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

	Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios( ...	Module: exec	Source: TwoBodyJastrowRef.h:106-132 [...]	Coverage (incl. loops): 2.09% \| (excl. loops): 0.00%

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional: 950 - 952

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

950: 	if (this->_M_is_engaged())

951: 	  return this->_M_get();

952: 	__throw_bad_optional_access();

/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); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h: 338 - 338

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

338:       { return *_M_data; }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 260

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

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/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 106 - 132

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

106:   {

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

108:       ratios[k] = std::exp(Uat[VP.refPtcl] - computeU(VP.getRefPS(), VP.refPtcl, VP.getDistTableAB(myTableID).getDistRow(k).data()));

109:   }

[...]

126:     const int igt = P.GroupID[iat] * NumGroups;

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

128:     {

129:       const FuncType& f2(*F[igt + jg]);

130:       int iStart = P.first(jg);

131:       int iEnd   = P.last(jg);

132:       curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data());

/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]; }

0x4239e0 PUSH	%RBP

0x4239e1 MOV	%RSP,%RBP

0x4239e4 PUSH	%R15

0x4239e6 PUSH	%R14

0x4239e8 PUSH	%R13

0x4239ea PUSH	%R12

0x4239ec PUSH	%RBX

0x4239ed SUB	$0x58,%RSP

0x4239f1 MOV	0x8(%RDX),%RAX

0x4239f5 MOV	%RDX,-0x48(%RBP)

0x4239f9 CMP	(%RDX),%RAX

0x4239fc JE	42420e

0x423a02 MOV	%RDI,%RBX

0x423a05 MOV	%RSI,%RDI

0x423a08 XOR	%R14D,%R14D

0x423a0b MOV	%RBX,-0x38(%RBP)

0x423a0f MOV	%RSI,-0x40(%RBP)

0x423a13 JMP	423a65

0x423a15 NOPW	%CS:(%RAX,%RAX,1)

(404) 0x423a20 VXORPD	%XMM0,%XMM0,%XMM0

(404) 0x423a24 VMOVSD	-0x50(%RBP),%XMM1

(404) 0x423a29 VSUBSD	%XMM0,%XMM1,%XMM0

(404) 0x423a2d VZEROUPPER

(404) 0x423a30 CALL	4df280 <exp>

(404) 0x423a35 MOV	-0x48(%RBP),%RCX

(404) 0x423a39 MOV	(%RCX),%RAX

(404) 0x423a3c MOV	-0x58(%RBP),%R14

(404) 0x423a40 VMOVSD	%XMM0,(%RAX,%R14,8)

(404) 0x423a46 INC	%R14

(404) 0x423a49 MOV	0x8(%RCX),%RCX

(404) 0x423a4d SUB	%RAX,%RCX

(404) 0x423a50 SAR	$0x3,%RCX

(404) 0x423a54 CMP	%R14,%RCX

(404) 0x423a57 MOV	-0x40(%RBP),%RDI

(404) 0x423a5b MOV	-0x38(%RBP),%RBX

(404) 0x423a5f JBE	42420e

(404) 0x423a65 CMPB	$0,0x298(%RDI)

(404) 0x423a6c JE	42421d

(404) 0x423a72 MOVSXD	0x2a0(%RDI),%R15

(404) 0x423a79 MOV	0xd8(%RBX),%RAX

(404) 0x423a80 VMOVQ	(%RAX,%R15,8),%XMM0

(404) 0x423a86 VMOVQ	%XMM0,-0x50(%RBP)

(404) 0x423a8b MOV	0x290(%RDI),%R13

(404) 0x423a92 MOV	0x248(%RBX),%ESI

(404) 0x423a98 CALL	460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

(404) 0x423a9d MOV	0xa0(%RBX),%R12

(404) 0x423aa4 TEST	%R12,%R12

(404) 0x423aa7 MOV	%R14,-0x58(%RBP)

(404) 0x423aab JE	423a20

(404) 0x423ab1 MOV	0x48(%RAX),%RAX

(404) 0x423ab5 LEA	(%R14,%R14,4),%RDX

(404) 0x423ab9 MOV	0x18(%RAX,%RDX,8),%RAX

(404) 0x423abe MOV	0x18(%R13),%RDX

(404) 0x423ac2 MOV	(%RDX,%R15,4),%ESI

(404) 0x423ac6 IMUL	%R12D,%ESI

(404) 0x423aca MOV	0x1d0(%RBX),%RDX

(404) 0x423ad1 MOV	0x200(%RBX),%RDI

(404) 0x423ad8 MOV	%RAX,%RBX

(404) 0x423adb MOV	%RDI,%RAX

(404) 0x423ade MOVSXD	%ESI,%RSI

(404) 0x423ae1 MOV	%RSI,-0x80(%RBP)

(404) 0x423ae5 DEC	%R12

(404) 0x423ae8 MOV	%R15,-0x78(%RBP)

(404) 0x423aec VPBROADCASTD	%R15D,%YMM1

(404) 0x423af2 VPXOR	%XMM0,%XMM0,%XMM0

(404) 0x423af6 XOR	%R8D,%R8D

(404) 0x423af9 VPMOVSXBQ	0xdaa61(%RIP),%YMM27

(404) 0x423b03 VPMOVSXBQ	0xdaa5b(%RIP),%YMM28

(404) 0x423b0d VPMOVSXBQ	0xdaa55(%RIP),%YMM29

(404) 0x423b17 VPMOVSXBQ	0xdaa4f(%RIP),%YMM30

(404) 0x423b21 VPMOVSXBD	0xda7ad(%RIP),%YMM31

(404) 0x423b2b VPMOVSXBD	0xda79b(%RIP),%YMM24

(404) 0x423b35 MOV	%R13,-0x70(%RBP)

(404) 0x423b39 MOV	%R12,-0x68(%RBP)

(404) 0x423b3d MOV	%RDI,-0x60(%RBP)

(404) 0x423b41 JMP	423c63

  (405) 0x423b46 VXORPD	%XMM20,%XMM20,%XMM20

  (405) 0x423b4c XOR	%R9D,%R9D

  (405) 0x423b4f VPBROADCASTQ	%R9,%YMM21

  (405) 0x423b55 VPSUBQ	%YMM21,%YMM18,%YMM18

  (405) 0x423b5b VPCMPNLEUQ	%YMM27,%YMM18,%K1

  (405) 0x423b62 VMOVUPD	(%RDX,%R9,8),%YMM18{%K1}{z}

  (405) 0x423b69 VMULPD	%YMM18,%YMM19,%YMM18

  (405) 0x423b6f VCVTTPD2DQ	%YMM18,%XMM19

  (405) 0x423b75 VRNDSCALEPD	$0xb,%YMM18,%YMM21

  (405) 0x423b7c VXORPD	%XMM22,%XMM22,%XMM22

  (405) 0x423b82 KMOVQ	%K1,%K2

  (405) 0x423b87 VGATHERDPD	(%R11,%XMM19,8),%YMM22{%K2}

  (405) 0x423b8e VSUBPD	%YMM21,%YMM18,%YMM18

  (405) 0x423b94 VMULPD	%YMM18,%YMM18,%YMM21

  (405) 0x423b9a VMULPD	%YMM18,%YMM21,%YMM23

  (405) 0x423ba0 VFMADD231PD	%YMM17,%YMM21,%YMM2

  (405) 0x423ba6 VXORPD	%XMM17,%XMM17,%XMM17

  (405) 0x423bac KMOVQ	%K1,%K2

  (405) 0x423bb1 VGATHERDPD	0x8(%R11,%XMM19,8),%YMM17{%K2}

  (405) 0x423bb9 VFMADD231PD	%YMM3,%YMM23,%YMM2

  (405) 0x423bbf VFMADD231PD	%YMM5,%YMM18,%YMM2

  (405) 0x423bc5 VFMADD231PD	%YMM10,%YMM23,%YMM16

  (405) 0x423bcb VFMADD231PD	%YMM14,%YMM21,%YMM16

  (405) 0x423bd1 VFMADD231PD	%YMM15,%YMM18,%YMM16

  (405) 0x423bd7 VMULPD	%YMM17,%YMM16,%YMM3

  (405) 0x423bdd VFMADD231PD	%YMM22,%YMM2,%YMM3

  (405) 0x423be3 VFMADD231PD	%YMM13,%YMM23,%YMM9

  (405) 0x423be9 VFMADD231PD	%YMM12,%YMM21,%YMM9

  (405) 0x423bef VFMADD231PD	%YMM11,%YMM18,%YMM9

  (405) 0x423bf5 VXORPD	%XMM2,%XMM2,%XMM2

  (405) 0x423bf9 KMOVQ	%K1,%K2

  (405) 0x423bfe VGATHERDPD	0x10(%R11,%XMM19,8),%YMM2{%K2}

  (405) 0x423c06 VFMADD213PD	%YMM3,%YMM9,%YMM2

  (405) 0x423c0b VFMADD231PD	%YMM8,%YMM23,%YMM4

  (405) 0x423c11 VFMADD231PD	%YMM7,%YMM21,%YMM4

  (405) 0x423c17 VFMADD231PD	%YMM6,%YMM18,%YMM4

  (405) 0x423c1d VXORPD	%XMM3,%XMM3,%XMM3

  (405) 0x423c21 KMOVQ	%K1,%K2

  (405) 0x423c26 VGATHERDPD	0x18(%R11,%XMM19,8),%YMM3{%K2}

  (405) 0x423c2e VFMADD213PD	%YMM2,%YMM4,%YMM3{%K1}{z}

  (405) 0x423c34 VEXTRACTF128	$0x1,%YMM3,%XMM2

  (405) 0x423c3a VADDPD	%XMM2,%XMM3,%XMM2

  (405) 0x423c3e VSHUFPD	$0x1,%XMM2,%XMM2,%XMM3

  (405) 0x423c43 VADDSD	%XMM3,%XMM2,%XMM2

  (405) 0x423c47 VADDSD	%XMM2,%XMM20,%XMM20

  (405) 0x423c4d VADDSD	%XMM0,%XMM20,%XMM0

  (405) 0x423c53 LEA	0x1(%R8),%RCX

  (405) 0x423c57 CMP	%R12,%R8

  (405) 0x423c5a MOV	%RCX,%R8

  (405) 0x423c5d JE	423a24

  (405) 0x423c63 MOV	0x268(%R13),%RSI

  (405) 0x423c6a MOV	0x18(%RSI),%RSI

  (405) 0x423c6e MOVSXD	(%RSI,%R8,4),%R15

  (405) 0x423c72 MOV	0x4(%RSI,%R8,4),%ESI

  (405) 0x423c77 SUB	%R15D,%ESI

  (405) 0x423c7a VXORPD	%XMM20,%XMM20,%XMM20

  (405) 0x423c80 TEST	%ESI,%ESI

  (405) 0x423c82 JLE	423c4d

  (405) 0x423c84 MOV	-0x80(%RBP),%RCX

  (405) 0x423c88 LEA	(%R8,%RCX,1),%RDI

  (405) 0x423c8c MOV	(%RAX,%RDI,8),%R9

  (405) 0x423c90 VMOVSD	0x8(%R9),%XMM2

  (405) 0x423c96 MOV	%ESI,%R14D

  (405) 0x423c99 MOV	%R14,%R11

  (405) 0x423c9c AND	$0x7ffffff0,%R11

  (405) 0x423ca3 JE	423cc0

  (405) 0x423ca5 CMP	$0x7,%ESI

  (405) 0x423ca8 JA	423ccb

  (405) 0x423caa XOR	%R10D,%R10D

  (405) 0x423cad XOR	%R11D,%R11D

  (405) 0x423cb0 JMP	423e18

0x423cb5 NOPW	%CS:(%RAX,%RAX,1)

  (405) 0x423cc0 XOR	%R10D,%R10D

  (405) 0x423cc3 XOR	%R11D,%R11D

  (405) 0x423cc6 JMP	423dff

  (405) 0x423ccb VBROADCASTSD	%XMM2,%YMM3

  (405) 0x423cd0 MOV	%R15D,%R12D

  (405) 0x423cd3 MOV	%RBX,%RAX

  (405) 0x423cd6 LEA	(%RBX,%R15,8),%R13

  (405) 0x423cda XOR	%R10D,%R10D

  (405) 0x423cdd XOR	%ESI,%ESI

  (405) 0x423cdf NOP

    (408) 0x423ce0 VMOVUPD	(%R13,%RSI,8),%YMM4

    (408) 0x423ce7 VMOVUPD	0x20(%R13,%RSI,8),%YMM5

    (408) 0x423cee VMOVUPD	0x40(%R13,%RSI,8),%YMM6

    (408) 0x423cf5 VMOVUPD	0x60(%R13,%RSI,8),%YMM7

    (408) 0x423cfc LEA	(%R12,%RSI,1),%EDI

    (408) 0x423d00 VPBROADCASTD	%EDI,%YMM8

    (408) 0x423d06 VPADDD	%YMM24,%YMM8,%YMM9

    (408) 0x423d0c VPADDD	%YMM31,%YMM8,%YMM8

    (408) 0x423d12 VPCMPNEQD	%YMM1,%YMM8,%K0

    (408) 0x423d19 VPCMPNEQD	%YMM1,%YMM9,%K2

    (408) 0x423d20 VCMPPD	$0x1,%YMM3,%YMM4,%K5

    (408) 0x423d27 VCMPPD	$0x1,%YMM3,%YMM5,%K1

    (408) 0x423d2e KMOVW	%K1,-0x2a(%RBP)

    (408) 0x423d33 KSHIFTLB	$0x4,%K1,%K3

    (408) 0x423d39 KORB	%K3,%K5,%K3

    (408) 0x423d3d VCMPPD	$0x1,%YMM3,%YMM6,%K6

    (408) 0x423d44 VCMPPD	$0x1,%YMM3,%YMM7,%K4

    (408) 0x423d4b MOVSXD	%R10D,%R10

    (408) 0x423d4e LEA	(%RDX,%R10,8),%RDI

    (408) 0x423d52 KANDB	%K0,%K3,%K7

    (408) 0x423d56 KMOVB	%K7,%EBX

    (408) 0x423d5a KANDW	%K2,%K6,%K7

    (408) 0x423d5e POPCNT	%EBX,%EBX

    (408) 0x423d62 VCOMPRESSPD	%YMM6,(%RDI,%RBX,8){%K7}

    (408) 0x423d69 KANDW	%K0,%K5,%K5

    (408) 0x423d6d VCOMPRESSPD	%YMM4,(%RDX,%R10,8){%K5}

    (408) 0x423d74 KSHIFTLB	$0x4,%K4,%K1

    (408) 0x423d7a KORB	%K1,%K6,%K1

    (408) 0x423d7e KMOVB	%K7,-0x2d(%RBP)

    (408) 0x423d83 KSHIFTRB	$0x4,%K2,%K6

    (408) 0x423d89 KANDW	%K6,%K4,%K4

    (408) 0x423d8d LEA	(%RDI,%RBX,8),%RBX

    (408) 0x423d91 MOVZX	-0x2d(%RBP),%ECX

    (408) 0x423d95 POPCNT	%ECX,%ECX

    (408) 0x423d99 VCOMPRESSPD	%YMM7,(%RBX,%RCX,8){%K4}

    (408) 0x423da0 KUNPCKBW	%K3,%K1,%K1

    (408) 0x423da4 KMOVB	%K5,-0x2e(%RBP)

    (408) 0x423da9 KUNPCKBW	%K0,%K2,%K2

    (408) 0x423dad KSHIFTRB	$0x4,%K0,%K0

    (408) 0x423db3 KMOVW	-0x2a(%RBP),%K3

    (408) 0x423db8 KANDW	%K0,%K3,%K3

    (408) 0x423dbc MOVZX	-0x2e(%RBP),%ECX

    (408) 0x423dc0 POPCNT	%ECX,%ECX

    (408) 0x423dc4 VCOMPRESSPD	%YMM5,(%RDI,%RCX,8){%K3}

    (408) 0x423dcb KANDW	%K2,%K1,%K0

    (408) 0x423dcf KMOVW	%K0,%ECX

    (408) 0x423dd3 POPCNT	%ECX,%ECX

    (408) 0x423dd7 ADD	%ECX,%R10D

    (408) 0x423dda ADD	$0x10,%RSI

    (408) 0x423dde CMP	%R11,%RSI

    (408) 0x423de1 JB	423ce0

  (405) 0x423de7 CMP	%R14D,%R11D

  (405) 0x423dea MOV	-0x70(%RBP),%R13

  (405) 0x423dee MOV	-0x68(%RBP),%R12

  (405) 0x423df2 MOV	%RAX,%RBX

  (405) 0x423df5 MOV	-0x60(%RBP),%RAX

  (405) 0x423df9 JE	423fe0

  (405) 0x423dff VMOVQ	%R14,%XMM4

  (405) 0x423e04 VMOVD	%R11D,%XMM3

  (405) 0x423e09 VPSUBQ	%YMM3,%YMM4,%YMM4

  (405) 0x423e0d VMOVQ	%XMM4,%RSI

  (405) 0x423e12 CMP	$0x8,%RSI

  (405) 0x423e16 JAE	423e5b

  (405) 0x423e18 MOV	-0x78(%RBP),%RSI

  (405) 0x423e1c SUB	%R15D,%ESI

  (405) 0x423e1f LEA	(%RBX,%R15,8),%RDI

  (405) 0x423e23 JMP	423e3c

0x423e25 NOPW	%CS:(%RAX,%RAX,1)

    (407) 0x423e30 INC	%R11

    (407) 0x423e33 CMP	%R11,%R14

    (407) 0x423e36 JE	423fe0

    (407) 0x423e3c VMOVSD	(%RDI,%R11,8),%XMM3

    (407) 0x423e42 VUCOMISD	%XMM3,%XMM2

    (407) 0x423e46 JBE	423e30

    (407) 0x423e48 CMP	%R11D,%ESI

    (407) 0x423e4b JE	423e30

    (407) 0x423e4d MOVSXD	%R10D,%R10

    (407) 0x423e50 VMOVSD	%XMM3,(%RDX,%R10,8)

    (407) 0x423e56 INC	%R10D

    (407) 0x423e59 JMP	423e30

  (405) 0x423e5b VPBROADCASTQ	%XMM4,%YMM4

  (405) 0x423e60 VPCMPNLEUQ	%YMM27,%YMM4,%K2

  (405) 0x423e67 VPCMPNLEUQ	%YMM28,%YMM4,%K3

  (405) 0x423e6e KSHIFTLB	$0x4,%K3,%K0

  (405) 0x423e74 KORB	%K0,%K2,%K1

  (405) 0x423e78 KMOVW	%K1,-0x2a(%RBP)

  (405) 0x423e7d VPCMPNLEUQ	%YMM29,%YMM4,%K4

  (405) 0x423e84 VPCMPNLEUQ	%YMM30,%YMM4,%K5

  (405) 0x423e8b KSHIFTLB	$0x4,%K5,%K0

  (405) 0x423e91 KORB	%K0,%K4,%K0

  (405) 0x423e95 ADD	%R15,%R11

  (405) 0x423e98 VMOVUPD	0x60(%RBX,%R11,8),%YMM4{%K5}{z}

  (405) 0x423ea0 VMOVUPD	0x40(%RBX,%R11,8),%YMM5{%K4}{z}

  (405) 0x423ea8 VMOVUPD	0x20(%RBX,%R11,8),%YMM6{%K3}{z}

  (405) 0x423eb0 VMOVUPD	(%RBX,%R11,8),%YMM7{%K2}{z}

  (405) 0x423eb7 VPBROADCASTD	%R15D,%YMM8

  (405) 0x423ebd VPMOVQD	%YMM3,%XMM3

  (405) 0x423ec3 VPBROADCASTD	%XMM3,%YMM3

  (405) 0x423ec8 VPORD	%YMM31,%YMM3,%YMM9

  (405) 0x423ece VPORD	%YMM24,%YMM3,%YMM3

  (405) 0x423ed4 VPADDD	%YMM3,%YMM8,%YMM3

  (405) 0x423ed8 VPADDD	%YMM9,%YMM8,%YMM8

  (405) 0x423edd VPCMPNEQD	%YMM1,%YMM8,%K3

  (405) 0x423ee4 VPCMPNEQD	%YMM1,%YMM3,%K4

  (405) 0x423eeb VBROADCASTSD	%XMM2,%YMM2

  (405) 0x423ef0 VCMPPD	$0x1,%YMM2,%YMM7,%K2

  (405) 0x423ef7 VCMPPD	$0x1,%YMM2,%YMM6,%K5

  (405) 0x423efe KSHIFTLB	$0x4,%K5,%K5

  (405) 0x423f04 KORB	%K5,%K2,%K2

  (405) 0x423f08 VCMPPD	$0x1,%YMM2,%YMM5,%K5

  (405) 0x423f0f VCMPPD	$0x1,%YMM2,%YMM4,%K6

  (405) 0x423f16 KSHIFTLB	$0x4,%K6,%K6

  (405) 0x423f1c KORB	%K6,%K5,%K5

  (405) 0x423f20 MOVSXD	%R10D,%RSI

  (405) 0x423f23 LEA	(%RDX,%RSI,8),%RDI

  (405) 0x423f27 KANDB	%K3,%K1,%K6

  (405) 0x423f2b KANDB	%K2,%K6,%K6

  (405) 0x423f2f VCOMPRESSPD	%YMM7,(%RDX,%RSI,8){%K6}

  (405) 0x423f36 KANDB	%K4,%K0,%K7

  (405) 0x423f3a KMOVQ	%K0,%K1

  (405) 0x423f3f KANDB	%K5,%K7,%K7

  (405) 0x423f43 KMOVB	%K6,%ECX

  (405) 0x423f47 POPCNT	%ECX,%ECX

  (405) 0x423f4b VCOMPRESSPD	%YMM5,(%RDI,%RCX,8){%K7}

  (405) 0x423f52 KSHIFTLB	$0x4,%K7,%K0

  (405) 0x423f58 KSHIFTRB	$0x4,%K0,%K0

  (405) 0x423f5e KMOVB	%K0,-0x2b(%RBP)

  (405) 0x423f63 LEA	(%RDI,%RCX,8),%RCX

  (405) 0x423f67 KSHIFTRB	$0x4,%K7,%K7

  (405) 0x423f6d MOVZX	-0x2b(%RBP),%R11D

  (405) 0x423f72 POPCNT	%R11D,%R11D

  (405) 0x423f77 VCOMPRESSPD	%YMM4,(%RCX,%R11,8){%K7}

  (405) 0x423f7e KUNPCKBW	%K3,%K4,%K0

  (405) 0x423f82 KSHIFTLB	$0x4,%K6,%K3

  (405) 0x423f88 KSHIFTRB	$0x4,%K3,%K3

  (405) 0x423f8e KMOVB	%K3,-0x2c(%RBP)

  (405) 0x423f93 KSHIFTRB	$0x4,%K6,%K3

  (405) 0x423f99 MOVZX	-0x2c(%RBP),%ECX

  (405) 0x423f9d POPCNT	%ECX,%ECX

  (405) 0x423fa1 VCOMPRESSPD	%YMM6,(%RDI,%RCX,8){%K3}

  (405) 0x423fa8 KUNPCKBW	%K2,%K5,%K2

  (405) 0x423fac KMOVW	-0x2a(%RBP),%K4

  (405) 0x423fb1 KUNPCKBW	%K4,%K1,%K3

  (405) 0x423fb5 KANDW	%K0,%K3,%K0

  (405) 0x423fb9 KANDW	%K0,%K3,%K0

  (405) 0x423fbd KANDW	%K2,%K0,%K0

  (405) 0x423fc1 KMOVW	%K0,%ECX

  (405) 0x423fc5 VMOVD	%R10D,%XMM2

  (405) 0x423fca POPCNT	%ECX,%ECX

  (405) 0x423fce ADD	%ECX,%ESI

  (405) 0x423fd0 VMOVD	%ESI,%XMM3

  (405) 0x423fd4 VINSERTI32X4	$0,%XMM3,%YMM0,%YMM2{%K4}

  (405) 0x423fdb VMOVD	%XMM2,%R10D

  (405) 0x423fe0 VXORPD	%XMM20,%XMM20,%XMM20

  (405) 0x423fe6 TEST	%R10D,%R10D

  (405) 0x423fe9 JLE	423c4d

  (405) 0x423fef VMOVSD	0x238(%R9),%XMM3

  (405) 0x423ff8 MOV	0x218(%R9),%R11

  (405) 0x423fff VMOVSD	0x18(%R9),%XMM20

  (405) 0x424006 VMOVSD	0x20(%R9),%XMM17

  (405) 0x42400d VMOVSD	0x28(%R9),%XMM5

  (405) 0x424013 VMOVSD	0x30(%R9),%XMM2

  (405) 0x424019 VMOVSD	0x38(%R9),%XMM10

  (405) 0x42401f VMOVSD	0x40(%R9),%XMM14

  (405) 0x424025 VMOVSD	0x48(%R9),%XMM15

  (405) 0x42402b VMOVSD	0x50(%R9),%XMM16

  (405) 0x424032 VMOVSD	0x58(%R9),%XMM13

  (405) 0x424038 VMOVSD	0x60(%R9),%XMM12

  (405) 0x42403e VMOVSD	0x68(%R9),%XMM11

  (405) 0x424044 VMOVSD	0x70(%R9),%XMM9

  (405) 0x42404a VMOVSD	0x78(%R9),%XMM8

  (405) 0x424050 VMOVSD	0x80(%R9),%XMM7

  (405) 0x424059 VMOVSD	0x88(%R9),%XMM6

  (405) 0x424062 VMOVSD	0x90(%R9),%XMM4

  (405) 0x42406b MOV	%R10D,%R10D

  (405) 0x42406e MOV	%R10,%R9

  (405) 0x424071 VPBROADCASTQ	%R10,%YMM18

  (405) 0x424077 VBROADCASTSD	%XMM3,%YMM19

  (405) 0x42407d VBROADCASTSD	%XMM20,%YMM3

  (405) 0x424083 VBROADCASTSD	%XMM17,%YMM17

  (405) 0x424089 VBROADCASTSD	%XMM5,%YMM5

  (405) 0x42408e VBROADCASTSD	%XMM2,%YMM2

  (405) 0x424093 VBROADCASTSD	%XMM10,%YMM10

  (405) 0x424098 VBROADCASTSD	%XMM14,%YMM14

  (405) 0x42409d VBROADCASTSD	%XMM15,%YMM15

  (405) 0x4240a2 VBROADCASTSD	%XMM16,%YMM16

  (405) 0x4240a8 VBROADCASTSD	%XMM13,%YMM13

  (405) 0x4240ad VBROADCASTSD	%XMM12,%YMM12

  (405) 0x4240b2 VBROADCASTSD	%XMM11,%YMM11

  (405) 0x4240b7 VBROADCASTSD	%XMM9,%YMM9

  (405) 0x4240bc VBROADCASTSD	%XMM8,%YMM8

  (405) 0x4240c1 VBROADCASTSD	%XMM7,%YMM7

  (405) 0x4240c6 VBROADCASTSD	%XMM6,%YMM6

  (405) 0x4240cb VBROADCASTSD	%XMM4,%YMM4

  (405) 0x4240d0 AND	$0x7ffffffc,%R9

  (405) 0x4240d7 JE	423b46

  (405) 0x4240dd VXORPD	%XMM20,%XMM20,%XMM20

  (405) 0x4240e3 XOR	%ESI,%ESI

  (405) 0x4240e5 NOPW	%CS:(%RAX,%RAX,1)

    (406) 0x4240f0 VMULPD	(%RDX,%RSI,8),%YMM19,%YMM21

    (406) 0x4240f7 VCVTTPD2DQ	%YMM21,%XMM22

    (406) 0x4240fd VRNDSCALEPD	$0xb,%YMM21,%YMM23

    (406) 0x424104 VSUBPD	%YMM23,%YMM21,%YMM21

    (406) 0x42410a VMULPD	%YMM21,%YMM21,%YMM23

    (406) 0x424110 VMULPD	%YMM21,%YMM23,%YMM24

    (406) 0x424116 VMOVAPD	%YMM23,%YMM25

    (406) 0x42411c VFMADD213PD	%YMM2,%YMM17,%YMM25

    (406) 0x424122 VFMADD231PD	%YMM3,%YMM24,%YMM25

    (406) 0x424128 VFMADD231PD	%YMM21,%YMM5,%YMM25

    (406) 0x42412e VXORPD	%XMM26,%XMM26,%XMM26

    (406) 0x424134 KXNORW	%K0,%K0,%K1

    (406) 0x424138 VGATHERDPD	(%R11,%XMM22,8),%YMM26{%K1}

    (406) 0x42413f VFMADD213PD	%YMM20,%YMM25,%YMM26

    (406) 0x424145 VMOVAPD	%YMM24,%YMM20

    (406) 0x42414b VFMADD213PD	%YMM16,%YMM10,%YMM20

    (406) 0x424151 VFMADD231PD	%YMM23,%YMM14,%YMM20

    (406) 0x424157 VXORPD	%XMM25,%XMM25,%XMM25

    (406) 0x42415d KXNORW	%K0,%K0,%K1

    (406) 0x424161 VGATHERDPD	0x8(%R11,%XMM22,8),%YMM25{%K1}

    (406) 0x424169 VFMADD231PD	%YMM21,%YMM15,%YMM20

    (406) 0x42416f VFMADD213PD	%YMM26,%YMM20,%YMM25

    (406) 0x424175 VMOVAPD	%YMM24,%YMM20

    (406) 0x42417b VFMADD213PD	%YMM9,%YMM13,%YMM20

    (406) 0x424181 VXORPD	%XMM26,%XMM26,%XMM26

    (406) 0x424187 KXNORW	%K0,%K0,%K1

    (406) 0x42418b VGATHERDPD	0x10(%R11,%XMM22,8),%YMM26{%K1}

    (406) 0x424193 VFMADD231PD	%YMM23,%YMM12,%YMM20

    (406) 0x424199 VFMADD231PD	%YMM21,%YMM11,%YMM20

    (406) 0x42419f VFMADD213PD	%YMM25,%YMM20,%YMM26

    (406) 0x4241a5 VXORPD	%XMM20,%XMM20,%XMM20

    (406) 0x4241ab KXNORW	%K0,%K0,%K1

    (406) 0x4241af VGATHERDPD	0x18(%R11,%XMM22,8),%YMM20{%K1}

    (406) 0x4241b7 VFMADD213PD	%YMM4,%YMM8,%YMM24

    (406) 0x4241bd VFMADD231PD	%YMM23,%YMM7,%YMM24

    (406) 0x4241c3 VFMADD231PD	%YMM21,%YMM6,%YMM24

    (406) 0x4241c9 VFMADD213PD	%YMM26,%YMM24,%YMM20

    (406) 0x4241cf ADD	$0x4,%RSI

    (406) 0x4241d3 CMP	%R9,%RSI

    (406) 0x4241d6 JB	4240f0

  (405) 0x4241dc VEXTRACTF32X4	$0x1,%YMM20,%XMM21

  (405) 0x4241e3 VADDPD	%XMM21,%XMM20,%XMM20

  (405) 0x4241e9 VSHUFPD	$0x1,%XMM20,%XMM20,%XMM21

  (405) 0x4241f0 VADDSD	%XMM21,%XMM20,%XMM20

  (405) 0x4241f6 CMP	%R10D,%R9D

  (405) 0x4241f9 VPMOVSXBD	0xda0cd(%RIP),%YMM24

  (405) 0x424203 JNE	423b4f

  (405) 0x424209 JMP	423c4d

0x42420e ADD	$0x58,%RSP

0x424212 POP	%RBX

0x424213 POP	%R12

0x424215 POP	%R13

0x424217 POP	%R14

0x424219 POP	%R15

0x42421b POP	%RBP

0x42421c RET

0x42421d CALL	4243a0 <_ZSt27__throw_bad_optional_accessv>

0x424222 NOPW	%CS:(%RAX,%RAX,1)

0x42422c NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►99.98+	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	TwoBodyJastrowRef.h:106-132
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:950-952
/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
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h:338
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-260
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:106-109,126-132
/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 5.50 to 0.41 cycles (13.54x 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

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.

std::__throw_bad_optional_access(): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:952

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	32
nb uops	33
loop length	120
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	5.50 cycles
front end	5.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	1.00	0.40	3.00	3.00	5.00	0.40	1.00	5.00	5.00	5.00	0.20	3.00
cycles	1.00	0.40	3.00	3.00	5.00	0.40	1.00	5.00	5.00	5.00	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	5.50
Dispatch	5.00
Overall L1	5.50

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 5.50 cycles. At this rate:

1% of peak load performance is reached (2.91 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.36 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 5.50 to 5.00 cycles (1.10x speedup).

ASM code

In the binary file, the address of the function is: 4239e0

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 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,-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%)
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 42420e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x82e>	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%)
MOV %RSI,%RDI	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 %RBX,-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 %RSI,-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%)
JMP 423a65 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x85>	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
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
CALL 4243a0 <_ZSt27__throw_bad_optional_accessv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	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
NOPL (%RAX)	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	TwoBodyJastrowRef.h:106-132
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:950-952
/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
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h:338
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-260
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:106-109,126-132
/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

CALL instructions

Detected function call instructions.

Details

std::__throw_bad_optional_access(): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional:952

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	32
nb uops	33
loop length	120
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	5.50 cycles
front end	5.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	1.00	0.40	3.00	3.00	5.00	0.40	1.00	5.00	5.00	5.00	0.20	3.00
cycles	1.00	0.40	3.00	3.00	5.00	0.40	1.00	5.00	5.00	5.00	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	5.50
Dispatch	5.00
Overall L1	5.50

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 5.50 cycles. At this rate:

1% of peak load performance is reached (2.91 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.36 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: 4239e0

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 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,-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%)
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 42420e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x82e>	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%)
MOV %RSI,%RDI	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 %RBX,-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 %RSI,-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%)
JMP 423a65 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x85>	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
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
CALL 4243a0 <_ZSt27__throw_bad_optional_accessv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	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
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	2.09	1.79
▼Loop 404 - TwoBodyJastrowRef.h:107-132 - exec–	0.01	0.01
▼Loop 405 - BsplineFunctor.h:236-260 - exec–	0.02	0.01
○Loop 408 - BsplineFunctor.h:236-241 - exec	1.98	1.69
○Loop 406 - BsplineFunctor.h:246-260 - exec	0.08	0.07
○Loop 407 - BsplineFunctor.h:236-241 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

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

CALL instructions

Details

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