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; }

0x4249c0 PUSH	%RBP

0x4249c1 MOV	%RSP,%RBP

0x4249c4 PUSH	%R15

0x4249c6 PUSH	%R14

0x4249c8 PUSH	%R13

0x4249ca PUSH	%R12

0x4249cc PUSH	%RBX

0x4249cd SUB	$0x18,%RSP

0x4249d1 MOV	%RCX,%R14

0x4249d4 MOV	%RDX,%R15

0x4249d7 MOV	%RDI,%RBX

0x4249da TEST	%R8B,%R8B

0x4249dd JE	424ec0

0x4249e3 MOV	%RSI,%R12

0x4249e6 MOV	0xa8(%RBX),%ESI

0x4249ec MOV	%R12,%RDI

0x4249ef CALL	4795d0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x4249f4 MOV	0x94(%RBX),%R8D

0x4249fb TEST	%R8D,%R8D

0x4249fe JLE	424ec7

0x424a04 MOV	%RAX,%R13

0x424a07 MOV	%R12,-0x40(%RBP)

0x424a0b MOV	%R15,-0x30(%RBP)

0x424a0f MOV	%R14,-0x38(%RBP)

0x424a13 MOV	$0x1fffffffffffffff,%R15

0x424a1d XOR	%R14D,%R14D

0x424a20 JMP	424a7a

0x424a22 NOPW	%CS:(%RAX,%RAX,1)

0x424a31 NOPW	%CS:(%RAX,%RAX,1)

(311) 0x424a40 LEA	(%R14,%R14,2),%RAX

(311) 0x424a44 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424a48 VMOVUPD	%XMM0,(%RDX,%RAX,8)

(311) 0x424a4d MOVQ	$0,0x10(%RDX,%RAX,8)

(311) 0x424a56 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424a5a MOV	0x1b8(%RBX),%RAX

(311) 0x424a61 VMOVSD	%XMM0,(%RAX,%R14,8)

(311) 0x424a67 INC	%R14

(311) 0x424a6a MOVSXD	0x94(%RBX),%R8

(311) 0x424a71 CMP	%R8,%R14

(311) 0x424a74 JGE	424f00

(311) 0x424a7a MOV	0x48(%R13),%RAX

(311) 0x424a7e LEA	(%R14,%R14,4),%R12

(311) 0x424a82 MOV	0x18(%RAX,%R12,8),%RCX

(311) 0x424a87 MOV	%RBX,%RDI

(311) 0x424a8a MOV	-0x40(%RBP),%RSI

(311) 0x424a8e MOV	%R14D,%EDX

(311) 0x424a91 VZEROUPPER

(311) 0x424a94 CALL	427540 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>

(311) 0x424a99 MOVSXD	0x90(%RBX),%RAX

(311) 0x424aa0 TEST	%R15,%RAX

(311) 0x424aa3 JE	424b40

(311) 0x424aa9 MOV	0x100(%RBX),%RCX

(311) 0x424ab0 LEA	(%RAX,%R15,1),%RDX

(311) 0x424ab4 AND	%R15,%RDX

(311) 0x424ab7 INC	%RDX

(311) 0x424aba MOV	%RDX,%RSI

(311) 0x424abd MOV	$0x3ffffffffffffffc,%RDI

(311) 0x424ac7 AND	%RDI,%RSI

(311) 0x424aca VMOVSD	0x1136fe(%RIP),%XMM2

(311) 0x424ad2 VBROADCASTSD	0x1136f5(%RIP),%YMM3

(311) 0x424adb JE	424b80

(311) 0x424ae1 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424ae5 XOR	%EDI,%EDI

(311) 0x424ae7 NOPW	(%RAX,%RAX,1)

  (323) 0x424af0 VADDPD	(%RCX,%RDI,8),%YMM0,%YMM0

  (323) 0x424af5 ADD	$0x4,%RDI

  (323) 0x424af9 CMP	%RSI,%RDI

  (323) 0x424afc JB	424af0

(311) 0x424afe VEXTRACTF128	$0x1,%YMM0,%XMM1

(311) 0x424b04 VADDPD	%XMM1,%XMM0,%XMM0

(311) 0x424b08 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

(311) 0x424b0d VADDSD	%XMM1,%XMM0,%XMM0

(311) 0x424b11 JMP	424b98

0x424b16 NOPW	%CS:(%RAX,%RAX,1)

0x424b25 NOPW	%CS:(%RAX,%RAX,1)

0x424b34 NOPW	%CS:(%RAX,%RAX,1)

(311) 0x424b40 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424b44 VMOVSD	0x113684(%RIP),%XMM2

(311) 0x424b4c VBROADCASTSD	0x11367b(%RIP),%YMM3

(311) 0x424b55 JMP	424b9d

0x424b57 NOPW	%CS:(%RAX,%RAX,1)

0x424b66 NOPW	%CS:(%RAX,%RAX,1)

0x424b75 NOPW	%CS:(%RAX,%RAX,1)

(311) 0x424b80 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424b84 XOR	%ESI,%ESI

(311) 0x424b86 NOPW	%CS:(%RAX,%RAX,1)

  (322) 0x424b90 VADDSD	(%RCX,%RSI,8),%XMM0,%XMM0

  (322) 0x424b95 INC	%RSI

  (322) 0x424b98 CMP	%RSI,%RDX

  (322) 0x424b9b JNE	424b90

(311) 0x424b9d MOV	0xf0(%RBX),%RCX

(311) 0x424ba4 VMOVSD	%XMM0,(%RCX,%R14,8)

(311) 0x424baa MOV	0x190(%RBX),%RDX

(311) 0x424bb1 TEST	%EAX,%EAX

(311) 0x424bb3 JLE	424a40

(311) 0x424bb9 MOV	0x118(%RBX),%RCX

(311) 0x424bc0 MOV	0x130(%RBX),%RDI

(311) 0x424bc7 MOV	%RAX,%RSI

(311) 0x424bca AND	$0x7ffffffc,%RSI

(311) 0x424bd1 JE	424c40

(311) 0x424bd3 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424bd7 XOR	%R8D,%R8D

(311) 0x424bda NOPW	(%RAX,%RAX,1)

  (321) 0x424be0 VADDPD	(%RDI,%R8,8),%YMM0,%YMM0

  (321) 0x424be6 VFMADD231PD	(%RCX,%R8,8),%YMM3,%YMM0

  (321) 0x424bec ADD	$0x4,%R8

  (321) 0x424bf0 CMP	%RSI,%R8

  (321) 0x424bf3 JB	424be0

(311) 0x424bf5 VEXTRACTF128	$0x1,%YMM0,%XMM1

(311) 0x424bfb VADDPD	%XMM1,%XMM0,%XMM0

(311) 0x424bff VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

(311) 0x424c04 VADDSD	%XMM1,%XMM0,%XMM0

(311) 0x424c08 MOV	%RSI,%R8

(311) 0x424c0b CMP	%RAX,%RSI

(311) 0x424c0e JNE	424c50

(311) 0x424c10 JMP	424c64

0x424c12 NOPW	%CS:(%RAX,%RAX,1)

0x424c21 NOPW	%CS:(%RAX,%RAX,1)

0x424c30 NOPW	%CS:(%RAX,%RAX,1)

0x424c3f NOP

(311) 0x424c40 VXORPD	%XMM0,%XMM0,%XMM0

(311) 0x424c44 XOR	%R8D,%R8D

(311) 0x424c47 NOPW	(%RAX,%RAX,1)

  (312) 0x424c50 VADDSD	(%RDI,%R8,8),%XMM0,%XMM0

  (312) 0x424c56 VFMADD231SD	(%RCX,%R8,8),%XMM2,%XMM0

  (312) 0x424c5c INC	%R8

  (312) 0x424c5f CMP	%R8,%RAX

  (312) 0x424c62 JNE	424c50

(311) 0x424c64 MOV	0x60(%R13),%RDI

(311) 0x424c68 MOV	0x8(%RDI,%R12,8),%R8

(311) 0x424c6d MOV	0x18(%RDI,%R12,8),%RDI

(311) 0x424c72 MOV	%R8,%R9

(311) 0x424c75 SAR	$0x3f,%R9

(311) 0x424c79 ANDN	%R8,%R9,%R9

(311) 0x424c7e TEST	%R8,%R8

(311) 0x424c81 LEA	(%RAX,%R9,2),%R9

(311) 0x424c85 LEA	-0x8(%RDI,%R9,8),%R12

(311) 0x424c8a LEA	(%R14,%R14,2),%R9

(311) 0x424c8e LEA	(%RDX,%R9,8),%R10

(311) 0x424c92 MOV	$0,%R11D

(311) 0x424c98 CMOVS	%R8,%R11

(311) 0x424c9c CMP	%R10,%R12

(311) 0x424c9f JB	424d00

(311) 0x424ca1 SAL	$0x4,%R11

(311) 0x424ca5 ADD	%RDI,%R11

(311) 0x424ca8 LEA	0x10(%RDX,%R9,8),%R12

(311) 0x424cad CMP	%R11,%R12

(311) 0x424cb0 JB	424d00

(311) 0x424cb2 SAL	$0x3,%R8

(311) 0x424cb6 XOR	%EDX,%EDX

(311) 0x424cb8 NOPL	(%RAX,%RAX,1)

  (320) 0x424cc0 VXORPD	%XMM1,%XMM1,%XMM1

  (320) 0x424cc4 XOR	%ESI,%ESI

  (320) 0x424cc6 NOPW	%CS:(%RAX,%RAX,1)

    (319) 0x424cd0 VMOVSD	(%RDI,%RSI,8),%XMM2

    (319) 0x424cd5 VFMADD231SD	(%RCX,%RSI,8),%XMM2,%XMM1

    (319) 0x424cdb INC	%RSI

    (319) 0x424cde CMP	%RSI,%RAX

    (319) 0x424ce1 JNE	424cd0

  (320) 0x424ce3 VMOVSD	%XMM1,(%R10,%RDX,8)

  (320) 0x424ce9 ADD	%R8,%RDI

  (320) 0x424cec CMP	$0x2,%RDX

  (320) 0x424cf0 LEA	0x1(%RDX),%RDX

  (320) 0x424cf4 JNE	424cc0

(311) 0x424cf6 JMP	424a5a

0x424cfb NOPL	(%RAX,%RAX,1)

(311) 0x424d00 TEST	%RSI,%RSI

(311) 0x424d03 JE	424d80

(311) 0x424d05 VXORPD	%XMM1,%XMM1,%XMM1

(311) 0x424d09 XOR	%R10D,%R10D

(311) 0x424d0c NOPL	(%RAX)

  (318) 0x424d10 VMOVUPD	(%RDI,%R10,8),%YMM2

  (318) 0x424d16 VFMADD231PD	(%RCX,%R10,8),%YMM2,%YMM1

  (318) 0x424d1c ADD	$0x4,%R10

  (318) 0x424d20 CMP	%RSI,%R10

  (318) 0x424d23 JB	424d10

(311) 0x424d25 VEXTRACTF128	$0x1,%YMM1,%XMM2

(311) 0x424d2b VADDPD	%XMM2,%XMM1,%XMM1

(311) 0x424d2f VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

(311) 0x424d34 VADDSD	%XMM2,%XMM1,%XMM1

(311) 0x424d38 MOV	%RSI,%R10

(311) 0x424d3b CMP	%RAX,%RSI

(311) 0x424d3e JNE	424d90

(311) 0x424d40 JMP	424da4

0x424d42 NOPW	%CS:(%RAX,%RAX,1)

0x424d51 NOPW	%CS:(%RAX,%RAX,1)

0x424d60 NOPW	%CS:(%RAX,%RAX,1)

0x424d6f NOPW	%CS:(%RAX,%RAX,1)

0x424d7e XCHG	%AX,%AX

(311) 0x424d80 VXORPD	%XMM1,%XMM1,%XMM1

(311) 0x424d84 XOR	%R10D,%R10D

(311) 0x424d87 NOPW	(%RAX,%RAX,1)

  (313) 0x424d90 VMOVSD	(%RDI,%R10,8),%XMM2

  (313) 0x424d96 VFMADD231SD	(%RCX,%R10,8),%XMM2,%XMM1

  (313) 0x424d9c INC	%R10

  (313) 0x424d9f CMP	%R10,%RAX

  (313) 0x424da2 JNE	424d90

(311) 0x424da4 VMOVSD	%XMM1,(%RDX,%R9,8)

(311) 0x424daa TEST	%RSI,%RSI

(311) 0x424dad JE	424e00

(311) 0x424daf LEA	(%RDI,%R8,8),%R10

(311) 0x424db3 VXORPD	%XMM1,%XMM1,%XMM1

(311) 0x424db7 XOR	%R11D,%R11D

(311) 0x424dba NOPW	(%RAX,%RAX,1)

  (317) 0x424dc0 VMOVUPD	(%R10,%R11,8),%YMM2

  (317) 0x424dc6 VFMADD231PD	(%RCX,%R11,8),%YMM2,%YMM1

  (317) 0x424dcc ADD	$0x4,%R11

  (317) 0x424dd0 CMP	%RSI,%R11

  (317) 0x424dd3 JB	424dc0

(311) 0x424dd5 VEXTRACTF128	$0x1,%YMM1,%XMM2

(311) 0x424ddb VADDPD	%XMM2,%XMM1,%XMM1

(311) 0x424ddf VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

(311) 0x424de4 VADDSD	%XMM2,%XMM1,%XMM1

(311) 0x424de8 MOV	%RSI,%R10

(311) 0x424deb CMP	%RAX,%RSI

(311) 0x424dee JNE	424e07

(311) 0x424df0 JMP	424e24

0x424df2 NOPW	%CS:(%RAX,%RAX,1)

(311) 0x424e00 VXORPD	%XMM1,%XMM1,%XMM1

(311) 0x424e04 XOR	%R10D,%R10D

(311) 0x424e07 LEA	(%RDI,%R8,8),%R11

(311) 0x424e0b NOPL	(%RAX,%RAX,1)

  (314) 0x424e10 VMOVSD	(%R11,%R10,8),%XMM2

  (314) 0x424e16 VFMADD231SD	(%RCX,%R10,8),%XMM2,%XMM1

  (314) 0x424e1c INC	%R10

  (314) 0x424e1f CMP	%R10,%RAX

  (314) 0x424e22 JNE	424e10

(311) 0x424e24 VMOVSD	%XMM1,0x8(%RDX,%R9,8)

(311) 0x424e2b TEST	%RSI,%RSI

(311) 0x424e2e JE	424e80

(311) 0x424e30 MOV	%R8,%R10

(311) 0x424e33 SAL	$0x4,%R10

(311) 0x424e37 ADD	%RDI,%R10

(311) 0x424e3a VXORPD	%XMM1,%XMM1,%XMM1

(311) 0x424e3e XOR	%R11D,%R11D

(311) 0x424e41 NOPW	%CS:(%RAX,%RAX,1)

  (316) 0x424e50 VMOVUPD	(%R10,%R11,8),%YMM2

  (316) 0x424e56 VFMADD231PD	(%RCX,%R11,8),%YMM2,%YMM1

  (316) 0x424e5c ADD	$0x4,%R11

  (316) 0x424e60 CMP	%RSI,%R11

  (316) 0x424e63 JB	424e50

(311) 0x424e65 VEXTRACTF128	$0x1,%YMM1,%XMM2

(311) 0x424e6b VADDPD	%XMM2,%XMM1,%XMM1

(311) 0x424e6f VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

(311) 0x424e74 VADDSD	%XMM2,%XMM1,%XMM1

(311) 0x424e78 CMP	%RAX,%RSI

(311) 0x424e7b JNE	424e86

(311) 0x424e7d JMP	424ea3

0x424e7f NOP

(311) 0x424e80 VXORPD	%XMM1,%XMM1,%XMM1

(311) 0x424e84 XOR	%ESI,%ESI

(311) 0x424e86 SAL	$0x4,%R8

(311) 0x424e8a ADD	%R8,%RDI

(311) 0x424e8d NOPL	(%RAX)

  (315) 0x424e90 VMOVSD	(%RDI,%RSI,8),%XMM2

  (315) 0x424e95 VFMADD231SD	(%RCX,%RSI,8),%XMM2,%XMM1

  (315) 0x424e9b INC	%RSI

  (315) 0x424e9e CMP	%RSI,%RAX

  (315) 0x424ea1 JNE	424e90

(311) 0x424ea3 VMOVSD	%XMM1,0x10(%RDX,%R9,8)

(311) 0x424eaa JMP	424a5a

0x424eaf NOPW	%CS:(%RAX,%RAX,1)

0x424ebe XCHG	%AX,%AX

0x424ec0 MOV	0x94(%RBX),%R8D

0x424ec7 VXORPD	%XMM0,%XMM0,%XMM0

0x424ecb TEST	%R8D,%R8D

0x424ece JNE	424f15

0x424ed0 JMP	425293

0x424ed5 NOPW	%CS:(%RAX,%RAX,1)

0x424ee4 NOPW	%CS:(%RAX,%RAX,1)

0x424ef3 NOPW	%CS:(%RAX,%RAX,1)

0x424f00 MOV	-0x38(%RBP),%R14

0x424f04 MOV	-0x30(%RBP),%R15

0x424f08 VXORPD	%XMM0,%XMM0,%XMM0

0x424f0c TEST	%R8D,%R8D

0x424f0f JE	425293

0x424f15 MOVSXD	%R8D,%RAX

0x424f18 MOV	0x190(%RBX),%RDX

0x424f1f MOV	0x18(%R15),%RSI

0x424f23 LEA	-0x1(%RAX),%RCX

0x424f27 LEA	-0x8(,%RAX,8),%RDI

0x424f2f LEA	(%RDI,%RDI,2),%RDI

0x424f33 LEA	0x10(%RSI,%RDI,1),%R9

0x424f38 CMP	%RDX,%R9

0x424f3b JB	424fc0

0x424f41 LEA	0x10(%RDX,%RDI,1),%RDI

0x424f46 CMP	%RSI,%RDI

0x424f49 JB	424fc0

0x424f4b XOR	%EDI,%EDI

0x424f4d NOPL	(%RAX)

(310) 0x424f50 XOR	%R8D,%R8D

(310) 0x424f53 NOPW	%CS:(%RAX,%RAX,1)

  (309) 0x424f60 VMOVSD	(%RSI,%R8,8),%XMM1

  (309) 0x424f66 VADDSD	(%RDX,%R8,8),%XMM1,%XMM1

  (309) 0x424f6c VMOVSD	%XMM1,(%RSI,%R8,8)

  (309) 0x424f72 INC	%R8

  (309) 0x424f75 CMP	$0x3,%R8

  (309) 0x424f79 JNE	424f60

(310) 0x424f7b ADD	$0x18,%RDX

(310) 0x424f7f ADD	$0x18,%RSI

(310) 0x424f83 CMP	%RCX,%RDI

(310) 0x424f86 LEA	0x1(%RDI),%RDI

(310) 0x424f8a JNE	424f50

0x424f8c JMP	425120

0x424f91 NOPW	%CS:(%RAX,%RAX,1)

0x424fa0 NOPW	%CS:(%RAX,%RAX,1)

0x424faf NOPW	%CS:(%RAX,%RAX,1)

0x424fbe XCHG	%AX,%AX

0x424fc0 MOV	%R8D,%EDI

0x424fc3 AND	$0x3,%EDI

0x424fc6 CMP	$0x4,%R8D

0x424fca JAE	425000

0x424fcc XOR	%R8D,%R8D

0x424fcf JMP	4250c6

0x424fd4 NOPW	%CS:(%RAX,%RAX,1)

0x424fe3 NOPW	%CS:(%RAX,%RAX,1)

0x424ff2 NOPW	%CS:(%RAX,%RAX,1)

0x425000 MOV	%RAX,%R9

0x425003 AND	$-0x4,%R9

0x425007 MOV	$0x58,%R10D

0x42500d XOR	%R8D,%R8D

(302) 0x425010 VMOVUPD	-0x58(%RSI,%R10,1),%XMM1

(302) 0x425017 VADDPD	-0x58(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x42501e VMOVUPD	%XMM1,-0x58(%RSI,%R10,1)

(302) 0x425025 VMOVSD	-0x48(%RSI,%R10,1),%XMM1

(302) 0x42502c VADDSD	-0x48(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x425033 VMOVSD	%XMM1,-0x48(%RSI,%R10,1)

(302) 0x42503a VMOVUPD	-0x40(%RSI,%R10,1),%XMM1

(302) 0x425041 VADDPD	-0x40(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x425048 VMOVUPD	%XMM1,-0x40(%RSI,%R10,1)

(302) 0x42504f VMOVSD	-0x30(%RSI,%R10,1),%XMM1

(302) 0x425056 VADDSD	-0x30(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x42505d VMOVSD	%XMM1,-0x30(%RSI,%R10,1)

(302) 0x425064 VMOVUPD	-0x28(%RSI,%R10,1),%XMM1

(302) 0x42506b VADDPD	-0x28(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x425072 VMOVUPD	%XMM1,-0x28(%RSI,%R10,1)

(302) 0x425079 VMOVSD	-0x18(%RSI,%R10,1),%XMM1

(302) 0x425080 VADDSD	-0x18(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x425087 VMOVSD	%XMM1,-0x18(%RSI,%R10,1)

(302) 0x42508e VMOVUPD	-0x10(%RSI,%R10,1),%XMM1

(302) 0x425095 VADDPD	-0x10(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x42509c VMOVUPD	%XMM1,-0x10(%RSI,%R10,1)

(302) 0x4250a3 VMOVSD	(%RSI,%R10,1),%XMM1

(302) 0x4250a9 VADDSD	(%RDX,%R10,1),%XMM1,%XMM1

(302) 0x4250af VMOVSD	%XMM1,(%RSI,%R10,1)

(302) 0x4250b5 ADD	$0x4,%R8

(302) 0x4250b9 ADD	$0x60,%R10

(302) 0x4250bd CMP	%R8,%R9

(302) 0x4250c0 JNE	425010

0x4250c6 TEST	%RDI,%RDI

0x4250c9 JE	425120

0x4250cb LEA	(%R8,%R8,2),%R8

0x4250cf LEA	0x10(%RDX,%R8,8),%RDX

0x4250d4 LEA	0x10(%RSI,%R8,8),%RSI

0x4250d9 SAL	$0x3,%EDI

0x4250dc LEA	(%RDI,%RDI,2),%RDI

0x4250e0 XOR	%R8D,%R8D

0x4250e3 NOPW	%CS:(%RAX,%RAX,1)

(308) 0x4250f0 VMOVUPD	-0x10(%RSI,%R8,1),%XMM1

(308) 0x4250f7 VADDPD	-0x10(%RDX,%R8,1),%XMM1,%XMM1

(308) 0x4250fe VMOVUPD	%XMM1,-0x10(%RSI,%R8,1)

(308) 0x425105 VMOVSD	(%RSI,%R8,1),%XMM1

(308) 0x42510b VADDSD	(%RDX,%R8,1),%XMM1,%XMM1

(308) 0x425111 VMOVSD	%XMM1,(%RSI,%R8,1)

(308) 0x425117 ADD	$0x18,%R8

(308) 0x42511b CMP	%R8,%RDI

(308) 0x42511e JNE	4250f0

0x425120 MOV	0x1b8(%RBX),%RDX

0x425127 MOV	0x18(%R14),%RSI

0x42512b LEA	(%RSI,%RCX,8),%RDI

0x42512f CMP	%RDX,%RDI

0x425132 JB	425180

0x425134 LEA	(%RDX,%RCX,8),%RCX

0x425138 CMP	%RSI,%RCX

0x42513b JB	425180

0x42513d XOR	%ECX,%ECX

0x42513f NOP

(307) 0x425140 VMOVSD	(%RSI,%RCX,8),%XMM1

(307) 0x425145 VSUBSD	(%RDX,%RCX,8),%XMM1,%XMM1

(307) 0x42514a VMOVSD	%XMM1,(%RSI,%RCX,8)

(307) 0x42514f INC	%RCX

(307) 0x425152 CMP	%RCX,%RAX

(307) 0x425155 JNE	425140

0x425157 JMP	4251e7

0x42515c NOPW	%CS:(%RAX,%RAX,1)

0x42516b NOPW	%CS:(%RAX,%RAX,1)

0x42517a NOPW	(%RAX,%RAX,1)

0x425180 MOV	%RAX,%RCX

0x425183 AND	$-0x4,%RCX

0x425187 JE	4251c0

0x425189 LEA	-0x1(%RCX),%RDI

0x42518d XOR	%R8D,%R8D

(306) 0x425190 VMOVUPD	(%RSI,%R8,8),%YMM1

(306) 0x425196 VSUBPD	(%RDX,%R8,8),%YMM1,%YMM1

(306) 0x42519c VMOVUPD	%YMM1,(%RSI,%R8,8)

(306) 0x4251a2 ADD	$0x4,%R8

(306) 0x4251a6 CMP	%RDI,%R8

(306) 0x4251a9 JBE	425190

0x4251ab CMP	%RAX,%RCX

0x4251ae JNE	4251d0

0x4251b0 JMP	4251e7

0x4251b2 NOPW	%CS:(%RAX,%RAX,1)

0x4251c0 XOR	%ECX,%ECX

0x4251c2 NOPW	%CS:(%RAX,%RAX,1)

(303) 0x4251d0 VMOVSD	(%RSI,%RCX,8),%XMM1

(303) 0x4251d5 VSUBSD	(%RDX,%RCX,8),%XMM1,%XMM1

(303) 0x4251da VMOVSD	%XMM1,(%RSI,%RCX,8)

(303) 0x4251df INC	%RCX

(303) 0x4251e2 CMP	%RCX,%RAX

(303) 0x4251e5 JNE	4251d0

0x4251e7 LEA	(,%RAX,8),%RCX

0x4251ef TEST	%RCX,%RCX

0x4251f2 JE	425293

0x4251f8 MOV	$0x1fffffffffffffff,%RDX

0x425202 MOV	0xf0(%RBX),%RCX

0x425209 ADD	%RDX,%RAX

0x42520c AND	%RDX,%RAX

0x42520f INC	%RAX

0x425212 MOV	$0x3ffffffffffffffc,%RDX

0x42521c AND	%RAX,%RDX

0x42521f JE	425280

0x425221 VXORPD	%XMM0,%XMM0,%XMM0

0x425225 XOR	%ESI,%ESI

0x425227 NOPW	(%RAX,%RAX,1)

(305) 0x425230 VADDPD	(%RCX,%RSI,8),%YMM0,%YMM0

(305) 0x425235 ADD	$0x4,%RSI

(305) 0x425239 CMP	%RDX,%RSI

(305) 0x42523c JB	425230

0x42523e VEXTRACTF128	$0x1,%YMM0,%XMM1

0x425244 VADDPD	%XMM1,%XMM0,%XMM0

0x425248 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

0x42524d VADDSD	%XMM1,%XMM0,%XMM0

0x425251 JMP	42528e

0x425253 NOPW	%CS:(%RAX,%RAX,1)

0x425262 NOPW	%CS:(%RAX,%RAX,1)

0x425271 NOPW	%CS:(%RAX,%RAX,1)

0x425280 XOR	%EDX,%EDX

0x425282 VXORPD	%XMM0,%XMM0,%XMM0

(304) 0x425286 VADDSD	(%RCX,%RDX,8),%XMM0,%XMM0

(304) 0x42528b INC	%RDX

(304) 0x42528e CMP	%RDX,%RAX

(304) 0x425291 JNE	425286

0x425293 VXORPD	0x111dab(%RIP){1to2},%XMM0,%XMM0

0x42529d VMOVLPD	%XMM0,0x10(%RBX)

0x4252a2 ADD	$0x18,%RSP

0x4252a6 POP	%RBX

0x4252a7 POP	%R12

0x4252a9 POP	%R13

0x4252ab POP	%R14

0x4252ad POP	%R15

0x4252af POP	%RBP

0x4252b0 VZEROUPPER

0x4252b3 RET

0x4252b4 NOPW	%CS:(%RAX,%RAX,1)

0x4252be XCHG	%AX,%AX

Coverage (%)	Name	Source Location	Module
►96.06+	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
►3.94+	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 icx_4

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 27.83 to 7.00 cycles (3.98x 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	165
nb uops	167
loop length	990
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	27.83 cycles
front end	27.83 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	27.83
Dispatch	9.67
Overall L1	27.83

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 27.83 cycles. At this rate:

1% of peak load performance is reached (2.73 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (1.15 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 27.83 to 9.67 cycles (2.88x speedup).

ASM code

In the binary file, the address of the function is: 4249c0

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 424ec0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x500>	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 4795d0 <_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 424ec7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x507>	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 424a7a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xba>	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 %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 %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 %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 %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 %CS:(%RAX,%RAX,1)	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
NOPL (%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 %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 %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
NOPW %CS:(%RAX,%RAX,1)	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
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 424f15 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x555>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 425293 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8d3>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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 425293 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8d3>	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 424fc0 <_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 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 424fc0 <_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
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 425120 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x760>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 %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 %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 425000 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x640>	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 4250c6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x706>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
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 425120 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x760>	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 425180 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7c0>	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 425180 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7c0>	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 4251e7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x827>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
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 4251c0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x800>	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
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 4251d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x810>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 4251e7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x827>	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
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 425293 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8d3>	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 425280 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8c0>	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 (%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 42528e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8ce>	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 %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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 0x111dab(%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 %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

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_4

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 27.83 to 7.00 cycles (3.98x 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	165
nb uops	167
loop length	990
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	27.83 cycles
front end	27.83 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	27.83
Dispatch	9.67
Overall L1	27.83

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 27.83 cycles. At this rate:

1% of peak load performance is reached (2.73 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (1.15 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: 4249c0

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 424ec0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x500>	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 4795d0 <_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 424ec7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x507>	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 424a7a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xba>	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 %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 %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 %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 %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 %CS:(%RAX,%RAX,1)	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
NOPL (%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 %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 %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
NOPW %CS:(%RAX,%RAX,1)	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
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 424f15 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x555>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 425293 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8d3>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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 425293 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8d3>	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 424fc0 <_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 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 424fc0 <_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
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 425120 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x760>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 %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 %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 425000 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x640>	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 4250c6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x706>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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 %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
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 425120 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x760>	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 425180 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7c0>	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 425180 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7c0>	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 4251e7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x827>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
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 4251c0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x800>	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
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 4251d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x810>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 4251e7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x827>	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
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 425293 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8d3>	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 425280 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8c0>	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 (%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 42528e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8ce>	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 %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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 0x111dab(%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 %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

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::Particle...–	0.01	0.01
○Loop 302 - OneBodyJastrowRef.h:169-169 - exec	0.00	0.00
▼Loop 311 - OneBodyJastrowRef.h:109-194 - exec–	0.00	0.00
○Loop 317 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.01
○Loop 318 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.01
○Loop 316 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.01
○Loop 321 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.01
○Loop 323 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 322 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 313 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 315 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 312 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.00
○Loop 314 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
▼Loop 320 - OneBodyJastrowRef.h:188-194 - exec–	0.00	0.00
○Loop 319 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 306 - OneBodyJastrowRef.h:171-172 - exec	0.00	0.00
○Loop 305 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 308 - OneBodyJastrowRef.h:169-169 - exec	0.00	0.00
▼Loop 310 - OneBodyJastrowRef.h:169-169 - exec–	0.00	0.00
○Loop 309 - TinyVectorOps.h:49-49 - exec	0.00	0.00
○Loop 307 - OneBodyJastrowRef.h:171-172 - exec	0.00	0.00
○Loop 303 - OneBodyJastrowRef.h:171-172 - exec	0.00	0.00
○Loop 304 - stl_numeric.h:140-141 - 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