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

	Function: miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalua ...	Module: exec	Source: DiracDeterminantRef.cpp:210-218 [...]	Coverage (incl. loops): 0.26% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h: 83 - 86

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

83:     for (int iat = 0; iat < VP.getTotalNum(); ++iat)

84:     {

85:       evaluate(VP, iat, psi);

86:       ratios[iat] = simd::dot(psi.data(), psiinv.data(), psi.size());

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 82 - 83

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

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

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

/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: 210 - 218

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

210: void DiracDeterminantRef<DU_TYPE>::evaluateRatios(VirtualParticleSet& VP, std::vector<ValueType>& ratios)

211: {

212:   SPOVTimer->start();

213:   const int WorkingIndex = VP.refPtcl - FirstIndex;

214:   invRow_id              = WorkingIndex;

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

216:   Phi->evaluateDetRatios(VP, psiV, invRow, ratios);

217:   SPOVTimer->stop();

218: }

/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; }

/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/unique_ptr.h: 193 - 193

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

193:       pointer    _M_ptr() const noexcept { return std::get<0>(_M_t); }

/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 - 249

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

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

[...]

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

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

0x49af10 PUSH	%R13

0x49af12 LEA	0x10(%RSP),%R13

0x49af17 AND	$-0x20,%RSP

0x49af1b PUSHQ	-0x8(%R13)

0x49af1f PUSH	%RBP

0x49af20 MOV	%RSP,%RBP

0x49af23 PUSH	%R15

0x49af25 MOV	%RDI,%R15

0x49af28 PUSH	%R14

0x49af2a PUSH	%R13

0x49af2c PUSH	%R12

0x49af2e MOV	%RDX,%R12

0x49af31 PUSH	%RBX

0x49af32 MOV	%RSI,%RBX

0x49af35 SUB	$0x48,%RSP

0x49af39 MOV	0x460(%RDI),%RDI

0x49af40 CALL	52c850 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x49af45 MOV	0x2a0(%RBX),%EAX

0x49af4b MOV	0x100(%R15),%RCX

0x49af52 SUB	0x478(%R15),%EAX

0x49af59 MOV	%EAX,0x430(%R15)

0x49af60 CLTQ

0x49af62 IMUL	0xd8(%R15),%RAX

0x49af6a MOV	0x370(%R15),%EDX

0x49af71 LEA	(%RCX,%RAX,8),%RSI

0x49af75 TEST	%EDX,%EDX

0x49af77 JE	49b3da

0x49af7d MOV	0x290(%R15),%RDI

0x49af84 MOV	0xd0(%R15),%R11

0x49af8b MOV	%RDI,-0x68(%RBP)

0x49af8f MOV	0x420(%R15),%RDI

0x49af96 TEST	%R11D,%R11D

0x49af99 JLE	49afca

0x49af9b MOVSXD	%R11D,%R8

0x49af9e SAL	$0x3,%R8

0x49afa2 CMP	$0x8,%R8

0x49afa6 JE	49b424

0x49afac MOV	%R8,%RDX

0x49afaf MOV	%R11,-0x70(%RBP)

0x49afb3 CALL	4040d0 <memmove@plt>

0x49afb8 MOV	0x420(%R15),%RDI

0x49afbf MOV	0x370(%R15),%EDX

0x49afc6 MOV	-0x70(%RBP),%R11

0x49afca MOV	0x11c8df(%RIP),%RSI

0x49afd1 SUB	$0x8,%RSP

0x49afd5 LEA	-0x44(%RBP),%R9

0x49afd9 MOV	%R11D,-0x54(%RBP)

0x49afdd MOV	%EDX,-0x50(%RBP)

0x49afe0 MOV	%RSI,-0x40(%RBP)

0x49afe4 MOV	%R11D,-0x4c(%RBP)

0x49afe8 MOV	%R11,-0x70(%RBP)

0x49afec MOVB	$0x54,-0x55(%RBP)

0x49aff0 MOVL	$0x1,-0x48(%RBP)

0x49aff7 MOVQ	$0,-0x38(%RBP)

0x49afff MOVL	$0x1,-0x44(%RBP)

0x49b006 PUSH	%R9

0x49b008 LEA	-0x38(%RBP),%R14

0x49b00c LEA	-0x48(%RBP),%R13

0x49b010 PUSHQ	0x348(%R15)

0x49b017 LEA	-0x4c(%RBP),%R9

0x49b01b LEA	-0x40(%RBP),%RCX

0x49b01f PUSH	%R14

0x49b021 LEA	-0x50(%RBP),%RDX

0x49b025 LEA	-0x54(%RBP),%RSI

0x49b029 PUSH	%R13

0x49b02b PUSH	%RDI

0x49b02c LEA	-0x55(%RBP),%RDI

0x49b030 MOV	0x238(%R15),%R8

0x49b037 CALL	404520 <dgemv_@plt>

0x49b03c MOVSXD	0x370(%R15),%R10

0x49b043 MOV	-0x68(%RBP),%EDX

0x49b046 MOV	0x11c863(%RIP),%RDI

0x49b04d ADD	$0x28,%RSP

0x49b051 MOV	%R10,%RAX

0x49b054 LEA	-0x44(%RBP),%R11

0x49b058 IMUL	0x290(%R15),%R10

0x49b060 MOV	0x2b8(%R15),%R8

0x49b067 MOV	%EAX,-0x54(%RBP)

0x49b06a MOV	%EAX,-0x50(%RBP)

0x49b06d MOV	%RDI,-0x40(%RBP)

0x49b071 MOV	%EDX,-0x4c(%RBP)

0x49b074 MOVB	$0x4e,-0x55(%RBP)

0x49b078 MOVL	$0x1,-0x48(%RBP)

0x49b07f MOVQ	$0,-0x38(%RBP)

0x49b087 MOVL	$0x1,-0x44(%RBP)

0x49b08e PUSH	%R11

0x49b090 LEA	(%R8,%R10,8),%RCX

0x49b094 LEA	-0x4c(%RBP),%R9

0x49b098 PUSH	%RCX

0x49b099 LEA	-0x50(%RBP),%RDX

0x49b09d LEA	-0x40(%RBP),%RCX

0x49b0a1 PUSH	%R14

0x49b0a3 LEA	-0x54(%RBP),%RSI

0x49b0a7 LEA	-0x55(%RBP),%RDI

0x49b0ab PUSH	%R13

0x49b0ad PUSHQ	0x348(%R15)

0x49b0b4 CALL	404520 <dgemv_@plt>

0x49b0b9 MOVSXD	0x370(%R15),%R8

0x49b0c0 MOV	-0x70(%RBP),%RAX

0x49b0c4 MOV	0x11c665(%RIP),%RCX

0x49b0cb MOV	0x11c7de(%RIP),%RDI

0x49b0d2 ADD	$0x28,%RSP

0x49b0d6 MOV	%R8,%RSI

0x49b0d9 LEA	-0x44(%RBP),%RDX

0x49b0dd IMUL	0x290(%R15),%R8

0x49b0e5 MOV	0x2b8(%R15),%R9

0x49b0ec MOV	%ESI,-0x50(%RBP)

0x49b0ef MOV	%RCX,-0x40(%RBP)

0x49b0f3 MOV	%RDI,-0x38(%RBP)

0x49b0f7 MOVB	$0x4e,-0x55(%RBP)

0x49b0fb MOV	%EAX,-0x54(%RBP)

0x49b0fe MOV	%EAX,-0x4c(%RBP)

0x49b101 MOVL	$0x1,-0x48(%RBP)

0x49b108 MOVL	$0x1,-0x44(%RBP)

0x49b10f PUSH	%RDX

0x49b110 LEA	(%R9,%R8,8),%R10

0x49b114 LEA	-0x40(%RBP),%RCX

0x49b118 PUSHQ	0x420(%R15)

0x49b11f LEA	-0x4c(%RBP),%R9

0x49b123 LEA	-0x50(%RBP),%RDX

0x49b127 PUSH	%R14

0x49b129 LEA	-0x54(%RBP),%RSI

0x49b12d LEA	-0x55(%RBP),%RDI

0x49b131 PUSH	%R13

0x49b133 PUSH	%R10

0x49b135 MOV	0x278(%R15),%R8

0x49b13c CALL	404520 <dgemv_@plt>

0x49b141 ADD	$0x30,%RSP

0x49b145 MOV	0x470(%R15),%R14

0x49b14c LEA	0x190(%R15),%R11

0x49b153 MOV	(%R14),%R9

0x49b156 MOV	0x20(%R9),%R13

0x49b15a CMP	$0x47ea80,%R13

0x49b161 JNE	49b409

0x49b167 XOR	%R8D,%R8D

0x49b16a CMPQ	$0,0x260(%RBX)

0x49b172 JE	49b39b

0x49b178 MOV	%R11,-0x68(%RBP)

0x49b17c MOV	%R12,%R13

0x49b17f MOV	%R15,%R12

0x49b182 MOV	%R8,%R15

0x49b185 NOPL	(%RAX)

(1125) 0x49b188 MOV	-0x68(%RBP),%RCX

(1125) 0x49b18c MOV	%RBX,%RSI

(1125) 0x49b18f MOV	%R15D,%EDX

(1125) 0x49b192 MOV	%R14,%RDI

(1125) 0x49b195 CALLQ	0x10(%R9)

(1125) 0x49b199 MOV	0x198(%R12),%RSI

(1125) 0x49b1a1 MOV	0x420(%R12),%R10

(1125) 0x49b1a9 MOV	0x1a8(%R12),%RCX

(1125) 0x49b1b1 TEST	%ESI,%ESI

(1125) 0x49b1b3 JLE	49b3c0

(1125) 0x49b1b9 LEA	-0x1(%RSI),%R9D

(1125) 0x49b1bd CMP	$0x2,%R9D

(1125) 0x49b1c1 JBE	49b3c6

(1125) 0x49b1c7 MOV	%ESI,%EDX

(1125) 0x49b1c9 SHR	$0x2,%EDX

(1125) 0x49b1cc SAL	$0x5,%RDX

(1125) 0x49b1d0 LEA	-0x20(%RDX),%RDI

(1125) 0x49b1d4 SHR	$0x5,%RDI

(1125) 0x49b1d8 INC	%RDI

(1125) 0x49b1db XOR	%EAX,%EAX

(1125) 0x49b1dd VXORPD	%XMM8,%XMM8,%XMM8

(1125) 0x49b1e2 AND	$0x7,%EDI

(1125) 0x49b1e5 JE	49b280

(1125) 0x49b1eb CMP	$0x1,%RDI

(1125) 0x49b1ef JE	49b268

(1125) 0x49b1f1 CMP	$0x2,%RDI

(1125) 0x49b1f5 JE	49b259

(1125) 0x49b1f7 CMP	$0x3,%RDI

(1125) 0x49b1fb JE	49b24a

(1125) 0x49b1fd CMP	$0x4,%RDI

(1125) 0x49b201 JE	49b23b

(1125) 0x49b203 CMP	$0x5,%RDI

(1125) 0x49b207 JE	49b22c

(1125) 0x49b209 CMP	$0x6,%RDI

(1125) 0x49b20d JE	49b21d

(1125) 0x49b20f VMOVUPD	(%RCX),%YMM3

(1125) 0x49b213 MOV	$0x20,%EAX

(1125) 0x49b218 VFMADD231PD	(%R10),%YMM3,%YMM8

(1125) 0x49b21d VMOVUPD	(%RCX,%RAX,1),%YMM4

(1125) 0x49b222 VFMADD231PD	(%R10,%RAX,1),%YMM4,%YMM8

(1125) 0x49b228 ADD	$0x20,%RAX

(1125) 0x49b22c VMOVUPD	(%RCX,%RAX,1),%YMM5

(1125) 0x49b231 VFMADD231PD	(%R10,%RAX,1),%YMM5,%YMM8

(1125) 0x49b237 ADD	$0x20,%RAX

(1125) 0x49b23b VMOVUPD	(%RCX,%RAX,1),%YMM6

(1125) 0x49b240 VFMADD231PD	(%R10,%RAX,1),%YMM6,%YMM8

(1125) 0x49b246 ADD	$0x20,%RAX

(1125) 0x49b24a VMOVUPD	(%RCX,%RAX,1),%YMM7

(1125) 0x49b24f VFMADD231PD	(%R10,%RAX,1),%YMM7,%YMM8

(1125) 0x49b255 ADD	$0x20,%RAX

(1125) 0x49b259 VMOVUPD	(%RCX,%RAX,1),%YMM9

(1125) 0x49b25e VFMADD231PD	(%R10,%RAX,1),%YMM9,%YMM8

(1125) 0x49b264 ADD	$0x20,%RAX

(1125) 0x49b268 VMOVUPD	(%RCX,%RAX,1),%YMM10

(1125) 0x49b26d VFMADD231PD	(%R10,%RAX,1),%YMM10,%YMM8

(1125) 0x49b273 ADD	$0x20,%RAX

(1125) 0x49b277 CMP	%RAX,%RDX

(1125) 0x49b27a JE	49b30d

  (1126) 0x49b280 VMOVUPD	(%RCX,%RAX,1),%YMM11

  (1126) 0x49b285 VMOVUPD	0x20(%RCX,%RAX,1),%YMM12

  (1126) 0x49b28b VFMADD231PD	(%R10,%RAX,1),%YMM11,%YMM8

  (1126) 0x49b291 VMOVUPD	0x40(%RCX,%RAX,1),%YMM13

  (1126) 0x49b297 VMOVUPD	0x60(%RCX,%RAX,1),%YMM14

  (1126) 0x49b29d VMOVUPD	0x80(%RCX,%RAX,1),%YMM15

  (1126) 0x49b2a6 VMOVUPD	0xa0(%RCX,%RAX,1),%YMM0

  (1126) 0x49b2af VFMADD231PD	0x20(%R10,%RAX,1),%YMM12,%YMM8

  (1126) 0x49b2b6 VMOVUPD	0xc0(%RCX,%RAX,1),%YMM1

  (1126) 0x49b2bf VMOVUPD	0xe0(%RCX,%RAX,1),%YMM2

  (1126) 0x49b2c8 VFMADD231PD	0x40(%R10,%RAX,1),%YMM13,%YMM8

  (1126) 0x49b2cf VFMADD231PD	0x60(%R10,%RAX,1),%YMM14,%YMM8

  (1126) 0x49b2d6 VFMADD231PD	0x80(%R10,%RAX,1),%YMM15,%YMM8

  (1126) 0x49b2e0 VFMADD231PD	0xa0(%R10,%RAX,1),%YMM0,%YMM8

  (1126) 0x49b2ea VFMADD231PD	0xc0(%R10,%RAX,1),%YMM1,%YMM8

  (1126) 0x49b2f4 VFMADD231PD	0xe0(%R10,%RAX,1),%YMM2,%YMM8

  (1126) 0x49b2fe ADD	$0x100,%RAX

  (1126) 0x49b304 CMP	%RAX,%RDX

  (1126) 0x49b307 JNE	49b280

(1125) 0x49b30d VEXTRACTF64X2	$0x1,%YMM8,%XMM3

(1125) 0x49b314 VADDPD	%XMM8,%XMM3,%XMM8

(1125) 0x49b319 MOV	%ESI,%R11D

(1125) 0x49b31c AND	$-0x4,%R11D

(1125) 0x49b320 VUNPCKHPD	%XMM8,%XMM8,%XMM4

(1125) 0x49b325 VADDPD	%XMM8,%XMM4,%XMM2

(1125) 0x49b32a MOV	%R11D,%R8D

(1125) 0x49b32d TEST	$0x3,%SIL

(1125) 0x49b331 JE	49b390

(1125) 0x49b333 VZEROUPPER

(1125) 0x49b336 SUB	%R11D,%ESI

(1125) 0x49b339 CMP	$0x1,%ESI

(1125) 0x49b33c JE	49b360

(1125) 0x49b33e VMOVUPD	(%RCX,%R11,8),%XMM5

(1125) 0x49b344 VFMADD231PD	(%R10,%R11,8),%XMM5,%XMM8

(1125) 0x49b34a VUNPCKHPD	%XMM8,%XMM8,%XMM6

(1125) 0x49b34f VADDPD	%XMM8,%XMM6,%XMM2

(1125) 0x49b354 TEST	$0x1,%SIL

(1125) 0x49b358 JE	49b36e

(1125) 0x49b35a AND	$-0x2,%ESI

(1125) 0x49b35d ADD	%ESI,%R8D

(1125) 0x49b360 MOVSXD	%R8D,%RSI

(1125) 0x49b363 VMOVSD	(%RCX,%RSI,8),%XMM7

(1125) 0x49b368 VFMADD231SD	(%R10,%RSI,8),%XMM7,%XMM2

(1125) 0x49b36e MOV	(%R13),%R10

(1125) 0x49b372 VMOVSD	%XMM2,(%R10,%R15,8)

(1125) 0x49b378 INC	%R15

(1125) 0x49b37b CMP	0x260(%RBX),%R15

(1125) 0x49b382 JAE	49b398

(1125) 0x49b384 MOV	(%R14),%R9

(1125) 0x49b387 JMP	49b188

0x49b38c NOPL	(%RAX)

(1125) 0x49b390 VZEROUPPER

(1125) 0x49b393 JMP	49b36e

0x49b395 NOPL	(%RAX)

0x49b398 MOV	%R12,%R15

0x49b39b MOV	0x460(%R15),%RDI

0x49b3a2 LEA	-0x28(%RBP),%RSP

0x49b3a6 POP	%RBX

0x49b3a7 POP	%R12

0x49b3a9 POP	%R13

0x49b3ab POP	%R14

0x49b3ad POP	%R15

0x49b3af POP	%RBP

0x49b3b0 LEA	-0x10(%R13),%RSP

0x49b3b4 POP	%R13

0x49b3b6 JMP	52ca80

0x49b3bb NOPL	(%RAX,%RAX,1)

(1125) 0x49b3c0 VXORPD	%XMM2,%XMM2,%XMM2

(1125) 0x49b3c4 JMP	49b36e

(1125) 0x49b3c6 VXORPD	%XMM8,%XMM8,%XMM8

(1125) 0x49b3cb XOR	%R11D,%R11D

(1125) 0x49b3ce VXORPD	%XMM2,%XMM2,%XMM2

(1125) 0x49b3d2 XOR	%R8D,%R8D

(1125) 0x49b3d5 JMP	49b336

0x49b3da MOV	0x410(%R15),%R14

0x49b3e1 TEST	%R14,%R14

0x49b3e4 JE	49b145

0x49b3ea LEA	(,%R14,8),%RDX

0x49b3f2 MOV	0x420(%R15),%RDI

0x49b3f9 CMP	$0x8,%RDX

0x49b3fd JLE	49b431

0x49b3ff CALL	4040d0 <memmove@plt>

0x49b404 JMP	49b145

0x49b409 LEA	0x408(%R15),%RCX

0x49b410 MOV	%R12,%R8

0x49b413 MOV	%R11,%RDX

0x49b416 MOV	%RBX,%RSI

0x49b419 MOV	%R14,%RDI

0x49b41c CALL	%R13

0x49b41f JMP	49b39b

0x49b424 VMOVSD	(%RSI),%XMM0

0x49b428 VMOVSD	%XMM0,(%RDI)

0x49b42c JMP	49afca

0x49b431 JNE	49b145

0x49b437 VMOVSD	(%RSI),%XMM1

0x49b43b VMOVSD	%XMM1,(%RDI)

0x49b43f JMP	49b145

0x49b444 NOPW	%CS:(%RAX,%RAX,1)

0x49b44e XCHG	%AX,%AX

Coverage (%)	Name	Source Location	Module
►49.17+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:266	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►48.25+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:993	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
►1.20+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:993	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
►1.04+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:266	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	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:210-218
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h:83-86
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:82-83
/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:210-218
/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
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/unique_ptr.h:193
/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:178,248-249

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 32.17 to 4.00 cycles (8.04x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 8% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 32.17 to 1.45 cycles (22.26x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

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:212
unknown: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:216

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:210
- /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

Conversion instructions

Detected expensive conversion instructions.

Details

CLTQ: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DelayedUpdate.h:101

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

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 284 bytes. The binary function is storing 163 bytes.

General properties

nb instructions	182
nb uops	193
loop length	797
used x86 registers	16
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	12

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	32.17 cycles
front end	32.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	5.00	4.80	15.33	15.33	30.50	4.60	5.00	30.50	30.50	30.50	4.60	15.33
cycles	5.00	5.63	15.33	15.33	30.50	4.60	5.00	30.50	30.50	30.50	4.60	15.33

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	32.17
Dispatch	30.50
Overall L1	32.17

Vectorization ratios

INT

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

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

INT+FP

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

Vector efficiency ratios

INT

all	8%
load	12%
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	11%

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

INT+FP

all	8%
load	12%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 32.17 cycles. At this rate:

4% of peak load performance is reached (8.83 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (5.07 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 32.17 to 30.50 cycles (1.05x speedup).

ASM code

In the binary file, the address of the function is: 49af10

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 %RDI,%R15	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
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 %RDX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
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 $0x48,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x460(%RDI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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 0x2a0(%RBX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x100(%R15),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x478(%R15),%EAX	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 %EAX,0x430(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
IMUL 0xd8(%R15),%RAX	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x370(%R15),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RCX,%RAX,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %EDX,%EDX	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 49b3da <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4ca>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x290(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xd0(%R15),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
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(%R15),%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 49afca <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xba>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %R11D,%R8	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SAL $0x3,%R8	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
CMP $0x8,%R8	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 49b424 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x514>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R8,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
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%)
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(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x370(%R15),%EDX	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	scal (12.5%)
MOV 0x11c8df(%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),%R9	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 %EDX,-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 %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%)
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%)
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 %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 -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(%R15)	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(%R15),%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(%R15),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c863(%RIP),%RDI	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 %R10,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x44(%RBP),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL 0x290(%R15),%R10	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x2b8(%R15),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %EAX,-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 %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 %EDX,-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 %R11	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,%R10,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x4c(%RBP),%R9	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 -0x50(%RBP),%RDX	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(%R15)	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(%R15),%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),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c665(%RIP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c7de(%RIP),%RDI	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
LEA -0x44(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL 0x290(%R15),%R8	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x2b8(%R15),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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%)
MOV %RCX,-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 %RDI,-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%)
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 %EAX,-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,-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 %RDX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA (%R9,%R8,8),%R10	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
PUSHQ 0x420(%R15)	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 -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
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
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
MOV 0x278(%R15),%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
ADD $0x30,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x470(%R15),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x190(%R15),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV (%R14),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%R9),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP $0x47ea80,%R13	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 49b409 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4f9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMPQ $0,0x260(%RBX)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 49b39b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x48b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R11,-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 %R12,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R8,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x460(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA -0x28(%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 %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 -0x10(%R13),%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 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x410(%R15),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R14,%R14	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 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R14,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x420(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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	N/A
JLE 49b431 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x521>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
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
JMP 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
LEA 0x408(%R15),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL %R13	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
JMP 49b39b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x48b>	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 49afca <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
JNE 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	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 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	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
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 0.00% of application time for run gcc_3

Source file and lines	DiracDeterminantRef.cpp:210-218
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h:83-86
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:82-83
/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:210-218
/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
/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/unique_ptr.h:193
/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:178,248-249

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 32.17 to 4.00 cycles (8.04x speedup).

Workaround

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

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

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:212
unknown: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:216

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:210
- /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

Conversion instructions

Detected expensive conversion instructions.

Details

CLTQ: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DelayedUpdate.h:101

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

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 284 bytes. The binary function is storing 163 bytes.

General properties

nb instructions	182
nb uops	193
loop length	797
used x86 registers	16
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	12

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	32.17 cycles
front end	32.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	5.00	4.80	15.33	15.33	30.50	4.60	5.00	30.50	30.50	30.50	4.60	15.33
cycles	5.00	5.63	15.33	15.33	30.50	4.60	5.00	30.50	30.50	30.50	4.60	15.33

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	32.17
Dispatch	30.50
Overall L1	32.17

Vectorization ratios

INT

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

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

INT+FP

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

Vector efficiency ratios

INT

all	8%
load	12%
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	11%

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

INT+FP

all	8%
load	12%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 32.17 cycles. At this rate:

4% of peak load performance is reached (8.83 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (5.07 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: 49af10

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 %RDI,%R15	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
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 %RDX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
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 $0x48,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x460(%RDI),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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 0x2a0(%RBX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x100(%R15),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB 0x478(%R15),%EAX	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 %EAX,0x430(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
IMUL 0xd8(%R15),%RAX	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x370(%R15),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RCX,%RAX,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %EDX,%EDX	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 49b3da <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4ca>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x290(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xd0(%R15),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
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(%R15),%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 49afca <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xba>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %R11D,%R8	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SAL $0x3,%R8	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
CMP $0x8,%R8	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 49b424 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x514>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R8,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
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%)
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(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x370(%R15),%EDX	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	scal (12.5%)
MOV 0x11c8df(%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),%R9	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 %EDX,-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 %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%)
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%)
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 %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 -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(%R15)	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(%R15),%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(%R15),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c863(%RIP),%RDI	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 %R10,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x44(%RBP),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL 0x290(%R15),%R10	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x2b8(%R15),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %EAX,-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 %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 %EDX,-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 %R11	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,%R10,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x4c(%RBP),%R9	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 -0x50(%RBP),%RDX	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(%R15)	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(%R15),%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),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c665(%RIP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x11c7de(%RIP),%RDI	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
LEA -0x44(%RBP),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL 0x290(%R15),%R8	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV 0x2b8(%R15),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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%)
MOV %RCX,-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 %RDI,-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%)
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 %EAX,-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,-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 %RDX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
LEA (%R9,%R8,8),%R10	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
PUSHQ 0x420(%R15)	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 -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
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
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
MOV 0x278(%R15),%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
ADD $0x30,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x470(%R15),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x190(%R15),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV (%R14),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%R9),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP $0x47ea80,%R13	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 49b409 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x4f9>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMPQ $0,0x260(%RBX)	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	scal (12.5%)
JE 49b39b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x48b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R11,-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 %R12,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R8,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x460(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA -0x28(%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 %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 -0x10(%R13),%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 52ca80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x410(%R15),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %R14,%R14	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 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%R14,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0x420(%R15),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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	N/A
JLE 49b431 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x521>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
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
JMP 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
LEA 0x408(%R15),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL %R13	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
JMP 49b39b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x48b>	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 49afca <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0xba>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
JNE 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	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 49b145 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x235>	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
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::DiracDeterminantRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)–	0.26	0.22
▼Loop 1125 - SPOSet.h:83-86 - exec–	0.00	0.01
○Loop 1126 - inner_product.hpp:82-83 - exec	0.25	0.21

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code