OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcpl ...	Module: exec	Source: OneBodyJastrowRef.h:184-264 [...]	Coverage (incl. loops): 0.04% \| (excl. loops): 0.01%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

94:     (const_cast<T1&>(a) += b);

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_numeric.h: 140 - 141

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

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h: 1262 - 1263

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

1262:       data() _GLIBCXX_NOEXCEPT

1263:       { return _M_data_ptr(this->_M_impl._M_start); }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 184 - 264

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

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;

[...]

255:   ValueType ratioGrad(ParticleSet& P, int iat, GradType& grad_iat)

256:   {

257:     UpdateMode = ORB_PBYP_PARTIAL;

258:

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

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

261:     curAt  = std::accumulate(U.begin(), U.begin() + Nions, valT());

262:     grad_iat += curGrad;

263:     return std::exp(Vat[iat] - curAt);

264:   }

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_iterator.h: 1068 - 1139

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

1068:       : _M_current(__i) { }

[...]

1102: 	++_M_current;

[...]

1139:       { return __normal_iterator(_M_current + __n); }

0x46e840 PUSH	%R13

0x46e842 LEA	0x10(%RSP),%R13

0x46e847 AND	$-0x20,%RSP

0x46e84b PUSHQ	-0x8(%R13)

0x46e84f PUSH	%RBP

0x46e850 MOV	%RSP,%RBP

0x46e853 PUSH	%R15

0x46e855 MOV	%EDX,%R15D

0x46e858 PUSH	%R14

0x46e85a MOV	%RSI,%R14

0x46e85d PUSH	%R13

0x46e85f PUSH	%R12

0x46e861 MOV	%RCX,%R12

0x46e864 PUSH	%RBX

0x46e865 MOV	%RDI,%RBX

0x46e868 SUB	$0x28,%RSP

0x46e86c MOVL	$0x2,0xc(%RDI)

0x46e873 MOV	0xa8(%RDI),%ESI

0x46e879 MOV	%R14,%RDI

0x46e87c CALL	4c58b0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x46e881 MOV	0x90(%RAX),%RSI

0x46e888 MOV	%RBX,%RDI

0x46e88b CALL	41def0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>

0x46e890 MOV	0xa8(%RBX),%ESI

0x46e896 MOV	%R14,%RDI

0x46e899 CALL	4c58b0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x46e89e MOV	0xa8(%RAX),%RDI

0x46e8a5 MOVSXD	0x90(%RBX),%RCX

0x46e8ac MOV	%RDI,-0x40(%RBP)

0x46e8b0 MOV	0x130(%RBX),%RSI

0x46e8b7 MOV	0x118(%RBX),%RDX

0x46e8be MOV	0xb8(%RAX),%R13

0x46e8c5 TEST	%ECX,%ECX

0x46e8c7 JLE	46ef0b

0x46e8cd LEA	-0x1(%RCX),%R8D

0x46e8d1 MOV	%R8D,-0x34(%RBP)

0x46e8d5 CMP	$0x2,%R8D

0x46e8d9 JBE	46ef23

0x46e8df MOV	%ECX,%R10D

0x46e8e2 SHR	$0x2,%R10D

0x46e8e6 SAL	$0x5,%R10

0x46e8ea LEA	-0x20(%R10),%R11

0x46e8ee SHR	$0x5,%R11

0x46e8f2 INC	%R11

0x46e8f5 VBROADCASTSD	0x148aa2(%RIP),%YMM3

0x46e8fe XOR	%R14D,%R14D

0x46e901 VXORPD	%XMM9,%XMM9,%XMM9

0x46e906 AND	$0x7,%R11D

0x46e90a JE	46e9be

0x46e910 CMP	$0x1,%R11

0x46e914 JE	46e9a0

0x46e91a CMP	$0x2,%R11

0x46e91e JE	46e98c

0x46e920 CMP	$0x3,%R11

0x46e924 JE	46e978

0x46e926 CMP	$0x4,%R11

0x46e92a JE	46e964

0x46e92c CMP	$0x5,%R11

0x46e930 JE	46e950

0x46e932 CMP	$0x6,%R11

0x46e936 JNE	46eee8

0x46e93c VMOVUPD	(%RDX,%R14,1),%YMM1

0x46e942 VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM1

0x46e948 ADD	$0x20,%R14

0x46e94c VADDPD	%YMM1,%YMM9,%YMM9

0x46e950 VMOVUPD	(%RDX,%R14,1),%YMM4

0x46e956 VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM4

0x46e95c ADD	$0x20,%R14

0x46e960 VADDPD	%YMM4,%YMM9,%YMM9

0x46e964 VMOVUPD	(%RDX,%R14,1),%YMM5

0x46e96a VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM5

0x46e970 ADD	$0x20,%R14

0x46e974 VADDPD	%YMM5,%YMM9,%YMM9

0x46e978 VMOVUPD	(%RDX,%R14,1),%YMM6

0x46e97e VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM6

0x46e984 ADD	$0x20,%R14

0x46e988 VADDPD	%YMM6,%YMM9,%YMM9

0x46e98c VMOVUPD	(%RDX,%R14,1),%YMM7

0x46e992 VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM7

0x46e998 ADD	$0x20,%R14

0x46e99c VADDPD	%YMM7,%YMM9,%YMM9

0x46e9a0 VMOVUPD	(%RDX,%R14,1),%YMM8

0x46e9a6 VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM8

0x46e9ac ADD	$0x20,%R14

0x46e9b0 VADDPD	%YMM8,%YMM9,%YMM9

0x46e9b5 CMP	%R10,%R14

0x46e9b8 JE	46ea78

(834) 0x46e9be VMOVUPD	(%RDX,%R14,1),%YMM10

(834) 0x46e9c4 VMOVUPD	0x20(%RDX,%R14,1),%YMM12

(834) 0x46e9cb VFMADD213PD	(%RSI,%R14,1),%YMM3,%YMM10

(834) 0x46e9d1 VFMADD213PD	0x20(%RSI,%R14,1),%YMM3,%YMM12

(834) 0x46e9d8 VMOVUPD	0x40(%RDX,%R14,1),%YMM14

(834) 0x46e9df VMOVUPD	0x60(%RDX,%R14,1),%YMM2

(834) 0x46e9e6 VFMADD213PD	0x40(%RSI,%R14,1),%YMM3,%YMM14

(834) 0x46e9ed VADDPD	%YMM10,%YMM9,%YMM11

(834) 0x46e9f2 VFMADD213PD	0x60(%RSI,%R14,1),%YMM3,%YMM2

(834) 0x46e9f9 VMOVUPD	0x80(%RDX,%R14,1),%YMM1

(834) 0x46ea03 VADDPD	%YMM12,%YMM11,%YMM13

(834) 0x46ea08 VFMADD213PD	0x80(%RSI,%R14,1),%YMM3,%YMM1

(834) 0x46ea12 VMOVUPD	0xa0(%RDX,%R14,1),%YMM5

(834) 0x46ea1c VADDPD	%YMM14,%YMM13,%YMM15

(834) 0x46ea21 VFMADD213PD	0xa0(%RSI,%R14,1),%YMM3,%YMM5

(834) 0x46ea2b VMOVUPD	0xc0(%RDX,%R14,1),%YMM7

(834) 0x46ea35 VADDPD	%YMM2,%YMM15,%YMM0

(834) 0x46ea39 VFMADD213PD	0xc0(%RSI,%R14,1),%YMM3,%YMM7

(834) 0x46ea43 VMOVUPD	0xe0(%RDX,%R14,1),%YMM9

(834) 0x46ea4d VADDPD	%YMM1,%YMM0,%YMM4

(834) 0x46ea51 VFMADD213PD	0xe0(%RSI,%R14,1),%YMM3,%YMM9

(834) 0x46ea5b ADD	$0x100,%R14

(834) 0x46ea62 VADDPD	%YMM5,%YMM4,%YMM6

(834) 0x46ea66 VADDPD	%YMM7,%YMM6,%YMM8

(834) 0x46ea6a VADDPD	%YMM9,%YMM8,%YMM9

(834) 0x46ea6f CMP	%R10,%R14

(834) 0x46ea72 JNE	46e9be

0x46ea78 VEXTRACTF64X2	$0x1,%YMM9,%XMM3

0x46ea7f VADDPD	%XMM9,%XMM3,%XMM0

0x46ea84 MOV	%ECX,%EAX

0x46ea86 AND	$-0x4,%EAX

0x46ea89 VUNPCKHPD	%XMM0,%XMM0,%XMM10

0x46ea8d VADDPD	%XMM0,%XMM10,%XMM2

0x46ea91 MOV	%EAX,%R9D

0x46ea94 CMP	%EAX,%ECX

0x46ea96 JE	46eae2

0x46ea98 MOV	%ECX,%EDI

0x46ea9a SUB	%R9D,%EDI

0x46ea9d CMP	$0x1,%EDI

0x46eaa0 JE	46eacd

0x46eaa2 VADDPD	(%RSI,%R9,8),%XMM0,%XMM11

0x46eaa8 VMOVUPD	(%RDX,%R9,8),%XMM12

0x46eaae VFMADD231PD	0x1488e8(%RIP){1to2},%XMM12,%XMM11

0x46eab8 VUNPCKHPD	%XMM11,%XMM11,%XMM13

0x46eabd VADDPD	%XMM11,%XMM13,%XMM2

0x46eac2 TEST	$0x1,%DIL

0x46eac6 JE	46eae2

0x46eac8 AND	$-0x2,%EDI

0x46eacb ADD	%EDI,%EAX

0x46eacd CLTQ

0x46eacf VADDSD	(%RSI,%RAX,8),%XMM2,%XMM2

0x46ead4 VMOVSD	(%RDX,%RAX,8),%XMM14

0x46ead9 VFMADD231SD	0x1488be(%RIP),%XMM14,%XMM2

0x46eae2 LEA	0xc0(%RBX),%RSI

0x46eae9 LEA	0xd8(%RBX),%R14

0x46eaf0 XOR	%R9D,%R9D

(828) 0x46eaf3 TEST	%ECX,%ECX

(828) 0x46eaf5 JLE	46eec8

0x46eafb MOV	%ECX,%R8D

0x46eafe SHR	$0x2,%R8D

0x46eb02 SAL	$0x5,%R8

0x46eb06 CMPL	$0x2,-0x34(%RBP)

0x46eb0a MOV	%RBX,-0x48(%RBP)

0x46eb0e LEA	(,%R9,8),%R11

0x46eb16 JBE	46ecde

    (831) 0x46eb1c LEA	-0x20(%R8),%R10

    (831) 0x46eb20 SHR	$0x5,%R10

    (831) 0x46eb24 INC	%R10

    (831) 0x46eb27 LEA	(%R13,%R11,1),%RBX

    (831) 0x46eb2c XOR	%EDI,%EDI

    (831) 0x46eb2e VXORPD	%XMM0,%XMM0,%XMM0

    (831) 0x46eb32 AND	$0x7,%R10D

    (831) 0x46eb36 JE	46ebc7

    (831) 0x46eb3c CMP	$0x1,%R10

    (831) 0x46eb40 JE	46ebaf

    (831) 0x46eb42 CMP	$0x2,%R10

    (831) 0x46eb46 JE	46eba0

    (831) 0x46eb48 CMP	$0x3,%R10

    (831) 0x46eb4c JE	46eb91

    (831) 0x46eb4e CMP	$0x4,%R10

    (831) 0x46eb52 JE	46eb82

    (831) 0x46eb54 CMP	$0x5,%R10

    (831) 0x46eb58 JE	46eb73

    (831) 0x46eb5a CMP	$0x6,%R10

    (831) 0x46eb5e JNE	46eeb0

    (831) 0x46eb64 VMOVUPD	(%RDX,%RDI,1),%YMM4

    (831) 0x46eb69 VFMADD231PD	(%RBX,%RDI,1),%YMM4,%YMM0

    (831) 0x46eb6f ADD	$0x20,%RDI

    (831) 0x46eb73 VMOVUPD	(%RDX,%RDI,1),%YMM5

    (831) 0x46eb78 VFMADD231PD	(%RBX,%RDI,1),%YMM5,%YMM0

    (831) 0x46eb7e ADD	$0x20,%RDI

    (831) 0x46eb82 VMOVUPD	(%RDX,%RDI,1),%YMM6

    (831) 0x46eb87 VFMADD231PD	(%RBX,%RDI,1),%YMM6,%YMM0

    (831) 0x46eb8d ADD	$0x20,%RDI

    (831) 0x46eb91 VMOVUPD	(%RDX,%RDI,1),%YMM7

    (831) 0x46eb96 VFMADD231PD	(%RBX,%RDI,1),%YMM7,%YMM0

    (831) 0x46eb9c ADD	$0x20,%RDI

    (831) 0x46eba0 VMOVUPD	(%RDX,%RDI,1),%YMM8

    (831) 0x46eba5 VFMADD231PD	(%RBX,%RDI,1),%YMM8,%YMM0

    (831) 0x46ebab ADD	$0x20,%RDI

    (831) 0x46ebaf VMOVUPD	(%RDX,%RDI,1),%YMM9

    (831) 0x46ebb4 VFMADD231PD	(%RBX,%RDI,1),%YMM9,%YMM0

    (831) 0x46ebba ADD	$0x20,%RDI

    (831) 0x46ebbe CMP	%R8,%RDI

    (831) 0x46ebc1 JE	46ec55

      (830) 0x46ebc7 VMOVUPD	(%RDX,%RDI,1),%YMM3

      (830) 0x46ebcc VMOVUPD	0x20(%RDX,%RDI,1),%YMM10

      (830) 0x46ebd2 VFMADD231PD	(%RBX,%RDI,1),%YMM3,%YMM0

      (830) 0x46ebd8 VMOVUPD	0x40(%RDX,%RDI,1),%YMM11

      (830) 0x46ebde VMOVUPD	0x60(%RDX,%RDI,1),%YMM12

      (830) 0x46ebe4 VMOVUPD	0x80(%RDX,%RDI,1),%YMM13

      (830) 0x46ebed VMOVUPD	0xa0(%RDX,%RDI,1),%YMM14

      (830) 0x46ebf6 VFMADD231PD	0x20(%RBX,%RDI,1),%YMM10,%YMM0

      (830) 0x46ebfd VMOVUPD	0xc0(%RDX,%RDI,1),%YMM15

      (830) 0x46ec06 VMOVUPD	0xe0(%RDX,%RDI,1),%YMM1

      (830) 0x46ec0f VFMADD231PD	0x40(%RBX,%RDI,1),%YMM11,%YMM0

      (830) 0x46ec16 VFMADD231PD	0x60(%RBX,%RDI,1),%YMM12,%YMM0

      (830) 0x46ec1d VFMADD231PD	0x80(%RBX,%RDI,1),%YMM13,%YMM0

      (830) 0x46ec27 VFMADD231PD	0xa0(%RBX,%RDI,1),%YMM14,%YMM0

      (830) 0x46ec31 VFMADD231PD	0xc0(%RBX,%RDI,1),%YMM15,%YMM0

      (830) 0x46ec3b VFMADD231PD	0xe0(%RBX,%RDI,1),%YMM1,%YMM0

      (830) 0x46ec45 ADD	$0x100,%RDI

      (830) 0x46ec4c CMP	%R8,%RDI

      (830) 0x46ec4f JNE	46ebc7

    (831) 0x46ec55 VEXTRACTF64X2	$0x1,%YMM0,%XMM4

    (831) 0x46ec5c VADDPD	%XMM0,%XMM4,%XMM15

    (831) 0x46ec60 MOV	%ECX,%EAX

    (831) 0x46ec62 AND	$-0x4,%EAX

    (831) 0x46ec65 VUNPCKHPD	%XMM15,%XMM15,%XMM0

    (831) 0x46ec6a VADDPD	%XMM15,%XMM0,%XMM7

    (831) 0x46ec6f MOV	%EAX,%EDI

    (831) 0x46ec71 CMP	%EAX,%ECX

    (831) 0x46ec73 JE	46ecb8

  (832) 0x46ec75 MOV	%ECX,%R10D

  (832) 0x46ec78 SUB	%EDI,%R10D

  (832) 0x46ec7b CMP	$0x1,%R10D

  (832) 0x46ec7f JE	46eca8

  (832) 0x46ec81 VMOVUPD	(%RDX,%RDI,8),%XMM5

  (832) 0x46ec86 LEA	(%R9,%RDI,1),%RBX

  (832) 0x46ec8a VFMADD231PD	(%R13,%RBX,8),%XMM5,%XMM15

  (832) 0x46ec91 VUNPCKHPD	%XMM15,%XMM15,%XMM6

  (832) 0x46ec96 VADDPD	%XMM15,%XMM6,%XMM7

  (832) 0x46ec9b TEST	$0x1,%R10B

  (832) 0x46ec9f JE	46ecb8

  (832) 0x46eca1 AND	$-0x2,%R10D

  (832) 0x46eca5 ADD	%R10D,%EAX

  (832) 0x46eca8 CLTQ

  (832) 0x46ecaa VMOVSD	(%RDX,%RAX,8),%XMM8

  (832) 0x46ecaf ADD	%R13,%R11

  (832) 0x46ecb2 VFMADD231SD	(%R11,%RAX,8),%XMM8,%XMM7

    (831) 0x46ecb8 VMOVSD	%XMM7,(%RSI)

    (831) 0x46ecbc ADD	$0x8,%RSI

    (831) 0x46ecc0 CMP	%R14,%RSI

    (831) 0x46ecc3 JE	46ecf0

    (831) 0x46ecc5 MOV	-0x40(%RBP),%RDI

    (831) 0x46ecc9 ADD	%RDI,%R9

    (831) 0x46eccc CMPL	$0x2,-0x34(%RBP)

    (831) 0x46ecd0 LEA	(,%R9,8),%R11

    (831) 0x46ecd8 JA	46eb1c

(833) 0x46ecde VXORPD	%XMM15,%XMM15,%XMM15

(833) 0x46ece3 XOR	%EDI,%EDI

(833) 0x46ece5 VXORPD	%XMM7,%XMM7,%XMM7

(833) 0x46ece9 XOR	%EAX,%EAX

(833) 0x46eceb JMP	46ec75

0x46eced NOPL	(%RAX)

0x46ecf0 MOV	-0x48(%RBP),%RBX

0x46ecf4 MOV	0x100(%RBX),%R13

0x46ecfb SAL	$0x3,%RCX

0x46ecff LEA	(%R13,%RCX,1),%R11

0x46ed04 VMOVSD	%XMM2,0xb8(%RBX)

0x46ed0c CMP	%R13,%R11

0x46ed0f JE	46ef1a

0x46ed15 SUB	$0x8,%RCX

0x46ed19 MOV	%RCX,%RSI

0x46ed1c SHR	$0x3,%RSI

0x46ed20 INC	%RSI

0x46ed23 CMP	$0x10,%RCX

0x46ed27 JBE	46ef35

0x46ed2d MOV	%RSI,%RDX

0x46ed30 SHR	$0x2,%RDX

0x46ed34 SAL	$0x5,%RDX

0x46ed38 LEA	(%RDX,%R13,1),%RCX

0x46ed3c SUB	$0x20,%RDX

0x46ed40 SHR	$0x5,%RDX

0x46ed44 INC	%RDX

0x46ed47 MOV	%R13,%R14

0x46ed4a VXORPD	%XMM9,%XMM9,%XMM9

0x46ed4f AND	$0x7,%EDX

0x46ed52 JE	46edb7

0x46ed54 CMP	$0x1,%RDX

0x46ed58 JE	46eda9

0x46ed5a CMP	$0x2,%RDX

0x46ed5e JE	46eda0

0x46ed60 CMP	$0x3,%RDX

0x46ed64 JE	46ed97

0x46ed66 CMP	$0x4,%RDX

0x46ed6a JE	46ed8e

0x46ed6c CMP	$0x5,%RDX

0x46ed70 JE	46ed85

0x46ed72 CMP	$0x6,%RDX

0x46ed76 JNE	46eefc

0x46ed7c VADDPD	(%R14),%YMM9,%YMM9

0x46ed81 ADD	$0x20,%R14

0x46ed85 VADDPD	(%R14),%YMM9,%YMM9

0x46ed8a ADD	$0x20,%R14

0x46ed8e VADDPD	(%R14),%YMM9,%YMM9

0x46ed93 ADD	$0x20,%R14

0x46ed97 VADDPD	(%R14),%YMM9,%YMM9

0x46ed9c ADD	$0x20,%R14

0x46eda0 VADDPD	(%R14),%YMM9,%YMM9

0x46eda5 ADD	$0x20,%R14

0x46eda9 VADDPD	(%R14),%YMM9,%YMM9

0x46edae ADD	$0x20,%R14

0x46edb2 CMP	%R14,%RCX

0x46edb5 JE	46edfb

(829) 0x46edb7 VADDPD	(%R14),%YMM9,%YMM3

(829) 0x46edbc ADD	$0x100,%R14

(829) 0x46edc3 VADDPD	-0xe0(%R14),%YMM3,%YMM10

(829) 0x46edcc VADDPD	-0xc0(%R14),%YMM10,%YMM11

(829) 0x46edd5 VADDPD	-0xa0(%R14),%YMM11,%YMM12

(829) 0x46edde VADDPD	-0x80(%R14),%YMM12,%YMM13

(829) 0x46ede4 VADDPD	-0x60(%R14),%YMM13,%YMM14

(829) 0x46edea VADDPD	-0x40(%R14),%YMM14,%YMM15

(829) 0x46edf0 VADDPD	-0x20(%R14),%YMM15,%YMM9

(829) 0x46edf6 CMP	%R14,%RCX

(829) 0x46edf9 JNE	46edb7

0x46edfb VEXTRACTF64X2	$0x1,%YMM9,%XMM1

0x46ee02 VADDPD	%XMM9,%XMM1,%XMM4

0x46ee07 VUNPCKHPD	%XMM4,%XMM4,%XMM0

0x46ee0b VADDPD	%XMM4,%XMM0,%XMM2

0x46ee0f TEST	$0x3,%SIL

0x46ee13 JE	46ee42

0x46ee15 AND	$-0x4,%RSI

0x46ee19 LEA	(%R13,%RSI,8),%R13

0x46ee1e LEA	0x8(%R13),%R9

0x46ee22 VADDSD	(%R13),%XMM2,%XMM2

0x46ee28 CMP	%R9,%R11

0x46ee2b JE	46ee42

0x46ee2d LEA	0x10(%R13),%R8

0x46ee31 VADDSD	0x8(%R13),%XMM2,%XMM2

0x46ee37 CMP	%R8,%R11

0x46ee3a JE	46ee42

0x46ee3c VADDSD	0x10(%R13),%XMM2,%XMM2

0x46ee42 VMOVSD	%XMM2,0xb0(%RBX)

0x46ee4a VMOVUPD	(%R12),%XMM5

0x46ee50 VMOVSD	0x10(%R12),%XMM7

0x46ee57 VADDPD	0xc0(%RBX),%XMM5,%XMM6

0x46ee5f MOVSXD	%R15D,%R15

0x46ee62 VMOVUPD	%XMM6,(%R12)

0x46ee68 VADDSD	0xd0(%RBX),%XMM7,%XMM8

0x46ee70 VMOVSD	%XMM8,0x10(%R12)

0x46ee77 MOV	0xf0(%RBX),%R12

0x46ee7e VMOVSD	(%R12,%R15,8),%XMM2

0x46ee84 VSUBSD	0xb0(%RBX),%XMM2,%XMM0

0x46ee8c VZEROUPPER

0x46ee8f ADD	$0x28,%RSP

0x46ee93 POP	%RBX

0x46ee94 POP	%R12

0x46ee96 POP	%RAX

0x46ee97 POP	%R14

0x46ee99 POP	%R15

0x46ee9b POP	%RBP

0x46ee9c LEA	-0x10(%RAX),%RSP

0x46eea0 POP	%R13

0x46eea2 JMP	4040b0

0x46eea7 NOPW	(%RAX,%RAX,1)

    (831) 0x46eeb0 VMOVUPD	(%RDX),%YMM1

    (831) 0x46eeb4 MOV	$0x20,%EDI

    (831) 0x46eeb9 VFMADD231PD	(%RBX),%YMM1,%YMM0

    (831) 0x46eebe JMP	46eb64

0x46eec3 NOPL	(%RAX,%RAX,1)

(828) 0x46eec8 MOV	-0x40(%RBP),%R8

(828) 0x46eecc MOVQ	$0,(%RSI)

(828) 0x46eed3 ADD	$0x8,%RSI

(828) 0x46eed7 ADD	%R8,%R9

(828) 0x46eeda CMP	%R14,%RSI

(828) 0x46eedd JNE	46eaf3

0x46eee3 JMP	46ecf4

0x46eee8 VMOVUPD	(%RDX),%YMM9

0x46eeec MOV	$0x20,%R14D

0x46eef2 VFMADD213PD	(%RSI),%YMM3,%YMM9

0x46eef7 JMP	46e93c

0x46eefc VMOVUPD	(%R13),%YMM9

0x46ef02 LEA	0x20(%R13),%R14

0x46ef06 JMP	46ed7c

0x46ef0b LEA	-0x1(%RCX),%EAX

0x46ef0e MOV	%EAX,-0x34(%RBP)

0x46ef11 VXORPD	%XMM2,%XMM2,%XMM2

0x46ef15 JMP	46eae2

0x46ef1a VXORPD	%XMM2,%XMM2,%XMM2

0x46ef1e JMP	46ee42

0x46ef23 VXORPD	%XMM0,%XMM0,%XMM0

0x46ef27 XOR	%R9D,%R9D

0x46ef2a VXORPD	%XMM2,%XMM2,%XMM2

0x46ef2e XOR	%EAX,%EAX

0x46ef30 JMP	46ea98

0x46ef35 VXORPD	%XMM2,%XMM2,%XMM2

0x46ef39 JMP	46ee1e

0x46ef3e XCHG	%AX,%AX

Coverage (%)	Name	Source Location	Module
►96.01+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main._omp_fn.1	refwrap.h:350	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►2.26+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main._omp_fn.1	refwrap.h:350	exec
○	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
►1.60+	main._omp_fn.1	refwrap.h:350	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0

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 0.01% of application time for run gcc_3

Source file and lines	OneBodyJastrowRef.h:184-264
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_numeric.h:140-141
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1262-1263
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:184-194,255-264
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_iterator.h:1068,1102,1139

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 41.67 to 17.83 cycles (2.34x 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 24% of vector register length is used (average across all SSE/AVX instructions).

Details

48% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

68% of SSE/AVX loads are used in vector version.
11% of SSE/AVX stores are used in vector version.
73% of SSE/AVX addition or subtraction instructions are used in vector version.
88% of SSE/AVX fused multiply-add instructions are used in vector version.
23% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

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

512-bits vectorization

On some x86 processors supporting 512-bits vectorization, compilers are often too conservative and limit vectorization to 256 bits. Performance can then be improved by enforcing 512-bits vectorization, especially with many vectorized and high trip count loops. 512-bits vectorization performance overhead (compared to 256-bits) is generally lower on newer processors.

Workaround

Recompile with -mprefer-vector-width=512

FMA

Detected 31 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.

miniqmcreference::OneBodyJastrowRef
>::computeU3(qmcplusplus::ParticleSet&, int, double const*) [clone .isra.0]: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
qmcplusplus::ParticleSet::getDistTableAB(int) const: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:260

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

PUSH: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:255
VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:263

Vector unaligned load/store instructions

Detected 8 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 8 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:188
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_numeric.h:141

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.

Conversion instructions

Detected expensive conversion instructions.

Details

CLTQ: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:187

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

7 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time). 19 AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (four at a time).

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

The binary function is composed of 130 FP arithmetical operations:

99: addition or subtraction (31 inside FMA instructions)
31: multiply (all inside FMA instructions)

The binary function is loading 920 bytes (115 double precision FP elements). The binary function is storing 68 bytes (8 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.13 FP operations per loaded or stored byte.

General properties

nb instructions	237
nb uops	242
loop length	1019
used x86 registers	16
used mmx registers	0
used xmm registers	15
used ymm registers	8
used zmm registers	0
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	41.67 cycles
front end	41.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	22.70	22.80	19.00	19.00	10.00	22.90	22.80	10.00	10.00	10.00	22.80	19.00
cycles	22.70	22.80	19.00	19.00	10.00	22.90	22.80	10.00	10.00	10.00	22.80	19.00

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	41.67
Dispatch	22.90
Overall L1	41.67

Vectorization ratios

INT

all	2%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	3%

all	73%
load	70%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	76%
fma	88%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	69%

INT+FP

all	48%
load	68%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	73%
fma	88%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	23%

Vector efficiency ratios

INT

all	10%
load	6%
store	8%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	32%
load	35%
store	15%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	34%
fma	43%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	21%

INT+FP

all	24%
load	34%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
fma	43%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 41.67 cycles. At this rate:

11% of peak load performance is reached (22.08 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.63 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 41.67 to 22.90 cycles (1.82x speedup).

ASM code

In the binary file, the address of the function is: 46e840

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
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
LEA 0x10(%RSP),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x20,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
PUSHQ -0x8(%R13)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
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
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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
MOV %RSI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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
MOV %RCX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0x2,0xc(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0xa8(%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4c58b0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x90(%RAX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 41def0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xa8(%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4c58b0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xa8(%RAX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x90(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x130(%RBX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x118(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xb8(%RAX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %ECX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 46ef0b <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6cb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RCX),%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %R8D,-0x34(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
CMP $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 46ef23 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6e3>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %ECX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x2,%R10D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA -0x20(%R10),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x5,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
INC %R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VBROADCASTSD 0x148aa2(%RIP),%YMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	0.33	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
AND $0x7,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
JE 46e9be <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x17e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e9a0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x160>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e98c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x14c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e978 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x138>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e964 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x124>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e950 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x110>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 46eee8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6a8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%RDX,%R14,1),%YMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM1,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM4	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM4,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM5	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM5,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM6	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM6,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM7	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM7,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM8	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM8,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
CMP %R10,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ea78 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x238>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VEXTRACTF64X2 $0x1,%YMM9,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM9,%XMM3,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %ECX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VUNPCKHPD %XMM0,%XMM0,%XMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM0,%XMM10,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %EAX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %EAX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 46eae2 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %ECX,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %R9D,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x1,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 46eacd <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x28d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDPD (%RSI,%R9,8),%XMM0,%XMM11	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (25.0%)
VMOVUPD (%RDX,%R9,8),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VFMADD231PD 0x1488e8(%RIP){1to2},%XMM12,%XMM11	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
VUNPCKHPD %XMM11,%XMM11,%XMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM11,%XMM13,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 46eae2 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
AND $-0x2,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %EDI,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VADDSD (%RSI,%RAX,8),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD (%RDX,%RAX,8),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFMADD231SD 0x1488be(%RIP),%XMM14,%XMM2	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
LEA 0xc0(%RBX),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0xd8(%RBX),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %ECX,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
SHR $0x2,%R8D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (6.3%)
SAL $0x5,%R8	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
CMPL $0x2,-0x34(%RBP)	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 (6.3%)
MOV %RBX,-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%)
LEA (,%R9,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JBE 46ecde <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x49e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x48(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x100(%RBX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R13,%RCX,1),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM2,0xb8(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %R13,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ef1a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6da>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB $0x8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x10,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JBE 46ef35 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6f5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x2,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RDX,%R13,1),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0x20,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x5,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
AND $0x7,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 46edb7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x577>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46eda9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x569>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46eda0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x560>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ed97 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x557>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ed8e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x54e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ed85 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x545>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 46eefc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6bc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R14,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46edfb <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x5bb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VEXTRACTF64X2 $0x1,%YMM9,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM9,%XMM1,%XMM4	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKHPD %XMM4,%XMM4,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM4,%XMM0,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
TEST $0x3,%SIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
AND $-0x4,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%R13,%RSI,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x8(%R13),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VADDSD (%R13),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
CMP %R9,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA 0x10(%R13),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VADDSD 0x8(%R13),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
CMP %R8,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDSD 0x10(%R13),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM2,0xb0(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVUPD (%R12),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMOVSD 0x10(%R12),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDPD 0xc0(%RBX),%XMM5,%XMM6	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (25.0%)
MOVSXD %R15D,%R15	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVUPD %XMM6,(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
VADDSD 0xd0(%RBX),%XMM7,%XMM8	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM8,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xf0(%RBX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%R12,%R15,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD 0xb0(%RBX),%XMM2,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
ADD $0x28,%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 %RAX	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
LEA -0x10(%RAX),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
JMP 4040b0 <exp@plt>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 46ecf4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x4b4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVUPD (%RDX),%YMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
MOV $0x20,%R14D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VFMADD213PD (%RSI),%YMM3,%YMM9	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
JMP 46e93c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xfc>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVUPD (%R13),%YMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
LEA 0x20(%R13),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 46ed7c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x53c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
LEA -0x1(%RCX),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %EAX,-0x34(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 46eae2 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a2>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 46ea98 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x258>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 46ee1e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x5de>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_3

Source file and lines	OneBodyJastrowRef.h:184-264
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_numeric.h:140-141
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_vector.h:1262-1263
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:184-194,255-264
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_iterator.h:1068,1102,1139

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

Your function is poorly vectorized. Only 24% of vector register length is used (average across all SSE/AVX instructions).

Details

48% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

68% of SSE/AVX loads are used in vector version.
11% of SSE/AVX stores are used in vector version.
73% of SSE/AVX addition or subtraction instructions are used in vector version.
88% of SSE/AVX fused multiply-add instructions are used in vector version.
23% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

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

512-bits vectorization

Workaround

Recompile with -mprefer-vector-width=512

FMA

Detected 31 FMA (fused multiply-add) operations.

CALL instructions

Detected function call instructions.

Details

miniqmcreference::OneBodyJastrowRef
>::computeU3(qmcplusplus::ParticleSet&, int, double const*) [clone .isra.0]: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
qmcplusplus::ParticleSet::getDistTableAB(int) const: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:260

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

PUSH: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:255
VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:263

Vector unaligned load/store instructions

Detected 8 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 8 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:188
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_numeric.h:141

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.

Conversion instructions

Detected expensive conversion instructions.

Details

CLTQ: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:187

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

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

The binary function is composed of 130 FP arithmetical operations:

99: addition or subtraction (31 inside FMA instructions)
31: multiply (all inside FMA instructions)

The binary function is loading 920 bytes (115 double precision FP elements). The binary function is storing 68 bytes (8 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.13 FP operations per loaded or stored byte.

General properties

nb instructions	237
nb uops	242
loop length	1019
used x86 registers	16
used mmx registers	0
used xmm registers	15
used ymm registers	8
used zmm registers	0
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	41.67 cycles
front end	41.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	22.70	22.80	19.00	19.00	10.00	22.90	22.80	10.00	10.00	10.00	22.80	19.00
cycles	22.70	22.80	19.00	19.00	10.00	22.90	22.80	10.00	10.00	10.00	22.80	19.00

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	41.67
Dispatch	22.90
Overall L1	41.67

Vectorization ratios

INT

all	2%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	3%

all	73%
load	70%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	76%
fma	88%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	69%

INT+FP

all	48%
load	68%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	73%
fma	88%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	23%

Vector efficiency ratios

INT

all	10%
load	6%
store	8%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	32%
load	35%
store	15%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	34%
fma	43%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	21%

INT+FP

all	24%
load	34%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
fma	43%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 41.67 cycles. At this rate:

11% of peak load performance is reached (22.08 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.63 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: 46e840

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
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
LEA 0x10(%RSP),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x20,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
PUSHQ -0x8(%R13)	2	0	0	0.33	0.33	0.50	0	0	0.50	0.50	0.50	0	0.33	5-12	0.62	N/A
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
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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
MOV %RSI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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
MOV %RCX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0x2,0xc(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0xa8(%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4c58b0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x90(%RAX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 41def0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd.isra.0>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xa8(%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4c58b0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xa8(%RAX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x90(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x130(%RBX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x118(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xb8(%RAX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %ECX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 46ef0b <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6cb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RCX),%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %R8D,-0x34(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
CMP $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 46ef23 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6e3>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %ECX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x2,%R10D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA -0x20(%R10),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x5,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
INC %R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
VBROADCASTSD 0x148aa2(%RIP),%YMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	0.33	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
AND $0x7,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
JE 46e9be <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x17e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e9a0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x160>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e98c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x14c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e978 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x138>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e964 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x124>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46e950 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x110>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 46eee8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6a8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%RDX,%R14,1),%YMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM1,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM4	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM4,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM5	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM5,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM6	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM6,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM7	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM7,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVUPD (%RDX,%R14,1),%YMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VFMADD213PD (%RSI,%R14,1),%YMM3,%YMM8	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD %YMM8,%YMM9,%YMM9	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
CMP %R10,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ea78 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x238>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VEXTRACTF64X2 $0x1,%YMM9,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM9,%XMM3,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %ECX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VUNPCKHPD %XMM0,%XMM0,%XMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM0,%XMM10,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %EAX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %EAX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 46eae2 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %ECX,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %R9D,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x1,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 46eacd <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x28d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDPD (%RSI,%R9,8),%XMM0,%XMM11	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (25.0%)
VMOVUPD (%RDX,%R9,8),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VFMADD231PD 0x1488e8(%RIP){1to2},%XMM12,%XMM11	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
VUNPCKHPD %XMM11,%XMM11,%XMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM11,%XMM13,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 46eae2 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
AND $-0x2,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %EDI,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VADDSD (%RSI,%RAX,8),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD (%RDX,%RAX,8),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFMADD231SD 0x1488be(%RIP),%XMM14,%XMM2	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
LEA 0xc0(%RBX),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0xd8(%RBX),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %ECX,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
SHR $0x2,%R8D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (6.3%)
SAL $0x5,%R8	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
CMPL $0x2,-0x34(%RBP)	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 (6.3%)
MOV %RBX,-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%)
LEA (,%R9,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JBE 46ecde <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x49e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x48(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x100(%RBX),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R13,%RCX,1),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM2,0xb8(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %R13,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ef1a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6da>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB $0x8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x10,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JBE 46ef35 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6f5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x2,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%RDX,%R13,1),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0x20,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x5,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VXORPD %XMM9,%XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
AND $0x7,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 46edb7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x577>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46eda9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x569>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46eda0 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x560>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ed97 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x557>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ed8e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x54e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ed85 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x545>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 46eefc <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x6bc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VADDPD (%R14),%YMM9,%YMM9	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (50.0%)
ADD $0x20,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R14,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46edfb <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x5bb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VEXTRACTF64X2 $0x1,%YMM9,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM9,%XMM1,%XMM4	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKHPD %XMM4,%XMM4,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM4,%XMM0,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
TEST $0x3,%SIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
AND $-0x4,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%R13,%RSI,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x8(%R13),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VADDSD (%R13),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
CMP %R9,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA 0x10(%R13),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VADDSD 0x8(%R13),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
CMP %R8,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VADDSD 0x10(%R13),%XMM2,%XMM2	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM2,0xb0(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVUPD (%R12),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
VMOVSD 0x10(%R12),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDPD 0xc0(%RBX),%XMM5,%XMM6	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	vect (25.0%)
MOVSXD %R15D,%R15	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVUPD %XMM6,(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
VADDSD 0xd0(%RBX),%XMM7,%XMM8	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM8,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xf0(%RBX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%R12,%R15,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD 0xb0(%RBX),%XMM2,%XMM0	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
ADD $0x28,%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 %RAX	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
LEA -0x10(%RAX),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
JMP 4040b0 <exp@plt>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 46ecf4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x4b4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVUPD (%RDX),%YMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
MOV $0x20,%R14D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VFMADD213PD (%RSI),%YMM3,%YMM9	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (50.0%)
JMP 46e93c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xfc>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVUPD (%R13),%YMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
LEA 0x20(%R13),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 46ed7c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x53c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
LEA -0x1(%RCX),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %EAX,-0x34(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 46eae2 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a2>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 46ee42 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x602>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 46ea98 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x258>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 46ee1e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x5de>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)–	0.04	0.03
○Loop 834 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.01
○Loop 829 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 828 - OneBodyJastrowRef.h:188-194 - exec	0.00	0.00
▼Loop 833 - OneBodyJastrowRef.h:184-194 - exec–	0.00	0.00
▼Loop 832 - OneBodyJastrowRef.h:184-194 - exec–	0.00	0.00
▼Loop 831 - OneBodyJastrowRef.h:184-194 - exec–	0.00	0.01
○Loop 830 - OneBodyJastrowRef.h:192-193 - exec	0.02	0.02

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

FMA

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

FMA

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion 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