5,%XMM9 |
(646) 0x44eaf8 VADDSD %XMM11,%XMM12,%XMM13 |
(646) 0x44eafd VADDSD %XMM4,%XMM0,%XMM0 |
(646) 0x44eb01 VMOVSD -0x50(%RBP),%XMM4 |
(646) 0x44eb06 VMULSD 0x8(%R10,%R8,8),%XMM9,%XMM10 |
(646) 0x44eb0d VMULSD 0x18(%R10,%R8,8),%XMM0,%XMM2 |
(646) 0x44eb14 VFMADD132SD (%R10,%R8,8),%XMM10,%XMM8 |
(646) 0x44eb1a VFMADD132SD 0x10(%R10,%R8,8),%XMM2,%XMM13 |
(646) 0x44eb21 VADDSD %XMM13,%XMM8,%XMM3 |
(646) 0x44eb26 VADDSD %XMM3,%XMM4,%XMM7 |
(646) 0x44eb2a LEA 0x4(%R15),%RSI |
(646) 0x44eb2e MOVSXD 0x4(%R15),%R15 |
(646) 0x44eb32 LEA 0x8(%R13),%RCX |
(646) 0x44eb36 MOV (%RBX,%R15,8),%R12 |
(646) 0x44eb3a TEST %R12,%R12 |
(646) 0x44eb3d JE 44ec4c |
(646) 0x44eb43 VMOVSD 0x8(%R13),%XMM6 |
(646) 0x44eb49 VCOMISD 0x8(%R12),%XMM6 |
(646) 0x44eb50 JAE 44ec4c |
(646) 0x44eb56 VMULSD 0x238(%R12),%XMM6,%XMM0 |
(646) 0x44eb60 MOV -0x48(%RBP),%RDI |
(646) 0x44eb64 MOV %RCX,-0x58(%RBP) |
(646) 0x44eb68 MOV %RSI,-0x50(%RBP) |
(646) 0x44eb6c VMOVSD %XMM7,-0x60(%RBP) |
(646) 0x44eb71 CALL 4042f0 <modf@plt> |
(646) 0x44eb76 VMOVSD 0x28(%R12),%XMM5 |
(646) 0x44eb7d VMOVSD 0x48(%R12),%XMM11 |
(646) 0x44eb84 VMULSD %XMM0,%XMM0,%XMM1 |
(646) 0x44eb88 VMOVSD 0x68(%R12),%XMM15 |
(646) 0x44eb8f VMOVSD 0x90(%R12),%XMM4 |
(646) 0x44eb99 VFMADD213SD 0x30(%R12),%XMM0,%XMM5 |
(646) 0x44eba0 VFMADD213SD 0x50(%R12),%XMM0,%XMM11 |
(646) 0x44eba7 VFMADD213SD 0x70(%R12),%XMM0,%XMM15 |
(646) 0x44ebae VCVTTSD2SI -0x40(%RBP),%EDX |
(646) 0x44ebb3 MOV 0x218(%R12),%R13 |
(646) 0x44ebbb MOV -0x58(%RBP),%RCX |
(646) 0x44ebbf MOV -0x50(%RBP),%RSI |
(646) 0x44ebc3 VMULSD %XMM1,%XMM0,%XMM8 |
(646) 0x44ebc7 VFMADD132SD 0x88(%R12),%XMM4,%XMM0 |
(646) 0x44ebd1 VMULSD 0x20(%R12),%XMM1,%XMM7 |
(646) 0x44ebd8 MOVSXD %EDX,%RAX |
(646) 0x44ebdb VMULSD 0x40(%R12),%XMM1,%XMM10 |
(646) 0x44ebe2 VMULSD 0x60(%R12),%XMM1,%XMM14 |
(646) 0x44ebe9 VMULSD 0x80(%R12),%XMM1,%XMM3 |
(646) 0x44ebf3 VMOVSD -0x60(%RBP),%XMM1 |
(646) 0x44ebf8 VFMADD231SD 0x18(%R12),%XMM8,%XMM7 |
(646) 0x44ebff VFMADD231SD 0x38(%R12),%XMM8,%XMM10 |
(646) 0x44ec06 VFMADD231SD 0x58(%R12),%XMM8,%XMM14 |
(646) 0x44ec0d VFMADD132SD 0x78(%R12),%XMM3,%XMM8 |
(646) 0x44ec14 VADDSD %XMM7,%XMM5,%XMM9 |
(646) 0x44ec18 VADDSD %XMM10,%XMM11,%XMM12 |
(646) 0x44ec1d VADDSD %XMM14,%XMM15,%XMM2 |
(646) 0x44ec22 VADDSD %XMM8,%XMM0,%XMM0 |
(646) 0x44ec27 VMULSD 0x8(%R13,%RAX,8),%XMM12,%XMM13 |
(646) 0x44ec2e VMULSD 0x18(%R13,%RAX,8),%XMM0,%XMM6 |
(646) 0x44ec35 VFMADD132SD (%R13,%RAX,8),%XMM13,%XMM9 |
(646) 0x44ec3c VFMADD132SD 0x10(%R13,%RAX,8),%XMM6,%XMM2 |
(646) 0x44ec43 VADDSD %XMM2,%XMM9,%XMM8 |
(646) 0x44ec47 VADDSD %XMM8,%XMM1,%XMM7 |
(646) 0x44ec4c LEA 0x4(%RSI),%R15 |
(646) 0x44ec50 LEA 0x8(%RCX),%R13 |
(646) 0x44ec54 CMP %R15,%R14 |
(646) 0x44ec57 JNE 44ea24 |
0x44ec5d MOV -0x68(%RBP),%RBX |
0x44ec61 MOVSXD -0x6c(%RBP),%R13 |
0x44ec65 JMP 44e98d |
0x44ec6a NOPW (%RAX,%RAX,1) |
0x44ec70 MOVSXD (%R15),%R11 |
0x44ec73 MOV (%R14,%R11,8),%R12 |
0x44ec77 TEST %R12,%R12 |
0x44ec7a JE 44ed7e |
0x44ec80 VMOVSD (%R8),%XMM0 |
0x44ec85 VCOMISD 0x8(%R12),%XMM0 |
0x44ec8c JAE 44ed7e |
0x44ec92 VMULSD 0x238(%R12),%XMM0,%XMM0 |
0x44ec9c MOV -0x48(%RBP),%RDI |
0x44eca0 MOV %RSI,-0x58(%RBP) |
0x44eca4 MOV %R8,-0x50(%RBP) |
0x44eca8 CALL 4042f0 <modf@plt> |
0x44ecad VMOVSD 0x28(%R12),%XMM1 |
0x44ecb4 VMOVSD 0x48(%R12),%XMM7 |
0x44ecbb VMULSD %XMM0,%XMM0,%XMM2 |
0x44ecbf VMOVSD 0x68(%R12),%XMM11 |
0x44ecc6 VMOVSD 0x90(%R12),%XMM14 |
0x44ecd0 VFMADD213SD 0x50(%R12),%XMM0,%XMM7 |
0x44ecd7 VFMADD213SD 0x30(%R12),%XMM0,%XMM1 |
0x44ecde VFMADD213SD 0x70(%R12),%XMM0,%XMM11 |
0x44ece5 VCVTTSD2SI -0x40(%RBP),%EDX |
0x44ecea MOV 0x218(%R12),%R8 |
0x44ecf2 MOV -0x58(%RBP),%RSI |
0x44ecf6 VMULSD %XMM2,%XMM0,%XMM3 |
0x44ecfa VFMADD132SD 0x88(%R12),%XMM14,%XMM0 |
0x44ed04 VMULSD 0x20(%R12),%XMM2,%XMM4 |
0x44ed0b MOVSXD %EDX,%RAX |
0x44ed0e VMULSD 0x40(%R12),%XMM2,%XMM5 |
0x44ed15 LEA (,%RAX,8),%RCX |
0x44ed1d VMULSD 0x60(%R12),%XMM2,%XMM10 |
0x44ed24 VMULSD 0x80(%R12),%XMM2,%XMM13 |
0x44ed2e VFMADD231SD 0x18(%R12),%XMM3,%XMM4 |
0x44ed35 VFMADD231SD 0x38(%R12),%XMM3,%XMM5 |
0x44ed3c VFMADD231SD 0x58(%R12),%XMM3,%XMM10 |
0x44ed43 VFMADD132SD 0x78(%R12),%XMM13,%XMM3 |
0x44ed4a VADDSD %XMM4,%XMM1,%XMM6 |
0x44ed4e VADDSD %XMM5,%XMM7,%XMM8 |
0x44ed52 VADDSD %XMM10,%XMM11,%XMM12 |
0x44ed57 VADDSD %XMM3,%XMM0,%XMM15 |
0x44ed5b VMULSD 0x8(%R8,%RAX,8),%XMM8,%XMM9 |
0x44ed62 VMULSD 0x18(%R8,%RCX,1),%XMM15,%XMM0 |
0x44ed69 VFMADD132SD (%R8,%RCX,1),%XMM9,%XMM6 |
0x44ed6f VFMADD231SD 0x10(%R8,%RCX,1),%XMM12,%XMM0 |
0x44ed76 MOV -0x50(%RBP),%R8 |
0x44ed7a VADDSD %XMM0,%XMM6,%XMM7 |
0x44ed7e ADD $0x4,%R15 |
0x44ed82 LEA 0x8(%R8),%RDI |
0x44ed86 CMP %R15,%RSI |
0x44ed89 JNE 44ea13 |
0x44ed8f JMP 44e98d |
0x44ed94 CALL 404140 <__stack_chk_fail@plt> |
0x44ed99 NOPL (%RAX) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►50.00+ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:219 | exec |
○ | main._omp_fn.1 | stl_vector.h:1126 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►50.00+ | main._omp_fn.1 | stl_vector.h:1123 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | OneBodyJastrowRef.h:129-159 |
Module | exec |
nb instructions | 179 |
nb uops | 186 |
loop length | 855 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
ADD-SUB / MUL ratio | 0.89 |
micro-operation queue | 47.50 cycles |
front end | 47.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 21.50 | 21.50 | 38.50 | 38.50 | 26.00 | 21.50 | 21.50 | 26.00 |
cycles | 21.50 | 21.50 | 38.50 | 38.50 | 26.00 | 21.50 | 21.50 | 26.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 48.92 |
Stall cycles | 2.23 |
LB full (events) | 1.47 |
LM full (events) | 2.98 |
Front-end | 47.50 |
Dispatch | 38.50 |
Overall L1 | 47.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 6% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 4% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 20% |
all | 11% |
load | NA (no load vectorizable/vectorized instructions) |
store | 11% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 13% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
all | 12% |
load | 12% |
store | 11% |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
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 |
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 $0x48,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 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 |
MOVSXD 0x90(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa10(%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVL $0,0xc(%RDI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOVSXD 0x9c(%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x68(%RCX),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R12D,%R12D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 44e9d0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SAL $0x2,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV 0x1c0(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R15D,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x4(%R12),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e859 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e805 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e7ba | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV (%R14),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e7b4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $-0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa98(%R9),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%R10),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R10),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,%XMM0,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV $0x4,%R15D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%R14,%R15,2),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e801 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $-0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM7,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa98(%R11),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%RDX,%R15,1),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%R15,1),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD -0x50(%RBP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD %XMM0,%XMM5,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%R14,%R15,2),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e84c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM7,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa98(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%RSI,%R15,1),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%R15,1),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $-0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD -0x50(%RBP),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD %XMM0,%XMM9,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R15,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e98d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R12,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD %XMM7,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD -0x48(%RBP),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM7,0xa8(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
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 44ed94 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xe8(%RBX),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RBX,%R13,8),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x48,%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 |
VSUBSD %XMM7,%XMM14,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 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 |
JMP 4040a0 | 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 |
MOV 0x94(%RDI),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST %ESI,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 44e98d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x1c0(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa0(%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %ESI,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x40(%RBP),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R10,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x5c0(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (%R15,%R9,4),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
AND $0x1,%R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44ec70 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R13D,-0x6c(%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 -0x68(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD -0x6c(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 44e98d | 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 |
MOVSXD (%R15),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R14,%R11,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R12,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44ed7e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%R8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD 0x8(%R12),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JAE 44ed7e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMULSD 0x238(%R12),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 4042f0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x28(%R12),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x48(%R12),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD %XMM0,%XMM0,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD 0x68(%R12),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x90(%R12),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD 0x50(%R12),%XMM0,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213SD 0x30(%R12),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213SD 0x70(%R12),%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCVTTSD2SI -0x40(%RBP),%EDX | 2 | 1.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 6 | 1 |
MOV 0x218(%R12),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD %XMM2,%XMM0,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD 0x88(%R12),%XMM14,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x20(%R12),%XMM2,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOVSXD %EDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMULSD 0x40(%R12),%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
LEA (,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMULSD 0x60(%R12),%XMM2,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x80(%R12),%XMM2,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x18(%R12),%XMM3,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x38(%R12),%XMM3,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x58(%R12),%XMM3,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD 0x78(%R12),%XMM13,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM4,%XMM1,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM5,%XMM7,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM10,%XMM11,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM3,%XMM0,%XMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x8(%R8,%RAX,8),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x18(%R8,%RCX,1),%XMM15,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD (%R8,%RCX,1),%XMM9,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x10(%R8,%RCX,1),%XMM12,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV -0x50(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD %XMM0,%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x8(%R8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44ea13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 44e98d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CALL 404140 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | OneBodyJastrowRef.h:129-159 |
Module | exec |
nb instructions | 179 |
nb uops | 186 |
loop length | 855 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
ADD-SUB / MUL ratio | 0.89 |
micro-operation queue | 47.50 cycles |
front end | 47.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 21.50 | 21.50 | 38.50 | 38.50 | 26.00 | 21.50 | 21.50 | 26.00 |
cycles | 21.50 | 21.50 | 38.50 | 38.50 | 26.00 | 21.50 | 21.50 | 26.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 48.92 |
Stall cycles | 2.23 |
LB full (events) | 1.47 |
LM full (events) | 2.98 |
Front-end | 47.50 |
Dispatch | 38.50 |
Overall L1 | 47.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 6% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 4% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 20% |
all | 11% |
load | NA (no load vectorizable/vectorized instructions) |
store | 11% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 13% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
all | 12% |
load | 12% |
store | 11% |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
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 |
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 $0x48,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 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 |
MOVSXD 0x90(%RDI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa10(%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVL $0,0xc(%RDI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOVSXD 0x9c(%RDI),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x68(%RCX),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R12D,%R12D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 44e9d0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SAL $0x2,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV 0x1c0(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R15D,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x4(%R12),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e859 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e805 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e7ba | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV (%R14),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e7b4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $-0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa98(%R9),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%R10),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R10),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,%XMM0,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV $0x4,%R15D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%R14,%R15,2),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e801 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $-0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM7,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa98(%R11),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%RDX,%R15,1),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%R15,1),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD -0x50(%RBP),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD %XMM0,%XMM5,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV (%R14,%R15,2),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e84c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM7,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xa98(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x4(%RSI,%R15,1),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%R15,1),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $-0x1,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CALL 44e180 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD -0x50(%RBP),%XMM9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD %XMM0,%XMM9,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R15,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44e98d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R12,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R15,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD %XMM7,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD -0x48(%RBP),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM7,0xa8(%RBX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
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 44ed94 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xe8(%RBX),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RBX,%R13,8),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x48,%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 |
VSUBSD %XMM7,%XMM14,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 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 |
JMP 4040a0 | 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 |
MOV 0x94(%RDI),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST %ESI,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 44e98d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x1c0(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa0(%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %ESI,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x40(%RBP),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R10,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x5c0(%RDI),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (%R15,%R9,4),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
AND $0x1,%R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44ec70 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R13D,-0x6c(%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 -0x68(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD -0x6c(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 44e98d | 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 |
MOVSXD (%R15),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R14,%R11,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R12,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44ed7e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%R8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VCOMISD 0x8(%R12),%XMM0 | 2 | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
JAE 44ed7e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMULSD 0x238(%R12),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 4042f0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD 0x28(%R12),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x48(%R12),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD %XMM0,%XMM0,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD 0x68(%R12),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x90(%R12),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD 0x50(%R12),%XMM0,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213SD 0x30(%R12),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD213SD 0x70(%R12),%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VCVTTSD2SI -0x40(%RBP),%EDX | 2 | 1.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 6 | 1 |
MOV 0x218(%R12),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD %XMM2,%XMM0,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD 0x88(%R12),%XMM14,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x20(%R12),%XMM2,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOVSXD %EDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMULSD 0x40(%R12),%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
LEA (,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMULSD 0x60(%R12),%XMM2,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x80(%R12),%XMM2,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x18(%R12),%XMM3,%XMM4 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x38(%R12),%XMM3,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x58(%R12),%XMM3,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD 0x78(%R12),%XMM13,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM4,%XMM1,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM5,%XMM7,%XMM8 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM10,%XMM11,%XMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM3,%XMM0,%XMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x8(%R8,%RAX,8),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD 0x18(%R8,%RCX,1),%XMM15,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132SD (%R8,%RCX,1),%XMM9,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD 0x10(%R8,%RCX,1),%XMM12,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
MOV -0x50(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDSD %XMM0,%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x8(%R8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R15,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44ea13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 44e98d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CALL 404140 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::OneBodyJastrowRef | 0.01 | 0.01 |
○Loop 647 - OneBodyJastrowRef.h:147-150 - exec | 0 | 0 |
○Loop 646 - OneBodyJastrowRef.h:155-159 - exec | 0 | 0 |