OV - exec - Function miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalGrad(qmcplusplus::ParticleSet&, int)

	Function: miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalGr ...	Module: exec	Source: DiracDeterminantRef.cpp:82-91 [...]	Coverage (incl. loops): 0.49% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 155 - 156

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

155:   for (int i = 0; i < n; i++)

156:     res += a[i] * b[i];

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 63 - 94

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

63:     return (a * b);

[...]

92:   inline typename BinaryReturn<T1, T2, OpAddAssign>::Type_t operator()(const T1& a, const T2& b) const

93:   {

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

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DelayedUpdate.h: 98 - 113

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

98:     if (delay_count == 0)

99:     {

100:       // Ainv is fresh, directly access Ainv

101:       std::copy_n(Ainv[rowchanged], invRow.size(), invRow.data());

102:       return;

103:     }

104:     const T cone(1);

105:     const T czero(0);

106:     const int norb     = Ainv.rows();

107:     const int lda_Binv = Binv.cols();

108:     // save Ainv[rowchanged] to invRow

109:     std::copy_n(Ainv[rowchanged], norb, invRow.data());

110:     // multiply V (NxK) Binv(KxK) U(KxN) invRow right to the left

111:     BLAS::gemv('T', norb, delay_count, cone, U.data(), norb, invRow.data(), 1, czero, p.data(), 1);

112:     BLAS::gemv('N', delay_count, delay_count, cone, Binv.data(), lda_Binv, p.data(), 1, czero, Binv[delay_count], 1);

113:     BLAS::gemv('N', norb, delay_count, -cone, V.data(), norb, Binv[delay_count], 1, cone, invRow.data(), 1);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp: 82 - 91

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

82: typename DiracDeterminantRef<DU_TYPE>::GradType DiracDeterminantRef<DU_TYPE>::evalGrad(ParticleSet& P, int iat)

83: {

84:   const int WorkingIndex = iat - FirstIndex;

85:   RatioTimer->start();

86:   invRow_id = WorkingIndex;

87:   updateEng.getInvRow(psiM, WorkingIndex, invRow);

88:   GradType g = simd::dot(invRow.data(), dpsiM[WorkingIndex], invRow.size());

89:   RatioTimer->stop();

90:   return g;

91: }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp: 187 - 187

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

187:     dgemv(trans_in, n, m, alpha, amat, lda, x, incx, beta, y, incy);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h: 214 - 217

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

214:   inline const Type_t* operator[](size_type i) const { return X.data() + i * D2; }

215:

216:   /// returns a pointer of i-th row, g++ iterator problem

217:   inline Type_t* operator[](size_type i) { return X.data() + i * D2; }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 62 - 62

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

62:       X[d] = T(0);

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h: 413 - 453

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

413: 	{ *__to = *__from; }

[...]

451: 	  if (__builtin_expect(_Num > 1, true))

452: 	    __builtin_memmove(__result, __first, sizeof(_Tp) * _Num);

453: 	  else if (_Num == 1)

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algo.h: 683 - 709

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

683:     { return std::copy(__first, __first + __n, __result); }

[...]

709:       if (__n2 <= 0)

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 178 - 248

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

178:   inline size_t size() const { return nLocal; }

[...]

248:   inline pointer data() { return X; }

0x49b450 LEA	0x8(%RSP),%R10

0x49b455 AND	$-0x20,%RSP

0x49b459 PUSHQ	-0x8(%R10)

0x49b45d PUSH	%RBP

0x49b45e MOV	%RSP,%RBP

0x49b461 PUSH	%R15

0x49b463 PUSH	%R14

0x49b465 PUSH	%R13

0x49b467 PUSH	%R12

0x49b469 MOV	%RDI,%R12

0x49b46c PUSH	%R10

0x49b46e PUSH	%RBX

0x49b46f MOV	%RSI,%RBX

0x49b472 SUB	$0x60,%RSP

0x49b476 MOV	0x448(%RSI),%RDI

0x49b47d SUB	0x478(%RSI),%ECX

0x49b483 MOV	%ECX,%R13D

0x49b486 CALL	52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x49b48b MOV	0xd8(%RBX),%RCX

0x49b492 MOVSXD	%R13D,%R14

0x49b495 IMUL	%R14,%RCX

0x49b499 MOV	0x100(%RBX),%RDX

0x49b4a0 MOV	0x370(%RBX),%EAX

0x49b4a6 MOV	%R13D,0x430(%RBX)

0x49b4ad LEA	(%RDX,%RCX,8),%RSI

0x49b4b1 TEST	%EAX,%EAX

0x49b4b3 JE	49bae0

0x49b4b9 MOV	0x290(%RBX),%RDI

0x49b4c0 MOV	0xd0(%RBX),%R11

0x49b4c7 MOV	%RDI,-0x68(%RBP)

0x49b4cb MOV	0x420(%RBX),%RDI

0x49b4d2 TEST	%R11D,%R11D

0x49b4d5 JLE	49b50a

0x49b4d7 MOVSXD	%R11D,%RDX

0x49b4da SAL	$0x3,%RDX

0x49b4de CMP	$0x8,%RDX

0x49b4e2 JE	49bb55

0x49b4e8 MOV	%R11,-0x78(%RBP)

0x49b4ec MOV	%R14,-0x70(%RBP)

0x49b4f0 CALL	4040d0 <memmove@plt>

0x49b4f5 MOV	0x420(%RBX),%RDI

0x49b4fc MOV	0x370(%RBX),%EAX

0x49b502 MOV	-0x70(%RBP),%R14

0x49b506 MOV	-0x78(%RBP),%R11

0x49b50a MOV	0x11c39f(%RIP),%RSI

0x49b511 SUB	$0x8,%RSP

0x49b515 LEA	-0x44(%RBP),%R15

0x49b519 MOV	%R11D,-0x54(%RBP)

0x49b51d MOV	%EAX,-0x50(%RBP)

0x49b520 MOV	%R11D,-0x4c(%RBP)

0x49b524 MOV	%R11,-0x70(%RBP)

0x49b528 MOV	%R14,-0x78(%RBP)

0x49b52c MOV	%RSI,-0x40(%RBP)

0x49b530 MOVB	$0x54,-0x55(%RBP)

0x49b534 MOVL	$0x1,-0x48(%RBP)

0x49b53b MOVQ	$0,-0x38(%RBP)

0x49b543 MOVL	$0x1,-0x44(%RBP)

0x49b54a PUSH	%R15

0x49b54c LEA	-0x38(%RBP),%R14

0x49b550 LEA	-0x48(%RBP),%R13

0x49b554 PUSHQ	0x348(%RBX)

0x49b55a LEA	-0x4c(%RBP),%R9

0x49b55e LEA	-0x40(%RBP),%RCX

0x49b562 PUSH	%R14

0x49b564 LEA	-0x50(%RBP),%RDX

0x49b568 LEA	-0x54(%RBP),%RSI

0x49b56c PUSH	%R13

0x49b56e PUSH	%RDI

0x49b56f LEA	-0x55(%RBP),%RDI

0x49b573 MOV	0x238(%RBX),%R8

0x49b57a CALL	404520 <dgemv_@plt>

0x49b57f MOVSXD	0x370(%RBX),%R9

0x49b586 MOV	-0x68(%RBP),%EDI

0x49b589 MOV	0x11c320(%RIP),%RDX

0x49b590 ADD	$0x28,%RSP

0x49b594 MOV	%R9,%R10

0x49b597 IMUL	0x290(%RBX),%R9

0x49b59f MOV	0x2b8(%RBX),%R8

0x49b5a6 MOV	%R10D,-0x54(%RBP)

0x49b5aa MOV	%R10D,-0x50(%RBP)

0x49b5ae MOV	%RDX,-0x40(%RBP)

0x49b5b2 MOV	%EDI,-0x4c(%RBP)

0x49b5b5 MOVB	$0x4e,-0x55(%RBP)

0x49b5b9 MOVL	$0x1,-0x48(%RBP)

0x49b5c0 MOVQ	$0,-0x38(%RBP)

0x49b5c8 MOVL	$0x1,-0x44(%RBP)

0x49b5cf PUSH	%R15

0x49b5d1 LEA	(%R8,%R9,8),%RCX

0x49b5d5 LEA	-0x50(%RBP),%RDX

0x49b5d9 PUSH	%RCX

0x49b5da LEA	-0x4c(%RBP),%R9

0x49b5de LEA	-0x40(%RBP),%RCX

0x49b5e2 PUSH	%R14

0x49b5e4 LEA	-0x54(%RBP),%RSI

0x49b5e8 LEA	-0x55(%RBP),%RDI

0x49b5ec PUSH	%R13

0x49b5ee PUSHQ	0x348(%RBX)

0x49b5f4 CALL	404520 <dgemv_@plt>

0x49b5f9 MOVSXD	0x370(%RBX),%R8

0x49b600 MOV	-0x70(%RBP),%R11

0x49b604 MOV	0x11c2a5(%RIP),%RCX

0x49b60b MOV	0x11c11e(%RIP),%R10

0x49b612 ADD	$0x28,%RSP

0x49b616 MOV	%R8,%RSI

0x49b619 MOV	%ESI,-0x50(%RBP)

0x49b61c IMUL	0x290(%RBX),%R8

0x49b624 MOV	%RCX,-0x38(%RBP)

0x49b628 MOV	0x2b8(%RBX),%RAX

0x49b62f MOVB	$0x4e,-0x55(%RBP)

0x49b633 MOV	%R11D,-0x54(%RBP)

0x49b637 MOV	%R10,-0x40(%RBP)

0x49b63b MOV	%R11D,-0x4c(%RBP)

0x49b63f MOVL	$0x1,-0x48(%RBP)

0x49b646 MOVL	$0x1,-0x44(%RBP)

0x49b64d PUSH	%R15

0x49b64f LEA	(%RAX,%R8,8),%R9

0x49b653 LEA	-0x55(%RBP),%RDI

0x49b657 PUSHQ	0x420(%RBX)

0x49b65d LEA	-0x40(%RBP),%RCX

0x49b661 LEA	-0x50(%RBP),%RDX

0x49b665 PUSH	%R14

0x49b667 LEA	-0x54(%RBP),%RSI

0x49b66b PUSH	%R13

0x49b66d PUSH	%R9

0x49b66f LEA	-0x4c(%RBP),%R9

0x49b673 MOV	0x278(%RBX),%R8

0x49b67a CALL	404520 <dgemv_@plt>

0x49b67f MOV	0x410(%RBX),%R15

0x49b686 MOV	0x420(%RBX),%RDI

0x49b68d MOV	-0x78(%RBP),%R14

0x49b691 ADD	$0x30,%RSP

0x49b695 VXORPD	%XMM2,%XMM2,%XMM2

0x49b699 IMUL	0x118(%RBX),%R14

0x49b6a1 MOVQ	$0,0x10(%R12)

0x49b6aa MOV	0x140(%RBX),%R8

0x49b6b1 VMOVUPD	%XMM2,(%R12)

0x49b6b7 TEST	%R15D,%R15D

0x49b6ba JLE	49babb

0x49b6c0 LEA	-0x1(%R15),%EDX

0x49b6c4 MOV	%R15D,%ESI

0x49b6c7 CMP	$0x2,%EDX

0x49b6ca JBE	49bb41

0x49b6d0 SHR	$0x2,%R15D

0x49b6d4 SAL	$0x5,%R15

0x49b6d8 LEA	(%R15,%RDI,1),%R9

0x49b6dc SUB	$0x20,%R15

0x49b6e0 SHR	$0x5,%R15

0x49b6e4 VXORPD	%XMM2,%XMM2,%XMM2

0x49b6e8 LEA	(%R14,%R14,2),%RAX

0x49b6ec INC	%R15

0x49b6ef VMOVDQA	0x11c229(%RIP),%YMM12

0x49b6f7 VMOVDQA	0x11c241(%RIP),%YMM11

0x49b6ff VMOVDQA	0x11c259(%RIP),%YMM10

0x49b707 VMOVDQA	0x11c271(%RIP),%YMM9

0x49b70f VMOVDQA	0x11bc49(%RIP),%YMM8

0x49b717 VMOVDQA	0x11bc61(%RIP),%YMM7

0x49b71f MOV	%RDI,%R10

0x49b722 LEA	(%R8,%RAX,8),%R11

0x49b726 VMOVAPD	%YMM2,%YMM1

0x49b72a VMOVAPD	%YMM2,%YMM0

0x49b72e AND	$0x3,%R15D

0x49b732 JE	49b85b

0x49b738 CMP	$0x1,%R15

0x49b73c JE	49b7f9

0x49b742 CMP	$0x2,%R15

0x49b746 JE	49b7a0

0x49b748 VMOVUPD	(%R11),%YMM0

0x49b74d VMOVUPD	0x20(%R11),%YMM6

0x49b753 VMOVUPD	0x40(%R11),%YMM5

0x49b759 VMOVAPD	%YMM0,%YMM1

0x49b75d VMOVAPD	%YMM0,%YMM3

0x49b761 VMOVUPD	(%RDI),%YMM4

0x49b765 VPERMT2PD	%YMM6,%YMM12,%YMM1

0x49b76b VPERMT2PD	%YMM6,%YMM10,%YMM3

0x49b771 VPERMT2PD	%YMM6,%YMM8,%YMM0

0x49b777 VPERMT2PD	%YMM5,%YMM11,%YMM1

0x49b77d VPERMT2PD	%YMM5,%YMM9,%YMM3

0x49b783 VPERMT2PD	%YMM5,%YMM7,%YMM0

0x49b789 VFMADD132PD	%YMM4,%YMM2,%YMM0

0x49b78e VFMADD132PD	%YMM4,%YMM2,%YMM1

0x49b793 VFMADD231PD	%YMM3,%YMM4,%YMM2

0x49b798 LEA	0x20(%RDI),%R10

0x49b79c ADD	$0x60,%R11

0x49b7a0 VMOVUPD	(%R11),%YMM5

0x49b7a5 VMOVUPD	0x20(%R11),%YMM14

0x49b7ab VMOVUPD	0x40(%R11),%YMM13

0x49b7b1 VMOVAPD	%YMM5,%YMM6

0x49b7b5 VMOVAPD	%YMM5,%YMM4

0x49b7b9 VMOVUPD	(%R10),%YMM15

0x49b7be VPERMT2PD	%YMM14,%YMM12,%YMM6

0x49b7c4 VPERMT2PD	%YMM14,%YMM10,%YMM4

0x49b7ca VPERMT2PD	%YMM14,%YMM8,%YMM5

0x49b7d0 VPERMT2PD	%YMM13,%YMM11,%YMM6

0x49b7d6 VPERMT2PD	%YMM13,%YMM9,%YMM4

0x49b7dc VPERMT2PD	%YMM13,%YMM7,%YMM5

0x49b7e2 VFMADD231PD	%YMM5,%YMM15,%YMM0

0x49b7e7 VFMADD231PD	%YMM6,%YMM15,%YMM1

0x49b7ec VFMADD231PD	%YMM4,%YMM15,%YMM2

0x49b7f1 ADD	$0x20,%R10

0x49b7f5 ADD	$0x60,%R11

0x49b7f9 VMOVUPD	(%R11),%YMM3

0x49b7fe VMOVUPD	0x20(%R11),%YMM5

0x49b804 VMOVUPD	0x40(%R11),%YMM14

0x49b80a VMOVAPD	%YMM3,%YMM13

0x49b80e VMOVAPD	%YMM3,%YMM6

0x49b812 VMOVUPD	(%R10),%YMM15

0x49b817 VPERMT2PD	%YMM5,%YMM12,%YMM13

0x49b81d VPERMT2PD	%YMM5,%YMM10,%YMM6

0x49b823 VPERMT2PD	%YMM5,%YMM8,%YMM3

0x49b829 VPERMT2PD	%YMM14,%YMM11,%YMM13

0x49b82f VPERMT2PD	%YMM14,%YMM9,%YMM6

0x49b835 VPERMT2PD	%YMM14,%YMM7,%YMM3

0x49b83b ADD	$0x20,%R10

0x49b83f VFMADD231PD	%YMM3,%YMM15,%YMM0

0x49b844 VFMADD231PD	%YMM13,%YMM15,%YMM1

0x49b849 VFMADD231PD	%YMM6,%YMM15,%YMM2

0x49b84e ADD	$0x60,%R11

0x49b852 CMP	%R10,%R9

0x49b855 JE	49b9d6

(1127) 0x49b85b VMOVUPD	0x20(%R11),%YMM3

(1127) 0x49b861 VMOVUPD	(%R11),%YMM15

(1127) 0x49b866 VMOVUPD	0x40(%R11),%YMM14

(1127) 0x49b86c VMOVUPD	(%R10),%YMM4

(1127) 0x49b871 VMOVAPD	%YMM15,%YMM5

(1127) 0x49b875 VMOVAPD	%YMM15,%YMM13

(1127) 0x49b87a VPERMT2PD	%YMM3,%YMM8,%YMM15

(1127) 0x49b880 VPERMT2PD	%YMM14,%YMM7,%YMM15

(1127) 0x49b886 VPERMT2PD	%YMM3,%YMM12,%YMM5

(1127) 0x49b88c VPERMT2PD	%YMM3,%YMM10,%YMM13

(1127) 0x49b892 VFMADD231PD	%YMM15,%YMM4,%YMM0

(1127) 0x49b897 VPERMT2PD	%YMM14,%YMM11,%YMM5

(1127) 0x49b89d VPERMT2PD	%YMM14,%YMM9,%YMM13

(1127) 0x49b8a3 VMOVUPD	0x80(%R11),%YMM15

(1127) 0x49b8ac VFMADD231PD	%YMM5,%YMM4,%YMM1

(1127) 0x49b8b1 VFMADD231PD	%YMM13,%YMM4,%YMM2

(1127) 0x49b8b6 VMOVUPD	0x60(%R11),%YMM4

(1127) 0x49b8bc VMOVUPD	0xa0(%R11),%YMM3

(1127) 0x49b8c5 VMOVUPD	0x20(%R10),%YMM5

(1127) 0x49b8cb VMOVAPD	%YMM4,%YMM6

(1127) 0x49b8cf VMOVAPD	%YMM4,%YMM14

(1127) 0x49b8d3 VPERMT2PD	%YMM15,%YMM8,%YMM4

(1127) 0x49b8d9 VPERMT2PD	%YMM15,%YMM12,%YMM6

(1127) 0x49b8df VPERMT2PD	%YMM15,%YMM10,%YMM14

(1127) 0x49b8e5 VPERMT2PD	%YMM3,%YMM7,%YMM4

(1127) 0x49b8eb VFMADD132PD	%YMM5,%YMM0,%YMM4

(1127) 0x49b8f0 VPERMT2PD	%YMM3,%YMM9,%YMM14

(1127) 0x49b8f6 VPERMT2PD	%YMM3,%YMM11,%YMM6

(1127) 0x49b8fc VMOVUPD	0xe0(%R11),%YMM0

(1127) 0x49b905 VFMADD132PD	%YMM5,%YMM1,%YMM6

(1127) 0x49b90a VFMADD231PD	%YMM14,%YMM5,%YMM2

(1127) 0x49b90f VMOVUPD	0xc0(%R11),%YMM3

(1127) 0x49b918 VMOVUPD	0x100(%R11),%YMM15

(1127) 0x49b921 VMOVUPD	0x40(%R10),%YMM1

(1127) 0x49b927 VMOVAPD	%YMM3,%YMM5

(1127) 0x49b92b VMOVAPD	%YMM3,%YMM13

(1127) 0x49b92f VPERMT2PD	%YMM0,%YMM8,%YMM3

(1127) 0x49b935 VPERMT2PD	%YMM0,%YMM12,%YMM5

(1127) 0x49b93b VPERMT2PD	%YMM0,%YMM10,%YMM13

(1127) 0x49b941 VPERMT2PD	%YMM15,%YMM7,%YMM3

(1127) 0x49b947 VFMADD132PD	%YMM1,%YMM4,%YMM3

(1127) 0x49b94c VPERMT2PD	%YMM15,%YMM11,%YMM5

(1127) 0x49b952 VPERMT2PD	%YMM15,%YMM9,%YMM13

(1127) 0x49b958 VMOVAPD	%YMM1,%YMM4

(1127) 0x49b95c VMOVUPD	0x120(%R11),%YMM0

(1127) 0x49b965 VFMADD132PD	%YMM1,%YMM6,%YMM5

(1127) 0x49b96a VFMADD132PD	%YMM13,%YMM2,%YMM4

(1127) 0x49b96f VMOVUPD	0x140(%R11),%YMM14

(1127) 0x49b978 VMOVUPD	0x160(%R11),%YMM15

(1127) 0x49b981 VMOVAPD	%YMM0,%YMM1

(1127) 0x49b985 VMOVAPD	%YMM0,%YMM6

(1127) 0x49b989 VMOVUPD	0x60(%R10),%YMM2

(1127) 0x49b98f VPERMT2PD	%YMM14,%YMM12,%YMM1

(1127) 0x49b995 VPERMT2PD	%YMM14,%YMM10,%YMM6

(1127) 0x49b99b VPERMT2PD	%YMM14,%YMM8,%YMM0

(1127) 0x49b9a1 VPERMT2PD	%YMM15,%YMM11,%YMM1

(1127) 0x49b9a7 VPERMT2PD	%YMM15,%YMM9,%YMM6

(1127) 0x49b9ad VPERMT2PD	%YMM15,%YMM7,%YMM0

(1127) 0x49b9b3 SUB	$-0x80,%R10

(1127) 0x49b9b7 VFMADD132PD	%YMM2,%YMM3,%YMM0

(1127) 0x49b9bc VFMADD132PD	%YMM2,%YMM5,%YMM1

(1127) 0x49b9c1 ADD	$0x180,%R11

(1127) 0x49b9c8 VFMADD132PD	%YMM6,%YMM4,%YMM2

(1127) 0x49b9cd CMP	%R10,%R9

(1127) 0x49b9d0 JNE	49b85b

0x49b9d6 VEXTRACTF64X2	$0x1,%YMM1,%XMM9

0x49b9dd VEXTRACTF64X2	$0x1,%YMM0,%XMM5

0x49b9e4 VADDPD	%XMM1,%XMM9,%XMM8

0x49b9e8 VADDPD	%XMM0,%XMM5,%XMM13

0x49b9ec VEXTRACTF64X2	$0x1,%YMM2,%XMM12

0x49b9f3 VADDPD	%XMM2,%XMM12,%XMM11

0x49b9f7 VUNPCKHPD	%XMM8,%XMM8,%XMM7

0x49b9fc VUNPCKHPD	%XMM13,%XMM13,%XMM0

0x49ba01 VADDPD	%XMM8,%XMM7,%XMM1

0x49ba06 VADDPD	%XMM13,%XMM0,%XMM3

0x49ba0b MOV	%ESI,%R15D

0x49ba0e VUNPCKHPD	%XMM11,%XMM11,%XMM10

0x49ba13 AND	$-0x4,%R15D

0x49ba17 VADDPD	%XMM11,%XMM10,%XMM2

0x49ba1c MOV	%R15D,%R13D

0x49ba1f VUNPCKLPD	%XMM1,%XMM3,%XMM11

0x49ba23 TEST	$0x3,%SIL

0x49ba27 JE	49bb24

0x49ba2d VZEROUPPER

0x49ba30 SUB	%R15D,%ESI

0x49ba33 CMP	$0x1,%ESI

0x49ba36 JE	49ba8b

0x49ba38 VMOVUPD	(%RDI,%R15,8),%XMM14

0x49ba3e LEA	(%R14,%R15,1),%RCX

0x49ba42 LEA	(%RCX,%RCX,2),%RDX

0x49ba46 LEA	(%R8,%RDX,8),%RAX

0x49ba4a VPERMILPD	$0x3,%XMM14,%XMM4

0x49ba50 VMULPD	0x20(%RAX),%XMM4,%XMM15

0x49ba55 VPERMILPD	$0,%XMM14,%XMM6

0x49ba5b VMOVQ	%XMM2,%XMM2

0x49ba5f VFMADD132PD	0x10(%RAX),%XMM2,%XMM14

0x49ba65 VFMADD231PD	(%RAX),%XMM6,%XMM11

0x49ba6a VUNPCKHPD	%XMM15,%XMM15,%XMM10

0x49ba6f VSHUFPD	$0x1,%XMM15,%XMM14,%XMM12

0x49ba75 VADDSD	%XMM10,%XMM14,%XMM2

0x49ba7a VADDPD	%XMM11,%XMM12,%XMM11

0x49ba7f TEST	$0x1,%SIL

0x49ba83 JE	49baae

0x49ba85 AND	$-0x2,%ESI

0x49ba88 ADD	%ESI,%R13D

0x49ba8b MOVSXD	%R13D,%RSI

0x49ba8e ADD	%RSI,%R14

0x49ba91 VMOVDDUP	(%RDI,%RSI,8),%XMM9

0x49ba96 VMOVSD	(%RDI,%RSI,8),%XMM8

0x49ba9b LEA	(%R14,%R14,2),%R14

0x49ba9f LEA	(%R8,%R14,8),%R8

0x49baa3 VFMADD231PD	(%R8),%XMM9,%XMM11

0x49baa8 VFMADD231SD	0x10(%R8),%XMM8,%XMM2

0x49baae VMOVUPD	%XMM11,(%R12)

0x49bab4 VMOVSD	%XMM2,0x10(%R12)

0x49babb MOV	0x448(%RBX),%RDI

0x49bac2 CALL	52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x49bac7 LEA	-0x30(%RBP),%RSP

0x49bacb POP	%RBX

0x49bacc POP	%RDI

0x49bacd MOV	%R12,%RAX

0x49bad0 POP	%R12

0x49bad2 POP	%R13

0x49bad4 POP	%R14

0x49bad6 POP	%R15

0x49bad8 POP	%RBP

0x49bad9 LEA	-0x8(%RDI),%RSP

0x49badd RET

0x49bade XCHG	%AX,%AX

0x49bae0 MOV	0x410(%RBX),%R15

0x49bae7 TEST	%R15,%R15

0x49baea JE	49bb29

0x49baec LEA	(,%R15,8),%R13

0x49baf4 MOV	0x420(%RBX),%RDI

0x49bafb CMP	$0x8,%R13

0x49baff JLE	49bb62

0x49bb01 MOV	%R13,%RDX

0x49bb04 MOV	%R14,-0x68(%RBP)

0x49bb08 CALL	4040d0 <memmove@plt>

0x49bb0d MOV	0x410(%RBX),%R15

0x49bb14 MOV	0x420(%RBX),%RDI

0x49bb1b MOV	-0x68(%RBP),%R14

0x49bb1f JMP	49b695

0x49bb24 VZEROUPPER

0x49bb27 JMP	49baae

0x49bb29 VXORPD	%XMM7,%XMM7,%XMM7

0x49bb2d MOVQ	$0,0x10(%R12)

0x49bb36 VMOVUPD	%XMM7,(%R12)

0x49bb3c JMP	49babb

0x49bb41 VXORPD	%XMM11,%XMM11,%XMM11

0x49bb46 XOR	%R15D,%R15D

0x49bb49 VXORPD	%XMM2,%XMM2,%XMM2

0x49bb4d XOR	%R13D,%R13D

0x49bb50 JMP	49ba30

0x49bb55 VMOVSD	(%RSI),%XMM0

0x49bb59 VMOVSD	%XMM0,(%RDI)

0x49bb5d JMP	49b50a

0x49bb62 JNE	49b695

0x49bb68 VMOVSD	(%RSI),%XMM1

0x49bb6c VMOVSD	%XMM1,(%RDI)

0x49bb70 JMP	49b695

0x49bb75 NOPW	%CS:(%RAX,%RAX,1)

0x49bb7f NOP

Coverage (%)	Name	Source Location	Module
►51.59+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:183	exec
○	main._omp_fn.1	stl_vector.h:1128	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►45.73+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:992	exec
○	main._omp_fn.1	stl_vector.h:1128	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►1.41+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:183	exec
○	main._omp_fn.1	stl_vector.h:1128	exec
○	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
►1.11+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:992	exec
○	main._omp_fn.1	stl_vector.h:1128	exec
○	GOMP_parallel	libgomp.h:982	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 0.00% of application time for run gcc_3

Source file and lines	DiracDeterminantRef.cpp:82-91
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:155-156
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,92-94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DelayedUpdate.h:98-113
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:82-91
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h:214-217
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:413,451-453
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algo.h:683,709
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:178,248

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 55.00 to 28.00 cycles (1.96x speedup).

Workaround

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

Vectorization

Your function is partially vectorized. Only 27% of vector register length is used (average across all SSE/AVX instructions).

Details

58% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

82% of SSE/AVX loads are used in vector version.
7% of SSE/AVX stores are used in vector version.
87% of SSE/AVX addition or subtraction instructions are used in vector version.
92% of SSE/AVX fused multiply-add instructions are used in vector version.
70% 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 43 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

dgemv_@plt: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
memmove@plt: 2 occurrences►
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:452
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:452
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:85
qmcplusplus::TimerType
::stop(): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:89

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: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:82
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
VZEROUPPER: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:155
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:248

Vector unaligned load/store instructions

Detected 12 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 12 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63

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

2 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 11 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time). 9 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 103 FP arithmetical operations:

58: addition or subtraction (43 inside FMA instructions)
45: multiply (43 inside FMA instructions)

The binary function is loading 1000 bytes (125 double precision FP elements). The binary function is storing 251 bytes (31 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.08 FP operations per loaded or stored byte.

General properties

nb instructions	317
nb uops	330
loop length	1461
used x86 registers	16
used mmx registers	0
used xmm registers	16
used ymm registers	16
used zmm registers	0
nb stack references	13
ADD-SUB / MUL ratio	8.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	55.00 cycles
front end	55.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	18.10	18.50	25.67	25.67	34.50	28.00	18.20	34.50	34.50	34.50	18.20	25.67
cycles	18.10	18.50	25.67	25.67	34.50	28.00	18.20	34.50	34.50	34.50	18.20	25.67

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	55.00
Dispatch	34.50
Overall L1	55.00

Vectorization ratios

INT

all	15%
load	100%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	15%

all	83%
load	77%
store	50%
mul	100%
add-sub	87%
fma	92%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	88%

INT+FP

all	58%
load	82%
store	7%
mul	100%
add-sub	87%
fma	92%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	70%

Vector efficiency ratios

INT

all	13%
load	50%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	12%

all	36%
load	35%
store	18%
mul	25%
add-sub	23%
fma	41%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	38%

INT+FP

all	27%
load	38%
store	9%
mul	25%
add-sub	23%
fma	41%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	32%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 55.00 cycles. At this rate:

9% of peak load performance is reached (18.18 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.56 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 55.00 to 34.50 cycles (1.59x speedup).

ASM code

In the binary file, the address of the function is: 49b450

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
LEA 0x8(%RSP),%R10	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(%R10)	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
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R10	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x60,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x448(%RSI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x478(%RSI),%ECX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %ECX,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xd8(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %R13D,%R14	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
IMUL %R14,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV 0x100(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x370(%RBX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R13D,0x430(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
LEA (%RDX,%RCX,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %EAX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JE 49bae0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x690>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x290(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xd0(%RBX),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-0x68(%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 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R11D,%R11D	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 49b50a <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0xba>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %R11D,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SAL $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
CMP $0x8,%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 49bb55 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x705>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R11,-0x78(%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 %R14,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4040d0 <memmove@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x370(%RBX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c39f(%RIP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x44(%RBP),%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11D,-0x54(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R11D,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R11,-0x70(%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 %R14,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVB $0x54,-0x55(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (1.6%)
MOVL $0x1,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVQ $0,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x44(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
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
LEA -0x38(%RBP),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x48(%RBP),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSHQ 0x348(%RBX)	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
LEA -0x4c(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x40(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
LEA -0x50(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x54(%RBP),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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 %RDI	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA -0x55(%RBP),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x238(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404520 <dgemv_@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOVSXD 0x370(%RBX),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%EDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c320(%RIP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL 0x290(%RBX),%R9	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x2b8(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R10D,-0x54(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R10D,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %RDX,-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 %EDI,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVB $0x4e,-0x55(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (1.6%)
MOVL $0x1,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVQ $0,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x44(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
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
LEA (%R8,%R9,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x50(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %RCX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA -0x4c(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x40(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
LEA -0x54(%RBP),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x55(%RBP),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
PUSHQ 0x348(%RBX)	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
CALL 404520 <dgemv_@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOVSXD 0x370(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c2a5(%RIP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c11e(%RIP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %ESI,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
IMUL 0x290(%RBX),%R8	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x2b8(%RBX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVB $0x4e,-0x55(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (1.6%)
MOV %R11D,-0x54(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R10,-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 %R11D,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x44(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
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
LEA (%RAX,%R8,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x55(%RBP),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSHQ 0x420(%RBX)	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
LEA -0x40(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x50(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
LEA -0x54(%RBP),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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 %R9	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA -0x4c(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x278(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404520 <dgemv_@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x410(%RBX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x30,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	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%)
IMUL 0x118(%RBX),%R14	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOVQ $0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x140(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVUPD %XMM2,(%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%)
TEST %R15D,%R15D	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 49babb <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x66b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%R15),%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
MOV %R15D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x2,%EDX	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 49bb41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x6f1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SHR $0x2,%R15D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R15,%RDI,1),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0x20,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x5,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	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%)
LEA (%R14,%R14,2),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVDQA 0x11c229(%RIP),%YMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11c241(%RIP),%YMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11c259(%RIP),%YMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11c271(%RIP),%YMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11bc49(%RIP),%YMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11bc61(%RIP),%YMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
MOV %RDI,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R8,%RAX,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVAPD %YMM2,%YMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM2,%YMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
AND $0x3,%R15D	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 49b85b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x40b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R15	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 49b7f9 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x3a9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R15	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 49b7a0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x350>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%R11),%YMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%R11),%YMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%R11),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD %YMM0,%YMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM0,%YMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVUPD (%RDI),%YMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPERMT2PD %YMM6,%YMM12,%YMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM6,%YMM10,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM6,%YMM8,%YMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM11,%YMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM9,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM7,%YMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VFMADD132PD %YMM4,%YMM2,%YMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD132PD %YMM4,%YMM2,%YMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM3,%YMM4,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
LEA 0x20(%RDI),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD $0x60,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%R11),%YMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%R11),%YMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD %YMM5,%YMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM5,%YMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVUPD (%R10),%YMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPERMT2PD %YMM14,%YMM12,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM10,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM8,%YMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM13,%YMM11,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM13,%YMM9,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM13,%YMM7,%YMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VFMADD231PD %YMM5,%YMM15,%YMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM6,%YMM15,%YMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM4,%YMM15,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
ADD $0x20,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD $0x60,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11),%YMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%R11),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%R11),%YMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD %YMM3,%YMM13	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM3,%YMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVUPD (%R10),%YMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPERMT2PD %YMM5,%YMM12,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM10,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM8,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM11,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM9,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM7,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
ADD $0x20,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VFMADD231PD %YMM3,%YMM15,%YMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM13,%YMM15,%YMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM6,%YMM15,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
ADD $0x60,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R10,%R9	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 49b9d6 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x586>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VEXTRACTF64X2 $0x1,%YMM1,%XMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VEXTRACTF64X2 $0x1,%YMM0,%XMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM9,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VADDPD %XMM0,%XMM5,%XMM13	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VEXTRACTF64X2 $0x1,%YMM2,%XMM12	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM12,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKHPD %XMM8,%XMM8,%XMM7	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VUNPCKHPD %XMM13,%XMM13,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM8,%XMM7,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VADDPD %XMM13,%XMM0,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %ESI,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VUNPCKHPD %XMM11,%XMM11,%XMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
AND $-0x4,%R15D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VADDPD %XMM11,%XMM10,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %R15D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VUNPCKLPD %XMM1,%XMM3,%XMM11	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
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 49bb24 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x6d4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
SUB %R15D,%ESI	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,%ESI	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 49ba8b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x63b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%RDI,%R15,8),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
LEA (%R14,%R15,1),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RCX,%RCX,2),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R8,%RDX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VPERMILPD $0x3,%XMM14,%XMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	vect (25.0%)
VMULPD 0x20(%RAX),%XMM4,%XMM15	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
VPERMILPD $0,%XMM14,%XMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	vect (25.0%)
VMOVQ %XMM2,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	scal (12.5%)
VFMADD132PD 0x10(%RAX),%XMM2,%XMM14	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
VFMADD231PD (%RAX),%XMM6,%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 %XMM15,%XMM15,%XMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VSHUFPD $0x1,%XMM15,%XMM14,%XMM12	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM10,%XMM14,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VADDPD %XMM11,%XMM12,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
TEST $0x1,%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 49baae <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x65e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
AND $-0x2,%ESI	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 %ESI,%R13D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOVSXD %R13D,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %RSI,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVDDUP (%RDI,%RSI,8),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%RDI,%RSI,8),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
LEA (%R14,%R14,2),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R8,%R14,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VFMADD231PD (%R8),%XMM9,%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%)
VFMADD231SD 0x10(%R8),%XMM8,%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%)
VMOVUPD %XMM11,(%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%)
VMOVSD %XMM2,0x10(%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 0x448(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
LEA -0x30(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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 %RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
MOV %R12,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
LEA -0x8(%RDI),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x410(%RBX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R15,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 49bb29 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x6d9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R15,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP $0x8,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JLE 49bb62 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x712>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4040d0 <memmove@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x410(%RBX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 49b695 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x245>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP 49baae <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x65e>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VXORPD %XMM7,%XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ $0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVUPD %XMM7,(%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%)
JMP 49babb <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x66b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM11,%XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R15D,%R15D	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 %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 49ba30 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x5e0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVSD (%RSI),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM0,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 49b50a <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0xba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
JNE 49b695 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x245>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD (%RSI),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM1,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 49b695 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x245>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run gcc_3

Source file and lines	DiracDeterminantRef.cpp:82-91
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:155-156
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,92-94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DelayedUpdate.h:98-113
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:82-91
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h:214-217
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:413,451-453
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algo.h:683,709
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:178,248

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 partially vectorized. Only 27% of vector register length is used (average across all SSE/AVX instructions).

Details

58% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

82% of SSE/AVX loads are used in vector version.
7% of SSE/AVX stores are used in vector version.
87% of SSE/AVX addition or subtraction instructions are used in vector version.
92% of SSE/AVX fused multiply-add instructions are used in vector version.
70% 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 43 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

CALL instructions

Detected function call instructions.

Details

dgemv_@plt: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
memmove@plt: 2 occurrences►
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:452
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algobase.h:452
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:85
qmcplusplus::TimerType
::stop(): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:89

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: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:82
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/BLAS.hpp:187
VZEROUPPER: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:155
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:248

Vector unaligned load/store instructions

Detected 12 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 12 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63

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 103 FP arithmetical operations:

58: addition or subtraction (43 inside FMA instructions)
45: multiply (43 inside FMA instructions)

The binary function is loading 1000 bytes (125 double precision FP elements). The binary function is storing 251 bytes (31 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.08 FP operations per loaded or stored byte.

General properties

nb instructions	317
nb uops	330
loop length	1461
used x86 registers	16
used mmx registers	0
used xmm registers	16
used ymm registers	16
used zmm registers	0
nb stack references	13
ADD-SUB / MUL ratio	8.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	55.00 cycles
front end	55.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	18.10	18.50	25.67	25.67	34.50	28.00	18.20	34.50	34.50	34.50	18.20	25.67
cycles	18.10	18.50	25.67	25.67	34.50	28.00	18.20	34.50	34.50	34.50	18.20	25.67

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	55.00
Dispatch	34.50
Overall L1	55.00

Vectorization ratios

INT

all	15%
load	100%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	15%

all	83%
load	77%
store	50%
mul	100%
add-sub	87%
fma	92%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	88%

INT+FP

all	58%
load	82%
store	7%
mul	100%
add-sub	87%
fma	92%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	70%

Vector efficiency ratios

INT

all	13%
load	50%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	12%

all	36%
load	35%
store	18%
mul	25%
add-sub	23%
fma	41%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	38%

INT+FP

all	27%
load	38%
store	9%
mul	25%
add-sub	23%
fma	41%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	32%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 55.00 cycles. At this rate:

9% of peak load performance is reached (18.18 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.56 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: 49b450

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
LEA 0x8(%RSP),%R10	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(%R10)	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
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R10	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB $0x60,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x448(%RSI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x478(%RSI),%ECX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %ECX,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0xd8(%RBX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %R13D,%R14	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
IMUL %R14,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV 0x100(%RBX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x370(%RBX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R13D,0x430(%RBX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
LEA (%RDX,%RCX,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %EAX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JE 49bae0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x690>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x290(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xd0(%RBX),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RDI,-0x68(%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 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R11D,%R11D	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 49b50a <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0xba>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %R11D,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SAL $0x3,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
CMP $0x8,%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 49bb55 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x705>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R11,-0x78(%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 %R14,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4040d0 <memmove@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x370(%RBX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c39f(%RIP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x44(%RBP),%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11D,-0x54(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R11D,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R11,-0x70(%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 %R14,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RSI,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVB $0x54,-0x55(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (1.6%)
MOVL $0x1,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVQ $0,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x44(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
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
LEA -0x38(%RBP),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x48(%RBP),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSHQ 0x348(%RBX)	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
LEA -0x4c(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x40(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
LEA -0x50(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x54(%RBP),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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 %RDI	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA -0x55(%RBP),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x238(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404520 <dgemv_@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOVSXD 0x370(%RBX),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%EDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c320(%RIP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL 0x290(%RBX),%R9	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x2b8(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R10D,-0x54(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R10D,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %RDX,-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 %EDI,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVB $0x4e,-0x55(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (1.6%)
MOVL $0x1,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVQ $0,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x44(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
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
LEA (%R8,%R9,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x50(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %RCX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA -0x4c(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x40(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
LEA -0x54(%RBP),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x55(%RBP),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
PUSHQ 0x348(%RBX)	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
CALL 404520 <dgemv_@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOVSXD 0x370(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c2a5(%RIP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c11e(%RIP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R8,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %ESI,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
IMUL 0x290(%RBX),%R8	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x2b8(%RBX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVB $0x4e,-0x55(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (1.6%)
MOV %R11D,-0x54(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R10,-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 %R11D,-0x4c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0x44(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
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
LEA (%RAX,%R8,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x55(%RBP),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSHQ 0x420(%RBX)	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
LEA -0x40(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x50(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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
LEA -0x54(%RBP),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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 %R9	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA -0x4c(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x278(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404520 <dgemv_@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x410(%RBX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD $0x30,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	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%)
IMUL 0x118(%RBX),%R14	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOVQ $0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x140(%RBX),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVUPD %XMM2,(%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%)
TEST %R15D,%R15D	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 49babb <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x66b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%R15),%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
MOV %R15D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x2,%EDX	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 49bb41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x6f1>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SHR $0x2,%R15D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (%R15,%RDI,1),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0x20,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x5,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	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%)
LEA (%R14,%R14,2),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVDQA 0x11c229(%RIP),%YMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11c241(%RIP),%YMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11c259(%RIP),%YMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11c271(%RIP),%YMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11bc49(%RIP),%YMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVDQA 0x11bc61(%RIP),%YMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
MOV %RDI,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R8,%RAX,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVAPD %YMM2,%YMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM2,%YMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
AND $0x3,%R15D	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 49b85b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x40b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R15	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 49b7f9 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x3a9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R15	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 49b7a0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x350>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%R11),%YMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%R11),%YMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%R11),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD %YMM0,%YMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM0,%YMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVUPD (%RDI),%YMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPERMT2PD %YMM6,%YMM12,%YMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM6,%YMM10,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM6,%YMM8,%YMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM11,%YMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM9,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM7,%YMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VFMADD132PD %YMM4,%YMM2,%YMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD132PD %YMM4,%YMM2,%YMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM3,%YMM4,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
LEA 0x20(%RDI),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD $0x60,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%R11),%YMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%R11),%YMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD %YMM5,%YMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM5,%YMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVUPD (%R10),%YMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPERMT2PD %YMM14,%YMM12,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM10,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM8,%YMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM13,%YMM11,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM13,%YMM9,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM13,%YMM7,%YMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VFMADD231PD %YMM5,%YMM15,%YMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM6,%YMM15,%YMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM4,%YMM15,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
ADD $0x20,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD $0x60,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11),%YMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%R11),%YMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%R11),%YMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD %YMM3,%YMM13	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVAPD %YMM3,%YMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (50.0%)
VMOVUPD (%R10),%YMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPERMT2PD %YMM5,%YMM12,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM10,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM5,%YMM8,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM11,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM9,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPERMT2PD %YMM14,%YMM7,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
ADD $0x20,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VFMADD231PD %YMM3,%YMM15,%YMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM13,%YMM15,%YMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM6,%YMM15,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
ADD $0x60,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R10,%R9	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 49b9d6 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x586>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VEXTRACTF64X2 $0x1,%YMM1,%XMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VEXTRACTF64X2 $0x1,%YMM0,%XMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM9,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VADDPD %XMM0,%XMM5,%XMM13	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VEXTRACTF64X2 $0x1,%YMM2,%XMM12	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM12,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VUNPCKHPD %XMM8,%XMM8,%XMM7	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VUNPCKHPD %XMM13,%XMM13,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VADDPD %XMM8,%XMM7,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VADDPD %XMM13,%XMM0,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %ESI,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VUNPCKHPD %XMM11,%XMM11,%XMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
AND $-0x4,%R15D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VADDPD %XMM11,%XMM10,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %R15D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VUNPCKLPD %XMM1,%XMM3,%XMM11	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
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 49bb24 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x6d4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
SUB %R15D,%ESI	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,%ESI	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 49ba8b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x63b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%RDI,%R15,8),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
LEA (%R14,%R15,1),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RCX,%RCX,2),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R8,%RDX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VPERMILPD $0x3,%XMM14,%XMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	vect (25.0%)
VMULPD 0x20(%RAX),%XMM4,%XMM15	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
VPERMILPD $0,%XMM14,%XMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	vect (25.0%)
VMOVQ %XMM2,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	scal (12.5%)
VFMADD132PD 0x10(%RAX),%XMM2,%XMM14	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
VFMADD231PD (%RAX),%XMM6,%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 %XMM15,%XMM15,%XMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VSHUFPD $0x1,%XMM15,%XMM14,%XMM12	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM10,%XMM14,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VADDPD %XMM11,%XMM12,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
TEST $0x1,%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 49baae <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x65e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
AND $-0x2,%ESI	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 %ESI,%R13D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOVSXD %R13D,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %RSI,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVDDUP (%RDI,%RSI,8),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%RDI,%RSI,8),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
LEA (%R14,%R14,2),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R8,%R14,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VFMADD231PD (%R8),%XMM9,%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%)
VFMADD231SD 0x10(%R8),%XMM8,%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%)
VMOVUPD %XMM11,(%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%)
VMOVSD %XMM2,0x10(%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 0x448(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
LEA -0x30(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	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 %RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
MOV %R12,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
LEA -0x8(%RDI),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x410(%RBX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R15,%R15	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 49bb29 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x6d9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R15,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP $0x8,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JLE 49bb62 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x712>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CALL 4040d0 <memmove@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x410(%RBX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x420(%RBX),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JMP 49b695 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x245>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP 49baae <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x65e>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VXORPD %XMM7,%XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ $0,0x10(%R12)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VMOVUPD %XMM7,(%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%)
JMP 49babb <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x66b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM11,%XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R15D,%R15D	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 %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 49ba30 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x5e0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VMOVSD (%RSI),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM0,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 49b50a <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0xba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
JNE 49b695 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x245>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD (%RSI),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM1,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JMP 49b695 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x245>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::DiracDeterminantRef >::evalGrad(qmcplusplus::ParticleSet&, int)–	0.49	0.41
○Loop 1127 - inner_product.hpp:155-155 - exec	0.48	0.41

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

FMA

Workaround

CALL instructions

Details

Complex 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

512-bits vectorization

Workaround

FMA

Workaround

CALL instructions

Details

Complex 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