OV - - Function _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1

	Function: _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveER ...	Module: exec	Source: OneBodyJastrowRef.h:184-279 [...]	Coverage: 0.01%

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 184 - 279

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

184:     valT lap(0);

185:     constexpr valT lapfac = OHMMS_DIM - RealType(1);

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

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

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

189:     {

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

191:       valT s                  = valT();

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

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

194:       grad[idim] = s;

[...]

267:   void acceptMove(ParticleSet& P, int iat)

268:   {

269:     if (UpdateMode == ORB_PBYP_RATIO)

270:     {

271:       computeU3(P, iat, P.getDistTableAB(myTableID).getTempDists().data());

272:       curLap = accumulateGL(dU.data(), d2U.data(), P.getDistTableAB(myTableID).getTempDispls(), curGrad);

273:     }

274:

275:     LogValue += Vat[iat] - curAt;

276:     Vat[iat]  = curAt;

277:     Grad[iat] = curGrad;

278:     Lap[iat]  = curLap;

279:   }

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223

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

223:     return X[i];

/cluster/comp/gcc/13.2.0/include/c++/13.2.0/bits/stl_vector.h: 1257 - 1258

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

1257:       data() _GLIBCXX_NOEXCEPT

1258:       { return _M_data_ptr(this->_M_impl._M_start); }

0x4656f0 PUSH	%RBP

0x4656f1 MOV	%RSP,%RBP

0x4656f4 PUSH	%R15

0x4656f6 PUSH	%R14

0x4656f8 PUSH	%R13

0x4656fa PUSH	%R12

0x4656fc PUSH	%RBX

0x4656fd MOV	%RDI,%RBX

0x465700 MOVSXD	%EDX,%R12

0x465703 AND	$-0x40,%RSP

0x465707 SUB	$0x40,%RSP

0x46570b MOV	0xc(%RDI),%EDI

0x46570e TEST	%EDI,%EDI

0x465710 JE	465790

0x465712 MOV	0xf0(%RBX),%RCX

0x465719 LEA	(,%R12,8),%RDX

0x465721 VMOVSD	0x10(%RBX),%XMM7

0x465726 VMOVSD	0xb0(%RBX),%XMM9

0x46572e MOV	0x190(%RBX),%R9

0x465735 VSUBSD	%XMM9,%XMM7,%XMM11

0x46573a LEA	(%R12,%R12,2),%R15

0x46573e MOV	0x1b8(%RBX),%R8

0x465745 ADD	%RDX,%RCX

0x465748 VADDSD	(%RCX),%XMM11,%XMM12

0x46574c VMOVSD	%XMM12,0x10(%RBX)

0x465751 VMOVSD	%XMM9,(%RCX)

0x465755 VMOVDQU	0xc0(%RBX),%XMM13

0x46575d LEA	(%R9,%R15,8),%R10

0x465761 VMOVDQU	%XMM13,(%R10)

0x465766 MOV	0xd0(%RBX),%R11

0x46576d MOV	%R11,0x10(%R10)

0x465771 VMOVSD	0xb8(%RBX),%XMM3

0x465779 VMOVSD	%XMM3,(%R8,%RDX,1)

0x46577f LEA	-0x28(%RBP),%RSP

0x465783 POP	%RBX

0x465784 POP	%R12

0x465786 POP	%R13

0x465788 POP	%R14

0x46578a POP	%R15

0x46578c POP	%RBP

0x46578d RET

0x46578e XCHG	%AX,%AX

0x465790 MOV	%RSI,%R13

0x465793 MOV	0xa8(%RBX),%ESI

0x465799 MOV	%R13,%RDI

0x46579c CALL	4beed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x4657a1 MOV	%RBX,%RDI

0x4657a4 MOV	0x90(%RAX),%RSI

0x4657ab CALL	41f410 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>

0x4657b0 MOV	0xa8(%RBX),%ESI

0x4657b6 MOV	%R13,%RDI

0x4657b9 CALL	4beed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x4657be MOV	0x90(%RBX),%ECX

0x4657c4 MOV	0x130(%RBX),%RSI

0x4657cb MOV	0x118(%RBX),%RDX

0x4657d2 MOV	0xa8(%RAX),%R14

0x4657d9 MOV	0xb8(%RAX),%R15

0x4657e0 TEST	%ECX,%ECX

0x4657e2 JLE	465d61

0x4657e8 LEA	-0x1(%RCX),%R8D

0x4657ec MOV	%R8D,0x3c(%RSP)

0x4657f1 CMP	$0x6,%R8D

0x4657f5 JBE	465d71

0x4657fb MOV	%ECX,%R9D

0x4657fe XOR	%R13D,%R13D

0x465801 VBROADCASTSD	0x13e7f5(%RIP),%ZMM3

0x46580b VXORPD	%XMM9,%XMM9,%XMM9

0x465810 SHR	$0x3,%R9D

0x465814 SAL	$0x6,%R9

0x465818 LEA	-0x40(%R9),%RDI

0x46581c SHR	$0x6,%RDI

0x465820 INC	%RDI

0x465823 AND	$0x7,%EDI

0x465826 JE	4658f1

0x46582c CMP	$0x1,%RDI

0x465830 JE	4658d0

0x465836 CMP	$0x2,%RDI

0x46583a JE	4658b8

0x46583c CMP	$0x3,%RDI

0x465840 JE	4658a0

0x465842 CMP	$0x4,%RDI

0x465846 JE	465888

0x465848 CMP	$0x5,%RDI

0x46584c JE	465870

0x46584e CMP	$0x6,%RDI

0x465852 JNE	465d4a

0x465858 VMOVUPD	(%RDX,%R13,1),%ZMM2

0x46585f VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM2

0x465866 VADDPD	%ZMM2,%ZMM9,%ZMM9

0x46586c ADD	$0x40,%R13

0x465870 VMOVUPD	(%RDX,%R13,1),%ZMM4

0x465877 VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM4

0x46587e VADDPD	%ZMM4,%ZMM9,%ZMM9

0x465884 ADD	$0x40,%R13

0x465888 VMOVUPD	(%RDX,%R13,1),%ZMM5

0x46588f VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM5

0x465896 VADDPD	%ZMM5,%ZMM9,%ZMM9

0x46589c ADD	$0x40,%R13

0x4658a0 VMOVUPD	(%RDX,%R13,1),%ZMM6

0x4658a7 VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM6

0x4658ae VADDPD	%ZMM6,%ZMM9,%ZMM9

0x4658b4 ADD	$0x40,%R13

0x4658b8 VMOVUPD	(%RDX,%R13,1),%ZMM7

0x4658bf VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM7

0x4658c6 VADDPD	%ZMM7,%ZMM9,%ZMM9

0x4658cc ADD	$0x40,%R13

0x4658d0 VMOVUPD	(%RDX,%R13,1),%ZMM8

0x4658d7 VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM8

0x4658de ADD	$0x40,%R13

0x4658e2 VADDPD	%ZMM8,%ZMM9,%ZMM9

0x4658e8 CMP	%R13,%R9

0x4658eb JE	4659af

(707) 0x4658f1 VMOVUPD	(%RDX,%R13,1),%ZMM10

(707) 0x4658f8 VFMADD213PD	(%RSI,%R13,1),%ZMM3,%ZMM10

(707) 0x4658ff VADDPD	%ZMM10,%ZMM9,%ZMM11

(707) 0x465905 VMOVUPD	0x40(%RDX,%R13,1),%ZMM12

(707) 0x46590d VFMADD213PD	0x40(%RSI,%R13,1),%ZMM3,%ZMM12

(707) 0x465915 VMOVUPD	0x80(%RDX,%R13,1),%ZMM14

(707) 0x46591d VFMADD213PD	0x80(%RSI,%R13,1),%ZMM3,%ZMM14

(707) 0x465925 VMOVUPD	0xc0(%RDX,%R13,1),%ZMM1

(707) 0x46592d VFMADD213PD	0xc0(%RSI,%R13,1),%ZMM3,%ZMM1

(707) 0x465935 VMOVUPD	0x100(%RDX,%R13,1),%ZMM2

(707) 0x46593d VFMADD213PD	0x100(%RSI,%R13,1),%ZMM3,%ZMM2

(707) 0x465945 VMOVUPD	0x140(%RDX,%R13,1),%ZMM5

(707) 0x46594d VADDPD	%ZMM12,%ZMM11,%ZMM13

(707) 0x465953 VFMADD213PD	0x140(%RSI,%R13,1),%ZMM3,%ZMM5

(707) 0x46595b VMOVUPD	0x180(%RDX,%R13,1),%ZMM7

(707) 0x465963 VFMADD213PD	0x180(%RSI,%R13,1),%ZMM3,%ZMM7

(707) 0x46596b VMOVUPD	0x1c0(%RDX,%R13,1),%ZMM9

(707) 0x465973 VFMADD213PD	0x1c0(%RSI,%R13,1),%ZMM3,%ZMM9

(707) 0x46597b ADD	$0x200,%R13

(707) 0x465982 VADDPD	%ZMM14,%ZMM13,%ZMM15

(707) 0x465988 VADDPD	%ZMM1,%ZMM15,%ZMM0

(707) 0x46598e VADDPD	%ZMM2,%ZMM0,%ZMM4

(707) 0x465994 VADDPD	%ZMM5,%ZMM4,%ZMM6

(707) 0x46599a VADDPD	%ZMM7,%ZMM6,%ZMM8

(707) 0x4659a0 VADDPD	%ZMM9,%ZMM8,%ZMM9

(707) 0x4659a6 CMP	%R13,%R9

(707) 0x4659a9 JNE	4658f1

0x4659af VEXTRACTF64X4	$0x1,%ZMM9,%YMM10

0x4659b6 MOV	%ECX,%R10D

0x4659b9 VADDPD	%YMM9,%YMM10,%YMM11

0x4659be AND	$-0x8,%R10D

0x4659c2 VADDPD	%YMM10,%YMM9,%YMM0

0x4659c7 MOV	%R10D,%R11D

0x4659ca VEXTRACTF64X2	$0x1,%YMM11,%XMM3

0x4659d1 VADDPD	%XMM11,%XMM3,%XMM12

0x4659d6 VUNPCKHPD	%XMM12,%XMM12,%XMM13

0x4659db VADDPD	%XMM12,%XMM13,%XMM1

0x4659e0 CMP	%R10D,%ECX

0x4659e3 JE	465a80

0x4659e9 MOV	%ECX,%EAX

0x4659eb SUB	%R11D,%EAX

0x4659ee LEA	-0x1(%RAX),%R8D

0x4659f2 CMP	$0x2,%R8D

0x4659f6 JBE	465a31

0x4659f8 VADDPD	(%RSI,%R11,8),%YMM0,%YMM14

0x4659fe VMOVUPD	(%RDX,%R11,8),%YMM15

0x465a04 MOV	%EAX,%R11D

0x465a07 AND	$-0x4,%R11D

0x465a0b ADD	%R11D,%R10D

0x465a0e AND	$0x3,%EAX

0x465a11 VFMADD231PD	0x13e5e5(%RIP){1to4},%YMM15,%YMM14

0x465a1b VEXTRACTF64X2	$0x1,%YMM14,%XMM1

0x465a22 VADDPD	%XMM14,%XMM1,%XMM0

0x465a27 VUNPCKHPD	%XMM0,%XMM0,%XMM2

0x465a2b VADDPD	%XMM0,%XMM2,%XMM1

0x465a2f JE	465a80

0x465a31 MOVSXD	%R10D,%R9

0x465a34 LEA	0x1(%R10),%R13D

0x465a38 VMOVSD	0x13e5c0(%RIP),%XMM4

0x465a40 VADDSD	(%RSI,%R9,8),%XMM1,%XMM1

0x465a46 LEA	(,%R9,8),%RDI

0x465a4e VFMADD231SD	(%RDX,%R9,8),%XMM4,%XMM1

0x465a54 CMP	%R13D,%ECX

0x465a57 JLE	465a80

0x465a59 ADD	$0x2,%R10D

0x465a5d VFMADD231SD	0x8(%RDX,%RDI,1),%XMM4,%XMM1

0x465a64 VADDSD	0x8(%RSI,%RDI,1),%XMM1,%XMM1

0x465a6a CMP	%R10D,%ECX

0x465a6d JLE	465a80

0x465a6f VMOVSD	0x10(%RSI,%RDI,1),%XMM5

0x465a75 VFMADD132SD	0x10(%RDX,%RDI,1),%XMM5,%XMM4

0x465a7c VADDSD	%XMM4,%XMM1,%XMM1

0x465a80 MOV	%ECX,%R10D

0x465a83 LEA	0xd8(%RBX),%RSI

0x465a8a MOV	%ECX,%R11D

0x465a8d LEA	0xc0(%RBX),%R9

0x465a94 SHR	$0x3,%R10D

0x465a98 MOV	%RBX,0x30(%RSP)

0x465a9d VMOVSD	%XMM1,%XMM1,%XMM8

0x465aa1 MOV	%R12D,0x38(%RSP)

0x465aa6 SAL	$0x6,%R10

0x465aaa AND	$-0x8,%R11D

0x465aae XOR	%R8D,%R8D

0x465ab1 MOV	%R14,%RDI

0x465ab4 MOV	%RSI,%RBX

(705) 0x465ab7 LEA	(,%R8,8),%R12

(705) 0x465abf TEST	%ECX,%ECX

(705) 0x465ac1 JLE	465d30

(705) 0x465ac7 CMPL	$0x6,0x3c(%RSP)

(705) 0x465acc JBE	465d37

(705) 0x465ad2 LEA	-0x40(%R10),%RSI

(705) 0x465ad6 XOR	%R14D,%R14D

(705) 0x465ad9 LEA	(%R15,%R12,1),%R13

(705) 0x465add VXORPD	%XMM10,%XMM10,%XMM10

(705) 0x465ae2 SHR	$0x6,%RSI

(705) 0x465ae6 INC	%RSI

(705) 0x465ae9 AND	$0x7,%ESI

(705) 0x465aec JE	465ba8

(705) 0x465af2 CMP	$0x1,%RSI

(705) 0x465af6 JE	465b8c

(705) 0x465afc CMP	$0x2,%RSI

(705) 0x465b00 JE	465b79

(705) 0x465b02 CMP	$0x3,%RSI

(705) 0x465b06 JE	465b66

(705) 0x465b08 CMP	$0x4,%RSI

(705) 0x465b0c JE	465b53

(705) 0x465b0e CMP	$0x5,%RSI

(705) 0x465b12 JE	465b40

(705) 0x465b14 CMP	$0x6,%RSI

(705) 0x465b18 JE	465b2d

(705) 0x465b1a MOV	$0x40,%R14D

(705) 0x465b20 VMOVUPD	(%R13),%ZMM11

(705) 0x465b27 VFMADD231PD	(%RDX),%ZMM11,%ZMM10

(705) 0x465b2d VMOVUPD	(%R13,%R14,1),%ZMM3

(705) 0x465b35 VFMADD231PD	(%RDX,%R14,1),%ZMM3,%ZMM10

(705) 0x465b3c ADD	$0x40,%R14

(705) 0x465b40 VMOVUPD	(%R13,%R14,1),%ZMM12

(705) 0x465b48 VFMADD231PD	(%RDX,%R14,1),%ZMM12,%ZMM10

(705) 0x465b4f ADD	$0x40,%R14

(705) 0x465b53 VMOVUPD	(%R13,%R14,1),%ZMM13

(705) 0x465b5b VFMADD231PD	(%RDX,%R14,1),%ZMM13,%ZMM10

(705) 0x465b62 ADD	$0x40,%R14

(705) 0x465b66 VMOVUPD	(%R13,%R14,1),%ZMM14

(705) 0x465b6e VFMADD231PD	(%RDX,%R14,1),%ZMM14,%ZMM10

(705) 0x465b75 ADD	$0x40,%R14

(705) 0x465b79 VMOVUPD	(%R13,%R14,1),%ZMM15

(705) 0x465b81 VFMADD231PD	(%RDX,%R14,1),%ZMM15,%ZMM10

(705) 0x465b88 ADD	$0x40,%R14

(705) 0x465b8c VMOVUPD	(%R13,%R14,1),%ZMM1

(705) 0x465b94 VFMADD231PD	(%RDX,%R14,1),%ZMM1,%ZMM10

(705) 0x465b9b ADD	$0x40,%R14

(705) 0x465b9f CMP	%R14,%R10

(705) 0x465ba2 JE	465c37

  (706) 0x465ba8 VMOVUPD	(%R13,%R14,1),%ZMM0

  (706) 0x465bb0 VMOVUPD	0x40(%R13,%R14,1),%ZMM2

  (706) 0x465bb8 VMOVUPD	0x80(%R13,%R14,1),%ZMM4

  (706) 0x465bc0 VFMADD231PD	(%RDX,%R14,1),%ZMM0,%ZMM10

  (706) 0x465bc7 VMOVUPD	0xc0(%R13,%R14,1),%ZMM5

  (706) 0x465bcf VMOVUPD	0x100(%R13,%R14,1),%ZMM6

  (706) 0x465bd7 VMOVUPD	0x140(%R13,%R14,1),%ZMM9

  (706) 0x465bdf VFMADD231PD	0x40(%RDX,%R14,1),%ZMM2,%ZMM10

  (706) 0x465be7 VMOVUPD	0x180(%R13,%R14,1),%ZMM7

  (706) 0x465bef VMOVUPD	0x1c0(%R13,%R14,1),%ZMM11

  (706) 0x465bf7 VFMADD231PD	0x80(%RDX,%R14,1),%ZMM4,%ZMM10

  (706) 0x465bff VFMADD231PD	0xc0(%RDX,%R14,1),%ZMM5,%ZMM10

  (706) 0x465c07 VFMADD231PD	0x100(%RDX,%R14,1),%ZMM6,%ZMM10

  (706) 0x465c0f VFMADD231PD	0x140(%RDX,%R14,1),%ZMM9,%ZMM10

  (706) 0x465c17 VFMADD231PD	0x180(%RDX,%R14,1),%ZMM7,%ZMM10

  (706) 0x465c1f VFMADD231PD	0x1c0(%RDX,%R14,1),%ZMM11,%ZMM10

  (706) 0x465c27 ADD	$0x200,%R14

  (706) 0x465c2e CMP	%R14,%R10

  (706) 0x465c31 JNE	465ba8

(705) 0x465c37 VEXTRACTF64X4	$0x1,%ZMM10,%YMM12

(705) 0x465c3e VADDPD	%YMM10,%YMM12,%YMM13

(705) 0x465c43 VADDPD	%YMM12,%YMM10,%YMM7

(705) 0x465c48 VEXTRACTF64X2	$0x1,%YMM13,%XMM3

(705) 0x465c4f VADDPD	%XMM13,%XMM3,%XMM14

(705) 0x465c54 VUNPCKHPD	%XMM14,%XMM14,%XMM15

(705) 0x465c59 VADDPD	%XMM14,%XMM15,%XMM9

(705) 0x465c5e CMP	%ECX,%R11D

(705) 0x465c61 JE	465cf4

(705) 0x465c67 MOV	%R11D,%EAX

(705) 0x465c6a MOV	%R11D,%R14D

(705) 0x465c6d MOV	%ECX,%ESI

(705) 0x465c6f SUB	%EAX,%ESI

(705) 0x465c71 LEA	-0x1(%RSI),%R13D

(705) 0x465c75 CMP	$0x2,%R13D

(705) 0x465c79 JBE	465ca9

(705) 0x465c7b LEA	(%R8,%RAX,1),%R13

(705) 0x465c7f VMOVUPD	(%RDX,%RAX,8),%YMM10

(705) 0x465c84 VFMADD231PD	(%R15,%R13,8),%YMM10,%YMM7

(705) 0x465c8a VEXTRACTF64X2	$0x1,%YMM7,%XMM1

(705) 0x465c91 VADDPD	%XMM7,%XMM1,%XMM0

(705) 0x465c95 VUNPCKHPD	%XMM0,%XMM0,%XMM2

(705) 0x465c99 VADDPD	%XMM0,%XMM2,%XMM9

(705) 0x465c9d TEST	$0x3,%SIL

(705) 0x465ca1 JE	465cf4

(705) 0x465ca3 AND	$-0x4,%ESI

(705) 0x465ca6 ADD	%ESI,%R14D

(705) 0x465ca9 MOVSXD	%R14D,%RAX

(705) 0x465cac LEA	0x1(%R14),%R13D

(705) 0x465cb0 SAL	$0x3,%RAX

(705) 0x465cb4 LEA	(%R15,%RAX,1),%RSI

(705) 0x465cb8 VMOVSD	(%RDX,%RAX,1),%XMM4

(705) 0x465cbd VFMADD231SD	(%RSI,%R12,1),%XMM4,%XMM9

(705) 0x465cc3 CMP	%R13D,%ECX

(705) 0x465cc6 JLE	465cf4

(705) 0x465cc8 LEA	0x8(%R15,%RAX,1),%RSI

(705) 0x465ccd ADD	$0x2,%R14D

(705) 0x465cd1 VMOVSD	0x8(%RDX,%RAX,1),%XMM5

(705) 0x465cd7 VFMADD231SD	(%RSI,%R12,1),%XMM5,%XMM9

(705) 0x465cdd CMP	%R14D,%ECX

(705) 0x465ce0 JLE	465cf4

(705) 0x465ce2 LEA	0x10(%R15,%RAX,1),%R14

(705) 0x465ce7 VMOVSD	(%R14,%R12,1),%XMM6

(705) 0x465ced VFMADD231SD	0x10(%RDX,%RAX,1),%XMM6,%XMM9

(705) 0x465cf4 VMOVSD	%XMM9,(%R9)

(705) 0x465cf9 ADD	$0x8,%R9

(705) 0x465cfd ADD	%RDI,%R8

(705) 0x465d00 CMP	%RBX,%R9

(705) 0x465d03 JNE	465ab7

0x465d09 MOV	0x30(%RSP),%RBX

0x465d0e MOVSXD	0x38(%RSP),%R12

0x465d13 VMOVSD	%XMM8,0xb8(%RBX)

0x465d1b VZEROUPPER

0x465d1e JMP	465712

0x465d23 NOPW	%CS:(%RAX,%RAX,1)

0x465d2e XCHG	%AX,%AX

(705) 0x465d30 VXORPD	%XMM9,%XMM9,%XMM9

(705) 0x465d35 JMP	465cf4

(705) 0x465d37 XOR	%R14D,%R14D

(705) 0x465d3a XOR	%EAX,%EAX

(705) 0x465d3c VXORPD	%XMM7,%XMM7,%XMM7

(705) 0x465d40 VXORPD	%XMM9,%XMM9,%XMM9

(705) 0x465d45 JMP	465c6d

0x465d4a VMOVUPD	(%RDX),%ZMM9

0x465d50 MOV	$0x40,%R13D

0x465d56 VFMADD213PD	(%RSI),%ZMM3,%ZMM9

0x465d5c JMP	465858

0x465d61 LEA	-0x1(%RCX),%EAX

0x465d64 VXORPD	%XMM1,%XMM1,%XMM1

0x465d68 MOV	%EAX,0x3c(%RSP)

0x465d6c JMP	465a80

0x465d71 XOR	%R10D,%R10D

0x465d74 XOR	%R11D,%R11D

0x465d77 VXORPD	%XMM0,%XMM0,%XMM0

0x465d7b VXORPD	%XMM1,%XMM1,%XMM1

0x465d7f JMP	4659e9

0x465d84 NOPW	%CS:(%RAX,%RAX,1)

0x465d8e XCHG	%AX,%AX

Path /

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

Source file and lines	OneBodyJastrowRef.h:184-279
Module	exec

The function is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:184-194,267-279
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/cluster/comp/gcc/13.2.0/include/c++/13.2.0/bits/stl_vector.h:1257-1258

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 31.67 to 17.00 cycles (1.86x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 38% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 31.67 to 24.34 cycles (1.30x speedup).

Details

49% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

58% of SSE/AVX loads are used in vector version.
10% of SSE/AVX stores are used in vector version.
72% of SSE/AVX addition or subtraction instructions are used in vector version.
72% of SSE/AVX fused multiply-add instructions are used in vector version.
32% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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.

FMA

Detected 63 FMA (fused multiply-add) operations.

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.

_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0: 1 occurrences
getDistTableAB: 2 occurrences

Vector unaligned load/store instructions

Detected 1 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 1 occurrences

Workaround

Use vector aligned instructions:

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

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 4 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time). 4 AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (four at a time). 13 AVX-512 instructions are processing arithmetic or math operations on double precision FP elements in vector mode (eight at a time).

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

The binary function is composed of 199 FP arithmetical operations:

136: addition or subtraction (63 inside FMA instructions)
63: multiply (all inside FMA instructions)

The binary function is loading 1180 bytes (147 double precision FP elements). The binary function is storing 76 bytes (9 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.16 FP operations per loaded or stored byte.

General properties

nb instructions	192
nb uops	190
loop length	886
used x86 registers	16
used mmx registers	0
used xmm registers	13
used ymm registers	6
used zmm registers	8
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	31.67 cycles
front end	31.67 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	16.25	16.25	16.25	16.25	12.00	19.33	19.33	19.33	9.00	9.00	9.00	9.00	2.50	2.50
cycles	16.25	16.25	16.25	16.25	12.00	24.00	24.00	24.00	13.00	12.00	12.00	12.00	2.50	2.50

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	31.67
Dispatch	24.00
Overall L1	31.67

Vectorization ratios

INT

all	13%
load	50%
store	16%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	63%
load	58%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	72%
fma	72%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	63%

INT+FP

all	49%
load	58%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	72%
fma	72%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	32%

Vector efficiency ratios

INT

all	11%
load	18%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	49%
load	58%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	71%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

INT+FP

all	38%
load	56%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	71%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 31.67 cycles. At this rate:

38% of peak load performance is reached (37.26 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (2.40 out of 64.00 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 31.67 to 24.00 cycles (1.32x speedup).

ASM code

In the binary file, the address of the function is: 4656f0

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOVSXD %EDX,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND $-0x40,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SUB $0x40,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV 0xc(%RDI),%EDI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
TEST %EDI,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465790 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0xa0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV 0xf0(%RBX),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
LEA (,%R12,8),%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVSD 0x10(%RBX),%XMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VMOVSD 0xb0(%RBX),%XMM9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOV 0x190(%RBX),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
VSUBSD %XMM9,%XMM7,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
LEA (%R12,%R12,2),%R15	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV 0x1b8(%RBX),%R8	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
ADD %RDX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VADDSD (%RCX),%XMM11,%XMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
VMOVSD %XMM12,0x10(%RBX)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
VMOVSD %XMM9,(%RCX)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
VMOVDQU 0xc0(%RBX),%XMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.50
LEA (%R9,%R15,8),%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVDQU %XMM13,(%R10)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	4	1
MOV 0xd0(%RBX),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R11,0x10(%R10)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
VMOVSD 0xb8(%RBX),%XMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VMOVSD %XMM3,(%R8,%RDX,1)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
LEA -0x28(%RBP),%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %RSI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0xa8(%RBX),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 4beed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0x90(%RAX),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
CALL 41f410 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0xa8(%RBX),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 4beed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0x90(%RBX),%ECX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0x130(%RBX),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0x118(%RBX),%RDX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xa8(%RAX),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xb8(%RAX),%R15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
TEST %ECX,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 465d61 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x671>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
LEA -0x1(%RCX),%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV %R8D,0x3c(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
CMP $0x6,%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JBE 465d71 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x681>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %ECX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
VBROADCASTSD 0x13e7f5(%RIP),%ZMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0.50	0.50	0	0	0	5	1
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SHR $0x3,%R9D	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SAL $0x6,%R9	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LEA -0x40(%R9),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SHR $0x6,%RDI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
INC %RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND $0x7,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658f1 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x201>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x1,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1e0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x2,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658b8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1c8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x3,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658a0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1b0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x4,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465888 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x198>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x5,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465870 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x180>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x6,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 465d4a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x65a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VMOVUPD (%RDX,%R13,1),%ZMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM2	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM2,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM4	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM4,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM5	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM5,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM6	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM6	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM6,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM7	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM7,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM8	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM8	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VADDPD %ZMM8,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
CMP %R13,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4659af <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x2bf>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VEXTRACTF64X4 $0x1,%ZMM9,%YMM10	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.50
MOV %ECX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
VADDPD %YMM9,%YMM10,%YMM11	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
AND $-0x8,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VADDPD %YMM10,%YMM9,%YMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
MOV %R10D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
VEXTRACTF64X2 $0x1,%YMM11,%XMM3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.25
VADDPD %XMM11,%XMM3,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
VUNPCKHPD %XMM12,%XMM12,%XMM13	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.33
VADDPD %XMM12,%XMM13,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %R10D,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %ECX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SUB %R11D,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
LEA -0x1(%RAX),%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP $0x2,%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JBE 465a31 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x341>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VADDPD (%RSI,%R11,8),%YMM0,%YMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
VMOVUPD (%RDX,%R11,8),%YMM15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.50
MOV %EAX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
AND $-0x4,%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
ADD %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND $0x3,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD231PD 0x13e5e5(%RIP){1to4},%YMM15,%YMM14	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
VEXTRACTF64X2 $0x1,%YMM14,%XMM1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.25
VADDPD %XMM14,%XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
VUNPCKHPD %XMM0,%XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.33
VADDPD %XMM0,%XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
JE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %R10D,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
LEA 0x1(%R10),%R13D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVSD 0x13e5c0(%RIP),%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VADDSD (%RSI,%R9,8),%XMM1,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
LEA (,%R9,8),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD231SD (%RDX,%R9,8),%XMM4,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
CMP %R13D,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
ADD $0x2,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD231SD 0x8(%RDX,%RDI,1),%XMM4,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
VADDSD 0x8(%RSI,%RDI,1),%XMM1,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
CMP %R10D,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VMOVSD 0x10(%RSI,%RDI,1),%XMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VFMADD132SD 0x10(%RDX,%RDI,1),%XMM5,%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
VADDSD %XMM4,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
MOV %ECX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
LEA 0xd8(%RBX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV %ECX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
LEA 0xc0(%RBX),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SHR $0x3,%R10D	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RBX,0x30(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
VMOVSD %XMM1,%XMM1,%XMM8	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
MOV %R12D,0x38(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
SAL $0x6,%R10	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
AND $-0x8,%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0x30(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSXD 0x38(%RSP),%R12	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33
VMOVSD %XMM8,0xb8(%RBX)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1
JMP 465712 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x22>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
VMOVUPD (%RDX),%ZMM9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
MOV $0x40,%R13D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD213PD (%RSI),%ZMM3,%ZMM9	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
JMP 465858 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x168>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
LEA -0x1(%RCX),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %EAX,0x3c(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
JMP 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 4659e9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x2f9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09

Source file and lines	OneBodyJastrowRef.h:184-279
Module	exec

The function is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:184-194,267-279
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/cluster/comp/gcc/13.2.0/include/c++/13.2.0/bits/stl_vector.h:1257-1258

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

49% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

58% of SSE/AVX loads are used in vector version.
10% of SSE/AVX stores are used in vector version.
72% of SSE/AVX addition or subtraction instructions are used in vector version.
72% of SSE/AVX fused multiply-add instructions are used in vector version.
32% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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.

FMA

Detected 63 FMA (fused multiply-add) operations.

CALL instructions

Detected function call instructions.

Details

_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0: 1 occurrences
getDistTableAB: 2 occurrences

Vector unaligned load/store instructions

Detected 1 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 1 occurrences

Workaround

Use vector aligned instructions:

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

Type of elements and instruction set

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

The binary function is composed of 199 FP arithmetical operations:

136: addition or subtraction (63 inside FMA instructions)
63: multiply (all inside FMA instructions)

The binary function is loading 1180 bytes (147 double precision FP elements). The binary function is storing 76 bytes (9 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.16 FP operations per loaded or stored byte.

General properties

nb instructions	192
nb uops	190
loop length	886
used x86 registers	16
used mmx registers	0
used xmm registers	13
used ymm registers	6
used zmm registers	8
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	31.67 cycles
front end	31.67 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	16.25	16.25	16.25	16.25	12.00	19.33	19.33	19.33	9.00	9.00	9.00	9.00	2.50	2.50
cycles	16.25	16.25	16.25	16.25	12.00	24.00	24.00	24.00	13.00	12.00	12.00	12.00	2.50	2.50

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	31.67
Dispatch	24.00
Overall L1	31.67

Vectorization ratios

INT

all	13%
load	50%
store	16%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	63%
load	58%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	72%
fma	72%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	63%

INT+FP

all	49%
load	58%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	72%
fma	72%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	32%

Vector efficiency ratios

INT

all	11%
load	18%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	49%
load	58%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	71%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

INT+FP

all	38%
load	56%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	71%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 31.67 cycles. At this rate:

38% of peak load performance is reached (37.26 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (2.40 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 4656f0

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOVSXD %EDX,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND $-0x40,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SUB $0x40,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV 0xc(%RDI),%EDI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
TEST %EDI,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465790 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0xa0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV 0xf0(%RBX),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
LEA (,%R12,8),%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVSD 0x10(%RBX),%XMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VMOVSD 0xb0(%RBX),%XMM9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOV 0x190(%RBX),%R9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
VSUBSD %XMM9,%XMM7,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
LEA (%R12,%R12,2),%R15	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV 0x1b8(%RBX),%R8	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
ADD %RDX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VADDSD (%RCX),%XMM11,%XMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
VMOVSD %XMM12,0x10(%RBX)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
VMOVSD %XMM9,(%RCX)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
VMOVDQU 0xc0(%RBX),%XMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.50
LEA (%R9,%R15,8),%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVDQU %XMM13,(%R10)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	4	1
MOV 0xd0(%RBX),%R11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R11,0x10(%R10)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
VMOVSD 0xb8(%RBX),%XMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VMOVSD %XMM3,(%R8,%RDX,1)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
LEA -0x28(%RBP),%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %RSI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0xa8(%RBX),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 4beed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0x90(%RAX),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
CALL 41f410 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0xa8(%RBX),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R13,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 4beed0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0x90(%RBX),%ECX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0x130(%RBX),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0x118(%RBX),%RDX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xa8(%RAX),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xb8(%RAX),%R15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
TEST %ECX,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 465d61 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x671>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
LEA -0x1(%RCX),%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV %R8D,0x3c(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
CMP $0x6,%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JBE 465d71 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x681>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %ECX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
VBROADCASTSD 0x13e7f5(%RIP),%ZMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0.50	0.50	0	0	0	5	1
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SHR $0x3,%R9D	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SAL $0x6,%R9	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LEA -0x40(%R9),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SHR $0x6,%RDI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
INC %RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND $0x7,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658f1 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x201>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x1,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658d0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1e0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x2,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658b8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1c8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x3,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4658a0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x1b0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x4,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465888 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x198>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x5,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465870 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x180>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
CMP $0x6,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 465d4a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x65a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VMOVUPD (%RDX,%R13,1),%ZMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM2	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM2,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM4	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM4,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM5	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM5,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM6	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM6	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM6,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM7	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
VADDPD %ZMM7,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVUPD (%RDX,%R13,1),%ZMM8	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
VFMADD213PD (%RSI,%R13,1),%ZMM3,%ZMM8	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
ADD $0x40,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VADDPD %ZMM8,%ZMM9,%ZMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1
CMP %R13,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4659af <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x2bf>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VEXTRACTF64X4 $0x1,%ZMM9,%YMM10	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.50
MOV %ECX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
VADDPD %YMM9,%YMM10,%YMM11	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
AND $-0x8,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VADDPD %YMM10,%YMM9,%YMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
MOV %R10D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
VEXTRACTF64X2 $0x1,%YMM11,%XMM3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.25
VADDPD %XMM11,%XMM3,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
VUNPCKHPD %XMM12,%XMM12,%XMM13	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.33
VADDPD %XMM12,%XMM13,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %R10D,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %ECX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SUB %R11D,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
LEA -0x1(%RAX),%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP $0x2,%R8D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JBE 465a31 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x341>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VADDPD (%RSI,%R11,8),%YMM0,%YMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
VMOVUPD (%RDX,%R11,8),%YMM15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.50
MOV %EAX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
AND $-0x4,%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
ADD %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND $0x3,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD231PD 0x13e5e5(%RIP){1to4},%YMM15,%YMM14	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
VEXTRACTF64X2 $0x1,%YMM14,%XMM1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.25
VADDPD %XMM14,%XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
VUNPCKHPD %XMM0,%XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.33
VADDPD %XMM0,%XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
JE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %R10D,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
LEA 0x1(%R10),%R13D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VMOVSD 0x13e5c0(%RIP),%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VADDSD (%RSI,%R9,8),%XMM1,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
LEA (,%R9,8),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD231SD (%RDX,%R9,8),%XMM4,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
CMP %R13D,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
ADD $0x2,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD231SD 0x8(%RDX,%RDI,1),%XMM4,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
VADDSD 0x8(%RSI,%RDI,1),%XMM1,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
CMP %R10D,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
VMOVSD 0x10(%RSI,%RDI,1),%XMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
VFMADD132SD 0x10(%RDX,%RDI,1),%XMM5,%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	0.50
VADDSD %XMM4,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
MOV %ECX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
LEA 0xd8(%RBX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV %ECX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
LEA 0xc0(%RBX),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SHR $0x3,%R10D	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RBX,0x30(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
VMOVSD %XMM1,%XMM1,%XMM8	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
MOV %R12D,0x38(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
SAL $0x6,%R10	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
AND $-0x8,%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0x30(%RSP),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSXD 0x38(%RSP),%R12	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33
VMOVSD %XMM8,0xb8(%RBX)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1
JMP 465712 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x22>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
VMOVUPD (%RDX),%ZMM9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1
MOV $0x40,%R13D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VFMADD213PD (%RSI),%ZMM3,%ZMM9	1	0	0	0	0	0	0.33	0.33	0.33	0.50	0.50	0	0	0	0	4	1
JMP 465858 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x168>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
LEA -0x1(%RCX),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %EAX,0x3c(%RSP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
JMP 465a80 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 4659e9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x2f9>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09

▶Scalability Runs Description

Run 2x1	Number processes: 2Number nodes: 1Number processes per node: 2Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -np <number_processes>Dataset: Run Directory: /beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/run/oneview_runs/compilers/gcc_2/oneview_run_1708580749OMP_NUM_THREADS: 1
Run 2x2	OMP_NUM_THREADS: 2
Run 2x4	OMP_NUM_THREADS: 4
Run 2x8	OMP_NUM_THREADS: 8
Run 2x16	OMP_NUM_THREADS: 16
Run 2x32	OMP_NUM_THREADS: 32
Run 2x64	OMP_NUM_THREADS: 64
Run 2x96	OMP_NUM_THREADS: 96

(2x1) Efficiency	(2x1) Potential Speed-Up (%)	(2x2) Efficiency	(2x2) Potential Speed-Up (%)	(2x4) Efficiency	(2x4) Potential Speed-Up (%)	(2x8) Efficiency	(2x8) Potential Speed-Up (%)	(2x16) Efficiency	(2x16) Potential Speed-Up (%)	(2x32) Efficiency	(2x32) Potential Speed-Up (%)	(2x64) Efficiency	(2x64) Potential Speed-Up (%)	(2x96) Efficiency	(2x96) Potential Speed-Up (%)
1	0	1	0	1	0			1	0	1	0	1	0	0	0

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
2x1	1	1	1	1	0	0.01
2x2	1	1	1	1.5	0	0
2x4	5	1	1	2.25	0	0.01
2x8
2x16	9	1	1	8.25	0	0
2x32	28	1	1	16.5	0.01	0
2x64	75	1	1	32.5	0.02	0
2x96	155	0	0	48.5	0.02	0

Name	Coverage (%)	Time (s)
▼_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi–	0.01	0
○Loop 707 - OneBodyJastrowRef.h:186-187 - exec	0	0
▼Loop 705 - OneBodyJastrowRef.h:184-194 - exec–	0	0
○Loop 706 - OneBodyJastrowRef.h:192-193 - exec	0	0

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

CALL instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

CALL instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

▶Scalability Runs Description

▼Colums Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency