Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcp ... | Module: exec | Source: TwoBodyJastrowRef.h:307-353 [...] | Coverage: 0.9% |
---|
Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcp ... | Module: exec | Source: TwoBodyJastrowRef.h:307-353 [...] | Coverage: 0.9% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 307 - 353 |
-------------------------------------------------------------------------------- |
307: void TwoBodyJastrowRef<FT>::acceptMove(ParticleSet& P, int iat) |
308: { |
309: // get the old u, du, d2u |
310: const DistanceTableData* d_table = P.DistTables[0]; |
311: computeU3(P, iat, d_table->Distances[iat], old_u.data(), old_du.data(), old_d2u.data()); |
312: if (UpdateMode == ORB_PBYP_RATIO) |
313: { // ratio-only during the move; need to compute derivatives |
314: const auto dist = d_table->Temp_r.data(); |
315: computeU3(P, iat, dist, cur_u.data(), cur_du.data(), cur_d2u.data()); |
316: } |
317: |
318: valT cur_d2Uat(0); |
319: const auto& new_dr = d_table->Temp_dr; |
320: const auto& old_dr = d_table->Displacements[iat]; |
321: constexpr valT lapfac = OHMMS_DIM - RealType(1); |
322: for (int jat = 0; jat < N; jat++) |
323: { |
324: const valT du = cur_u[jat] - old_u[jat]; |
325: const valT newl = cur_d2u[jat] + lapfac * cur_du[jat]; |
326: const valT dl = old_d2u[jat] + lapfac * old_du[jat] - newl; |
327: Uat[jat] += du; |
328: d2Uat[jat] += dl; |
329: cur_d2Uat -= newl; |
330: } |
331: posT cur_dUat; |
332: for (int idim = 0; idim < OHMMS_DIM; ++idim) |
[...] |
339: valT cur_g = cur_dUat[idim]; |
340: for (int jat = 0; jat < N; jat++) |
341: { |
342: const valT newg = cur_du_pt[jat] * new_dX[jat]; |
343: const valT dg = newg - old_du_pt[jat] * old_dX[jat]; |
344: save_g[jat] -= dg; |
345: cur_g += newg; |
346: } |
347: cur_dUat[idim] = cur_g; |
348: } |
349: LogValue += Uat[iat] - cur_Uat; |
350: Uat[iat] = cur_Uat; |
351: dUat(iat) = cur_dUat; |
352: d2Uat[iat] = cur_d2Uat; |
353: } |
/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: 181 - 183 |
-------------------------------------------------------------------------------- |
181: inline typename BinaryReturn<T1, T2, OpAssign>::Type_t operator()(const T1& a, const T2& b) const |
182: { |
183: return (const_cast<T1&>(a) = b); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223 |
-------------------------------------------------------------------------------- |
223: 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); |
[...] |
1145: 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/Numerics/OhmmsPETE/VectorSoAContainer.h: 216 - 241 |
-------------------------------------------------------------------------------- |
216: *(_base + M * i) = rhs[i]; |
[...] |
241: T* restrict data(size_t i) { return myData + i * nGhosts; } |
0x449880 PUSH %RBP |
0x449881 MOVSXD %EDX,%R8 |
0x449884 MOV %RSP,%RBP |
0x449887 PUSH %R15 |
0x449889 PUSH %R14 |
0x44988b PUSH %R13 |
0x44988d PUSH %R12 |
0x44988f MOV %RDI,%R12 |
0x449892 PUSH %RBX |
0x449893 SUB $0x58,%RSP |
0x449897 MOV %FS:0x28,%RAX |
0x4498a0 MOV %RAX,-0x38(%RBP) |
0x4498a4 MOV 0xa10(%RSI),%RAX |
0x4498ab MOV 0x1a0(%RDI),%RBX |
0x4498b2 MOV 0x188(%RDI),%R13 |
0x4498b9 MOV %R8,-0x78(%RBP) |
0x4498bd SAL $0x3,%R8 |
0x4498c1 MOV 0x1b8(%RDI),%R14 |
0x4498c8 MOV %R8,-0x80(%RBP) |
0x4498cc MOV %RBX,%R9 |
0x4498cf MOV (%RAX),%R15 |
0x4498d2 MOV 0x18(%R15),%RCX |
0x4498d6 IMUL %R8,%RCX |
0x4498da MOV %R13,%R8 |
0x4498dd ADD 0x40(%R15),%RCX |
0x4498e1 PUSH $0 |
0x4498e3 PUSH %R14 |
0x4498e5 MOV %EDX,-0x60(%RBP) |
0x4498e8 MOV %RSI,-0x58(%RBP) |
0x4498ec CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> |
0x4498f1 MOV 0xc(%R12),%EDI |
0x4498f6 POP %RCX |
0x4498f7 POP %RSI |
0x4498f8 MOV -0x60(%RBP),%EDX |
0x4498fb TEST %EDI,%EDI |
0x4498fd MOV -0x58(%RBP),%RSI |
0x449901 JE 449fe8 |
0x449907 MOV -0x78(%RBP),%RDX |
0x44990b MOV 0x50(%R15),%RSI |
0x44990f MOV 0x90(%R12),%R11 |
0x449917 MOV 0xd8(%R12),%R9 |
0x44991f LEA (%RDX,%RDX,4),%RCX |
0x449923 MOV 0x128(%R12),%R10 |
0x44992b LEA (%RSI,%RCX,8),%RAX |
0x44992f MOV %R11,-0x58(%RBP) |
0x449933 MOV 0x158(%R12),%RCX |
0x44993b TEST %R11,%R11 |
0x44993e JE 44a015 |
0x449944 LEA (,%R11,8),%R11 |
0x44994c MOV 0x140(%R12),%RDI |
0x449954 MOV 0x170(%R12),%RSI |
0x44995c XOR %EDX,%EDX |
0x44995e LEA -0x8(%R11),%R8 |
0x449962 VMOVSD 0x85a56(%RIP),%XMM4 |
0x44996a VXORPD %XMM1,%XMM1,%XMM1 |
0x44996e SHR $0x3,%R8 |
0x449972 INC %R8 |
0x449975 AND $0x3,%R8D |
0x449979 JE 449a73 |
0x44997f CMP $0x1,%R8 |
0x449983 JE 449a1e |
0x449989 CMP $0x2,%R8 |
0x44998d JE 4499d2 |
0x44998f VMOVSD (%RDI),%XMM2 |
0x449993 VMOVSD (%RCX),%XMM5 |
0x449997 MOV $0x8,%EDX |
0x44999c VMOVSD (%RBX),%XMM0 |
0x4499a0 VMOVSD (%R14),%XMM3 |
0x4499a5 VFMADD213SD (%RSI),%XMM4,%XMM5 |
0x4499aa VADDSD (%R9),%XMM2,%XMM6 |
0x4499af VSUBSD (%R13),%XMM6,%XMM7 |
0x4499b5 VFMSUB132SD %XMM4,%XMM5,%XMM0 |
0x4499ba VSUBSD %XMM5,%XMM1,%XMM1 |
0x4499be VMOVSD %XMM7,(%R9) |
0x4499c3 VADDSD (%R10),%XMM3,%XMM8 |
0x4499c8 VADDSD %XMM8,%XMM0,%XMM9 |
0x4499cd VMOVSD %XMM9,(%R10) |
0x4499d2 VMOVSD (%RDI,%RDX,1),%XMM10 |
0x4499d7 VMOVSD (%RCX,%RDX,1),%XMM11 |
0x4499dc VMOVSD (%RBX,%RDX,1),%XMM13 |
0x4499e1 VMOVSD (%R14,%RDX,1),%XMM12 |
0x4499e7 VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM11 |
0x4499ed VADDSD (%R9,%RDX,1),%XMM10,%XMM14 |
0x4499f3 VSUBSD (%R13,%RDX,1),%XMM14,%XMM15 |
0x4499fa VFMSUB132SD %XMM4,%XMM11,%XMM13 |
0x4499ff VSUBSD %XMM11,%XMM1,%XMM1 |
0x449a04 VMOVSD %XMM15,(%R9,%RDX,1) |
0x449a0a VADDSD (%R10,%RDX,1),%XMM12,%XMM2 |
0x449a10 VADDSD %XMM2,%XMM13,%XMM5 |
0x449a14 VMOVSD %XMM5,(%R10,%RDX,1) |
0x449a1a ADD $0x8,%RDX |
0x449a1e VMOVSD (%RDI,%RDX,1),%XMM6 |
0x449a23 VMOVSD (%RCX,%RDX,1),%XMM7 |
0x449a28 VMOVSD (%RBX,%RDX,1),%XMM0 |
0x449a2d VMOVSD (%R14,%RDX,1),%XMM3 |
0x449a33 VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM7 |
0x449a39 VADDSD (%R9,%RDX,1),%XMM6,%XMM8 |
0x449a3f VSUBSD (%R13,%RDX,1),%XMM8,%XMM9 |
0x449a46 VFMSUB132SD %XMM4,%XMM7,%XMM0 |
0x449a4b VSUBSD %XMM7,%XMM1,%XMM1 |
0x449a4f VMOVSD %XMM9,(%R9,%RDX,1) |
0x449a55 VADDSD (%R10,%RDX,1),%XMM3,%XMM10 |
0x449a5b VADDSD %XMM10,%XMM0,%XMM11 |
0x449a60 VMOVSD %XMM11,(%R10,%RDX,1) |
0x449a66 ADD $0x8,%RDX |
0x449a6a CMP %RDX,%R11 |
0x449a6d JE 449bbd |
(595) 0x449a73 VMOVSD (%RDI,%RDX,1),%XMM12 |
(595) 0x449a78 VMOVSD (%RCX,%RDX,1),%XMM13 |
(595) 0x449a7d VMOVSD (%RBX,%RDX,1),%XMM15 |
(595) 0x449a82 VMOVSD (%R14,%RDX,1),%XMM14 |
(595) 0x449a88 VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM13 |
(595) 0x449a8e VADDSD (%R9,%RDX,1),%XMM12,%XMM2 |
(595) 0x449a94 VSUBSD (%R13,%RDX,1),%XMM2,%XMM5 |
(595) 0x449a9b VFMSUB132SD %XMM4,%XMM13,%XMM15 |
(595) 0x449aa0 VSUBSD %XMM13,%XMM1,%XMM8 |
(595) 0x449aa5 VMOVSD %XMM5,(%R9,%RDX,1) |
(595) 0x449aab VADDSD (%R10,%RDX,1),%XMM14,%XMM6 |
(595) 0x449ab1 VADDSD %XMM6,%XMM15,%XMM7 |
(595) 0x449ab5 VMOVSD %XMM7,(%R10,%RDX,1) |
(595) 0x449abb VMOVSD 0x8(%RDI,%RDX,1),%XMM9 |
(595) 0x449ac1 VMOVSD 0x8(%RCX,%RDX,1),%XMM10 |
(595) 0x449ac7 VMOVSD 0x8(%RBX,%RDX,1),%XMM0 |
(595) 0x449acd VMOVSD 0x8(%R14,%RDX,1),%XMM3 |
(595) 0x449ad4 VFMADD213SD 0x8(%RSI,%RDX,1),%XMM4,%XMM10 |
(595) 0x449adb VADDSD 0x8(%R9,%RDX,1),%XMM9,%XMM11 |
(595) 0x449ae2 VSUBSD 0x8(%R13,%RDX,1),%XMM11,%XMM1 |
(595) 0x449ae9 VFMSUB132SD %XMM4,%XMM10,%XMM0 |
(595) 0x449aee VSUBSD %XMM10,%XMM8,%XMM14 |
(595) 0x449af3 VMOVSD %XMM1,0x8(%R9,%RDX,1) |
(595) 0x449afa VADDSD 0x8(%R10,%RDX,1),%XMM3,%XMM12 |
(595) 0x449b01 VADDSD %XMM12,%XMM0,%XMM13 |
(595) 0x449b06 VMOVSD %XMM13,0x8(%R10,%RDX,1) |
(595) 0x449b0d VMOVSD 0x10(%RDI,%RDX,1),%XMM15 |
(595) 0x449b13 VMOVSD 0x10(%RCX,%RDX,1),%XMM5 |
(595) 0x449b19 VMOVSD 0x10(%RBX,%RDX,1),%XMM7 |
(595) 0x449b1f VMOVSD 0x10(%R14,%RDX,1),%XMM6 |
(595) 0x449b26 VFMADD213SD 0x10(%RSI,%RDX,1),%XMM4,%XMM5 |
(595) 0x449b2d VADDSD 0x10(%R9,%RDX,1),%XMM15,%XMM2 |
(595) 0x449b34 VSUBSD 0x10(%R13,%RDX,1),%XMM2,%XMM8 |
(595) 0x449b3b VFMSUB132SD %XMM4,%XMM5,%XMM7 |
(595) 0x449b40 VSUBSD %XMM5,%XMM14,%XMM11 |
(595) 0x449b44 VMOVSD %XMM8,0x10(%R9,%RDX,1) |
(595) 0x449b4b VADDSD 0x10(%R10,%RDX,1),%XMM6,%XMM9 |
(595) 0x449b52 VADDSD %XMM9,%XMM7,%XMM10 |
(595) 0x449b57 VMOVSD %XMM10,0x10(%R10,%RDX,1) |
(595) 0x449b5e VMOVSD 0x18(%RDI,%RDX,1),%XMM1 |
(595) 0x449b64 VMOVSD 0x18(%RCX,%RDX,1),%XMM12 |
(595) 0x449b6a VFMADD213SD 0x18(%RSI,%RDX,1),%XMM4,%XMM12 |
(595) 0x449b71 VADDSD 0x18(%R9,%RDX,1),%XMM1,%XMM13 |
(595) 0x449b78 VMOVSD 0x18(%RBX,%RDX,1),%XMM0 |
(595) 0x449b7e VMOVSD 0x18(%R14,%RDX,1),%XMM3 |
(595) 0x449b85 VSUBSD 0x18(%R13,%RDX,1),%XMM13,%XMM14 |
(595) 0x449b8c VFMSUB132SD %XMM4,%XMM12,%XMM0 |
(595) 0x449b91 VSUBSD %XMM12,%XMM11,%XMM1 |
(595) 0x449b96 VMOVSD %XMM14,0x18(%R9,%RDX,1) |
(595) 0x449b9d VADDSD 0x18(%R10,%RDX,1),%XMM3,%XMM15 |
(595) 0x449ba4 VADDSD %XMM15,%XMM0,%XMM5 |
(595) 0x449ba9 VMOVSD %XMM5,0x18(%R10,%RDX,1) |
(595) 0x449bb0 ADD $0x20,%RDX |
(595) 0x449bb4 CMP %RDX,%R11 |
(595) 0x449bb7 JNE 449a73 |
0x449bbd MOV 0x88(%R15),%RDI |
0x449bc4 LEA -0x38(%RBP),%R8 |
0x449bc8 MOV 0x100(%R12),%R14 |
0x449bd0 MOVQ $0,-0x40(%RBP) |
0x449bd8 MOV 0x18(%RAX),%RSI |
0x449bdc MOV %R8,-0x68(%RBP) |
0x449be0 VXORPD %XMM4,%XMM4,%XMM4 |
0x449be4 LEA -0x50(%RBP),%R13 |
0x449be8 SAL $0x3,%RDI |
0x449bec VMOVAPD %XMM4,-0x50(%RBP) |
0x449bf1 MOV %R14,%RDX |
0x449bf4 MOV %RDI,-0x60(%RBP) |
0x449bf8 MOV 0x98(%R15),%RDI |
0x449bff MOV 0x8(%RAX),%R15 |
0x449c03 MOV 0xf0(%R12),%RAX |
0x449c0b SAL $0x3,%R15 |
0x449c0f MOV %R15,-0x70(%RBP) |
0x449c13 LEA (,%RAX,8),%R15 |
(593) 0x449c1b CMPQ $0,-0x58(%RBP) |
(593) 0x449c20 VMOVSD (%R13),%XMM0 |
(593) 0x449c26 JE 449f0d |
(593) 0x449c2c LEA -0x8(%R11),%R8 |
(593) 0x449c30 XOR %EAX,%EAX |
(593) 0x449c32 SHR $0x3,%R8 |
(593) 0x449c36 INC %R8 |
(593) 0x449c39 AND $0x7,%R8D |
(593) 0x449c3d JE 449d8e |
(593) 0x449c43 CMP $0x1,%R8 |
(593) 0x449c47 JE 449d58 |
(593) 0x449c4d CMP $0x2,%R8 |
(593) 0x449c51 JE 449d2b |
(593) 0x449c57 CMP $0x3,%R8 |
(593) 0x449c5b JE 449cfe |
(593) 0x449c61 CMP $0x4,%R8 |
(593) 0x449c65 JE 449cd1 |
(593) 0x449c67 CMP $0x5,%R8 |
(593) 0x449c6b JE 449ca4 |
(593) 0x449c6d CMP $0x6,%R8 |
(593) 0x449c71 JNE 449fb8 |
(593) 0x449c77 VMOVSD (%RBX,%RAX,1),%XMM11 |
(593) 0x449c7c VMOVSD (%RDX,%RAX,1),%XMM12 |
(593) 0x449c81 VMOVSD (%RCX,%RAX,1),%XMM9 |
(593) 0x449c86 VMOVSD (%RDI,%RAX,1),%XMM10 |
(593) 0x449c8b VFMADD132SD (%RSI,%RAX,1),%XMM12,%XMM11 |
(593) 0x449c91 VFMADD231SD %XMM10,%XMM9,%XMM0 |
(593) 0x449c96 VFNMADD231SD %XMM10,%XMM9,%XMM11 |
(593) 0x449c9b VMOVSD %XMM11,(%RDX,%RAX,1) |
(593) 0x449ca0 ADD $0x8,%RAX |
(593) 0x449ca4 VMOVSD (%RBX,%RAX,1),%XMM14 |
(593) 0x449ca9 VMOVSD (%RDX,%RAX,1),%XMM15 |
(593) 0x449cae VMOVSD (%RCX,%RAX,1),%XMM13 |
(593) 0x449cb3 VMOVSD (%RDI,%RAX,1),%XMM3 |
(593) 0x449cb8 VFMADD132SD (%RSI,%RAX,1),%XMM15,%XMM14 |
(593) 0x449cbe VFMADD231SD %XMM3,%XMM13,%XMM0 |
(593) 0x449cc3 VFNMADD231SD %XMM3,%XMM13,%XMM14 |
(593) 0x449cc8 VMOVSD %XMM14,(%RDX,%RAX,1) |
(593) 0x449ccd ADD $0x8,%RAX |
(593) 0x449cd1 VMOVSD (%RBX,%RAX,1),%XMM8 |
(593) 0x449cd6 VMOVSD (%RDX,%RAX,1),%XMM6 |
(593) 0x449cdb VMOVSD (%RCX,%RAX,1),%XMM5 |
(593) 0x449ce0 VMOVSD (%RDI,%RAX,1),%XMM4 |
(593) 0x449ce5 VFMADD132SD (%RSI,%RAX,1),%XMM6,%XMM8 |
(593) 0x449ceb VFMADD231SD %XMM4,%XMM5,%XMM0 |
(593) 0x449cf0 VFNMADD231SD %XMM4,%XMM5,%XMM8 |
(593) 0x449cf5 VMOVSD %XMM8,(%RDX,%RAX,1) |
(593) 0x449cfa ADD $0x8,%RAX |
(593) 0x449cfe VMOVSD (%RBX,%RAX,1),%XMM2 |
(593) 0x449d03 VMOVSD (%RDX,%RAX,1),%XMM7 |
(593) 0x449d08 VMOVSD (%RCX,%RAX,1),%XMM9 |
(593) 0x449d0d VMOVSD (%RDI,%RAX,1),%XMM10 |
(593) 0x449d12 VFMADD132SD (%RSI,%RAX,1),%XMM7,%XMM2 |
(593) 0x449d18 VFMADD231SD %XMM10,%XMM9,%XMM0 |
(593) 0x449d1d VFNMADD231SD %XMM10,%XMM9,%XMM2 |
(593) 0x449d22 VMOVSD %XMM2,(%RDX,%RAX,1) |
(593) 0x449d27 ADD $0x8,%RAX |
(593) 0x449d2b VMOVSD (%RBX,%RAX,1),%XMM13 |
(593) 0x449d30 VMOVSD (%RDX,%RAX,1),%XMM3 |
(593) 0x449d35 VMOVSD (%RCX,%RAX,1),%XMM11 |
(593) 0x449d3a VMOVSD (%RDI,%RAX,1),%XMM12 |
(593) 0x449d3f VFMADD132SD (%RSI,%RAX,1),%XMM3,%XMM13 |
(593) 0x449d45 VFMADD231SD %XMM12,%XMM11,%XMM0 |
(593) 0x449d4a VFNMADD231SD %XMM12,%XMM11,%XMM13 |
(593) 0x449d4f VMOVSD %XMM13,(%RDX,%RAX,1) |
(593) 0x449d54 ADD $0x8,%RAX |
(593) 0x449d58 VMOVSD (%RBX,%RAX,1),%XMM5 |
(593) 0x449d5d VMOVSD (%RDX,%RAX,1),%XMM4 |
(593) 0x449d62 VMOVSD (%RCX,%RAX,1),%XMM14 |
(593) 0x449d67 VMOVSD (%RDI,%RAX,1),%XMM15 |
(593) 0x449d6c VFMADD132SD (%RSI,%RAX,1),%XMM4,%XMM5 |
(593) 0x449d72 VFMADD231SD %XMM15,%XMM14,%XMM0 |
(593) 0x449d77 VFNMADD231SD %XMM15,%XMM14,%XMM5 |
(593) 0x449d7c VMOVSD %XMM5,(%RDX,%RAX,1) |
(593) 0x449d81 ADD $0x8,%RAX |
(593) 0x449d85 CMP %RAX,%R11 |
(593) 0x449d88 JE 449f0d |
(594) 0x449d8e VMOVSD (%RBX,%RAX,1),%XMM10 |
(594) 0x449d93 VMOVSD (%RDX,%RAX,1),%XMM6 |
(594) 0x449d98 VMOVSD (%RDI,%RAX,1),%XMM9 |
(594) 0x449d9d VMOVSD (%RCX,%RAX,1),%XMM8 |
(594) 0x449da2 VFMADD132SD (%RSI,%RAX,1),%XMM6,%XMM10 |
(594) 0x449da8 VMOVSD 0x8(%RAX,%RDX,1),%XMM7 |
(594) 0x449dae VMOVSD 0x10(%RAX,%RDX,1),%XMM14 |
(594) 0x449db4 VMOVSD 0x20(%RAX,%RDX,1),%XMM6 |
(594) 0x449dba VFNMADD231SD %XMM9,%XMM8,%XMM10 |
(594) 0x449dbf VFMADD132SD %XMM9,%XMM0,%XMM8 |
(594) 0x449dc4 VMOVSD 0x18(%RAX,%RDX,1),%XMM9 |
(594) 0x449dca VMOVSD %XMM10,(%RDX,%RAX,1) |
(594) 0x449dcf VMOVSD 0x8(%RBX,%RAX,1),%XMM11 |
(594) 0x449dd5 VMOVSD 0x8(%RCX,%RAX,1),%XMM0 |
(594) 0x449ddb VMOVSD 0x8(%RDI,%RAX,1),%XMM2 |
(594) 0x449de1 VFMADD132SD 0x8(%RSI,%RAX,1),%XMM7,%XMM11 |
(594) 0x449de8 VFMADD231SD %XMM2,%XMM0,%XMM8 |
(594) 0x449ded VFNMADD231SD %XMM2,%XMM0,%XMM11 |
(594) 0x449df2 VMOVSD %XMM11,0x8(%RAX,%RDX,1) |
(594) 0x449df8 VMOVSD 0x10(%RBX,%RAX,1),%XMM3 |
(594) 0x449dfe VMOVSD 0x10(%RCX,%RAX,1),%XMM12 |
(594) 0x449e04 VMOVSD 0x10(%RDI,%RAX,1),%XMM13 |
(594) 0x449e0a VFMADD132SD 0x10(%RSI,%RAX,1),%XMM14,%XMM3 |
(594) 0x449e11 VFMADD231SD %XMM13,%XMM12,%XMM8 |
(594) 0x449e16 VFNMADD231SD %XMM13,%XMM12,%XMM3 |
(594) 0x449e1b VMOVSD %XMM3,0x10(%RAX,%RDX,1) |
(594) 0x449e21 VMOVSD 0x18(%RBX,%RAX,1),%XMM4 |
(594) 0x449e27 VMOVSD 0x18(%RCX,%RAX,1),%XMM15 |
(594) 0x449e2d VMOVSD 0x18(%RDI,%RAX,1),%XMM5 |
(594) 0x449e33 VFMADD132SD 0x18(%RSI,%RAX,1),%XMM9,%XMM4 |
(594) 0x449e3a VFMADD231SD %XMM5,%XMM15,%XMM8 |
(594) 0x449e3f VFNMADD231SD %XMM5,%XMM15,%XMM4 |
(594) 0x449e44 VMOVSD %XMM4,0x18(%RAX,%RDX,1) |
(594) 0x449e4a VMOVSD 0x20(%RBX,%RAX,1),%XMM2 |
(594) 0x449e50 VMOVSD 0x20(%RDI,%RAX,1),%XMM0 |
(594) 0x449e56 VMOVSD 0x20(%RCX,%RAX,1),%XMM10 |
(594) 0x449e5c VFMADD132SD 0x20(%RSI,%RAX,1),%XMM6,%XMM2 |
(594) 0x449e63 VFMADD231SD %XMM0,%XMM10,%XMM8 |
(594) 0x449e68 VFNMADD231SD %XMM0,%XMM10,%XMM2 |
(594) 0x449e6d VMOVSD %XMM2,0x20(%RAX,%RDX,1) |
(594) 0x449e73 VMOVSD 0x28(%RCX,%RAX,1),%XMM11 |
(594) 0x449e79 VMOVSD 0x28(%RDI,%RAX,1),%XMM12 |
(594) 0x449e7f VMOVSD 0x28(%RBX,%RAX,1),%XMM13 |
(594) 0x449e85 VMOVSD 0x28(%RAX,%RDX,1),%XMM7 |
(594) 0x449e8b VMOVSD 0x30(%RAX,%RDX,1),%XMM15 |
(594) 0x449e91 VMOVSD 0x38(%RAX,%RDX,1),%XMM9 |
(594) 0x449e97 VFMADD231SD %XMM12,%XMM11,%XMM8 |
(594) 0x449e9c VFMADD132SD 0x28(%RSI,%RAX,1),%XMM7,%XMM13 |
(594) 0x449ea3 VFNMADD231SD %XMM12,%XMM11,%XMM13 |
(594) 0x449ea8 VMOVSD %XMM13,0x28(%RAX,%RDX,1) |
(594) 0x449eae VMOVSD 0x30(%RBX,%RAX,1),%XMM3 |
(594) 0x449eb4 VMOVSD 0x30(%RCX,%RAX,1),%XMM0 |
(594) 0x449eba VMOVSD 0x30(%RDI,%RAX,1),%XMM14 |
(594) 0x449ec0 VFMADD132SD 0x30(%RSI,%RAX,1),%XMM15,%XMM3 |
(594) 0x449ec7 VFNMADD231SD %XMM14,%XMM0,%XMM3 |
(594) 0x449ecc VFMADD132SD %XMM14,%XMM8,%XMM0 |
(594) 0x449ed1 VMOVSD %XMM3,0x30(%RAX,%RDX,1) |
(594) 0x449ed7 VMOVSD 0x38(%RBX,%RAX,1),%XMM4 |
(594) 0x449edd VMOVSD 0x38(%RCX,%RAX,1),%XMM8 |
(594) 0x449ee3 VMOVSD 0x38(%RDI,%RAX,1),%XMM5 |
(594) 0x449ee9 VFMADD132SD 0x38(%RSI,%RAX,1),%XMM9,%XMM4 |
(594) 0x449ef0 ADD $0x40,%RAX |
(594) 0x449ef4 VFMADD231SD %XMM5,%XMM8,%XMM0 |
(594) 0x449ef9 VFNMADD231SD %XMM5,%XMM8,%XMM4 |
(594) 0x449efe VMOVSD %XMM4,-0x8(%RAX,%RDX,1) |
(594) 0x449f04 CMP %RAX,%R11 |
(594) 0x449f07 JNE 449d8e |
(593) 0x449f0d MOV -0x60(%RBP),%R8 |
(593) 0x449f11 MOV -0x70(%RBP),%RAX |
(593) 0x449f15 VMOVSD %XMM0,(%R13) |
(593) 0x449f1b ADD $0x8,%R13 |
(593) 0x449f1f ADD %R15,%RDX |
(593) 0x449f22 ADD %R8,%RDI |
(593) 0x449f25 MOV -0x68(%RBP),%R8 |
(593) 0x449f29 ADD %RAX,%RSI |
(593) 0x449f2c CMP %R8,%R13 |
(593) 0x449f2f JNE 449c1b |
0x449f35 VMOVSD 0x10(%R12),%XMM2 |
0x449f3c VMOVSD 0x138(%R12),%XMM10 |
0x449f46 MOV -0x80(%RBP),%RCX |
0x449f4a VMOVSD -0x50(%RBP),%XMM12 |
0x449f4f VSUBSD %XMM10,%XMM2,%XMM6 |
0x449f54 VMOVSD -0x48(%RBP),%XMM13 |
0x449f59 VMOVSD -0x40(%RBP),%XMM7 |
0x449f5e ADD %RCX,%R9 |
0x449f61 ADD %R15,%RCX |
0x449f64 VADDSD (%R9),%XMM6,%XMM11 |
0x449f69 VMOVSD %XMM11,0x10(%R12) |
0x449f70 MOV -0x78(%RBP),%R12 |
0x449f74 VMOVSD %XMM10,(%R9) |
0x449f79 VMOVSD %XMM12,(%R14,%R12,8) |
0x449f7f VMOVSD %XMM13,(%R14,%RCX,1) |
0x449f85 ADD %R15,%R14 |
0x449f88 VMOVSD %XMM7,(%R14,%RCX,1) |
0x449f8e VMOVSD %XMM1,(%R10,%R12,8) |
0x449f94 MOV -0x38(%RBP),%RAX |
0x449f98 SUB %FS:0x28,%RAX |
0x449fa1 JNE 44a021 |
0x449fa3 LEA -0x28(%RBP),%RSP |
0x449fa7 POP %RBX |
0x449fa8 POP %R12 |
0x449faa POP %R13 |
0x449fac POP %R14 |
0x449fae POP %R15 |
0x449fb0 POP %RBP |
0x449fb1 RET |
0x449fb2 NOPW (%RAX,%RAX,1) |
(593) 0x449fb8 VMOVSD (%RBX),%XMM2 |
(593) 0x449fbc VMOVSD (%RDX),%XMM7 |
(593) 0x449fc0 MOV $0x8,%EAX |
(593) 0x449fc5 VMOVSD (%RCX),%XMM6 |
(593) 0x449fc9 VMOVSD (%RDI),%XMM8 |
(593) 0x449fcd VFMADD132SD (%RSI),%XMM7,%XMM2 |
(593) 0x449fd2 VFMADD231SD %XMM8,%XMM6,%XMM0 |
(593) 0x449fd7 VFNMADD231SD %XMM8,%XMM6,%XMM2 |
(593) 0x449fdc VMOVSD %XMM2,(%RDX) |
(593) 0x449fe0 JMP 449c77 |
0x449fe5 NOPL (%RAX) |
0x449fe8 MOV 0x68(%R15),%RCX |
0x449fec PUSH $0 |
0x449fee MOV %R12,%RDI |
0x449ff1 PUSHQ 0x170(%R12) |
0x449ff9 MOV 0x158(%R12),%R9 |
0x44a001 MOV 0x140(%R12),%R8 |
0x44a009 CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> |
0x44a00e POP %RAX |
0x44a00f POP %RDX |
0x44a010 JMP 449907 |
0x44a015 VXORPD %XMM1,%XMM1,%XMM1 |
0x44a019 XOR %R11D,%R11D |
0x44a01c JMP 449bbd |
0x44a021 CALL 404140 <__stack_chk_fail@plt> |
0x44a026 NOPW %CS:(%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | exec |
○ | main._omp_fn.1 | stl_vector.h:1126 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | TwoBodyJastrowRef.h:307-353 |
Module | exec |
nb instructions | 171 |
nb uops | 175 |
loop length | 799 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 11 |
micro-operation queue | 45.75 cycles |
front end | 45.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.50 | 16.50 | 37.00 | 37.00 | 36.00 | 16.50 | 16.50 | 37.00 |
cycles | 16.50 | 16.50 | 37.00 | 37.00 | 36.00 | 16.50 | 16.50 | 37.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 45.24 |
Stall cycles | 0.00 |
Front-end | 45.75 |
Dispatch | 37.00 |
Overall L1 | 45.75 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 7% |
load | 0% |
store | 7% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 5% |
load | 0% |
store | 4% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 23% |
all | 11% |
load | 12% |
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 | 13% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
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 |
MOVSXD %EDX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 |
MOV %RDI,%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 |
SUB $0x58,%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 |
MOV 0xa10(%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x1a0(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x188(%RDI),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SAL $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV 0x1b8(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%R15),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R13,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD 0x40(%R15),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
PUSH $0 | 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 |
MOV %EDX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0xc(%R12),%EDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
POP %RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
MOV -0x60(%RBP),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EDI,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 449fe8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x50(%R15),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x90(%R12),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xd8(%R12),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RDX,4),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x128(%R12),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RSI,%RCX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R11,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x158(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R11,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a015 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (,%R11,8),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x140(%R12),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x170(%R12),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x8(%R11),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0x85a56(%RIP),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%R8D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449a73 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449a1e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4499d2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%RDI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x8,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RBX),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R14),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RSI),%XMM4,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD (%R9),%XMM2,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD (%R13),%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD %XMM4,%XMM5,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM5,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM7,(%R9) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD (%R10),%XMM3,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM8,%XMM0,%XMM9 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,(%R10) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD (%RDI,%RDX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RDX,1),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RBX,%RDX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R14,%RDX,1),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD (%R9,%RDX,1),%XMM10,%XMM14 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD (%R13,%RDX,1),%XMM14,%XMM15 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD %XMM4,%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM11,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM15,(%R9,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD (%R10,%RDX,1),%XMM12,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM2,%XMM13,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM5,(%R10,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI,%RDX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RDX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RBX,%RDX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R14,%RDX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD (%R9,%RDX,1),%XMM6,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD (%R13,%RDX,1),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD %XMM4,%XMM7,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM7,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,(%R9,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD (%R10,%RDX,1),%XMM3,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM10,%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,(%R10,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449bbd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x88(%R15),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x38(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x100(%R12),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV 0x18(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x50(%RBP),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMOVAPD %XMM4,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x98(%R15),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xf0(%R12),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SAL $0x3,%R15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R15,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (,%RAX,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0x10(%R12),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x138(%R12),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x80(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x50(%RBP),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD %XMM10,%XMM2,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD -0x48(%RBP),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x40(%RBP),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R15,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R9),%XMM6,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,0x10(%R12) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x78(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM10,(%R9) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM12,(%R14,%R12,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM13,(%R14,%RCX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD %R15,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD %XMM7,(%R14,%RCX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM1,(%R10,%R12,8) | 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 44a021 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPW (%RAX,%RAX,1) | 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 |
MOV 0x68(%R15),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSH $0 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSHQ 0x170(%R12) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x158(%R12),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%R12),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
POP %RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
JMP 449907 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 449bbd | 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 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | TwoBodyJastrowRef.h:307-353 |
Module | exec |
nb instructions | 171 |
nb uops | 175 |
loop length | 799 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 16 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 11 |
micro-operation queue | 45.75 cycles |
front end | 45.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 16.50 | 16.50 | 37.00 | 37.00 | 36.00 | 16.50 | 16.50 | 37.00 |
cycles | 16.50 | 16.50 | 37.00 | 37.00 | 36.00 | 16.50 | 16.50 | 37.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 45.24 |
Stall cycles | 0.00 |
Front-end | 45.75 |
Dispatch | 37.00 |
Overall L1 | 45.75 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 7% |
load | 0% |
store | 7% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 5% |
load | 0% |
store | 4% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 23% |
all | 11% |
load | 12% |
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 | 13% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
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 |
MOVSXD %EDX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 |
MOV %RDI,%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 |
SUB $0x58,%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 |
MOV 0xa10(%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x1a0(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x188(%RDI),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SAL $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV 0x1b8(%RDI),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%R15),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R13,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD 0x40(%R15),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
PUSH $0 | 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 |
MOV %EDX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0xc(%R12),%EDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
POP %RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
MOV -0x60(%RBP),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %EDI,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 449fe8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x50(%R15),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x90(%R12),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xd8(%R12),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RDX,4),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x128(%R12),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RSI,%RCX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R11,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x158(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R11,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a015 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (,%R11,8),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x140(%R12),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x170(%R12),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x8(%R11),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0x85a56(%RIP),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x3,%R8D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449a73 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449a1e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4499d2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%RDI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x8,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RBX),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R14),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RSI),%XMM4,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD (%R9),%XMM2,%XMM6 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD (%R13),%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD %XMM4,%XMM5,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM5,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM7,(%R9) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD (%R10),%XMM3,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM8,%XMM0,%XMM9 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,(%R10) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD (%RDI,%RDX,1),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RDX,1),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RBX,%RDX,1),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R14,%RDX,1),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD (%R9,%RDX,1),%XMM10,%XMM14 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD (%R13,%RDX,1),%XMM14,%XMM15 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD %XMM4,%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM11,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM15,(%R9,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD (%R10,%RDX,1),%XMM12,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM2,%XMM13,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM5,(%R10,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI,%RDX,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RDX,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RBX,%RDX,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R14,%RDX,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RSI,%RDX,1),%XMM4,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD (%R9,%RDX,1),%XMM6,%XMM8 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD (%R13,%RDX,1),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD %XMM4,%XMM7,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VSUBSD %XMM7,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,(%R9,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VADDSD (%R10,%RDX,1),%XMM3,%XMM10 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD %XMM10,%XMM0,%XMM11 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,(%R10,%RDX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449bbd | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x88(%R15),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x38(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x100(%R12),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV 0x18(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VXORPD %XMM4,%XMM4,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x50(%RBP),%R13 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
VMOVAPD %XMM4,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x98(%R15),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xf0(%R12),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SAL $0x3,%R15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R15,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (,%RAX,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0x10(%R12),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x138(%R12),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x80(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x50(%RBP),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VSUBSD %XMM10,%XMM2,%XMM6 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD -0x48(%RBP),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD -0x40(%RBP),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R15,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R9),%XMM6,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,0x10(%R12) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x78(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM10,(%R9) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM12,(%R14,%R12,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM13,(%R14,%RCX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD %R15,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD %XMM7,(%R14,%RCX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM1,(%R10,%R12,8) | 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 44a021 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPW (%RAX,%RAX,1) | 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 |
MOV 0x68(%R15),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSH $0 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSHQ 0x170(%R12) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x158(%R12),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%R12),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
POP %RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
JMP 449907 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 449bbd | 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 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::TwoBodyJastrowRef | 0.9 | 0.88 |
○Loop 595 - TwoBodyJastrowRef.h:322-329 - exec | 0.3 | 0.29 |
▼Loop 593 - TwoBodyJastrowRef.h:332-353 - exec– | 0 | 0 |
○Loop 594 - TwoBodyJastrowRef.h:340-345 - exec | 0.6 | 0.58 |