OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > >&, qmcplusplus::ParticleAttrib<double, std::allocator<double> >&, bool)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcp ...	Module: exec	Source: OneBodyJastrowRef.h:108-194 [...]	Coverage (incl. loops): 0.01% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

--------------------------------------------------------------------------------

94:     (const_cast<T1&>(a) += b);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 273 - 273

--------------------------------------------------------------------------------

273:   inline const T* restrict data(size_t i) const { return myData + i * nGhosts; }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h: 49 - 49

--------------------------------------------------------------------------------

49:     for (unsigned d = 0; d < D; ++d)

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h: 140 - 141

--------------------------------------------------------------------------------

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1064 - 1169

--------------------------------------------------------------------------------

1064: 	return *(this->_M_impl._M_start + __n);

[...]

1169:       { return _M_data_ptr(this->_M_impl._M_start); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h: 1028 - 1182

--------------------------------------------------------------------------------

1028:       : _M_current(__i) { }

[...]

1182:     { return __lhs.base() != __rhs.base(); }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 169 - 170

--------------------------------------------------------------------------------

169:   inline Type_t& operator[](unsigned int i) { return X[i]; }

170:   inline const Type_t& operator[](unsigned int i) const { return X[i]; }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 108 - 194

--------------------------------------------------------------------------------

108:     const auto& d_ie = P.getDistTableAB(myTableID);

109:     for (int iat = 0; iat < Nelec; ++iat)

110:     {

111:       computeU3(P, iat, d_ie.getDistRow(iat).data());

112:       Vat[iat] = std::accumulate(U.begin(), U.begin() + Nions, valT());

113:       Lap[iat] = accumulateGL(dU.data(), d2U.data(), d_ie.getDisplRow(iat), Grad[iat]);

[...]

165:   {

166:     if (fromscratch)

167:       recompute(P);

168:

169:     for (size_t iat = 0; iat < Nelec; ++iat)

170:       G[iat] += Grad[iat];

171:     for (size_t iat = 0; iat < Nelec; ++iat)

172:       L[iat] -= Lap[iat];

173:     LogValue = -std::accumulate(Vat.begin(), Vat.begin() + Nelec, valT());

174:   }

[...]

186:     for (int jat = 0; jat < Nions; ++jat)

187:       lap += d2u[jat] + lapfac * du[jat];

188:     for (int idim = 0; idim < OHMMS_DIM; ++idim)

189:     {

190:       const valT* restrict dX = displ.data(idim);

191:       valT s                  = valT();

192:       for (int jat = 0; jat < Nions; ++jat)

193:         s += du[jat] * dX[jat];

194:       grad[idim] = s;

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

--------------------------------------------------------------------------------

223:     return X[i];

[...]

242:   inline iterator begin() { return X; }

[...]

249:   inline const_pointer data() const { return X; }

0x41da90 PUSH	%RBP

0x41da91 MOV	%RSP,%RBP

0x41da94 PUSH	%R15

0x41da96 PUSH	%R14

0x41da98 PUSH	%R13

0x41da9a PUSH	%R12

0x41da9c PUSH	%RBX

0x41da9d SUB	$0x18,%RSP

0x41daa1 MOV	%RCX,%R14

0x41daa4 MOV	%RDX,%R15

0x41daa7 MOV	%RDI,%RBX

0x41daaa TEST	%R8B,%R8B

0x41daad JE	41deaf

0x41dab3 MOV	%RSI,%R12

0x41dab6 MOV	0xa8(%RBX),%ESI

0x41dabc MOV	%R12,%RDI

0x41dabf CALL	460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x41dac4 MOV	0x94(%RBX),%R8D

0x41dacb TEST	%R8D,%R8D

0x41dace JLE	41deb6

0x41dad4 MOV	%RAX,%R13

0x41dad7 MOV	%R12,-0x40(%RBP)

0x41dadb MOV	%R15,-0x30(%RBP)

0x41dadf MOV	%R14,-0x38(%RBP)

0x41dae3 MOV	$0x1fffffffffffffff,%R15

0x41daed XOR	%R14D,%R14D

0x41daf0 JMP	41db3a

0x41daf2 NOPW	%CS:(%RAX,%RAX,1)

(310) 0x41db00 LEA	(%R14,%R14,2),%RAX

(310) 0x41db04 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41db08 VMOVUPD	%XMM0,(%RDX,%RAX,8)

(310) 0x41db0d MOVQ	$0,0x10(%RDX,%RAX,8)

(310) 0x41db16 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41db1a MOV	0x1b8(%RBX),%RAX

(310) 0x41db21 VMOVSD	%XMM0,(%RAX,%R14,8)

(310) 0x41db27 INC	%R14

(310) 0x41db2a MOVSXD	0x94(%RBX),%R8

(310) 0x41db31 CMP	%R8,%R14

(310) 0x41db34 JGE	41dec4

(310) 0x41db3a MOV	0x48(%R13),%RAX

(310) 0x41db3e LEA	(%R14,%R14,4),%R12

(310) 0x41db42 MOV	0x18(%RAX,%R12,8),%RCX

(310) 0x41db47 MOV	%RBX,%RDI

(310) 0x41db4a MOV	-0x40(%RBP),%RSI

(310) 0x41db4e MOV	%R14D,%EDX

(310) 0x41db51 VZEROUPPER

(310) 0x41db54 CALL	41fa10 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>

(310) 0x41db59 MOVSXD	0x90(%RBX),%RAX

(310) 0x41db60 TEST	%R15,%RAX

(310) 0x41db63 JE	41dbd0

(310) 0x41db65 MOV	0x100(%RBX),%RCX

(310) 0x41db6c LEA	(%RAX,%R15,1),%RDX

(310) 0x41db70 AND	%R15,%RDX

(310) 0x41db73 INC	%RDX

(310) 0x41db76 MOV	%RDX,%RSI

(310) 0x41db79 MOV	$0x3ffffffffffffffc,%RDI

(310) 0x41db83 AND	%RDI,%RSI

(310) 0x41db86 VMOVSD	0xe072a(%RIP),%XMM2

(310) 0x41db8e VBROADCASTSD	0xe0721(%RIP),%YMM3

(310) 0x41db97 JE	41dbf0

(310) 0x41db99 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41db9d XOR	%EDI,%EDI

(310) 0x41db9f NOP

  (322) 0x41dba0 VADDPD	(%RCX,%RDI,8),%YMM0,%YMM0

  (322) 0x41dba5 ADD	$0x4,%RDI

  (322) 0x41dba9 CMP	%RSI,%RDI

  (322) 0x41dbac JB	41dba0

(310) 0x41dbae VEXTRACTF128	$0x1,%YMM0,%XMM1

(310) 0x41dbb4 VADDPD	%XMM1,%XMM0,%XMM0

(310) 0x41dbb8 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

(310) 0x41dbbd VADDSD	%XMM1,%XMM0,%XMM0

(310) 0x41dbc1 JMP	41dc08

0x41dbc3 NOPW	%CS:(%RAX,%RAX,1)

(310) 0x41dbd0 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41dbd4 VMOVSD	0xe06dc(%RIP),%XMM2

(310) 0x41dbdc VBROADCASTSD	0xe06d3(%RIP),%YMM3

(310) 0x41dbe5 JMP	41dc0d

0x41dbe7 NOPW	(%RAX,%RAX,1)

(310) 0x41dbf0 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41dbf4 XOR	%ESI,%ESI

(310) 0x41dbf6 NOPW	%CS:(%RAX,%RAX,1)

  (321) 0x41dc00 VADDSD	(%RCX,%RSI,8),%XMM0,%XMM0

  (321) 0x41dc05 INC	%RSI

  (321) 0x41dc08 CMP	%RSI,%RDX

  (321) 0x41dc0b JNE	41dc00

(310) 0x41dc0d MOV	0xf0(%RBX),%RCX

(310) 0x41dc14 VMOVSD	%XMM0,(%RCX,%R14,8)

(310) 0x41dc1a MOV	0x190(%RBX),%RDX

(310) 0x41dc21 TEST	%EAX,%EAX

(310) 0x41dc23 JLE	41db00

(310) 0x41dc29 MOV	0x118(%RBX),%RCX

(310) 0x41dc30 MOV	0x130(%RBX),%RDI

(310) 0x41dc37 MOV	%RAX,%RSI

(310) 0x41dc3a AND	$0x7ffffffc,%RSI

(310) 0x41dc41 JE	41dc90

(310) 0x41dc43 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41dc47 XOR	%R8D,%R8D

(310) 0x41dc4a NOPW	(%RAX,%RAX,1)

  (320) 0x41dc50 VADDPD	(%RDI,%R8,8),%YMM0,%YMM0

  (320) 0x41dc56 VFMADD231PD	(%RCX,%R8,8),%YMM3,%YMM0

  (320) 0x41dc5c ADD	$0x4,%R8

  (320) 0x41dc60 CMP	%RSI,%R8

  (320) 0x41dc63 JB	41dc50

(310) 0x41dc65 VEXTRACTF128	$0x1,%YMM0,%XMM1

(310) 0x41dc6b VADDPD	%XMM1,%XMM0,%XMM0

(310) 0x41dc6f VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

(310) 0x41dc74 VADDSD	%XMM1,%XMM0,%XMM0

(310) 0x41dc78 MOV	%RSI,%R8

(310) 0x41dc7b CMP	%RAX,%RSI

(310) 0x41dc7e JNE	41dca0

(310) 0x41dc80 JMP	41dcb4

0x41dc82 NOPW	%CS:(%RAX,%RAX,1)

(310) 0x41dc90 VXORPD	%XMM0,%XMM0,%XMM0

(310) 0x41dc94 XOR	%R8D,%R8D

(310) 0x41dc97 NOPW	(%RAX,%RAX,1)

  (311) 0x41dca0 VADDSD	(%RDI,%R8,8),%XMM0,%XMM0

  (311) 0x41dca6 VFMADD231SD	(%RCX,%R8,8),%XMM2,%XMM0

  (311) 0x41dcac INC	%R8

  (311) 0x41dcaf CMP	%R8,%RAX

  (311) 0x41dcb2 JNE	41dca0

(310) 0x41dcb4 MOV	0x60(%R13),%RDI

(310) 0x41dcb8 MOV	0x8(%RDI,%R12,8),%R8

(310) 0x41dcbd MOV	0x18(%RDI,%R12,8),%RDI

(310) 0x41dcc2 MOV	%R8,%R9

(310) 0x41dcc5 SAR	$0x3f,%R9

(310) 0x41dcc9 ANDN	%R8,%R9,%R9

(310) 0x41dcce TEST	%R8,%R8

(310) 0x41dcd1 LEA	(%RAX,%R9,2),%R9

(310) 0x41dcd5 LEA	-0x8(%RDI,%R9,8),%R12

(310) 0x41dcda LEA	(%R14,%R14,2),%R9

(310) 0x41dcde LEA	(%RDX,%R9,8),%R10

(310) 0x41dce2 MOV	$0,%R11D

(310) 0x41dce8 CMOVS	%R8,%R11

(310) 0x41dcec CMP	%R10,%R12

(310) 0x41dcef JB	41dd50

(310) 0x41dcf1 SAL	$0x4,%R11

(310) 0x41dcf5 ADD	%RDI,%R11

(310) 0x41dcf8 LEA	0x10(%RDX,%R9,8),%R12

(310) 0x41dcfd CMP	%R11,%R12

(310) 0x41dd00 JB	41dd50

(310) 0x41dd02 SAL	$0x3,%R8

(310) 0x41dd06 XOR	%EDX,%EDX

(310) 0x41dd08 NOPL	(%RAX,%RAX,1)

  (319) 0x41dd10 VXORPD	%XMM1,%XMM1,%XMM1

  (319) 0x41dd14 XOR	%ESI,%ESI

  (319) 0x41dd16 NOPW	%CS:(%RAX,%RAX,1)

    (318) 0x41dd20 VMOVSD	(%RDI,%RSI,8),%XMM2

    (318) 0x41dd25 VFMADD231SD	(%RCX,%RSI,8),%XMM2,%XMM1

    (318) 0x41dd2b INC	%RSI

    (318) 0x41dd2e CMP	%RSI,%RAX

    (318) 0x41dd31 JNE	41dd20

  (319) 0x41dd33 VMOVSD	%XMM1,(%R10,%RDX,8)

  (319) 0x41dd39 LEA	0x1(%RDX),%RSI

  (319) 0x41dd3d ADD	%R8,%RDI

  (319) 0x41dd40 CMP	$0x2,%RDX

  (319) 0x41dd44 MOV	%RSI,%RDX

  (319) 0x41dd47 JNE	41dd10

(310) 0x41dd49 JMP	41db1a

0x41dd4e XCHG	%AX,%AX

(310) 0x41dd50 TEST	%RSI,%RSI

(310) 0x41dd53 JE	41dd92

(310) 0x41dd55 VXORPD	%XMM1,%XMM1,%XMM1

(310) 0x41dd59 XOR	%R10D,%R10D

(310) 0x41dd5c NOPL	(%RAX)

  (317) 0x41dd60 VMOVUPD	(%RDI,%R10,8),%YMM2

  (317) 0x41dd66 VFMADD231PD	(%RCX,%R10,8),%YMM2,%YMM1

  (317) 0x41dd6c ADD	$0x4,%R10

  (317) 0x41dd70 CMP	%RSI,%R10

  (317) 0x41dd73 JB	41dd60

(310) 0x41dd75 VEXTRACTF128	$0x1,%YMM1,%XMM2

(310) 0x41dd7b VADDPD	%XMM2,%XMM1,%XMM1

(310) 0x41dd7f VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

(310) 0x41dd84 VADDSD	%XMM2,%XMM1,%XMM1

(310) 0x41dd88 MOV	%RSI,%R10

(310) 0x41dd8b CMP	%RAX,%RSI

(310) 0x41dd8e JNE	41dda0

(310) 0x41dd90 JMP	41ddb4

(310) 0x41dd92 VXORPD	%XMM1,%XMM1,%XMM1

(310) 0x41dd96 XOR	%R10D,%R10D

(310) 0x41dd99 NOPL	(%RAX)

  (312) 0x41dda0 VMOVSD	(%RDI,%R10,8),%XMM2

  (312) 0x41dda6 VFMADD231SD	(%RCX,%R10,8),%XMM2,%XMM1

  (312) 0x41ddac INC	%R10

  (312) 0x41ddaf CMP	%R10,%RAX

  (312) 0x41ddb2 JNE	41dda0

(310) 0x41ddb4 VMOVSD	%XMM1,(%RDX,%R9,8)

(310) 0x41ddba TEST	%RSI,%RSI

(310) 0x41ddbd JE	41de02

(310) 0x41ddbf LEA	(%RDI,%R8,8),%R10

(310) 0x41ddc3 VXORPD	%XMM1,%XMM1,%XMM1

(310) 0x41ddc7 XOR	%R11D,%R11D

(310) 0x41ddca NOPW	(%RAX,%RAX,1)

  (316) 0x41ddd0 VMOVUPD	(%R10,%R11,8),%YMM2

  (316) 0x41ddd6 VFMADD231PD	(%RCX,%R11,8),%YMM2,%YMM1

  (316) 0x41dddc ADD	$0x4,%R11

  (316) 0x41dde0 CMP	%RSI,%R11

  (316) 0x41dde3 JB	41ddd0

(310) 0x41dde5 VEXTRACTF128	$0x1,%YMM1,%XMM2

(310) 0x41ddeb VADDPD	%XMM2,%XMM1,%XMM1

(310) 0x41ddef VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

(310) 0x41ddf4 VADDSD	%XMM2,%XMM1,%XMM1

(310) 0x41ddf8 MOV	%RSI,%R10

(310) 0x41ddfb CMP	%RAX,%RSI

(310) 0x41ddfe JNE	41de09

(310) 0x41de00 JMP	41de24

(310) 0x41de02 VXORPD	%XMM1,%XMM1,%XMM1

(310) 0x41de06 XOR	%R10D,%R10D

(310) 0x41de09 LEA	(%RDI,%R8,8),%R11

(310) 0x41de0d NOPL	(%RAX)

  (313) 0x41de10 VMOVSD	(%R11,%R10,8),%XMM2

  (313) 0x41de16 VFMADD231SD	(%RCX,%R10,8),%XMM2,%XMM1

  (313) 0x41de1c INC	%R10

  (313) 0x41de1f CMP	%R10,%RAX

  (313) 0x41de22 JNE	41de10

(310) 0x41de24 VMOVSD	%XMM1,0x8(%RDX,%R9,8)

(310) 0x41de2b TEST	%RSI,%RSI

(310) 0x41de2e JE	41de7f

(310) 0x41de30 MOV	%R8,%R10

(310) 0x41de33 SAL	$0x4,%R10

(310) 0x41de37 ADD	%RDI,%R10

(310) 0x41de3a VXORPD	%XMM1,%XMM1,%XMM1

(310) 0x41de3e XOR	%R11D,%R11D

(310) 0x41de41 NOPW	%CS:(%RAX,%RAX,1)

  (315) 0x41de50 VMOVUPD	(%R10,%R11,8),%YMM2

  (315) 0x41de56 VFMADD231PD	(%RCX,%R11,8),%YMM2,%YMM1

  (315) 0x41de5c ADD	$0x4,%R11

  (315) 0x41de60 CMP	%RSI,%R11

  (315) 0x41de63 JB	41de50

(310) 0x41de65 VEXTRACTF128	$0x1,%YMM1,%XMM2

(310) 0x41de6b VADDPD	%XMM2,%XMM1,%XMM1

(310) 0x41de6f VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

(310) 0x41de74 VADDSD	%XMM2,%XMM1,%XMM1

(310) 0x41de78 CMP	%RAX,%RSI

(310) 0x41de7b JNE	41de85

(310) 0x41de7d JMP	41dea3

(310) 0x41de7f VXORPD	%XMM1,%XMM1,%XMM1

(310) 0x41de83 XOR	%ESI,%ESI

(310) 0x41de85 SAL	$0x4,%R8

(310) 0x41de89 ADD	%R8,%RDI

(310) 0x41de8c NOPL	(%RAX)

  (314) 0x41de90 VMOVSD	(%RDI,%RSI,8),%XMM2

  (314) 0x41de95 VFMADD231SD	(%RCX,%RSI,8),%XMM2,%XMM1

  (314) 0x41de9b INC	%RSI

  (314) 0x41de9e CMP	%RSI,%RAX

  (314) 0x41dea1 JNE	41de90

(310) 0x41dea3 VMOVSD	%XMM1,0x10(%RDX,%R9,8)

(310) 0x41deaa JMP	41db1a

0x41deaf MOV	0x94(%RBX),%R8D

0x41deb6 VXORPD	%XMM0,%XMM0,%XMM0

0x41deba TEST	%R8D,%R8D

0x41debd JNE	41ded9

0x41debf JMP	41e1a6

0x41dec4 MOV	-0x38(%RBP),%R14

0x41dec8 MOV	-0x30(%RBP),%R15

0x41decc VXORPD	%XMM0,%XMM0,%XMM0

0x41ded0 TEST	%R8D,%R8D

0x41ded3 JE	41e1a6

0x41ded9 MOVSXD	%R8D,%RAX

0x41dedc MOV	0x190(%RBX),%RDX

0x41dee3 MOV	0x18(%R15),%RSI

0x41dee7 LEA	-0x1(%RAX),%RCX

0x41deeb LEA	-0x8(,%RAX,8),%RDI

0x41def3 LEA	(%RDI,%RDI,2),%RDI

0x41def7 LEA	0x10(%RSI,%RDI,1),%R9

0x41defc CMP	%RDX,%R9

0x41deff JB	41df54

0x41df01 LEA	0x10(%RDX,%RDI,1),%RDI

0x41df06 CMP	%RSI,%RDI

0x41df09 JB	41df54

0x41df0b XOR	%EDI,%EDI

0x41df0d NOPL	(%RAX)

(309) 0x41df10 XOR	%R8D,%R8D

(309) 0x41df13 NOPW	%CS:(%RAX,%RAX,1)

  (308) 0x41df20 VMOVSD	(%RSI,%R8,8),%XMM1

  (308) 0x41df26 VADDSD	(%RDX,%R8,8),%XMM1,%XMM1

  (308) 0x41df2c VMOVSD	%XMM1,(%RSI,%R8,8)

  (308) 0x41df32 INC	%R8

  (308) 0x41df35 CMP	$0x3,%R8

  (308) 0x41df39 JNE	41df20

(309) 0x41df3b LEA	0x1(%RDI),%R8

(309) 0x41df3f ADD	$0x18,%RDX

(309) 0x41df43 ADD	$0x18,%RSI

(309) 0x41df47 CMP	%RCX,%RDI

(309) 0x41df4a MOV	%R8,%RDI

(309) 0x41df4d JNE	41df10

0x41df4f JMP	41e090

0x41df54 MOV	%R8D,%EDI

0x41df57 AND	$0x3,%EDI

0x41df5a CMP	$0x4,%R8D

0x41df5e JAE	41df68

0x41df60 XOR	%R8D,%R8D

0x41df63 JMP	41e036

0x41df68 MOV	%RAX,%R9

0x41df6b AND	$-0x4,%R9

0x41df6f MOV	$0x58,%R10D

0x41df75 XOR	%R8D,%R8D

0x41df78 NOPL	(%RAX,%RAX,1)

(301) 0x41df80 VMOVUPD	-0x58(%RSI,%R10,1),%XMM1

(301) 0x41df87 VADDPD	-0x58(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41df8e VMOVUPD	%XMM1,-0x58(%RSI,%R10,1)

(301) 0x41df95 VMOVSD	-0x48(%RSI,%R10,1),%XMM1

(301) 0x41df9c VADDSD	-0x48(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41dfa3 VMOVSD	%XMM1,-0x48(%RSI,%R10,1)

(301) 0x41dfaa VMOVUPD	-0x40(%RSI,%R10,1),%XMM1

(301) 0x41dfb1 VADDPD	-0x40(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41dfb8 VMOVUPD	%XMM1,-0x40(%RSI,%R10,1)

(301) 0x41dfbf VMOVSD	-0x30(%RSI,%R10,1),%XMM1

(301) 0x41dfc6 VADDSD	-0x30(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41dfcd VMOVSD	%XMM1,-0x30(%RSI,%R10,1)

(301) 0x41dfd4 VMOVUPD	-0x28(%RSI,%R10,1),%XMM1

(301) 0x41dfdb VADDPD	-0x28(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41dfe2 VMOVUPD	%XMM1,-0x28(%RSI,%R10,1)

(301) 0x41dfe9 VMOVSD	-0x18(%RSI,%R10,1),%XMM1

(301) 0x41dff0 VADDSD	-0x18(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41dff7 VMOVSD	%XMM1,-0x18(%RSI,%R10,1)

(301) 0x41dffe VMOVUPD	-0x10(%RSI,%R10,1),%XMM1

(301) 0x41e005 VADDPD	-0x10(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41e00c VMOVUPD	%XMM1,-0x10(%RSI,%R10,1)

(301) 0x41e013 VMOVSD	(%RSI,%R10,1),%XMM1

(301) 0x41e019 VADDSD	(%RDX,%R10,1),%XMM1,%XMM1

(301) 0x41e01f VMOVSD	%XMM1,(%RSI,%R10,1)

(301) 0x41e025 ADD	$0x4,%R8

(301) 0x41e029 ADD	$0x60,%R10

(301) 0x41e02d CMP	%R8,%R9

(301) 0x41e030 JNE	41df80

0x41e036 TEST	%RDI,%RDI

0x41e039 JE	41e090

0x41e03b LEA	(%R8,%R8,2),%R8

0x41e03f LEA	0x10(%RDX,%R8,8),%RDX

0x41e044 LEA	0x10(%RSI,%R8,8),%RSI

0x41e049 SAL	$0x3,%EDI

0x41e04c LEA	(%RDI,%RDI,2),%RDI

0x41e050 XOR	%R8D,%R8D

0x41e053 NOPW	%CS:(%RAX,%RAX,1)

(307) 0x41e060 VMOVUPD	-0x10(%RSI,%R8,1),%XMM1

(307) 0x41e067 VADDPD	-0x10(%RDX,%R8,1),%XMM1,%XMM1

(307) 0x41e06e VMOVUPD	%XMM1,-0x10(%RSI,%R8,1)

(307) 0x41e075 VMOVSD	(%RSI,%R8,1),%XMM1

(307) 0x41e07b VADDSD	(%RDX,%R8,1),%XMM1,%XMM1

(307) 0x41e081 VMOVSD	%XMM1,(%RSI,%R8,1)

(307) 0x41e087 ADD	$0x18,%R8

(307) 0x41e08b CMP	%R8,%RDI

(307) 0x41e08e JNE	41e060

0x41e090 MOV	0x1b8(%RBX),%RDX

0x41e097 MOV	0x18(%R14),%RSI

0x41e09b LEA	(%RSI,%RCX,8),%RDI

0x41e09f CMP	%RDX,%RDI

0x41e0a2 JB	41e0c9

0x41e0a4 LEA	(%RDX,%RCX,8),%RCX

0x41e0a8 CMP	%RSI,%RCX

0x41e0ab JB	41e0c9

0x41e0ad XOR	%ECX,%ECX

0x41e0af NOP

(306) 0x41e0b0 VMOVSD	(%RSI,%RCX,8),%XMM1

(306) 0x41e0b5 VSUBSD	(%RDX,%RCX,8),%XMM1,%XMM1

(306) 0x41e0ba VMOVSD	%XMM1,(%RSI,%RCX,8)

(306) 0x41e0bf INC	%RCX

(306) 0x41e0c2 CMP	%RCX,%RAX

(306) 0x41e0c5 JNE	41e0b0

0x41e0c7 JMP	41e127

0x41e0c9 MOV	%RAX,%RCX

0x41e0cc AND	$-0x4,%RCX

0x41e0d0 JE	41e102

0x41e0d2 LEA	-0x1(%RCX),%RDI

0x41e0d6 XOR	%R8D,%R8D

0x41e0d9 NOPL	(%RAX)

(305) 0x41e0e0 VMOVUPD	(%RSI,%R8,8),%YMM1

(305) 0x41e0e6 VSUBPD	(%RDX,%R8,8),%YMM1,%YMM1

(305) 0x41e0ec VMOVUPD	%YMM1,(%RSI,%R8,8)

(305) 0x41e0f2 ADD	$0x4,%R8

(305) 0x41e0f6 CMP	%RDI,%R8

(305) 0x41e0f9 JBE	41e0e0

0x41e0fb CMP	%RAX,%RCX

0x41e0fe JNE	41e110

0x41e100 JMP	41e127

0x41e102 XOR	%ECX,%ECX

0x41e104 NOPW	%CS:(%RAX,%RAX,1)

(302) 0x41e110 VMOVSD	(%RSI,%RCX,8),%XMM1

(302) 0x41e115 VSUBSD	(%RDX,%RCX,8),%XMM1,%XMM1

(302) 0x41e11a VMOVSD	%XMM1,(%RSI,%RCX,8)

(302) 0x41e11f INC	%RCX

(302) 0x41e122 CMP	%RCX,%RAX

(302) 0x41e125 JNE	41e110

0x41e127 LEA	(,%RAX,8),%RCX

0x41e12f TEST	%RCX,%RCX

0x41e132 JE	41e1a6

0x41e134 MOV	$0x1fffffffffffffff,%RDX

0x41e13e MOV	0xf0(%RBX),%RCX

0x41e145 ADD	%RDX,%RAX

0x41e148 AND	%RDX,%RAX

0x41e14b INC	%RAX

0x41e14e MOV	$0x3ffffffffffffffc,%RDX

0x41e158 AND	%RAX,%RDX

0x41e15b JE	41e193

0x41e15d VXORPD	%XMM0,%XMM0,%XMM0

0x41e161 XOR	%ESI,%ESI

0x41e163 NOPW	%CS:(%RAX,%RAX,1)

(304) 0x41e170 VADDPD	(%RCX,%RSI,8),%YMM0,%YMM0

(304) 0x41e175 ADD	$0x4,%RSI

(304) 0x41e179 CMP	%RDX,%RSI

(304) 0x41e17c JB	41e170

0x41e17e VEXTRACTF128	$0x1,%YMM0,%XMM1

0x41e184 VADDPD	%XMM1,%XMM0,%XMM0

0x41e188 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

0x41e18d VADDSD	%XMM1,%XMM0,%XMM0

0x41e191 JMP	41e1a1

0x41e193 XOR	%EDX,%EDX

0x41e195 VXORPD	%XMM0,%XMM0,%XMM0

(303) 0x41e199 VADDSD	(%RCX,%RDX,8),%XMM0,%XMM0

(303) 0x41e19e INC	%RDX

(303) 0x41e1a1 CMP	%RDX,%RAX

(303) 0x41e1a4 JNE	41e199

0x41e1a6 VXORPD	0xdee98(%RIP){1to2},%XMM0,%XMM0

0x41e1b0 VMOVLPD	%XMM0,0x10(%RBX)

0x41e1b5 ADD	$0x18,%RSP

0x41e1b9 POP	%RBX

0x41e1ba POP	%R12

0x41e1bc POP	%R13

0x41e1be POP	%R14

0x41e1c0 POP	%R15

0x41e1c2 POP	%RBP

0x41e1c3 VZEROUPPER

0x41e1c6 RET

0x41e1c7 NOPW	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►96.20+	miniqmcreference::OneBodyJastr[...]	OneBodyJastrowRef.h:122	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.extracted.112	miniqmc.cpp:397	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
►3.80+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:1046	exec
○	main.extracted.107	miniqmc.cpp:467	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

Path /

Average path: Display a virtual path defined by average values of all real paths

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	OneBodyJastrowRef.h:108-194
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h:49
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064,1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:169-170
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:108-113,165-174,186-194
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,242,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 22.33 to 7.00 cycles (3.19x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is poorly vectorized. Only 15% of vector register length is used (average across all SSE/AVX instructions).

Details

30% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX stores are used in vector version.
50% of SSE/AVX addition or subtraction instructions are used in vector version.
33% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

512-bits vectorization

On some x86 processors supporting 512-bits vectorization, compilers are often too conservative and limit vectorization to 256 bits. Performance can then be improved by enforcing 512-bits vectorization, especially with many vectorized and high trip count loops. 512-bits vectorization performance overhead (compared to 256-bits) is generally lower on newer processors.

Workaround

Recompile with -mprefer-vector-width=512

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

qmcplusplus::ParticleSet::getDistTableAB(int) const: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:108

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:174

Vector unaligned load/store instructions

Detected 1 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:141

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Use vector aligned instructions:
1. align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
2. inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Type of elements and instruction set

1 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 1 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time).

Matching between your function (in the source code) and the binary function

The binary function is composed of 3 FP arithmetical operations:

3: addition or subtraction

The binary function is loading 76 bytes (9 double precision FP elements). The binary function is storing 32 bytes (4 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.03 FP operations per loaded or stored byte.

General properties

nb instructions	132
nb uops	134
loop length	558
used x86 registers	15
used mmx registers	0
used xmm registers	2
used ymm registers	1
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	22.33 cycles
front end	22.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	9.60	9.67	6.00	6.00	5.50	9.53	9.60	5.50	5.50	5.50	9.60	6.00
cycles	9.60	9.67	6.00	6.00	5.50	9.53	9.60	5.50	5.50	5.50	9.60	6.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	22.33
Dispatch	9.67
Overall L1	22.33

Vectorization ratios

INT

all	5%
load	NA (no load vectorizable/vectorized instructions)
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	5%

all	80%
load	100%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	30%
load	100%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	33%

Vector efficiency ratios

INT

all	11%
load	NA (no load vectorizable/vectorized instructions)
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	22%
load	25%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	18%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	15%
load	25%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	18%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 22.33 cycles. At this rate:

1% of peak load performance is reached (3.40 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.43 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 22.33 to 9.67 cycles (2.31x speedup).

ASM code

In the binary file, the address of the function is: 41da90

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x18,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %R8B,%R8B	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 41deaf <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x41f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0xa8(%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x94(%RBX),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R8D,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 41deb6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x426>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R12,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R15,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x1fffffffffffffff,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41db3a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xaa>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x94(%RBX),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R8D,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JNE 41ded9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x449>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41e1a6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x716>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x38(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x30(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R8D,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JE 41e1a6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x716>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %R8D,%RAX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV 0x190(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%R15),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA -0x1(%RAX),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x8(,%RAX,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RDI,%RDI,2),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(%RSI,%RDI,1),%R9	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %RDX,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41df54 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x4c4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA 0x10(%RDX,%RDI,1),%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %RSI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41df54 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x4c4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41e090 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x600>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV %R8D,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x3,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x4,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JAE 41df68 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x4d8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41e036 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x5a6>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $-0x4,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
MOV $0x58,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RDI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41e090 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x600>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R8,%R8,2),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(%RDX,%R8,8),%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA 0x10(%RSI,%R8,8),%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SAL $0x3,%EDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RDI,%RDI,2),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x1b8(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%R14),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RSI,%RCX,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RDX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41e0c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x639>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDX,%RCX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41e0c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x639>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41e127 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x697>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 41e102 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x672>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RCX),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41e110 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x680>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41e127 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x697>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (,%RAX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RCX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41e1a6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x716>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x1fffffffffffffff,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV 0xf0(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x3ffffffffffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
AND %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 41e193 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x703>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
JMP 41e1a1 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x711>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD 0xdee98(%RIP){1to2},%XMM0,%XMM0	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMOVLPD %XMM0,0x10(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	OneBodyJastrowRef.h:108-194
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h:49
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064,1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:169-170
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:108-113,165-174,186-194
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,242,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 22.33 to 7.00 cycles (3.19x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is poorly vectorized. Only 15% of vector register length is used (average across all SSE/AVX instructions).

Details

30% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX stores are used in vector version.
50% of SSE/AVX addition or subtraction instructions are used in vector version.
33% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

512-bits vectorization

Workaround

Recompile with -mprefer-vector-width=512

CALL instructions

Detected function call instructions.

Details

qmcplusplus::ParticleSet::getDistTableAB(int) const: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:108

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:174

Vector unaligned load/store instructions

Detected 1 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:141

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Use vector aligned instructions:
1. align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
2. inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

The binary function is composed of 3 FP arithmetical operations:

3: addition or subtraction

The binary function is loading 76 bytes (9 double precision FP elements). The binary function is storing 32 bytes (4 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.03 FP operations per loaded or stored byte.

General properties

nb instructions	132
nb uops	134
loop length	558
used x86 registers	15
used mmx registers	0
used xmm registers	2
used ymm registers	1
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	22.33 cycles
front end	22.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	9.60	9.67	6.00	6.00	5.50	9.53	9.60	5.50	5.50	5.50	9.60	6.00
cycles	9.60	9.67	6.00	6.00	5.50	9.53	9.60	5.50	5.50	5.50	9.60	6.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	22.33
Dispatch	9.67
Overall L1	22.33

Vectorization ratios

INT

all	5%
load	NA (no load vectorizable/vectorized instructions)
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	5%

all	80%
load	100%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	30%
load	100%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	33%

Vector efficiency ratios

INT

all	11%
load	NA (no load vectorizable/vectorized instructions)
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	22%
load	25%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	18%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	15%
load	25%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	18%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 22.33 cycles. At this rate:

1% of peak load performance is reached (3.40 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.43 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 41da90

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x18,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %R8B,%R8B	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 41deaf <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x41f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0xa8(%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x94(%RBX),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R8D,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 41deb6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x426>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R12,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R15,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R14,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x1fffffffffffffff,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41db3a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xaa>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x94(%RBX),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R8D,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JNE 41ded9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x449>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41e1a6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x716>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV -0x38(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x30(%RBP),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R8D,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JE 41e1a6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x716>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %R8D,%RAX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV 0x190(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%R15),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA -0x1(%RAX),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x8(,%RAX,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RDI,%RDI,2),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(%RSI,%RDI,1),%R9	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %RDX,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41df54 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x4c4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA 0x10(%RDX,%RDI,1),%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMP %RSI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41df54 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x4c4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41e090 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x600>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV %R8D,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x3,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x4,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JAE 41df68 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x4d8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41e036 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x5a6>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $-0x4,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
MOV $0x58,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RDI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41e090 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x600>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R8,%R8,2),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x10(%RDX,%R8,8),%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA 0x10(%RSI,%R8,8),%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SAL $0x3,%EDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RDI,%RDI,2),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x1b8(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%R14),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RSI,%RCX,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RDX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41e0c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x639>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RDX,%RCX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41e0c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x639>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 41e127 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x697>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 41e102 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x672>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RCX),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41e110 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x680>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41e127 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x697>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (,%RAX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RCX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41e1a6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x716>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x1fffffffffffffff,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV 0xf0(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x3ffffffffffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
AND %RAX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 41e193 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x703>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
JMP 41e1a1 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x711>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD 0xdee98(%RIP){1to2},%XMM0,%XMM0	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMOVLPD %XMM0,0x10(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
ADD $0x18,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::Particle...–	0.01	0.01
○Loop 301 - OneBodyJastrowRef.h:169-169 - exec	0.00	0.01
▼Loop 310 - OneBodyJastrowRef.h:109-194 - exec–	0.00	0.00
○Loop 317 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.01
○Loop 316 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.01
○Loop 315 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.01
○Loop 320 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.01
○Loop 322 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 312 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 313 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 321 - stl_numeric.h:140-141 - exec	0.00	0.00
▼Loop 319 - OneBodyJastrowRef.h:188-194 - exec–	0.00	0.00
○Loop 318 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 311 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.00
○Loop 314 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 305 - OneBodyJastrowRef.h:171-172 - exec	0.00	0.00
○Loop 304 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 302 - OneBodyJastrowRef.h:171-172 - exec	0.00	0.00
○Loop 306 - OneBodyJastrowRef.h:171-172 - exec	0.00	0.00
▼Loop 309 - OneBodyJastrowRef.h:169-169 - exec–	0.00	0.00
○Loop 308 - TinyVectorOps.h:49-49 - exec	0.00	0.00
○Loop 303 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 307 - OneBodyJastrowRef.h:169-169 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Type of elements and instruction set

Matching between your function (in the source code) and the binary function

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code