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: OneBodyJastrowRef.h:133-155 [...]	Coverage (incl. loops): 0.05% \| (excl. loops): 0.00%

/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 - 1169

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

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);

[...]

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

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 133 - 155

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

133:   {

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_GNR/173-773-5521/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);

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

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

223:     return X[i];

[...]

229:     return X[i];

[...]

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

/home/eoseret/qaas_runs_GNR/173-773-5521/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]; }

0x41e1e0 PUSH	%RBP

0x41e1e1 MOV	%RSP,%RBP

0x41e1e4 PUSH	%R15

0x41e1e6 PUSH	%R14

0x41e1e8 PUSH	%R13

0x41e1ea PUSH	%R12

0x41e1ec PUSH	%RBX

0x41e1ed SUB	$0x58,%RSP

0x41e1f1 MOV	%RSI,-0x50(%RBP)

0x41e1f5 MOV	0x8(%RDX),%RAX

0x41e1f9 MOV	%RDX,-0x58(%RBP)

0x41e1fd CMP	(%RDX),%RAX

0x41e200 JE	41eaf6

0x41e206 MOV	%RDI,%RBX

0x41e209 XOR	%R14D,%R14D

0x41e20c MOV	%RDI,-0x48(%RBP)

0x41e210 JMP	41e25f

(323) 0x41e212 VXORPD	%XMM27,%XMM27,%XMM27

(323) 0x41e218 NOPL	(%RAX,%RAX,1)

(323) 0x41e220 VMOVSD	-0x60(%RBP),%XMM0

(323) 0x41e225 VSUBSD	%XMM27,%XMM0,%XMM0

(323) 0x41e22b VZEROUPPER

(323) 0x41e22e CALL	4df280 <exp>

(323) 0x41e233 MOV	-0x58(%RBP),%RCX

(323) 0x41e237 MOV	(%RCX),%RAX

(323) 0x41e23a MOV	-0x68(%RBP),%R14

(323) 0x41e23e VMOVSD	%XMM0,(%RAX,%R14,8)

(323) 0x41e244 INC	%R14

(323) 0x41e247 MOV	0x8(%RCX),%RCX

(323) 0x41e24b SUB	%RAX,%RCX

(323) 0x41e24e SAR	$0x3,%RCX

(323) 0x41e252 CMP	%R14,%RCX

(323) 0x41e255 MOV	-0x48(%RBP),%RBX

(323) 0x41e259 JBE	41eaf6

(323) 0x41e25f MOV	-0x50(%RBP),%RDI

(323) 0x41e263 MOVSXD	0x2a0(%RDI),%RAX

(323) 0x41e26a MOV	0xf0(%RBX),%RCX

(323) 0x41e271 VMOVSD	(%RCX,%RAX,8),%XMM0

(323) 0x41e276 VMOVSD	%XMM0,-0x60(%RBP)

(323) 0x41e27b MOV	0xa8(%RBX),%ESI

(323) 0x41e281 CALL	460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

(323) 0x41e286 MOV	0x48(%RAX),%RAX

(323) 0x41e28a LEA	(%R14,%R14,4),%RCX

(323) 0x41e28e MOV	0x18(%RAX,%RCX,8),%RCX

(323) 0x41e293 MOVSXD	0x98(%RBX),%RAX

(323) 0x41e29a TEST	%RAX,%RAX

(323) 0x41e29d MOV	%RCX,-0x40(%RBP)

(323) 0x41e2a1 MOV	%R14,-0x68(%RBP)

(323) 0x41e2a5 JLE	41e9c0

(323) 0x41e2ab MOV	0x1c8(%RBX),%R15

(323) 0x41e2b2 MOV	0xa0(%RBX),%R12

(323) 0x41e2b9 MOV	0x148(%RBX),%RSI

(323) 0x41e2c0 DEC	%RAX

(323) 0x41e2c3 VXORPD	%XMM27,%XMM27,%XMM27

(323) 0x41e2c9 XOR	%EDI,%EDI

(323) 0x41e2cb VPMOVSXBD	0xdffeb(%RIP),%YMM25

(323) 0x41e2d5 VPMOVSXBD	0xdffe9(%RIP),%YMM26

(323) 0x41e2df MOV	%RAX,-0x78(%RBP)

(323) 0x41e2e3 MOV	%R12,-0x70(%RBP)

(323) 0x41e2e7 JMP	41e409

  (325) 0x41e2ec VXORPD	%XMM0,%XMM0,%XMM0

  (325) 0x41e2f0 XOR	%R8D,%R8D

  (325) 0x41e2f3 VPBROADCASTQ	%R8,%YMM19

  (325) 0x41e2f9 VPSUBQ	%YMM19,%YMM17,%YMM17

  (325) 0x41e2ff VPCMPNLEUQ	0xe00d6(%RIP),%YMM17,%K1

  (325) 0x41e30a VMOVUPD	(%RSI,%R8,8),%YMM17{%K1}{z}

  (325) 0x41e311 VMULPD	%YMM17,%YMM18,%YMM17

  (325) 0x41e317 VCVTTPD2DQ	%YMM17,%XMM18

  (325) 0x41e31d VRNDSCALEPD	$0xb,%YMM17,%YMM19

  (325) 0x41e324 VXORPD	%XMM20,%XMM20,%XMM20

  (325) 0x41e32a KMOVQ	%K1,%K2

  (325) 0x41e32f VGATHERDPD	(%R10,%XMM18,8),%YMM20{%K2}

  (325) 0x41e336 VSUBPD	%YMM19,%YMM17,%YMM17

  (325) 0x41e33c VMULPD	%YMM17,%YMM17,%YMM19

  (325) 0x41e342 VMULPD	%YMM17,%YMM19,%YMM21

  (325) 0x41e348 VFMADD231PD	%YMM16,%YMM19,%YMM1

  (325) 0x41e34e VXORPD	%XMM16,%XMM16,%XMM16

  (325) 0x41e354 KMOVQ	%K1,%K2

  (325) 0x41e359 VGATHERDPD	0x8(%R10,%XMM18,8),%YMM16{%K2}

  (325) 0x41e361 VFMADD231PD	%YMM2,%YMM21,%YMM1

  (325) 0x41e367 VFMADD231PD	%YMM4,%YMM17,%YMM1

  (325) 0x41e36d VFMADD231PD	%YMM9,%YMM21,%YMM15

  (325) 0x41e373 VFMADD231PD	%YMM13,%YMM19,%YMM15

  (325) 0x41e379 VFMADD231PD	%YMM14,%YMM17,%YMM15

  (325) 0x41e37f VMULPD	%YMM16,%YMM15,%YMM2

  (325) 0x41e385 VFMADD231PD	%YMM20,%YMM1,%YMM2

  (325) 0x41e38b VFMADD231PD	%YMM12,%YMM21,%YMM8

  (325) 0x41e391 VFMADD231PD	%YMM11,%YMM19,%YMM8

  (325) 0x41e397 VFMADD231PD	%YMM10,%YMM17,%YMM8

  (325) 0x41e39d VXORPD	%XMM1,%XMM1,%XMM1

  (325) 0x41e3a1 KMOVQ	%K1,%K2

  (325) 0x41e3a6 VGATHERDPD	0x10(%R10,%XMM18,8),%YMM1{%K2}

  (325) 0x41e3ae VFMADD213PD	%YMM2,%YMM8,%YMM1

  (325) 0x41e3b3 VFMADD231PD	%YMM7,%YMM21,%YMM3

  (325) 0x41e3b9 VFMADD231PD	%YMM6,%YMM19,%YMM3

  (325) 0x41e3bf VFMADD231PD	%YMM5,%YMM17,%YMM3

  (325) 0x41e3c5 VXORPD	%XMM2,%XMM2,%XMM2

  (325) 0x41e3c9 KMOVQ	%K1,%K2

  (325) 0x41e3ce VGATHERDPD	0x18(%R10,%XMM18,8),%YMM2{%K2}

  (325) 0x41e3d6 VFMADD213PD	%YMM1,%YMM3,%YMM2{%K1}{z}

  (325) 0x41e3dc VEXTRACTF128	$0x1,%YMM2,%XMM1

  (325) 0x41e3e2 VADDPD	%XMM1,%XMM2,%XMM1

  (325) 0x41e3e6 VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

  (325) 0x41e3eb VADDSD	%XMM2,%XMM1,%XMM1

  (325) 0x41e3ef VADDSD	%XMM1,%XMM0,%XMM0

  (325) 0x41e3f3 LEA	0x1(%RDI),%R8

  (325) 0x41e3f7 VADDSD	%XMM27,%XMM0,%XMM27

  (325) 0x41e3fd CMP	%RAX,%RDI

  (325) 0x41e400 MOV	%R8,%RDI

  (325) 0x41e403 JE	41e220

  (325) 0x41e409 MOV	(%R15,%RDI,8),%R8

  (325) 0x41e40d TEST	%R8,%R8

  (325) 0x41e410 JE	41e460

  (325) 0x41e412 MOV	0x268(%R12),%R9

  (325) 0x41e41a MOV	0x18(%R9),%R9

  (325) 0x41e41e MOVSXD	(%R9,%RDI,4),%R11

  (325) 0x41e422 MOV	0x4(%R9,%RDI,4),%R9D

  (325) 0x41e427 SUB	%R11D,%R9D

  (325) 0x41e42a VXORPD	%XMM0,%XMM0,%XMM0

  (325) 0x41e42e TEST	%R9D,%R9D

  (325) 0x41e431 JLE	41e3f3

  (325) 0x41e433 VMOVSD	0x8(%R8),%XMM1

  (325) 0x41e439 MOV	%R9D,%R10D

  (325) 0x41e43c MOV	%R10,%R14

  (325) 0x41e43f AND	$0x7ffffff0,%R14

  (325) 0x41e446 JE	41e471

  (325) 0x41e448 CMP	$0x7,%R9D

  (325) 0x41e44c JA	41e47c

  (325) 0x41e44e XOR	%R9D,%R9D

  (325) 0x41e451 XOR	%R14D,%R14D

  (325) 0x41e454 JMP	41e5cb

0x41e459 NOPL	(%RAX)

  (325) 0x41e460 LEA	0x1(%RDI),%R8

  (325) 0x41e464 CMP	%RAX,%RDI

  (325) 0x41e467 MOV	%R8,%RDI

  (325) 0x41e46a JNE	41e409

(323) 0x41e46c JMP	41e220

  (325) 0x41e471 XOR	%R9D,%R9D

  (325) 0x41e474 XOR	%R14D,%R14D

  (325) 0x41e477 JMP	41e5b2

  (325) 0x41e47c MOV	%R15,%RAX

  (325) 0x41e47f VBROADCASTSD	%XMM1,%YMM2

  (325) 0x41e484 MOV	%R11D,%EBX

  (325) 0x41e487 LEA	(%RCX,%R11,8),%R15

  (325) 0x41e48b XOR	%R9D,%R9D

  (325) 0x41e48e XOR	%R13D,%R13D

  (325) 0x41e491 NOPW	%CS:(%RAX,%RAX,1)

    (328) 0x41e4a0 VMOVUPD	(%R15,%R13,8),%YMM3

    (328) 0x41e4a6 VMOVUPD	0x20(%R15,%R13,8),%YMM4

    (328) 0x41e4ad VMOVUPD	0x40(%R15,%R13,8),%YMM5

    (328) 0x41e4b4 VMOVUPD	0x60(%R15,%R13,8),%YMM6

    (328) 0x41e4bb LEA	(%RBX,%R13,1),%R12D

    (328) 0x41e4bf VPBROADCASTD	%R12D,%YMM7

    (328) 0x41e4c5 VPCMPNEQD	%YMM25,%YMM7,%K0

    (328) 0x41e4cc VPCMPNEQD	%YMM26,%YMM7,%K2

    (328) 0x41e4d3 VCMPPD	$0x1,%YMM2,%YMM3,%K4

    (328) 0x41e4da VCMPPD	$0x1,%YMM2,%YMM4,%K1

    (328) 0x41e4e1 KMOVW	%K1,-0x38(%RBP)

    (328) 0x41e4e6 KSHIFTLB	$0x4,%K1,%K3

    (328) 0x41e4ec KORB	%K3,%K4,%K3

    (328) 0x41e4f0 MOVSXD	%R9D,%R9

    (328) 0x41e4f3 KANDW	%K0,%K4,%K4

    (328) 0x41e4f7 VCOMPRESSPD	%YMM3,(%RSI,%R9,8){%K4}

    (328) 0x41e4fe VCMPPD	$0x1,%YMM2,%YMM5,%K6

    (328) 0x41e505 VCMPPD	$0x1,%YMM2,%YMM6,%K5

    (328) 0x41e50c LEA	(%RSI,%R9,8),%R12

    (328) 0x41e510 KANDB	%K0,%K3,%K7

    (328) 0x41e514 KMOVB	%K7,%EDX

    (328) 0x41e518 KANDW	%K2,%K6,%K7

    (328) 0x41e51c POPCNT	%EDX,%EDX

    (328) 0x41e520 VCOMPRESSPD	%YMM5,(%R12,%RDX,8){%K7}

    (328) 0x41e527 KSHIFTLB	$0x4,%K5,%K1

    (328) 0x41e52d KORB	%K1,%K6,%K1

    (328) 0x41e531 KMOVB	%K7,-0x2b(%RBP)

    (328) 0x41e536 KSHIFTRB	$0x4,%K2,%K6

    (328) 0x41e53c KANDW	%K6,%K5,%K5

    (328) 0x41e540 LEA	(%R12,%RDX,8),%RDX

    (328) 0x41e544 MOVZX	-0x2b(%RBP),%ECX

    (328) 0x41e548 POPCNT	%ECX,%ECX

    (328) 0x41e54c VCOMPRESSPD	%YMM6,(%RDX,%RCX,8){%K5}

    (328) 0x41e553 KUNPCKBW	%K3,%K1,%K1

    (328) 0x41e557 KMOVB	%K4,-0x2c(%RBP)

    (328) 0x41e55c KUNPCKBW	%K0,%K2,%K2

    (328) 0x41e560 KSHIFTRB	$0x4,%K0,%K0

    (328) 0x41e566 KMOVW	-0x38(%RBP),%K3

    (328) 0x41e56b KANDW	%K0,%K3,%K3

    (328) 0x41e56f MOVZX	-0x2c(%RBP),%ECX

    (328) 0x41e573 POPCNT	%ECX,%ECX

    (328) 0x41e577 VCOMPRESSPD	%YMM4,(%R12,%RCX,8){%K3}

    (328) 0x41e57e KANDW	%K2,%K1,%K0

    (328) 0x41e582 KMOVW	%K0,%ECX

    (328) 0x41e586 POPCNT	%ECX,%ECX

    (328) 0x41e58a ADD	%ECX,%R9D

    (328) 0x41e58d ADD	$0x10,%R13

    (328) 0x41e591 CMP	%R14,%R13

    (328) 0x41e594 JB	41e4a0

  (325) 0x41e59a CMP	%R10D,%R14D

  (325) 0x41e59d MOV	-0x40(%RBP),%RCX

  (325) 0x41e5a1 MOV	%RAX,%R15

  (325) 0x41e5a4 MOV	-0x78(%RBP),%RAX

  (325) 0x41e5a8 MOV	-0x70(%RBP),%R12

  (325) 0x41e5ac JE	41e7ac

  (325) 0x41e5b2 VMOVQ	%R10,%XMM3

  (325) 0x41e5b7 VMOVD	%R14D,%XMM2

  (325) 0x41e5bc VPSUBQ	%YMM2,%YMM3,%YMM3

  (325) 0x41e5c0 VMOVQ	%XMM3,%RBX

  (325) 0x41e5c5 CMP	$0x8,%RBX

  (325) 0x41e5c9 JAE	41e60b

  (325) 0x41e5cb SUB	%R14,%R10

  (325) 0x41e5ce LEA	(%R14,%R11,1),%EBX

  (325) 0x41e5d2 NOT	%EBX

  (325) 0x41e5d4 ADD	%R11,%R14

  (325) 0x41e5d7 LEA	(%RCX,%R14,8),%R11

  (325) 0x41e5db XOR	%R14D,%R14D

  (325) 0x41e5de JMP	41e5ec

    (327) 0x41e5e0 INC	%R14

    (327) 0x41e5e3 CMP	%R14,%R10

    (327) 0x41e5e6 JE	41e7ac

    (327) 0x41e5ec VMOVSD	(%R11,%R14,8),%XMM2

    (327) 0x41e5f2 VUCOMISD	%XMM2,%XMM1

    (327) 0x41e5f6 JBE	41e5e0

    (327) 0x41e5f8 CMP	%R14D,%EBX

    (327) 0x41e5fb JE	41e5e0

    (327) 0x41e5fd MOVSXD	%R9D,%R9

    (327) 0x41e600 VMOVSD	%XMM2,(%RSI,%R9,8)

    (327) 0x41e606 INC	%R9D

    (327) 0x41e609 JMP	41e5e0

  (325) 0x41e60b VPBROADCASTQ	%XMM3,%YMM3

  (325) 0x41e610 VPCMPNLEUQ	0xdfdc5(%RIP),%YMM3,%K2

  (325) 0x41e61b VPCMPNLEUQ	0xdfdda(%RIP),%YMM3,%K3

  (325) 0x41e626 KSHIFTLB	$0x4,%K3,%K0

  (325) 0x41e62c KORB	%K0,%K2,%K1

  (325) 0x41e630 KMOVW	%K1,-0x38(%RBP)

  (325) 0x41e635 VPCMPNLEUQ	0xdfde0(%RIP),%YMM3,%K4

  (325) 0x41e640 VPCMPNLEUQ	0xdfdf5(%RIP),%YMM3,%K5

  (325) 0x41e64b KSHIFTLB	$0x4,%K5,%K0

  (325) 0x41e651 KORB	%K0,%K4,%K0

  (325) 0x41e655 ADD	%R11,%R14

  (325) 0x41e658 VMOVUPD	0x60(%RCX,%R14,8),%YMM3{%K5}{z}

  (325) 0x41e660 VMOVUPD	0x40(%RCX,%R14,8),%YMM4{%K4}{z}

  (325) 0x41e668 VMOVUPD	0x20(%RCX,%R14,8),%YMM5{%K3}{z}

  (325) 0x41e670 VMOVUPD	(%RCX,%R14,8),%YMM6{%K2}{z}

  (325) 0x41e677 VPBROADCASTD	%R11D,%YMM7

  (325) 0x41e67d VPMOVQD	%YMM2,%XMM2

  (325) 0x41e683 VPBROADCASTD	%XMM2,%YMM2

  (325) 0x41e688 VPOR	0xdfe10(%RIP),%YMM2,%YMM8

  (325) 0x41e690 VPOR	0xdfe28(%RIP),%YMM2,%YMM2

  (325) 0x41e698 VPADDD	%YMM2,%YMM7,%YMM2

  (325) 0x41e69c VPADDD	%YMM7,%YMM8,%YMM7

  (325) 0x41e6a0 VPCMPEQD	%YMM8,%YMM8,%YMM8

  (325) 0x41e6a5 VPCMPNEQD	%YMM8,%YMM7,%K3

  (325) 0x41e6ac VPCMPNEQD	%YMM8,%YMM2,%K4

  (325) 0x41e6b3 VBROADCASTSD	%XMM1,%YMM1

  (325) 0x41e6b8 VCMPPD	$0x1,%YMM1,%YMM6,%K2

  (325) 0x41e6bf VCMPPD	$0x1,%YMM1,%YMM5,%K5

  (325) 0x41e6c6 KSHIFTLB	$0x4,%K5,%K5

  (325) 0x41e6cc KORB	%K5,%K2,%K2

  (325) 0x41e6d0 VCMPPD	$0x1,%YMM1,%YMM4,%K5

  (325) 0x41e6d7 VCMPPD	$0x1,%YMM1,%YMM3,%K6

  (325) 0x41e6de KSHIFTLB	$0x4,%K6,%K6

  (325) 0x41e6e4 KORB	%K6,%K5,%K5

  (325) 0x41e6e8 MOVSXD	%R9D,%R10

  (325) 0x41e6eb LEA	(%RSI,%R10,8),%R11

  (325) 0x41e6ef KANDB	%K3,%K1,%K6

  (325) 0x41e6f3 KANDB	%K2,%K6,%K6

  (325) 0x41e6f7 VCOMPRESSPD	%YMM6,(%RSI,%R10,8){%K6}

  (325) 0x41e6fe KANDB	%K4,%K0,%K7

  (325) 0x41e702 KMOVQ	%K0,%K1

  (325) 0x41e707 KANDB	%K5,%K7,%K7

  (325) 0x41e70b KMOVB	%K6,%ECX

  (325) 0x41e70f POPCNT	%ECX,%ECX

  (325) 0x41e713 VCOMPRESSPD	%YMM4,(%R11,%RCX,8){%K7}

  (325) 0x41e71a KSHIFTLB	$0x4,%K7,%K0

  (325) 0x41e720 KSHIFTRB	$0x4,%K0,%K0

  (325) 0x41e726 KMOVB	%K0,-0x29(%RBP)

  (325) 0x41e72b LEA	(%R11,%RCX,8),%RCX

  (325) 0x41e72f KSHIFTRB	$0x4,%K7,%K7

  (325) 0x41e735 MOVZX	-0x29(%RBP),%EDX

  (325) 0x41e739 POPCNT	%EDX,%EDX

  (325) 0x41e73d VCOMPRESSPD	%YMM3,(%RCX,%RDX,8){%K7}

  (325) 0x41e744 KUNPCKBW	%K3,%K4,%K0

  (325) 0x41e748 KSHIFTLB	$0x4,%K6,%K3

  (325) 0x41e74e KSHIFTRB	$0x4,%K3,%K3

  (325) 0x41e754 KMOVB	%K3,-0x2a(%RBP)

  (325) 0x41e759 KSHIFTRB	$0x4,%K6,%K3

  (325) 0x41e75f MOVZX	-0x2a(%RBP),%ECX

  (325) 0x41e763 POPCNT	%ECX,%ECX

  (325) 0x41e767 VCOMPRESSPD	%YMM5,(%R11,%RCX,8){%K3}

  (325) 0x41e76e KUNPCKBW	%K2,%K5,%K2

  (325) 0x41e772 KMOVW	-0x38(%RBP),%K4

  (325) 0x41e777 KUNPCKBW	%K4,%K1,%K3

  (325) 0x41e77b KANDW	%K0,%K3,%K0

  (325) 0x41e77f KANDW	%K0,%K3,%K0

  (325) 0x41e783 KANDW	%K2,%K0,%K0

  (325) 0x41e787 KMOVW	%K0,%ECX

  (325) 0x41e78b VMOVD	%R9D,%XMM1

  (325) 0x41e790 POPCNT	%ECX,%ECX

  (325) 0x41e794 ADD	%ECX,%R10D

  (325) 0x41e797 MOV	-0x40(%RBP),%RCX

  (325) 0x41e79b VMOVD	%R10D,%XMM2

  (325) 0x41e7a0 VINSERTI32X4	$0,%XMM2,%YMM0,%YMM1{%K4}

  (325) 0x41e7a7 VMOVD	%XMM1,%R9D

  (325) 0x41e7ac TEST	%R9D,%R9D

  (325) 0x41e7af JLE	41e3f3

  (325) 0x41e7b5 VMOVSD	0x238(%R8),%XMM2

  (325) 0x41e7be MOV	0x218(%R8),%R10

  (325) 0x41e7c5 VMOVSD	0x18(%R8),%XMM16

  (325) 0x41e7cc VMOVSD	0x20(%R8),%XMM15

  (325) 0x41e7d2 VMOVSD	0x28(%R8),%XMM4

  (325) 0x41e7d8 VMOVSD	0x30(%R8),%XMM1

  (325) 0x41e7de VMOVSD	0x38(%R8),%XMM9

  (325) 0x41e7e4 VMOVSD	0x40(%R8),%XMM13

  (325) 0x41e7ea VMOVSD	0x48(%R8),%XMM14

  (325) 0x41e7f0 VMOVSD	0x50(%R8),%XMM12

  (325) 0x41e7f6 VMOVSD	0x58(%R8),%XMM11

  (325) 0x41e7fc VMOVSD	0x60(%R8),%XMM10

  (325) 0x41e802 VMOVSD	0x68(%R8),%XMM8

  (325) 0x41e808 VMOVSD	0x70(%R8),%XMM7

  (325) 0x41e80e VMOVSD	0x78(%R8),%XMM6

  (325) 0x41e814 VMOVSD	0x80(%R8),%XMM5

  (325) 0x41e81d VMOVSD	0x88(%R8),%XMM3

  (325) 0x41e826 VMOVSD	0x90(%R8),%XMM0

  (325) 0x41e82f MOV	%R9D,%R9D

  (325) 0x41e832 MOV	%R9,%R8

  (325) 0x41e835 VPBROADCASTQ	%R9,%YMM17

  (325) 0x41e83b VBROADCASTSD	%XMM2,%YMM18

  (325) 0x41e841 VBROADCASTSD	%XMM16,%YMM2

  (325) 0x41e847 VBROADCASTSD	%XMM15,%YMM16

  (325) 0x41e84d VBROADCASTSD	%XMM4,%YMM4

  (325) 0x41e852 VBROADCASTSD	%XMM1,%YMM1

  (325) 0x41e857 VBROADCASTSD	%XMM9,%YMM9

  (325) 0x41e85c VBROADCASTSD	%XMM13,%YMM13

  (325) 0x41e861 VBROADCASTSD	%XMM14,%YMM14

  (325) 0x41e866 VBROADCASTSD	%XMM12,%YMM15

  (325) 0x41e86b VBROADCASTSD	%XMM11,%YMM12

  (325) 0x41e870 VBROADCASTSD	%XMM10,%YMM11

  (325) 0x41e875 VBROADCASTSD	%XMM8,%YMM10

  (325) 0x41e87a VBROADCASTSD	%XMM7,%YMM8

  (325) 0x41e87f VBROADCASTSD	%XMM6,%YMM7

  (325) 0x41e884 VBROADCASTSD	%XMM5,%YMM6

  (325) 0x41e889 VBROADCASTSD	%XMM3,%YMM5

  (325) 0x41e88e VBROADCASTSD	%XMM0,%YMM3

  (325) 0x41e893 AND	$0x7ffffffc,%R8

  (325) 0x41e89a JE	41e2ec

  (325) 0x41e8a0 VXORPD	%XMM0,%XMM0,%XMM0

  (325) 0x41e8a4 XOR	%R11D,%R11D

  (325) 0x41e8a7 NOPW	(%RAX,%RAX,1)

    (326) 0x41e8b0 VMULPD	(%RSI,%R11,8),%YMM18,%YMM19

    (326) 0x41e8b7 VCVTTPD2DQ	%YMM19,%XMM20

    (326) 0x41e8bd VRNDSCALEPD	$0xb,%YMM19,%YMM21

    (326) 0x41e8c4 VSUBPD	%YMM21,%YMM19,%YMM19

    (326) 0x41e8ca VMULPD	%YMM19,%YMM19,%YMM21

    (326) 0x41e8d0 VMULPD	%YMM19,%YMM21,%YMM22

    (326) 0x41e8d6 VMOVAPD	%YMM21,%YMM23

    (326) 0x41e8dc VFMADD213PD	%YMM1,%YMM16,%YMM23

    (326) 0x41e8e2 VFMADD231PD	%YMM2,%YMM22,%YMM23

    (326) 0x41e8e8 VFMADD231PD	%YMM19,%YMM4,%YMM23

    (326) 0x41e8ee KXNORW	%K0,%K0,%K1

    (326) 0x41e8f2 VXORPD	%XMM24,%XMM24,%XMM24

    (326) 0x41e8f8 VGATHERDPD	(%R10,%XMM20,8),%YMM24{%K1}

    (326) 0x41e8ff VFMADD213PD	%YMM0,%YMM23,%YMM24

    (326) 0x41e905 VMOVAPD	%YMM22,%YMM0

    (326) 0x41e90b VFMADD213PD	%YMM15,%YMM9,%YMM0

    (326) 0x41e910 VFMADD231PD	%YMM21,%YMM13,%YMM0

    (326) 0x41e916 KXNORW	%K0,%K0,%K1

    (326) 0x41e91a VXORPD	%XMM23,%XMM23,%XMM23

    (326) 0x41e920 VGATHERDPD	0x8(%R10,%XMM20,8),%YMM23{%K1}

    (326) 0x41e928 VFMADD231PD	%YMM19,%YMM14,%YMM0

    (326) 0x41e92e VFMADD213PD	%YMM24,%YMM0,%YMM23

    (326) 0x41e934 VMOVAPD	%YMM22,%YMM0

    (326) 0x41e93a VFMADD213PD	%YMM8,%YMM12,%YMM0

    (326) 0x41e93f KXNORW	%K0,%K0,%K1

    (326) 0x41e943 VXORPD	%XMM24,%XMM24,%XMM24

    (326) 0x41e949 VGATHERDPD	0x10(%R10,%XMM20,8),%YMM24{%K1}

    (326) 0x41e951 VFMADD231PD	%YMM21,%YMM11,%YMM0

    (326) 0x41e957 VFMADD231PD	%YMM19,%YMM10,%YMM0

    (326) 0x41e95d VFMADD213PD	%YMM23,%YMM0,%YMM24

    (326) 0x41e963 KXNORW	%K0,%K0,%K1

    (326) 0x41e967 VXORPD	%XMM0,%XMM0,%XMM0

    (326) 0x41e96b VGATHERDPD	0x18(%R10,%XMM20,8),%YMM0{%K1}

    (326) 0x41e973 VFMADD213PD	%YMM3,%YMM7,%YMM22

    (326) 0x41e979 VFMADD231PD	%YMM21,%YMM6,%YMM22

    (326) 0x41e97f VFMADD231PD	%YMM19,%YMM5,%YMM22

    (326) 0x41e985 VFMADD213PD	%YMM24,%YMM22,%YMM0

    (326) 0x41e98b ADD	$0x4,%R11

    (326) 0x41e98f CMP	%R8,%R11

    (326) 0x41e992 JB	41e8b0

  (325) 0x41e998 VEXTRACTF32X4	$0x1,%YMM0,%XMM19

  (325) 0x41e99f VADDPD	%XMM19,%XMM0,%XMM0

  (325) 0x41e9a5 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM19

  (325) 0x41e9ac VADDSD	%XMM19,%XMM0,%XMM0

  (325) 0x41e9b2 CMP	%R9D,%R8D

  (325) 0x41e9b5 JNE	41e2f3

  (325) 0x41e9bb JMP	41e3f3

(323) 0x41e9c0 MOVSXD	0x90(%RBX),%R14

(323) 0x41e9c7 TEST	%R14,%R14

(323) 0x41e9ca JLE	41e212

(323) 0x41e9d0 MOV	0xa0(%RBX),%RAX

(323) 0x41e9d7 MOV	0x1c8(%RBX),%RBX

(323) 0x41e9de MOV	0x18(%RAX),%R15

(323) 0x41e9e2 VXORPD	%XMM27,%XMM27,%XMM27

(323) 0x41e9e8 XOR	%R13D,%R13D

(323) 0x41e9eb JMP	41ea02

0x41e9ed NOPL	(%RAX)

  (324) 0x41e9f0 VADDSD	%XMM27,%XMM1,%XMM27

  (324) 0x41e9f6 INC	%R13

  (324) 0x41e9f9 CMP	%R13,%R14

  (324) 0x41e9fc JE	41e220

  (324) 0x41ea02 MOVSXD	(%R15,%R13,4),%RAX

  (324) 0x41ea06 MOV	(%RBX,%RAX,8),%R12

  (324) 0x41ea0a TEST	%R12,%R12

  (324) 0x41ea0d JE	41e9f6

  (324) 0x41ea0f VMOVSD	(%RCX,%R13,8),%XMM0

  (324) 0x41ea15 VXORPD	%XMM1,%XMM1,%XMM1

  (324) 0x41ea19 VUCOMISD	0x8(%R12),%XMM0

  (324) 0x41ea20 JAE	41e9f0

  (324) 0x41ea22 VMULSD	0x238(%R12),%XMM0,%XMM0

  (324) 0x41ea2c LEA	-0x80(%RBP),%RDI

  (324) 0x41ea30 VMOVSD	%XMM27,-0x38(%RBP)

  (324) 0x41ea37 CALL	4df2f0 <modf>

  (324) 0x41ea3c VMOVSD	-0x38(%RBP),%XMM27

  (324) 0x41ea43 VCVTTSD2SI	-0x80(%RBP),%EAX

  (324) 0x41ea48 VMULSD	%XMM0,%XMM0,%XMM2

  (324) 0x41ea4c VMULSD	%XMM0,%XMM2,%XMM3

  (324) 0x41ea50 CLTQ

  (324) 0x41ea52 MOV	0x218(%R12),%RCX

  (324) 0x41ea5a VMOVSD	0x18(%R12),%XMM1

  (324) 0x41ea61 VMOVSD	0x38(%R12),%XMM4

  (324) 0x41ea68 VFMADD213SD	0x30(%R12),%XMM3,%XMM1

  (324) 0x41ea6f VFMADD231SD	0x20(%R12),%XMM2,%XMM1

  (324) 0x41ea76 VFMADD231SD	0x28(%R12),%XMM0,%XMM1

  (324) 0x41ea7d VMULSD	(%RCX,%RAX,8),%XMM1,%XMM1

  (324) 0x41ea82 VFMADD213SD	0x50(%R12),%XMM3,%XMM4

  (324) 0x41ea89 VFMADD231SD	0x40(%R12),%XMM2,%XMM4

  (324) 0x41ea90 VFMADD231SD	0x48(%R12),%XMM0,%XMM4

  (324) 0x41ea97 VFMADD132SD	0x8(%RCX,%RAX,8),%XMM1,%XMM4

  (324) 0x41ea9e VMOVSD	0x58(%R12),%XMM5

  (324) 0x41eaa5 VFMADD213SD	0x70(%R12),%XMM3,%XMM5

  (324) 0x41eaac VFMADD231SD	0x60(%R12),%XMM2,%XMM5

  (324) 0x41eab3 VFMADD231SD	0x68(%R12),%XMM0,%XMM5

  (324) 0x41eaba VFMADD132SD	0x10(%RCX,%RAX,8),%XMM4,%XMM5

  (324) 0x41eac1 VMOVSD	0x78(%R12),%XMM1

  (324) 0x41eac8 VFMADD213SD	0x90(%R12),%XMM3,%XMM1

  (324) 0x41ead2 VFMADD231SD	0x80(%R12),%XMM2,%XMM1

  (324) 0x41eadc VFMADD231SD	0x88(%R12),%XMM0,%XMM1

  (324) 0x41eae6 VFMADD132SD	0x18(%RCX,%RAX,8),%XMM5,%XMM1

  (324) 0x41eaed MOV	-0x40(%RBP),%RCX

  (324) 0x41eaf1 JMP	41e9f0

0x41eaf6 ADD	$0x58,%RSP

0x41eafa POP	%RBX

0x41eafb POP	%R12

0x41eafd POP	%R13

0x41eaff POP	%R14

0x41eb01 POP	%R15

0x41eb03 POP	%RBP

0x41eb04 RET

0x41eb05 NOPW	%CS:(%RAX,%RAX,1)

0x41eb0f NOP

Coverage (%)	Name	Source Location	Module
►99.66+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

Path /

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

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

Source file and lines	OneBodyJastrowRef.h:133-155
Module	exec

The function is defined in:

/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:919,1046,1064,1169
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:133-155
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:166-173,179-182,236-260
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 11% 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 4.83 to 0.37 cycles (12.89x 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	29
nb uops	29
loop length	86
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	4.83 cycles
front end	4.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	1.00	0.40	3.00	3.00	4.50	0.40	1.00	4.50	4.50	4.50	0.20	3.00
cycles	1.00	0.40	3.00	3.00	4.50	0.40	1.00	4.50	4.50	4.50	0.20	3.00

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	4.83
Dispatch	4.50
Overall L1	4.83

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	11%
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	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 4.83 cycles. At this rate:

1% of peak load performance is reached (3.31 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.97 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 4.83 to 4.50 cycles (1.07x speedup).

ASM code

In the binary file, the address of the function is: 41e1e0

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 $0x58,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0x50(%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 0x8(%RDX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP (%RDX),%RAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 41eaf6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x916>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV %RDI,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 41e25f <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x7f>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPL (%RAX)	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
ADD $0x58,%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
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
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

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

Source file and lines	OneBodyJastrowRef.h:133-155
Module	exec

The function is defined in:

/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:919,1046,1064,1169
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:133-155
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:166-173,179-182,236-260
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,229,249
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316

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	29
nb uops	29
loop length	86
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	4.83 cycles
front end	4.83 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	1.00	0.40	3.00	3.00	4.50	0.40	1.00	4.50	4.50	4.50	0.20	3.00
cycles	1.00	0.40	3.00	3.00	4.50	0.40	1.00	4.50	4.50	4.50	0.20	3.00

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	4.83
Dispatch	4.50
Overall L1	4.83

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	11%
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	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 4.83 cycles. At this rate:

1% of peak load performance is reached (3.31 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.97 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: 41e1e0

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 $0x58,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0x50(%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 0x8(%RDX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP (%RDX),%RAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 41eaf6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x916>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV %RDI,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 41e25f <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x7f>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
NOPL (%RAX)	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
ADD $0x58,%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
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
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	0.05	0.04
▼Loop 323 - OneBodyJastrowRef.h:134-155 - exec–	0.00	0.01
▼Loop 325 - OneBodyJastrowRef.h:134-146 - exec–	0.01	0.01
○Loop 328 - BsplineFunctor.h:236-241 - exec	0.04	0.03
○Loop 326 - BsplineFunctor.h:246-260 - exec	0.00	0.00
○Loop 327 - BsplineFunctor.h:236-241 - exec	0.00	0.00
○Loop 324 - 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