OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios( ...	Module: exec	Source: stl_vector.h:919-1064 [...]	Coverage (incl. loops): 0.03% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316

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

313:   inline int first(int igroup) const { return (*group_offsets_)[igroup]; }

314:

315:   ///return the last index of a group i

316:   inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 134 - 155

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

134:     for (int k = 0; k < ratios.size(); ++k)

135:       ratios[k] = std::exp(Vat[VP.refPtcl] - computeU(VP.getDistTableAB(myTableID).getDistRow(k).data()));

136:   }

137:

138:   inline valT computeU(const valT* dist)

139:   {

140:     valT curVat(0);

141:     if (NumGroups > 0)

142:     {

143:       for (int jg = 0; jg < NumGroups; ++jg)

144:       {

145:         if (F[jg] != nullptr)

146:           curVat += F[jg]->evaluateV(-1, Ions.first(jg), Ions.last(jg), dist, DistCompressed.data());

147:       }

148:     }

149:     else

150:     {

151:       for (int c = 0; c < Nions; ++c)

152:       {

153:         int gid = Ions.GroupID[c];

154:         if (F[gid] != nullptr)

155:           curVat += F[gid]->evaluate(dist[c]);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 166 - 260

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

166:     if (r >= cutoff_radius)

167:       return 0.0;

168:     r *= DeltaRInv;

169:     real_type ipart, t;

170:     t     = std::modf(r, &ipart);

171:     int i = (int)ipart;

172:     real_type tp[4];

173:     tp[0] = t * t * t;

[...]

179:       (SplineCoefs[i+0]*(A[ 0]*tp[0] + A[ 1]*tp[1] + A[ 2]*tp[2] + A[ 3]*tp[3])+

180:        SplineCoefs[i+1]*(A[ 4]*tp[0] + A[ 5]*tp[1] + A[ 6]*tp[2] + A[ 7]*tp[3])+

181:        SplineCoefs[i+2]*(A[ 8]*tp[0] + A[ 9]*tp[1] + A[10]*tp[2] + A[11]*tp[3])+

182:        SplineCoefs[i+3]*(A[12]*tp[0] + A[13]*tp[1] + A[14]*tp[2] + A[15]*tp[3]));

[...]

236:   for (int jat = 0; jat < iLimit; jat++)

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

240:     if (r < cutoff_radius && iStart + jat != iat)

241:       distArrayCompressed[iCount++] = distArray[jat];

242:   }

243:

244:   real_type d = 0.0;

245:   //#pragma omp simd reduction(+:d)

246:   for (int jat = 0; jat < iCount; jat++)

247:   {

248:     real_type r = distArrayCompressed[jat];

249:     r *= DeltaRInv;

250:     int i         = (int)r;

251:     real_type t   = r - real_type(i);

252:     real_type tp0 = t * t * t;

253:     real_type tp1 = t * t;

254:     real_type tp2 = t;

255:

256:     real_type d1 = SplineCoefs[i + 0] * (A[0] * tp0 + A[1] * tp1 + A[2] * tp2 + A[3]);

257:     real_type d2 = SplineCoefs[i + 1] * (A[4] * tp0 + A[5] * tp1 + A[6] * tp2 + A[7]);

258:     real_type d3 = SplineCoefs[i + 2] * (A[8] * tp0 + A[9] * tp1 + A[10] * tp2 + A[11]);

259:     real_type d4 = SplineCoefs[i + 3] * (A[12] * tp0 + A[13] * tp1 + A[14] * tp2 + A[15]);

260:     d += (d1 + d2 + d3 + d4);

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h: 1296 - 1296

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

1296:       { return _M_ptr; }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 919 - 1064

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

919:       { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); }

[...]

1046: 	return *(this->_M_impl._M_start + __n);

[...]

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

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

223:     return X[i];

[...]

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

0x238bd0 MOV	0x8(%RDX),%RAX

0x238bd4 CMP	%RAX,(%RDX)

0x238bd7 JE	23964f

0x238bdd PUSH	%RBP

0x238bde MOV	%RSP,%RBP

0x238be1 PUSH	%R15

0x238be3 PUSH	%R14

0x238be5 PUSH	%R13

0x238be7 PUSH	%R12

0x238be9 PUSH	%RBX

0x238bea AND	$-0x20,%RSP

0x238bee SUB	$0x180,%RSP

0x238bf5 MOV	%RDI,0x10(%RSP)

0x238bfa MOV	%RSI,0x30(%RSP)

0x238bff MOV	%RDX,0x28(%RSP)

0x238c04 XOR	%R15D,%R15D

0x238c07 XOR	%R14D,%R14D

0x238c0a JMP	238c62

(225) 0x238c0c VXORPD	%XMM14,%XMM14,%XMM14

(225) 0x238c11 NOPW	%CS:(%RAX,%RAX,1)

(225) 0x238c20 VMOVSD	0x48(%RSP),%XMM0

(225) 0x238c26 VSUBSD	%XMM14,%XMM0,%XMM0

(225) 0x238c2b VZEROUPPER

(225) 0x238c2e CALL	2f6fa0 <@plt_start@+0x360>

(225) 0x238c33 MOV	0x28(%RSP),%RAX

(225) 0x238c38 MOV	0x50(%RSP),%R14

(225) 0x238c3d MOV	(%RAX),%RCX

(225) 0x238c40 MOV	0x28(%RSP),%RAX

(225) 0x238c45 VMOVSD	%XMM0,(%RCX,%R14,8)

(225) 0x238c4b INC	%R14

(225) 0x238c4e MOV	0x8(%RAX),%RAX

(225) 0x238c52 SUB	%RCX,%RAX

(225) 0x238c55 SAR	$0x3,%RAX

(225) 0x238c59 CMP	%R14,%RAX

(225) 0x238c5c JBE	239641

(225) 0x238c62 MOV	0x30(%RSP),%RAX

(225) 0x238c67 MOV	0x10(%RSP),%RDX

(225) 0x238c6c MOV	0x30(%RSP),%RDI

(225) 0x238c71 MOVSXD	0x2a0(%RAX),%RCX

(225) 0x238c78 MOV	0xf0(%RDX),%RAX

(225) 0x238c7f VMOVSD	(%RAX,%RCX,8),%XMM0

(225) 0x238c84 MOV	0x10(%RSP),%RCX

(225) 0x238c89 MOV	0xa8(%RCX),%ESI

(225) 0x238c8f VMOVSD	%XMM0,0x48(%RSP)

(225) 0x238c95 CALL	27d7e0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

(225) 0x238c9a MOV	0x48(%RAX),%RAX

(225) 0x238c9e LEA	(%R14,%R14,4),%RCX

(225) 0x238ca2 MOV	%R14,0x50(%RSP)

(225) 0x238ca7 MOV	0x18(%RAX,%RCX,8),%RDI

(225) 0x238cac MOV	0x10(%RSP),%RCX

(225) 0x238cb1 MOV	0x98(%RCX),%EAX

(225) 0x238cb7 MOV	%RDI,0x40(%RSP)

(225) 0x238cbc TEST	%EAX,%EAX

(225) 0x238cbe JLE	2394d0

(225) 0x238cc4 MOV	0x10(%RSP),%RSI

(225) 0x238cc9 MOV	0x10(%RSP),%RDX

(225) 0x238cce MOV	0x10(%RSP),%RCX

(225) 0x238cd3 MOV	%RAX,0x38(%RSP)

(225) 0x238cd8 VXORPD	%XMM14,%XMM14,%XMM14

(225) 0x238cdd VPTERNLOGD	$-0x1,%ZMM13,%ZMM13,%ZMM13

(225) 0x238ce4 XOR	%R13D,%R13D

(225) 0x238ce7 MOV	0x1c8(%RCX),%RAX

(225) 0x238cee MOV	0xa0(%RDX),%R12

(225) 0x238cf5 MOV	0x38(%RSP),%RCX

(225) 0x238cfa MOV	0x148(%RSI),%RSI

(225) 0x238d01 MOV	%RAX,%RDX

(225) 0x238d04 MOV	%R12,0x18(%RSP)

(225) 0x238d09 MOV	%RAX,0x58(%RSP)

(225) 0x238d0e JMP	238d21

  (227) 0x238d10 VADDSD	%XMM14,%XMM15,%XMM14

  (227) 0x238d15 INC	%R13

  (227) 0x238d18 CMP	%RCX,%R13

  (227) 0x238d1b JE	238c20

  (227) 0x238d21 MOV	(%RDX,%R13,8),%R9

  (227) 0x238d25 TEST	%R9,%R9

  (227) 0x238d28 JE	238d70

  (227) 0x238d2a MOV	0x268(%R12),%R8

  (227) 0x238d32 VXORPD	%XMM15,%XMM15,%XMM15

  (227) 0x238d37 MOV	0x18(%R8),%R8

  (227) 0x238d3b MOVSXD	(%R8,%R13,4),%R11

  (227) 0x238d3f MOV	0x4(%R8,%R13,4),%R10D

  (227) 0x238d44 SUB	%R11D,%R10D

  (227) 0x238d47 JLE	238d10

  (227) 0x238d49 VMOVSD	0x8(%R9),%XMM0

  (227) 0x238d4f MOV	%R10D,%R8D

  (227) 0x238d52 CMP	$0x8,%R10D

  (227) 0x238d56 JAE	238d7d

  (227) 0x238d58 XOR	%EBX,%EBX

  (227) 0x238d5a XOR	%R10D,%R10D

  (227) 0x238d5d JMP	238ea0

0x238d62 NOPW	%CS:(%RAX,%RAX,1)

  (227) 0x238d70 INC	%R13

  (227) 0x238d73 CMP	%RCX,%R13

  (227) 0x238d76 JNE	238d21

(225) 0x238d78 JMP	238c20

  (227) 0x238d7d VMOVDQA64	-0x30187(%RIP),%ZMM3

  (227) 0x238d87 LEA	(%RDI,%R11,8),%R14

  (227) 0x238d8b VBROADCASTSD	%XMM0,%ZMM1

  (227) 0x238d91 MOV	%R8D,%EBX

  (227) 0x238d94 AND	$-0x8,%EBX

  (227) 0x238d97 VPBROADCASTQ	%R11,%ZMM2

  (227) 0x238d9d MOV	%R13,%RAX

  (227) 0x238da0 XOR	%R12D,%R12D

  (227) 0x238da3 XOR	%R10D,%R10D

  (227) 0x238da6 NOPW	%CS:(%RAX,%RAX,1)

    (228) 0x238db0 VMOVUPD	(%R14,%R12,8),%ZMM4

    (228) 0x238db7 VPADDQ	%ZMM2,%ZMM3,%ZMM5

    (228) 0x238dbd VPADDQ	-0x34ccf(%RIP){1to8},%ZMM3,%ZMM3

    (228) 0x238dc7 MOVSXD	%R10D,%R10

    (228) 0x238dca VPCMPNEQQ	%ZMM13,%ZMM5,%K1

    (228) 0x238dd1 VCMPPD	$0x1,%ZMM1,%ZMM4,%K1{%K1}

    (228) 0x238dd8 KMOVB	%K1,%R13D

    (228) 0x238ddc VCOMPRESSPD	%ZMM4,(%RSI,%R10,8){%K1}

    (228) 0x238de3 POPCNT	%R13D,%R13D

    (228) 0x238de8 KORTESTB	%K1,%K1

    (228) 0x238dec CMOVE	%R15D,%R13D

    (228) 0x238df0 ADD	$0x8,%R12

    (228) 0x238df4 ADD	%R13D,%R10D

    (228) 0x238df7 CMP	%R12,%RBX

    (228) 0x238dfa JNE	238db0

  (227) 0x238dfc MOV	0x18(%RSP),%R12

  (227) 0x238e01 MOV	%RAX,%R13

  (227) 0x238e04 CMP	%R8,%RBX

  (227) 0x238e07 JNE	238ea0

  (227) 0x238e0d TEST	%R10D,%R10D

  (227) 0x238e10 JLE	238d10

  (227) 0x238e16 VMOVSD	0x238(%R9),%XMM16

  (227) 0x238e1d VMOVUPD	0x18(%R9),%XMM17

  (227) 0x238e27 VMOVSD	0x28(%R9),%XMM18

  (227) 0x238e2e VMOVSD	0x30(%R9),%XMM19

  (227) 0x238e35 VMOVSD	0x38(%R9),%XMM2

  (227) 0x238e3b VMOVSD	0x40(%R9),%XMM5

  (227) 0x238e41 VMOVSD	0x48(%R9),%XMM0

  (227) 0x238e47 VMOVSD	0x50(%R9),%XMM3

  (227) 0x238e4d VMOVSD	0x58(%R9),%XMM6

  (227) 0x238e53 VMOVSD	0x60(%R9),%XMM7

  (227) 0x238e59 VMOVSD	0x68(%R9),%XMM8

  (227) 0x238e5f VMOVSD	0x70(%R9),%XMM9

  (227) 0x238e65 VMOVUPD	0x78(%R9),%XMM4

  (227) 0x238e6b VMOVSD	0x88(%R9),%XMM30

  (227) 0x238e72 VMOVSD	0x90(%R9),%XMM31

  (227) 0x238e79 MOV	0x218(%R9),%R8

  (227) 0x238e80 MOV	%R10D,%R9D

  (227) 0x238e83 CMP	$0x8,%R10D

  (227) 0x238e87 JAE	238eea

  (227) 0x238e89 VXORPD	%XMM15,%XMM15,%XMM15

  (227) 0x238e8e XOR	%R10D,%R10D

  (227) 0x238e91 JMP	239406

0x238e96 NOPW	%CS:(%RAX,%RAX,1)

  (227) 0x238ea0 LEA	(%RBX,%R11,1),%R14

  (227) 0x238ea4 SAL	$0x3,%R11

  (227) 0x238ea8 SUB	%RBX,%R8

  (227) 0x238eab LEA	(%R11,%RBX,8),%R11

  (227) 0x238eaf NOT	%R14

  (227) 0x238eb2 XOR	%EBX,%EBX

  (227) 0x238eb4 ADD	%RDI,%R11

  (227) 0x238eb7 JMP	238ecc

0x238eb9 NOPL	(%RAX)

    (231) 0x238ec0 INC	%RBX

    (231) 0x238ec3 CMP	%RBX,%R8

    (231) 0x238ec6 JE	238e0d

    (231) 0x238ecc CMP	%RBX,%R14

    (231) 0x238ecf JE	238ec0

    (231) 0x238ed1 VMOVSD	(%R11,%RBX,8),%XMM1

    (231) 0x238ed7 VUCOMISD	%XMM0,%XMM1

    (231) 0x238edb JAE	238ec0

    (231) 0x238edd MOVSXD	%R10D,%RAX

    (231) 0x238ee0 INC	%R10D

    (231) 0x238ee3 VMOVSD	%XMM1,(%RSI,%RAX,8)

    (231) 0x238ee8 JMP	238ec0

  (227) 0x238eea MOV	%R9D,%R11D

  (227) 0x238eed SHR	$0x3,%R11D

  (227) 0x238ef1 VMOVAPD	%XMM19,0x110(%RSP)

  (227) 0x238ef9 VMOVAPD	%XMM30,0x100(%RSP)

  (227) 0x238f01 VMOVAPD	%XMM31,0xf0(%RSP)

  (227) 0x238f09 VMOVAPD	%XMM16,0x130(%RSP)

  (227) 0x238f11 VBROADCASTSD	%XMM16,%YMM15

  (227) 0x238f17 VBROADCASTSD	%XMM17,%YMM16

  (227) 0x238f1d VMOVAPD	%YMM17,0x140(%RSP)

  (227) 0x238f25 VPERMPD	$0x55,%YMM17,%YMM17

  (227) 0x238f2c VBROADCASTSD	%XMM18,%YMM1

  (227) 0x238f32 VBROADCASTSD	%XMM19,%YMM19

  (227) 0x238f38 VBROADCASTSD	%XMM2,%YMM20

  (227) 0x238f3e VBROADCASTSD	%XMM5,%YMM21

  (227) 0x238f44 VBROADCASTSD	%XMM0,%YMM22

  (227) 0x238f4a VBROADCASTSD	%XMM3,%YMM23

  (227) 0x238f50 VBROADCASTSD	%XMM6,%YMM24

  (227) 0x238f56 VBROADCASTSD	%XMM7,%YMM25

  (227) 0x238f5c VBROADCASTSD	%XMM8,%YMM26

  (227) 0x238f62 VBROADCASTSD	%XMM9,%YMM27

  (227) 0x238f68 VBROADCASTSD	%XMM4,%YMM28

  (227) 0x238f6e VPERMPD	$0x55,%YMM4,%YMM29

  (227) 0x238f75 VBROADCASTSD	%XMM30,%YMM30

  (227) 0x238f7b VBROADCASTSD	%XMM31,%YMM31

  (227) 0x238f81 MOV	%R9D,%R10D

  (227) 0x238f84 VMOVAPD	%XMM0,0xb0(%RSP)

  (227) 0x238f8d VMOVAPD	%XMM3,0xa0(%RSP)

  (227) 0x238f96 AND	$-0x8,%R10D

  (227) 0x238f9a VXORPD	%XMM0,%XMM0,%XMM0

  (227) 0x238f9e VXORPD	%XMM3,%XMM3,%XMM3

  (227) 0x238fa2 MOV	%R13,0x60(%RSP)

  (227) 0x238fa7 VMOVSD	%XMM14,0x20(%RSP)

  (227) 0x238fad VMOVAPD	%XMM18,0x120(%RSP)

  (227) 0x238fb5 VMOVAPD	%XMM2,0xe0(%RSP)

  (227) 0x238fbe VMOVAPD	%XMM5,0xd0(%RSP)

  (227) 0x238fc7 VMOVAPD	%XMM6,0xc0(%RSP)

  (227) 0x238fd0 VMOVAPD	%XMM7,0x90(%RSP)

  (227) 0x238fd9 VMOVAPD	%XMM8,0x80(%RSP)

  (227) 0x238fe2 VMOVAPD	%XMM9,0x70(%RSP)

  (227) 0x238fe8 XOR	%EBX,%EBX

  (227) 0x238fea SAL	$0x6,%R11

  (227) 0x238fee XCHG	%AX,%AX

    (229) 0x238ff0 VMULPD	(%RSI,%RBX,1),%YMM15,%YMM7

    (229) 0x238ff5 VMULPD	0x20(%RSI,%RBX,1),%YMM15,%YMM9

    (229) 0x238ffb VMOVAPD	%YMM1,%YMM18

    (229) 0x239001 ADD	$0x40,%RBX

    (229) 0x239005 VCVTTPD2DQ	%YMM7,%XMM13

    (229) 0x239009 VCVTTPD2DQ	%YMM9,%XMM14

    (229) 0x23900e VROUNDPD	$0xb,%YMM7,%YMM8

    (229) 0x239014 VROUNDPD	$0xb,%YMM9,%YMM10

    (229) 0x23901a VPMOVSXDQ	%XMM13,%YMM2

    (229) 0x23901f VPMOVSXDQ	%XMM14,%YMM5

    (229) 0x239024 VSUBPD	%YMM8,%YMM7,%YMM8

    (229) 0x239029 VSUBPD	%YMM10,%YMM9,%YMM7

    (229) 0x23902e VPEXTRQ	$0x1,%XMM2,%R14

    (229) 0x239034 VMOVQ	%XMM2,%R12

    (229) 0x239039 VEXTRACTI128	$0x1,%YMM2,%XMM2

    (229) 0x23903f VMOVQ	%XMM5,%RCX

    (229) 0x239044 VPEXTRQ	$0x1,%XMM5,%RAX

    (229) 0x23904a VMOVQ	%XMM2,%R13

    (229) 0x23904f VPEXTRQ	$0x1,%XMM2,%RDX

    (229) 0x239055 VEXTRACTI128	$0x1,%YMM5,%XMM2

    (229) 0x23905b VMOVSD	(%R8,%R12,8),%XMM5

    (229) 0x239061 VMOVSD	(%R8,%RCX,8),%XMM6

    (229) 0x239067 VMULPD	%YMM8,%YMM8,%YMM12

    (229) 0x23906c VFMADD213PD	%YMM19,%YMM7,%YMM18

    (229) 0x239072 VMULPD	%YMM7,%YMM7,%YMM11

    (229) 0x239076 VMOVQ	%XMM2,%R15

    (229) 0x23907b VPEXTRQ	$0x1,%XMM2,%RDI

    (229) 0x239081 VMOVSD	(%R8,%R13,8),%XMM2

    (229) 0x239087 VMOVHPD	(%R8,%R14,8),%XMM5,%XMM5

    (229) 0x23908d VMOVHPD	(%R8,%RAX,8),%XMM6,%XMM6

    (229) 0x239093 VMOVHPD	(%R8,%RDX,8),%XMM2,%XMM2

    (229) 0x239099 VMULPD	%YMM8,%YMM12,%YMM10

    (229) 0x23909e VMULPD	%YMM7,%YMM11,%YMM9

    (229) 0x2390a2 VFMADD231PD	%YMM17,%YMM11,%YMM18

    (229) 0x2390a8 VFMADD231PD	%YMM16,%YMM9,%YMM18

    (229) 0x2390ae VINSERTF128	$0x1,%XMM2,%YMM5,%YMM2

    (229) 0x2390b4 VMOVSD	(%R8,%R15,8),%XMM5

    (229) 0x2390ba VMOVHPD	(%R8,%RDI,8),%XMM5,%XMM5

    (229) 0x2390c0 VINSERTF128	$0x1,%XMM5,%YMM6,%YMM5

    (229) 0x2390c6 VMOVAPD	%YMM1,%YMM6

    (229) 0x2390ca VFMADD213PD	%YMM19,%YMM8,%YMM6

    (229) 0x2390d0 VFMADD213PD	%YMM3,%YMM5,%YMM18

    (229) 0x2390d6 VMOVAPD	%YMM22,%YMM5

    (229) 0x2390dc VFMADD213PD	%YMM23,%YMM7,%YMM5

    (229) 0x2390e2 VFMADD231PD	%YMM17,%YMM12,%YMM6

    (229) 0x2390e8 VFMADD231PD	%YMM21,%YMM11,%YMM5

    (229) 0x2390ee VFMADD231PD	%YMM16,%YMM10,%YMM6

    (229) 0x2390f4 VFMADD231PD	%YMM20,%YMM9,%YMM5

    (229) 0x2390fa VFMADD213PD	%YMM0,%YMM2,%YMM6

    (229) 0x2390ff VPCMPEQD	%XMM2,%XMM2,%XMM2

    (229) 0x239103 VPSUBD	%XMM2,%XMM13,%XMM0

    (229) 0x239107 VPSUBD	%XMM2,%XMM14,%XMM2

    (229) 0x23910b VPMOVSXDQ	%XMM0,%YMM0

    (229) 0x239110 VPMOVSXDQ	%XMM2,%YMM2

    (229) 0x239115 VMOVQ	%XMM0,%RAX

    (229) 0x23911a VPEXTRQ	$0x1,%XMM0,%RCX

    (229) 0x239120 VEXTRACTI128	$0x1,%YMM0,%XMM0

    (229) 0x239126 VMOVQ	%XMM2,%R14

    (229) 0x23912b VPEXTRQ	$0x1,%XMM2,%R15

    (229) 0x239131 VPEXTRQ	$0x1,%XMM0,%RDX

    (229) 0x239137 VMOVQ	%XMM0,%RDI

    (229) 0x23913c VEXTRACTI128	$0x1,%YMM2,%XMM0

    (229) 0x239142 VMOVSD	(%R8,%RAX,8),%XMM2

    (229) 0x239148 VMOVSD	(%R8,%R14,8),%XMM3

    (229) 0x23914e VMOVQ	%XMM0,%R12

    (229) 0x239153 VPEXTRQ	$0x1,%XMM0,%R13

    (229) 0x239159 VMOVSD	(%R8,%RDI,8),%XMM0

    (229) 0x23915f VMOVHPD	(%R8,%RCX,8),%XMM2,%XMM2

    (229) 0x239165 VMOVHPD	(%R8,%R15,8),%XMM3,%XMM3

    (229) 0x23916b VMOVHPD	(%R8,%RDX,8),%XMM0,%XMM0

    (229) 0x239171 VINSERTF128	$0x1,%XMM0,%YMM2,%YMM0

    (229) 0x239177 VMOVSD	(%R8,%R12,8),%XMM2

    (229) 0x23917d VMOVHPD	(%R8,%R13,8),%XMM2,%XMM2

    (229) 0x239183 VINSERTF128	$0x1,%XMM2,%YMM3,%YMM2

    (229) 0x239189 VMOVAPD	%YMM22,%YMM3

    (229) 0x23918f VFMADD213PD	%YMM23,%YMM8,%YMM3

    (229) 0x239195 VFMADD213PD	%YMM18,%YMM2,%YMM5

    (229) 0x23919b VMOVAPD	%YMM26,%YMM18

    (229) 0x2391a1 VFMADD213PD	%YMM27,%YMM7,%YMM18

    (229) 0x2391a7 VFMADD213PD	%YMM31,%YMM30,%YMM7

    (229) 0x2391ad VFMADD231PD	%YMM21,%YMM12,%YMM3

    (229) 0x2391b3 VFMADD231PD	%YMM25,%YMM11,%YMM18

    (229) 0x2391b9 VFMADD231PD	%YMM11,%YMM29,%YMM7

    (229) 0x2391bf VFMADD231PD	%YMM20,%YMM10,%YMM3

    (229) 0x2391c5 VFMADD231PD	%YMM24,%YMM9,%YMM18

    (229) 0x2391cb VFMADD231PD	%YMM9,%YMM28,%YMM7

    (229) 0x2391d1 VFMADD213PD	%YMM6,%YMM0,%YMM3

    (229) 0x2391d6 VPBROADCASTD	-0x3510f(%RIP),%XMM0

    (229) 0x2391df VPADDD	%XMM0,%XMM13,%XMM2

    (229) 0x2391e3 VPADDD	%XMM0,%XMM14,%XMM0

    (229) 0x2391e7 VPMOVSXDQ	%XMM2,%YMM2

    (229) 0x2391ec VPMOVSXDQ	%XMM0,%YMM0

    (229) 0x2391f1 VMOVQ	%XMM2,%RAX

    (229) 0x2391f6 VPEXTRQ	$0x1,%XMM2,%RCX

    (229) 0x2391fc VEXTRACTI128	$0x1,%YMM2,%XMM2

    (229) 0x239202 VMOVQ	%XMM0,%R15

    (229) 0x239207 VPEXTRQ	$0x1,%XMM0,%R14

    (229) 0x23920d VEXTRACTI128	$0x1,%YMM0,%XMM0

    (229) 0x239213 VMOVQ	%XMM2,%RDX

    (229) 0x239218 VPEXTRQ	$0x1,%XMM2,%RDI

    (229) 0x23921e VMOVSD	(%R8,%RAX,8),%XMM2

    (229) 0x239224 VMOVQ	%XMM0,%R12

    (229) 0x239229 VPEXTRQ	$0x1,%XMM0,%R13

    (229) 0x23922f VMOVSD	(%R8,%R15,8),%XMM6

    (229) 0x239235 VMOVSD	(%R8,%RDX,8),%XMM0

    (229) 0x23923b VMOVHPD	(%R8,%RCX,8),%XMM2,%XMM2

    (229) 0x239241 VMOVHPD	(%R8,%R14,8),%XMM6,%XMM6

    (229) 0x239247 VMOVHPD	(%R8,%RDI,8),%XMM0,%XMM0

    (229) 0x23924d VINSERTF128	$0x1,%XMM0,%YMM2,%YMM0

    (229) 0x239253 VMOVSD	(%R8,%R12,8),%XMM2

    (229) 0x239259 VMOVHPD	(%R8,%R13,8),%XMM2,%XMM2

    (229) 0x23925f VINSERTF128	$0x1,%XMM2,%YMM6,%YMM2

    (229) 0x239265 VMOVAPD	%YMM26,%YMM6

    (229) 0x23926b VFMADD213PD	%YMM27,%YMM8,%YMM6

    (229) 0x239271 VFMADD213PD	%YMM31,%YMM30,%YMM8

    (229) 0x239277 VFMADD213PD	%YMM5,%YMM2,%YMM18

    (229) 0x23927d VFMADD231PD	%YMM25,%YMM12,%YMM6

    (229) 0x239283 VFMADD231PD	%YMM12,%YMM29,%YMM8

    (229) 0x239289 VFMADD231PD	%YMM24,%YMM10,%YMM6

    (229) 0x23928f VFMADD231PD	%YMM10,%YMM28,%YMM8

    (229) 0x239295 VFMADD213PD	%YMM3,%YMM0,%YMM6

    (229) 0x23929a VPBROADCASTD	-0x351cf(%RIP),%XMM0

    (229) 0x2392a3 VPADDD	%XMM0,%XMM13,%XMM2

    (229) 0x2392a7 VPADDD	%XMM0,%XMM14,%XMM0

    (229) 0x2392ab VPMOVSXDQ	%XMM2,%YMM2

    (229) 0x2392b0 VPMOVSXDQ	%XMM0,%YMM0

    (229) 0x2392b5 VMOVQ	%XMM2,%RAX

    (229) 0x2392ba VPEXTRQ	$0x1,%XMM2,%RCX

    (229) 0x2392c0 VEXTRACTI128	$0x1,%YMM2,%XMM2

    (229) 0x2392c6 VMOVQ	%XMM0,%R14

    (229) 0x2392cb VPEXTRQ	$0x1,%XMM0,%R15

    (229) 0x2392d1 VEXTRACTI128	$0x1,%YMM0,%XMM0

    (229) 0x2392d7 VMOVQ	%XMM2,%RDI

    (229) 0x2392dc VPEXTRQ	$0x1,%XMM2,%RDX

    (229) 0x2392e2 VMOVSD	(%R8,%RAX,8),%XMM2

    (229) 0x2392e8 VMOVQ	%XMM0,%R12

    (229) 0x2392ed VPEXTRQ	$0x1,%XMM0,%R13

    (229) 0x2392f3 VMOVSD	(%R8,%R14,8),%XMM3

    (229) 0x2392f9 VMOVSD	(%R8,%RDI,8),%XMM0

    (229) 0x2392ff VMOVHPD	(%R8,%RCX,8),%XMM2,%XMM2

    (229) 0x239305 VMOVHPD	(%R8,%R15,8),%XMM3,%XMM3

    (229) 0x23930b VMOVHPD	(%R8,%RDX,8),%XMM0,%XMM0

    (229) 0x239311 VINSERTF128	$0x1,%XMM0,%YMM2,%YMM2

    (229) 0x239317 VMOVSD	(%R8,%R12,8),%XMM0

    (229) 0x23931d VMOVHPD	(%R8,%R13,8),%XMM0,%XMM0

    (229) 0x239323 VINSERTF128	$0x1,%XMM0,%YMM3,%YMM5

    (229) 0x239329 VMOVAPD	%YMM8,%YMM0

    (229) 0x23932d VMOVAPD	%YMM7,%YMM3

    (229) 0x239331 VFMADD213PD	%YMM6,%YMM2,%YMM0

    (229) 0x239336 VFMADD213PD	%YMM18,%YMM5,%YMM3

    (229) 0x23933c CMP	%RBX,%R11

    (229) 0x23933f JNE	238ff0

  (227) 0x239345 VADDPD	%YMM0,%YMM3,%YMM0

  (227) 0x239349 VMOVSD	0x20(%RSP),%XMM14

  (227) 0x23934f VMOVAPD	0x130(%RSP),%XMM16

  (227) 0x239357 VMOVAPD	0x140(%RSP),%YMM17

  (227) 0x23935f VMOVAPD	0x120(%RSP),%XMM18

  (227) 0x239367 VMOVAPD	0x110(%RSP),%XMM19

  (227) 0x23936f VMOVAPD	0x100(%RSP),%XMM30

  (227) 0x239377 VMOVAPD	0xf0(%RSP),%XMM31

  (227) 0x23937f VMOVAPD	0xe0(%RSP),%XMM2

  (227) 0x239388 VMOVAPD	0xd0(%RSP),%XMM5

  (227) 0x239391 VMOVAPD	0xc0(%RSP),%XMM6

  (227) 0x23939a VMOVAPD	0xa0(%RSP),%XMM3

  (227) 0x2393a3 VMOVAPD	0x90(%RSP),%XMM7

  (227) 0x2393ac VMOVAPD	0x80(%RSP),%XMM8

  (227) 0x2393b5 VMOVAPD	0x70(%RSP),%XMM9

  (227) 0x2393bb MOV	0x40(%RSP),%RDI

  (227) 0x2393c0 MOV	0x38(%RSP),%RCX

  (227) 0x2393c5 MOV	0x58(%RSP),%RDX

  (227) 0x2393ca MOV	0x18(%RSP),%R12

  (227) 0x2393cf MOV	0x60(%RSP),%R13

  (227) 0x2393d4 MOV	$0,%R15D

  (227) 0x2393da VPTERNLOGD	$-0x1,%ZMM13,%ZMM13,%ZMM13

  (227) 0x2393e1 VEXTRACTF128	$0x1,%YMM0,%XMM1

  (227) 0x2393e7 VADDPD	%XMM1,%XMM0,%XMM0

  (227) 0x2393eb VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

  (227) 0x2393f0 VADDSD	%XMM1,%XMM0,%XMM15

  (227) 0x2393f4 VMOVAPD	0xb0(%RSP),%XMM0

  (227) 0x2393fd CMP	%R9,%R10

  (227) 0x239400 JE	238d10

  (227) 0x239406 VUNPCKLPD	%XMM8,%XMM0,%XMM0

  (227) 0x23940b VUNPCKLPD	%XMM9,%XMM3,%XMM3

  (227) 0x239410 VUNPCKLPD	%XMM7,%XMM5,%XMM7

  (227) 0x239414 VUNPCKLPD	%XMM6,%XMM2,%XMM8

  (227) 0x239418 NOPL	(%RAX,%RAX,1)

    (230) 0x239420 VMULSD	(%RSI,%R10,8),%XMM16,%XMM1

    (230) 0x239427 INC	%R10

    (230) 0x23942a VROUNDSD	$0xb,%XMM1,%XMM1,%XMM2

    (230) 0x239430 VCVTTSD2SI	%XMM1,%EAX

    (230) 0x239434 MOVSXD	%EAX,%R11

    (230) 0x239437 VSUBSD	%XMM2,%XMM1,%XMM1

    (230) 0x23943b VMOVAPD	%XMM18,%XMM2

    (230) 0x239441 VMULSD	%XMM1,%XMM1,%XMM6

    (230) 0x239445 VMOVDDUP	%XMM1,%XMM5

    (230) 0x239449 VFMADD213SD	%XMM19,%XMM1,%XMM2

    (230) 0x23944f VFMADD213PD	%XMM3,%XMM0,%XMM5

    (230) 0x239454 VMULSD	%XMM1,%XMM6,%XMM9

    (230) 0x239458 VMOVDDUP	%XMM6,%XMM6

    (230) 0x23945c VFMADD213SD	%XMM31,%XMM30,%XMM1

    (230) 0x239462 VMOVDDUP	%XMM9,%XMM9

    (230) 0x239467 VFMADD231PD	%XMM6,%XMM7,%XMM5

    (230) 0x23946c VUNPCKLPD	%XMM6,%XMM9,%XMM10

    (230) 0x239470 VMULPD	%XMM17,%XMM10,%XMM11

    (230) 0x239476 VMULPD	%XMM4,%XMM10,%XMM6

    (230) 0x23947a VFMADD231PD	%XMM9,%XMM8,%XMM5

    (230) 0x23947f VMULPD	0x8(%R8,%R11,8),%XMM5,%XMM5

    (230) 0x239486 VADDSD	%XMM2,%XMM11,%XMM2

    (230) 0x23948a VSHUFPD	$0x1,%XMM11,%XMM11,%XMM12

    (230) 0x239490 VSHUFPD	$0x1,%XMM6,%XMM6,%XMM9

    (230) 0x239495 VADDSD	%XMM6,%XMM1,%XMM1

    (230) 0x239499 VADDSD	%XMM2,%XMM12,%XMM2

    (230) 0x23949d VFMADD132SD	(%R8,%R11,8),%XMM15,%XMM2

    (230) 0x2394a3 VADDSD	%XMM1,%XMM9,%XMM1

    (230) 0x2394a7 VSHUFPD	$0x1,%XMM5,%XMM5,%XMM6

    (230) 0x2394ac VADDSD	%XMM6,%XMM5,%XMM5

    (230) 0x2394b0 VADDSD	%XMM5,%XMM2,%XMM15

    (230) 0x2394b4 VFMADD231SD	0x18(%R8,%R11,8),%XMM1,%XMM15

    (230) 0x2394bb CMP	%R10,%R9

    (230) 0x2394be JNE	239420

  (227) 0x2394c4 JMP	238d10

0x2394c9 NOPL	(%RAX)

(225) 0x2394d0 MOV	0x10(%RSP),%RAX

(225) 0x2394d5 MOV	0x90(%RAX),%EBX

(225) 0x2394db TEST	%EBX,%EBX

(225) 0x2394dd JLE	238c0c

(225) 0x2394e3 MOV	0x10(%RSP),%RAX

(225) 0x2394e8 VXORPD	%XMM14,%XMM14,%XMM14

(225) 0x2394ed XOR	%R14D,%R14D

(225) 0x2394f0 MOV	0xa0(%RAX),%RCX

(225) 0x2394f7 MOV	0x10(%RSP),%RAX

(225) 0x2394fc MOV	0x18(%RCX),%RCX

(225) 0x239500 MOV	0x1c8(%RAX),%R13

(225) 0x239507 MOV	%RCX,0x18(%RSP)

(225) 0x23950c JMP	239520

0x23950e XCHG	%AX,%AX

  (226) 0x239510 VADDSD	%XMM0,%XMM14,%XMM14

  (226) 0x239514 INC	%R14

  (226) 0x239517 CMP	%R14,%RBX

  (226) 0x23951a JE	238c20

  (226) 0x239520 MOVSXD	(%RCX,%R14,4),%RAX

  (226) 0x239524 MOV	(%R13,%RAX,8),%R12

  (226) 0x239529 TEST	%R12,%R12

  (226) 0x23952c JE	239514

  (226) 0x23952e VMOVSD	(%RDI,%R14,8),%XMM1

  (226) 0x239534 VMOVSD	0x8(%R12),%XMM2

  (226) 0x23953b VXORPD	%XMM0,%XMM0,%XMM0

  (226) 0x23953f VUCOMISD	%XMM1,%XMM2

  (226) 0x239543 JBE	239510

  (226) 0x239545 VMULSD	0x238(%R12),%XMM1,%XMM0

  (226) 0x23954f LEA	0x68(%RSP),%RDI

  (226) 0x239554 VMOVSD	%XMM14,0x20(%RSP)

  (226) 0x23955a CALL	2f6fb0 <@plt_start@+0x370>

  (226) 0x23955f VMOVSD	0x18(%R12),%XMM3

  (226) 0x239566 VMOVSD	0x30(%R12),%XMM6

  (226) 0x23956d VMULSD	%XMM0,%XMM0,%XMM1

  (226) 0x239571 VMOVSD	0x20(%R12),%XMM4

  (226) 0x239578 VCVTTSD2SI	0x68(%RSP),%EAX

  (226) 0x23957e VMOVSD	0x28(%R12),%XMM5

  (226) 0x239585 MOV	0x218(%R12),%RCX

  (226) 0x23958d VMOVSD	0x20(%RSP),%XMM14

  (226) 0x239593 MOV	0x40(%RSP),%RDI

  (226) 0x239598 VMOVHPD	0x40(%R12),%XMM3,%XMM3

  (226) 0x23959f VMOVHPD	0x50(%R12),%XMM6,%XMM6

  (226) 0x2395a6 VMOVHPD	0x38(%R12),%XMM4,%XMM4

  (226) 0x2395ad VMULSD	%XMM0,%XMM1,%XMM2

  (226) 0x2395b1 VMOVDDUP	%XMM0,%XMM0

  (226) 0x2395b5 VUNPCKLPD	%XMM1,%XMM2,%XMM8

  (226) 0x2395b9 VUNPCKLPD	%XMM2,%XMM1,%XMM7

  (226) 0x2395bd CLTQ

  (226) 0x2395bf VFMADD231PD	%XMM8,%XMM3,%XMM6

  (226) 0x2395c4 VMOVHPD	0x48(%R12),%XMM5,%XMM3

  (226) 0x2395cb VFMADD231PD	%XMM7,%XMM4,%XMM6

  (226) 0x2395d0 VFMADD213PD	%XMM6,%XMM0,%XMM3

  (226) 0x2395d5 VMULPD	(%RCX,%RAX,8),%XMM3,%XMM3

  (226) 0x2395da VUNPCKLPD	%XMM0,%XMM1,%XMM0

  (226) 0x2395de VMULPD	0x60(%R12),%XMM0,%XMM1

  (226) 0x2395e5 VMULPD	0x80(%R12),%XMM0,%XMM0

  (226) 0x2395ef VSHUFPD	$0x1,%XMM3,%XMM3,%XMM4

  (226) 0x2395f4 VADDSD	%XMM3,%XMM4,%XMM3

  (226) 0x2395f8 VSHUFPD	$0x1,%XMM1,%XMM1,%XMM4

  (226) 0x2395fd VFMADD231SD	0x58(%R12),%XMM2,%XMM1

  (226) 0x239604 VADDSD	%XMM4,%XMM1,%XMM1

  (226) 0x239608 VADDSD	0x70(%R12),%XMM1,%XMM1

  (226) 0x23960f VFMADD132SD	0x10(%RCX,%RAX,8),%XMM3,%XMM1

  (226) 0x239616 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM3

  (226) 0x23961b VFMADD231SD	0x78(%R12),%XMM2,%XMM0

  (226) 0x239622 VADDSD	%XMM3,%XMM0,%XMM0

  (226) 0x239626 VADDSD	0x90(%R12),%XMM0,%XMM0

  (226) 0x239630 VFMADD132SD	0x18(%RCX,%RAX,8),%XMM1,%XMM0

  (226) 0x239637 MOV	0x18(%RSP),%RCX

  (226) 0x23963c JMP	239510

0x239641 LEA	-0x28(%RBP),%RSP

0x239645 POP	%RBX

0x239646 POP	%R12

0x239648 POP	%R13

0x23964a POP	%R14

0x23964c POP	%R15

0x23964e POP	%RBP

0x23964f RET

Coverage (%)	Name	Source Location	Module
►95.99+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:272	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.80+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:272	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

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	stl_vector.h:919-1064
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:134-155
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:166-173,179-182,236-260
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h:1296
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:919,1046,1064
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 10% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 3.25 to 0.23 cycles (14.17x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 16 bytes. The binary function is storing 24 bytes.

General properties

nb instructions	31
nb uops	26
loop length	115
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.25 cycles
front end	3.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.17	1.17	1.17	1.17	1.17	1.17	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.17	1.17	1.17	1.17	1.17	1.17	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.25
Dispatch	1.25
Overall L1	3.25

Vectorization ratios

all	0%
load	0%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

all	10%
load	12%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 3.25 cycles. At this rate:

1% of peak load performance is reached (4.92 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.38 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 3.25 to 1.25 cycles (2.60x speedup).

ASM code

In the binary file, the address of the function is: 238bd0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV 0x8(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,(%RDX)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 23964f <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xa7f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
AND $-0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB $0x180,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RDI,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RSI,0x30(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,0x28(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 238c62 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x92>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
LEA -0x28(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	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	stl_vector.h:919-1064
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:134-155
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:166-173,179-182,236-260
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h:1296
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:919,1046,1064
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 16 bytes. The binary function is storing 24 bytes.

General properties

nb instructions	31
nb uops	26
loop length	115
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.25 cycles
front end	3.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.17	1.17	1.17	1.17	1.17	1.17	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.17	1.17	1.17	1.17	1.17	1.17	1.25	1.25	1.25	1.25	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.25
Dispatch	1.25
Overall L1	3.25

Vectorization ratios

all	0%
load	0%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

all	10%
load	12%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 3.25 cycles. At this rate:

1% of peak load performance is reached (4.92 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.38 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: 238bd0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV 0x8(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,(%RDX)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 23964f <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xa7f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
AND $-0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB $0x180,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RDI,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RSI,0x30(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,0x28(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 238c62 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x92>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
LEA -0x28(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	0.03	0.04
▼Loop 225 - OneBodyJastrowRef.h:134-155 - exec–	0.01	0.01
▼Loop 227 - OneBodyJastrowRef.h:143-146 - exec–	0.00	0.01
○Loop 228 - BsplineFunctor.h:236-241 - exec	0.02	0.03
○Loop 230 - BsplineFunctor.h:246-260 - exec	0.00	0.01
○Loop 229 - BsplineFunctor.h:246-260 - exec	0.00	0.00
○Loop 231 - BsplineFunctor.h:236-241 - exec	0.00	0.00
○Loop 226 - BsplineFunctor.h:166-182 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code