OV - exec - Function miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > >&, qmcplusplus::ParticleAttrib<double, std::allocator<double> >&, bool)

	Function: miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalua ...	Module: exec	Source: DiracDeterminantRef.cpp:152-181 [...]	Coverage (incl. loops): 0.63% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h: 217 - 217

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h: 129 - 131

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

129:     Type_t res = lhs[0] * rhs[0];

130:     for (unsigned d = 1; d < D; ++d)

131:       res += lhs[d] * rhs[d];

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 62 - 62

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 82 - 156

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

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

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

[...]

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h: 106 - 111

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

106:     for (int iat = first, i = 0; iat < last; ++iat, ++i)

107:     {

108:       ValueVector_t v(logdet[i], OrbitalSetSize);

109:       GradVector_t g(dlogdet[i], OrbitalSetSize);

110:       ValueVector_t l(d2logdet[i], OrbitalSetSize);

111:       evaluate(P, iat, v, g, l);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 56 - 248

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

56:   explicit inline Vector(T* ref, size_t n) : nLocal(n), X(ref) {}

[...]

144:   virtual ~Vector() { free(); }

[...]

210:     if (nAllocated)

[...]

221:   inline Type_t& operator[](size_t i)

222:   {

223:     return X[i];

[...]

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

/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/new_allocator.h: 104 - 172

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

104:       ~__new_allocator() _GLIBCXX_USE_NOEXCEPT { }

[...]

172: 	_GLIBCXX_OPERATOR_DELETE(_GLIBCXX_SIZED_DEALLOC(__p, __n));

/home/eoseret/qaas_runs_ZEN5/173-938-0042/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_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp: 152 - 181

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

152: void DiracDeterminantRef<DU_TYPE>::evaluateGL(ParticleSet& P,

153:                                               ParticleSet::ParticleGradient& G,

154:                                               ParticleSet::ParticleLaplacian& L,

155:                                               bool fromscratch)

156: {

157:   if (UpdateMode == ORB_PBYP_RATIO)

158:   { //need to compute dpsiM and d2psiM. Do not touch psiM!

159:     SPOVGLTimer->start();

160:     Phi->evaluate_notranspose(P, FirstIndex, LastIndex, psiM_temp, dpsiM, d2psiM);

161:     SPOVGLTimer->stop();

162:   }

163:

164:   if (NumPtcls == 1)

165:   {

166:     ValueType y = psiM(0, 0);

167:     GradType rv = y * dpsiM(0, 0);

168:     G[FirstIndex] += rv;

169:     L[FirstIndex] += y * d2psiM(0, 0) - dot(rv, rv);

170:   }

171:   else

172:   {

173:     for (size_t i = 0, iat = FirstIndex; i < NumPtcls; ++i, ++iat)

174:     {

175:       mValueType dot_temp = simd::dot(psiM[i], d2psiM[i], NumOrbitals);

176:       mGradType rv        = simd::dot(psiM[i], dpsiM[i], NumOrbitals);

177:       G[iat] += rv;

178:       L[iat] += dot_temp - dot(rv, rv);

179:     }

180:   }

181: }

0x49d100 LEA	0x8(%RSP),%R10

0x49d105 AND	$-0x20,%RSP

0x49d109 PUSHQ	-0x8(%R10)

0x49d10d PUSH	%RBP

0x49d10e MOV	%RSP,%RBP

0x49d111 PUSH	%R15

0x49d113 PUSH	%R14

0x49d115 PUSH	%R13

0x49d117 PUSH	%R12

0x49d119 PUSH	%R10

0x49d11b PUSH	%RBX

0x49d11c MOV	%RDI,%R13

0x49d11f SUB	$0xc0,%RSP

0x49d126 MOV	%RCX,-0xe0(%RBP)

0x49d12d MOV	0xc(%RDI),%ECX

0x49d130 MOV	%RDX,-0xd0(%RBP)

0x49d137 TEST	%ECX,%ECX

0x49d139 JE	49d9c4

0x49d13f MOV	0x484(%R13),%R11D

0x49d146 MOVSXD	0x478(%R13),%R9

0x49d14d CMP	$0x1,%R11D

0x49d151 JE	49d937

0x49d157 MOVSXD	%R11D,%RDX

0x49d15a VMOVQ	%RDX,%XMM15

0x49d15f TEST	%R11D,%R11D

0x49d162 JE	49d8a0

0x49d168 VMOVQ	0xd8(%R13),%XMM13

0x49d171 MOV	-0xe0(%RBP),%RAX

0x49d178 MOV	-0xd0(%RBP),%RSI

0x49d17f MOV	0x480(%R13),%EDI

0x49d186 MOV	0x158(%R13),%R15

0x49d18d VMOVQ	0x180(%R13),%XMM11

0x49d196 MOV	0x100(%R13),%R10

0x49d19d VMOVDQA	0x1236fb(%RIP),%YMM9

0x49d1a5 VMOVDQA	0x123713(%RIP),%YMM8

0x49d1ad VMOVDQA	0x12372b(%RIP),%YMM7

0x49d1b5 LEA	(%R9,%R9,2),%R8

0x49d1b9 MOV	%R13,-0xd0(%RBP)

0x49d1c0 VMOVDQA	0x123738(%RIP),%YMM6

0x49d1c8 VMOVDQA	0x123170(%RIP),%YMM5

0x49d1d0 VMOVDQA	0x123188(%RIP),%YMM4

0x49d1d8 MOV	0x18(%RAX),%R11

0x49d1dc MOV	0x18(%RSI),%R12

0x49d1e0 LEA	-0x1(%RDI),%R14D

0x49d1e4 VMOVQ	%XMM13,%RBX

0x49d1e9 MOV	%R14D,-0xc8(%RBP)

0x49d1f0 MOV	%R10,%RCX

0x49d1f3 MOV	%R10,-0xd8(%RBP)

0x49d1fa SAL	$0x3,%RBX

0x49d1fe VMOVQ	%XMM11,%R14

0x49d203 VMOVQ	%RBX,%XMM14

0x49d208 MOV	%EDI,%EBX

0x49d20a SHR	$0x2,%EBX

0x49d20d SAL	$0x3,%R15

0x49d211 LEA	(%R11,%R9,8),%R9

0x49d215 LEA	(%R12,%R8,8),%R8

0x49d219 VMOVQ	%R15,%XMM12

0x49d21e XOR	%R12D,%R12D

0x49d221 SAL	$0x5,%RBX

0x49d225 VMOVQ	%R9,%XMM10

0x49d22a XOR	%R15D,%R15D

0x49d22d XOR	%R9D,%R9D

(1109) 0x49d230 TEST	%EDI,%EDI

(1109) 0x49d232 JLE	49d909

(1109) 0x49d238 CMPL	$0x2,-0xc8(%RBP)

(1109) 0x49d23f JBE	49d92a

(1109) 0x49d245 LEA	-0x20(%RBX),%R10

(1109) 0x49d249 XOR	%ESI,%ESI

(1109) 0x49d24b LEA	(%R14,%R12,1),%RDX

(1109) 0x49d24f VXORPD	%XMM0,%XMM0,%XMM0

(1109) 0x49d253 SHR	$0x5,%R10

(1109) 0x49d257 INC	%R10

(1109) 0x49d25a AND	$0x7,%R10D

(1109) 0x49d25e JE	49d2f9

(1109) 0x49d264 CMP	$0x1,%R10

(1109) 0x49d268 JE	49d2e1

(1109) 0x49d26a CMP	$0x2,%R10

(1109) 0x49d26e JE	49d2d2

(1109) 0x49d270 CMP	$0x3,%R10

(1109) 0x49d274 JE	49d2c3

(1109) 0x49d276 CMP	$0x4,%R10

(1109) 0x49d27a JE	49d2b4

(1109) 0x49d27c CMP	$0x5,%R10

(1109) 0x49d280 JE	49d2a5

(1109) 0x49d282 CMP	$0x6,%R10

(1109) 0x49d286 JE	49d296

(1109) 0x49d288 MOV	$0x20,%ESI

(1109) 0x49d28d VMOVUPD	(%RCX),%YMM3

(1109) 0x49d291 VFMADD231PD	(%RDX),%YMM3,%YMM0

(1109) 0x49d296 VMOVUPD	(%RCX,%RSI,1),%YMM1

(1109) 0x49d29b VFMADD231PD	(%RDX,%RSI,1),%YMM1,%YMM0

(1109) 0x49d2a1 ADD	$0x20,%RSI

(1109) 0x49d2a5 VMOVUPD	(%RCX,%RSI,1),%YMM11

(1109) 0x49d2aa VFMADD231PD	(%RDX,%RSI,1),%YMM11,%YMM0

(1109) 0x49d2b0 ADD	$0x20,%RSI

(1109) 0x49d2b4 VMOVUPD	(%RCX,%RSI,1),%YMM2

(1109) 0x49d2b9 VFMADD231PD	(%RDX,%RSI,1),%YMM2,%YMM0

(1109) 0x49d2bf ADD	$0x20,%RSI

(1109) 0x49d2c3 VMOVUPD	(%RCX,%RSI,1),%YMM3

(1109) 0x49d2c8 VFMADD231PD	(%RDX,%RSI,1),%YMM3,%YMM0

(1109) 0x49d2ce ADD	$0x20,%RSI

(1109) 0x49d2d2 VMOVUPD	(%RCX,%RSI,1),%YMM1

(1109) 0x49d2d7 VFMADD231PD	(%RDX,%RSI,1),%YMM1,%YMM0

(1109) 0x49d2dd ADD	$0x20,%RSI

(1109) 0x49d2e1 VMOVUPD	(%RCX,%RSI,1),%YMM11

(1109) 0x49d2e6 VFMADD231PD	(%RDX,%RSI,1),%YMM11,%YMM0

(1109) 0x49d2ec ADD	$0x20,%RSI

(1109) 0x49d2f0 CMP	%RSI,%RBX

(1109) 0x49d2f3 JE	49d387

  (1111) 0x49d2f9 VMOVUPD	(%RCX,%RSI,1),%YMM2

  (1111) 0x49d2fe VMOVUPD	0x20(%RSI,%RCX,1),%YMM3

  (1111) 0x49d304 VMOVUPD	0x40(%RSI,%RCX,1),%YMM1

  (1111) 0x49d30a VMOVUPD	0x60(%RSI,%RCX,1),%YMM11

  (1111) 0x49d310 VFMADD231PD	(%RDX,%RSI,1),%YMM2,%YMM0

  (1111) 0x49d316 VMOVUPD	0x80(%RSI,%RCX,1),%YMM2

  (1111) 0x49d31f VFMADD231PD	0x20(%RDX,%RSI,1),%YMM3,%YMM0

  (1111) 0x49d326 VMOVUPD	0xa0(%RSI,%RCX,1),%YMM3

  (1111) 0x49d32f VFMADD231PD	0x40(%RDX,%RSI,1),%YMM1,%YMM0

  (1111) 0x49d336 VMOVUPD	0xc0(%RSI,%RCX,1),%YMM1

  (1111) 0x49d33f VFMADD231PD	0x60(%RDX,%RSI,1),%YMM11,%YMM0

  (1111) 0x49d346 VMOVUPD	0xe0(%RSI,%RCX,1),%YMM11

  (1111) 0x49d34f VFMADD231PD	0x80(%RDX,%RSI,1),%YMM2,%YMM0

  (1111) 0x49d359 VFMADD231PD	0xa0(%RDX,%RSI,1),%YMM3,%YMM0

  (1111) 0x49d363 VFMADD231PD	0xc0(%RDX,%RSI,1),%YMM1,%YMM0

  (1111) 0x49d36d VFMADD231PD	0xe0(%RDX,%RSI,1),%YMM11,%YMM0

  (1111) 0x49d377 ADD	$0x100,%RSI

  (1111) 0x49d37e CMP	%RSI,%RBX

  (1111) 0x49d381 JNE	49d2f9

(1109) 0x49d387 VEXTRACTF64X2	$0x1,%YMM0,%XMM2

(1109) 0x49d38e VADDPD	%XMM0,%XMM2,%XMM0

(1109) 0x49d392 MOV	%EDI,%R13D

(1109) 0x49d395 AND	$-0x4,%R13D

(1109) 0x49d399 VUNPCKHPD	%XMM0,%XMM0,%XMM3

(1109) 0x49d39d VADDPD	%XMM0,%XMM3,%XMM11

(1109) 0x49d3a1 TEST	$0x3,%DIL

(1109) 0x49d3a5 JE	49d8eb

(1109) 0x49d3ab MOVSXD	%R13D,%R11

(1109) 0x49d3ae LEA	0x1(%R13),%R10D

(1109) 0x49d3b2 SAL	$0x3,%R11

(1109) 0x49d3b6 LEA	(%R14,%R11,1),%RDX

(1109) 0x49d3ba VMOVSD	(%RCX,%R11,1),%XMM1

(1109) 0x49d3c0 VFMADD231SD	(%RDX,%R12,1),%XMM1,%XMM11

(1109) 0x49d3c6 CMP	%R10D,%EDI

(1109) 0x49d3c9 JLE	49d8b4

(1109) 0x49d3cf LEA	0x8(%R14,%R11,1),%RSI

(1109) 0x49d3d4 ADD	$0x2,%R13D

(1109) 0x49d3d8 VMOVSD	0x8(%R11,%RCX,1),%XMM2

(1109) 0x49d3df VFMADD231SD	(%RSI,%R12,1),%XMM2,%XMM11

(1109) 0x49d3e5 CMP	%R13D,%EDI

(1109) 0x49d3e8 JLE	49d3fc

(1109) 0x49d3ea LEA	(%R14,%R12,1),%RAX

(1109) 0x49d3ee VMOVSD	0x10(%R11,%RCX,1),%XMM0

(1109) 0x49d3f5 VFMADD231SD	0x10(%R11,%RAX,1),%XMM0,%XMM11

(1109) 0x49d3fc MOV	-0xd0(%RBP),%R11

(1109) 0x49d403 MOV	0x140(%R11),%R10

(1109) 0x49d40a MOV	0x118(%R11),%R11

(1109) 0x49d411 IMUL	%R9,%R11

(1109) 0x49d415 CMPL	$0x2,-0xc8(%RBP)

(1109) 0x49d41c JBE	49dbd1

(1109) 0x49d422 LEA	-0x20(%RBX),%RSI

(1109) 0x49d426 LEA	(%R11,%R11,2),%R13

(1109) 0x49d42a VXORPD	%XMM2,%XMM2,%XMM2

(1109) 0x49d42e MOV	%RCX,%RDX

(1109) 0x49d431 SHR	$0x5,%RSI

(1109) 0x49d435 VMOVAPD	%YMM2,%YMM1

(1109) 0x49d439 VMOVAPD	%YMM2,%YMM0

(1109) 0x49d43d INC	%RSI

(1109) 0x49d440 LEA	(%R10,%R13,8),%RAX

(1109) 0x49d444 LEA	(%RBX,%RCX,1),%R13

(1109) 0x49d448 AND	$0x3,%ESI

(1109) 0x49d44b JE	49d592

(1109) 0x49d451 CMP	$0x1,%RSI

(1109) 0x49d455 JE	49d525

(1109) 0x49d45b CMP	$0x2,%RSI

(1109) 0x49d45f JE	49d4c1

(1109) 0x49d461 VMOVUPD	(%RAX),%YMM0

(1109) 0x49d465 VMOVUPD	0x20(%RAX),%YMM20

(1109) 0x49d46c VMOVUPD	0x40(%RAX),%YMM19

(1109) 0x49d473 VMOVUPD	(%RCX),%YMM21

(1109) 0x49d479 ADD	$0x60,%RAX

(1109) 0x49d47d LEA	0x20(%RCX),%RDX

(1109) 0x49d481 VMOVAPD	%YMM0,%YMM1

(1109) 0x49d485 VMOVAPD	%YMM0,%YMM18

(1109) 0x49d48b VPERMT2PD	%YMM20,%YMM5,%YMM0

(1109) 0x49d491 VPERMT2PD	%YMM20,%YMM9,%YMM1

(1109) 0x49d497 VPERMT2PD	%YMM20,%YMM7,%YMM18

(1109) 0x49d49d VPERMT2PD	%YMM19,%YMM4,%YMM0

(1109) 0x49d4a3 VPERMT2PD	%YMM19,%YMM8,%YMM1

(1109) 0x49d4a9 VFMADD132PD	%YMM21,%YMM2,%YMM0

(1109) 0x49d4af VPERMT2PD	%YMM19,%YMM6,%YMM18

(1109) 0x49d4b5 VFMADD132PD	%YMM21,%YMM2,%YMM1

(1109) 0x49d4bb VFMADD231PD	%YMM21,%YMM18,%YMM2

(1109) 0x49d4c1 VMOVUPD	(%RAX),%YMM24

(1109) 0x49d4c7 VMOVUPD	0x20(%RAX),%YMM22

(1109) 0x49d4ce VMOVUPD	0x40(%RAX),%YMM25

(1109) 0x49d4d5 VMOVUPD	(%RDX),%YMM23

(1109) 0x49d4db ADD	$0x60,%RAX

(1109) 0x49d4df ADD	$0x20,%RDX

(1109) 0x49d4e3 VMOVAPD	%YMM24,%YMM26

(1109) 0x49d4e9 VMOVAPD	%YMM24,%YMM27

(1109) 0x49d4ef VPERMT2PD	%YMM22,%YMM5,%YMM24

(1109) 0x49d4f5 VPERMT2PD	%YMM22,%YMM9,%YMM26

(1109) 0x49d4fb VPERMT2PD	%YMM22,%YMM7,%YMM27

(1109) 0x49d501 VPERMT2PD	%YMM25,%YMM4,%YMM24

(1109) 0x49d507 VPERMT2PD	%YMM25,%YMM8,%YMM26

(1109) 0x49d50d VFMADD231PD	%YMM23,%YMM24,%YMM0

(1109) 0x49d513 VPERMT2PD	%YMM25,%YMM6,%YMM27

(1109) 0x49d519 VFMADD231PD	%YMM23,%YMM26,%YMM1

(1109) 0x49d51f VFMADD231PD	%YMM23,%YMM27,%YMM2

(1109) 0x49d525 VMOVUPD	(%RAX),%YMM29

(1109) 0x49d52b VMOVUPD	0x20(%RAX),%YMM30

(1109) 0x49d532 VMOVUPD	0x40(%RAX),%YMM31

(1109) 0x49d539 VMOVUPD	(%RDX),%YMM28

(1109) 0x49d53f ADD	$0x20,%RDX

(1109) 0x49d543 ADD	$0x60,%RAX

(1109) 0x49d547 VMOVAPD	%YMM29,%YMM17

(1109) 0x49d54d VMOVAPD	%YMM29,%YMM16

(1109) 0x49d553 VPERMT2PD	%YMM30,%YMM5,%YMM29

(1109) 0x49d559 VPERMT2PD	%YMM30,%YMM9,%YMM17

(1109) 0x49d55f VPERMT2PD	%YMM30,%YMM7,%YMM16

(1109) 0x49d565 VPERMT2PD	%YMM31,%YMM4,%YMM29

(1109) 0x49d56b VPERMT2PD	%YMM31,%YMM8,%YMM17

(1109) 0x49d571 VFMADD231PD	%YMM28,%YMM29,%YMM0

(1109) 0x49d577 VPERMT2PD	%YMM31,%YMM6,%YMM16

(1109) 0x49d57d VFMADD231PD	%YMM28,%YMM17,%YMM1

(1109) 0x49d583 VFMADD231PD	%YMM28,%YMM16,%YMM2

(1109) 0x49d589 CMP	%RDX,%R13

(1109) 0x49d58c JE	49d717

  (1110) 0x49d592 VMOVUPD	(%RAX),%YMM3

  (1110) 0x49d596 VMOVUPD	0x20(%RAX),%YMM21

  (1110) 0x49d59d VMOVUPD	0x40(%RAX),%YMM20

  (1110) 0x49d5a4 VMOVUPD	(%RDX),%YMM19

  (1110) 0x49d5aa VMOVUPD	0x80(%RAX),%YMM22

  (1110) 0x49d5b1 VMOVUPD	0xa0(%RAX),%YMM25

  (1110) 0x49d5b8 VMOVUPD	0x20(%RDX),%YMM24

  (1110) 0x49d5bf VMOVUPD	0xe0(%RAX),%YMM28

  (1110) 0x49d5c6 VMOVUPD	0x100(%RAX),%YMM29

  (1110) 0x49d5cd VMOVUPD	0x140(%RAX),%YMM16

  (1110) 0x49d5d4 VMOVUPD	0x60(%RDX),%YMM17

  (1110) 0x49d5db SUB	$-0x80,%RDX

  (1110) 0x49d5df ADD	$0x180,%RAX

  (1110) 0x49d5e5 VMOVAPD	%YMM3,%YMM18

  (1110) 0x49d5eb VMOVAPD	%YMM3,%YMM23

  (1110) 0x49d5f1 VPERMT2PD	%YMM21,%YMM5,%YMM3

  (1110) 0x49d5f7 VPERMT2PD	%YMM20,%YMM4,%YMM3

  (1110) 0x49d5fd VPERMT2PD	%YMM21,%YMM9,%YMM18

  (1110) 0x49d603 VPERMT2PD	%YMM21,%YMM7,%YMM23

  (1110) 0x49d609 VFMADD231PD	%YMM19,%YMM3,%YMM0

  (1110) 0x49d60f VMOVUPD	-0x120(%RAX),%YMM3

  (1110) 0x49d617 VPERMT2PD	%YMM20,%YMM8,%YMM18

  (1110) 0x49d61d VPERMT2PD	%YMM20,%YMM6,%YMM23

  (1110) 0x49d623 VFMADD132PD	%YMM19,%YMM1,%YMM18

  (1110) 0x49d629 VFMADD231PD	%YMM19,%YMM23,%YMM2

  (1110) 0x49d62f VMOVUPD	-0x20(%RAX),%YMM19

  (1110) 0x49d636 VMOVAPD	%YMM3,%YMM26

  (1110) 0x49d63c VMOVAPD	%YMM3,%YMM1

  (1110) 0x49d640 VPERMT2PD	%YMM22,%YMM5,%YMM3

  (1110) 0x49d646 VPERMT2PD	%YMM25,%YMM4,%YMM3

  (1110) 0x49d64c VPERMT2PD	%YMM22,%YMM7,%YMM1

  (1110) 0x49d652 VPERMT2PD	%YMM22,%YMM9,%YMM26

  (1110) 0x49d658 VFMADD132PD	%YMM24,%YMM0,%YMM3

  (1110) 0x49d65e VMOVUPD	-0xc0(%RAX),%YMM0

  (1110) 0x49d666 VPERMT2PD	%YMM25,%YMM6,%YMM1

  (1110) 0x49d66c VPERMT2PD	%YMM25,%YMM8,%YMM26

  (1110) 0x49d672 VFMADD132PD	%YMM24,%YMM2,%YMM1

  (1110) 0x49d678 VMOVUPD	-0x40(%RDX),%YMM2

  (1110) 0x49d67d VFMADD132PD	%YMM24,%YMM18,%YMM26

  (1110) 0x49d683 VMOVAPD	%YMM3,%YMM27

  (1110) 0x49d689 VMOVAPD	%YMM0,%YMM30

  (1110) 0x49d68f VMOVAPD	%YMM0,%YMM31

  (1110) 0x49d695 VPERMT2PD	%YMM28,%YMM5,%YMM0

  (1110) 0x49d69b VPERMT2PD	%YMM29,%YMM4,%YMM0

  (1110) 0x49d6a1 VPERMT2PD	%YMM28,%YMM9,%YMM30

  (1110) 0x49d6a7 VPERMT2PD	%YMM28,%YMM7,%YMM31

  (1110) 0x49d6ad VFMADD231PD	%YMM2,%YMM0,%YMM27

  (1110) 0x49d6b3 VMOVUPD	-0x60(%RAX),%YMM0

  (1110) 0x49d6b8 VPERMT2PD	%YMM29,%YMM8,%YMM30

  (1110) 0x49d6be VPERMT2PD	%YMM29,%YMM6,%YMM31

  (1110) 0x49d6c4 VFMADD132PD	%YMM2,%YMM1,%YMM31

  (1110) 0x49d6ca VFMADD132PD	%YMM2,%YMM26,%YMM30

  (1110) 0x49d6d0 VMOVAPD	%YMM0,%YMM1

  (1110) 0x49d6d4 VMOVAPD	%YMM0,%YMM2

  (1110) 0x49d6d8 VPERMT2PD	%YMM16,%YMM5,%YMM0

  (1110) 0x49d6de VPERMT2PD	%YMM16,%YMM9,%YMM1

  (1110) 0x49d6e4 VPERMT2PD	%YMM16,%YMM7,%YMM2

  (1110) 0x49d6ea VPERMT2PD	%YMM19,%YMM4,%YMM0

  (1110) 0x49d6f0 VPERMT2PD	%YMM19,%YMM8,%YMM1

  (1110) 0x49d6f6 VFMADD132PD	%YMM17,%YMM27,%YMM0

  (1110) 0x49d6fc VPERMT2PD	%YMM19,%YMM6,%YMM2

  (1110) 0x49d702 VFMADD132PD	%YMM17,%YMM30,%YMM1

  (1110) 0x49d708 VFMADD132PD	%YMM17,%YMM31,%YMM2

  (1110) 0x49d70e CMP	%RDX,%R13

  (1110) 0x49d711 JNE	49d592

(1109) 0x49d717 VEXTRACTF64X2	$0x1,%YMM2,%XMM21

(1109) 0x49d71e VEXTRACTF64X2	$0x1,%YMM1,%XMM18

(1109) 0x49d725 VADDPD	%XMM2,%XMM21,%XMM20

(1109) 0x49d72b VADDPD	%XMM1,%XMM18,%XMM23

(1109) 0x49d731 VEXTRACTF64X2	$0x1,%YMM0,%XMM24

(1109) 0x49d738 VADDPD	%XMM0,%XMM24,%XMM22

(1109) 0x49d73e MOV	%EDI,%EAX

(1109) 0x49d740 AND	$-0x4,%EAX

(1109) 0x49d743 VUNPCKHPD	%XMM20,%XMM20,%XMM3

(1109) 0x49d749 VUNPCKHPD	%XMM23,%XMM23,%XMM1

(1109) 0x49d74f MOV	%EAX,%EDX

(1109) 0x49d751 VUNPCKHPD	%XMM22,%XMM22,%XMM0

(1109) 0x49d757 VADDPD	%XMM20,%XMM3,%XMM2

(1109) 0x49d75d VADDPD	%XMM23,%XMM1,%XMM3

(1109) 0x49d763 VADDPD	%XMM22,%XMM0,%XMM1

(1109) 0x49d769 VUNPCKLPD	%XMM3,%XMM1,%XMM0

(1109) 0x49d76d CMP	%EDI,%EAX

(1109) 0x49d76f JE	49d820

(1109) 0x49d775 MOV	%EDI,%ESI

(1109) 0x49d777 SUB	%EDX,%ESI

(1109) 0x49d779 CMP	$0x1,%ESI

(1109) 0x49d77c JE	49d7fd

(1109) 0x49d77e LEA	(%RDX,%R11,1),%R13

(1109) 0x49d782 ADD	%R15,%RDX

(1109) 0x49d785 VMOVQ	%XMM2,%XMM2

(1109) 0x49d789 LEA	(%R13,%R13,2),%R13

(1109) 0x49d78e VMOVQ	%R13,%XMM25

(1109) 0x49d794 LEA	(%R10,%R13,8),%R13

(1109) 0x49d798 VMOVQ	%R13,%XMM3

(1109) 0x49d79d MOV	-0xd8(%RBP),%R13

(1109) 0x49d7a4 VMOVUPD	(%R13,%RDX,8),%XMM1

(1109) 0x49d7ab VMOVQ	%XMM25,%RDX

(1109) 0x49d7b1 VMOVQ	%XMM3,%R13

(1109) 0x49d7b6 VPERMILPD	$0x3,%XMM1,%XMM26

(1109) 0x49d7bd VMULPD	0x20(%R10,%RDX,8),%XMM26,%XMM27

(1109) 0x49d7c5 VPERMILPD	$0,%XMM1,%XMM28

(1109) 0x49d7cc VFMADD132PD	0x10(%R13),%XMM2,%XMM1

(1109) 0x49d7d2 VFMADD132PD	(%R13),%XMM0,%XMM28

(1109) 0x49d7d9 VSHUFPD	$0x1,%XMM27,%XMM1,%XMM0

(1109) 0x49d7e0 VUNPCKHPD	%XMM27,%XMM27,%XMM29

(1109) 0x49d7e6 VADDSD	%XMM29,%XMM1,%XMM2

(1109) 0x49d7ec VADDPD	%XMM28,%XMM0,%XMM0

(1109) 0x49d7f2 TEST	$0x1,%SIL

(1109) 0x49d7f6 JE	49d820

(1109) 0x49d7f8 AND	$-0x2,%ESI

(1109) 0x49d7fb ADD	%ESI,%EAX

(1109) 0x49d7fd CLTQ

(1109) 0x49d7ff ADD	%RAX,%R11

(1109) 0x49d802 VMOVDDUP	(%RCX,%RAX,8),%XMM3

(1109) 0x49d807 LEA	(%R11,%R11,2),%R11

(1109) 0x49d80b LEA	(%R10,%R11,8),%R10

(1109) 0x49d80f VMOVSD	0x10(%R10),%XMM1

(1109) 0x49d815 VFMADD231PD	(%R10),%XMM3,%XMM0

(1109) 0x49d81a VFMADD231SD	(%RCX,%RAX,8),%XMM1,%XMM2

(1109) 0x49d820 VUNPCKHPD	%XMM0,%XMM0,%XMM30

(1109) 0x49d826 VMULSD	%XMM2,%XMM2,%XMM17

(1109) 0x49d82c VMULSD	%XMM30,%XMM30,%XMM16

(1109) 0x49d832 VMULSD	%XMM0,%XMM0,%XMM1

(1109) 0x49d836 VADDPD	(%R8),%XMM0,%XMM0

(1109) 0x49d83b VMOVQ	%XMM10,%RAX

(1109) 0x49d840 VADDSD	0x10(%R8),%XMM2,%XMM2

(1109) 0x49d846 VMOVQ	%XMM14,%RSI

(1109) 0x49d84b VMOVSD	%XMM2,0x10(%R8)

(1109) 0x49d851 VMOVQ	%XMM12,%RDX

(1109) 0x49d856 VADDSD	%XMM1,%XMM16,%XMM31

(1109) 0x49d85c ADD	$0x18,%R8

(1109) 0x49d860 VMOVQ	%XMM13,%R13

(1109) 0x49d865 VMOVQ	%XMM15,%R11

(1109) 0x49d86a ADD	%RSI,%RCX

(1109) 0x49d86d ADD	%RDX,%R12

(1109) 0x49d870 ADD	%R13,%R15

(1109) 0x49d873 VMOVUPD	%XMM0,-0x18(%R8)

(1109) 0x49d879 VADDSD	(%RAX,%R9,8),%XMM11,%XMM11

(1109) 0x49d87f VSUBSD	%XMM17,%XMM11,%XMM3

(1109) 0x49d885 VSUBSD	%XMM31,%XMM3,%XMM1

(1109) 0x49d88b VMOVSD	%XMM1,(%RAX,%R9,8)

(1109) 0x49d891 INC	%R9

(1109) 0x49d894 CMP	%R11,%R9

(1109) 0x49d897 JNE	49d230

0x49d89d VZEROUPPER

0x49d8a0 LEA	-0x30(%RBP),%RSP

0x49d8a4 POP	%RBX

0x49d8a5 POP	%RSI

0x49d8a6 POP	%R12

0x49d8a8 POP	%R13

0x49d8aa POP	%R14

0x49d8ac POP	%R15

0x49d8ae POP	%RBP

0x49d8af LEA	-0x8(%RSI),%RSP

0x49d8b3 RET

(1109) 0x49d8b4 MOV	-0xd0(%RBP),%R13

(1109) 0x49d8bb MOV	0x118(%R13),%R11

(1109) 0x49d8c2 MOV	0x140(%R13),%R10

(1109) 0x49d8c9 IMUL	%R9,%R11

(1109) 0x49d8cd CMPL	$0x2,-0xc8(%RBP)

(1109) 0x49d8d4 JA	49d422

(1109) 0x49d8da XOR	%EDX,%EDX

(1109) 0x49d8dc XOR	%EAX,%EAX

(1109) 0x49d8de VXORPD	%XMM0,%XMM0,%XMM0

(1109) 0x49d8e2 VXORPD	%XMM2,%XMM2,%XMM2

(1109) 0x49d8e6 JMP	49d775

(1109) 0x49d8eb MOV	-0xd0(%RBP),%RAX

(1109) 0x49d8f2 MOV	0x118(%RAX),%R11

(1109) 0x49d8f9 MOV	0x140(%RAX),%R10

(1109) 0x49d900 IMUL	%R9,%R11

(1109) 0x49d904 JMP	49d422

(1109) 0x49d909 VXORPD	%XMM1,%XMM1,%XMM1

(1109) 0x49d90d VXORPD	%XMM0,%XMM0,%XMM0

(1109) 0x49d911 VMOVAPD	%XMM1,%XMM17

(1109) 0x49d917 VMOVAPD	%XMM1,%XMM16

(1109) 0x49d91d VMOVAPD	%XMM1,%XMM11

(1109) 0x49d921 VMOVAPD	%XMM1,%XMM2

(1109) 0x49d925 JMP	49d836

(1109) 0x49d92a XOR	%R13D,%R13D

(1109) 0x49d92d VXORPD	%XMM11,%XMM11,%XMM11

(1109) 0x49d932 JMP	49d3ab

0x49d937 MOV	-0xd0(%RBP),%R8

0x49d93e MOV	0x140(%R13),%RBX

0x49d945 MOV	0x100(%R13),%RCX

0x49d94c MOV	-0xe0(%RBP),%R15

0x49d953 LEA	(%R9,%R9,2),%RDI

0x49d957 MOV	0x180(%R13),%RAX

0x49d95e MOV	0x18(%R8),%R12

0x49d962 VMOVSD	(%RCX),%XMM6

0x49d966 VMOVDDUP	%XMM6,%XMM4

0x49d96a VMULPD	(%RBX),%XMM4,%XMM5

0x49d96e MOV	0x18(%R15),%R10

0x49d972 VMULSD	0x10(%RBX),%XMM6,%XMM9

0x49d977 VMULSD	%XMM9,%XMM9,%XMM13

0x49d97c LEA	(%R12,%RDI,8),%R14

0x49d980 VADDPD	(%R14),%XMM5,%XMM10

0x49d985 LEA	(%R10,%R9,8),%R9

0x49d989 VADDSD	0x10(%R14),%XMM9,%XMM12

0x49d98f VMOVSD	%XMM12,0x10(%R14)

0x49d995 VMOVAPD	%XMM5,%XMM8

0x49d999 VUNPCKHPD	%XMM5,%XMM5,%XMM7

0x49d99d VFMADD132SD	%XMM7,%XMM13,%XMM7

0x49d9a2 VMOVUPD	%XMM10,(%R14)

0x49d9a7 VMOVSD	(%R9),%XMM14

0x49d9ac VFMADD132SD	(%RAX),%XMM14,%XMM6

0x49d9b1 VFNMADD132SD	%XMM5,%XMM6,%XMM8

0x49d9b6 VSUBSD	%XMM7,%XMM8,%XMM15

0x49d9ba VMOVSD	%XMM15,(%R9)

0x49d9bf JMP	49d8a0

0x49d9c4 MOV	0x468(%RDI),%RDI

0x49d9cb MOV	%RSI,%R12

0x49d9ce MOV	%R13,-0xc8(%RBP)

0x49d9d5 CALL	531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x49d9da MOV	-0xc8(%RBP),%RSI

0x49d9e1 MOV	0x470(%RSI),%RBX

0x49d9e8 MOV	0x47c(%RSI),%ECX

0x49d9ee MOV	0x478(%RSI),%R15D

0x49d9f5 MOV	(%RBX),%RAX

0x49d9f8 MOV	0x28(%RAX),%R11

0x49d9fc CMP	$0x47dca0,%R11

0x49da03 JNE	49dbe4

0x49da09 CMP	%R15D,%ECX

0x49da0c JLE	49db41

0x49da12 MOV	%ECX,%R14D

0x49da15 XOR	%R13D,%R13D

0x49da18 SUB	%R15D,%R14D

0x49da1b NOPL	(%RAX,%RAX,1)

(1112) 0x49da20 MOV	0x98(%RSI),%R8

(1112) 0x49da27 MOV	0xc0(%RSI),%R9

(1112) 0x49da2e MOV	0x118(%RSI),%RCX

(1112) 0x49da35 MOV	0x140(%RSI),%R11

(1112) 0x49da3c MOVSXD	0x8(%RBX),%RDI

(1112) 0x49da40 MOVQ	$0x5bf788,-0xc0(%RBP)

(1112) 0x49da4b MOVQ	$0x5beb98,-0x90(%RBP)

(1112) 0x49da56 MOVQ	$0x5bf788,-0x60(%RBP)

(1112) 0x49da5e MOV	%RSI,-0xc8(%RBP)

(1112) 0x49da65 MOVQ	$0,-0xb0(%RBP)

(1112) 0x49da70 MOVQ	$0,-0x80(%RBP)

(1112) 0x49da78 MOVQ	$0,-0x50(%RBP)

(1112) 0x49da80 IMUL	%R13,%R8

(1112) 0x49da84 IMUL	%R13,%RCX

(1112) 0x49da88 MOV	%RDI,-0xb8(%RBP)

(1112) 0x49da8f MOV	%RDI,-0x88(%RBP)

(1112) 0x49da96 MOV	%RDI,-0x58(%RBP)

(1112) 0x49da9a MOV	%RBX,%RDI

(1112) 0x49da9d LEA	(%R9,%R8,8),%R10

(1112) 0x49daa1 MOV	0x158(%RSI),%R8

(1112) 0x49daa8 MOV	0x180(%RSI),%R9

(1112) 0x49daaf MOV	%R10,-0xa8(%RBP)

(1112) 0x49dab6 MOV	(%RBX),%R10

(1112) 0x49dab9 LEA	(%RCX,%RCX,2),%RAX

(1112) 0x49dabd LEA	-0xc0(%RBP),%RCX

(1112) 0x49dac4 LEA	(%R11,%RAX,8),%RDX

(1112) 0x49dac8 MOV	%RDX,-0x78(%RBP)

(1112) 0x49dacc LEA	(%R15,%R13,1),%EDX

(1112) 0x49dad0 IMUL	%R13,%R8

(1112) 0x49dad4 LEA	(%R9,%R8,8),%RSI

(1112) 0x49dad8 LEA	-0x60(%RBP),%R9

(1112) 0x49dadc LEA	-0x90(%RBP),%R8

(1112) 0x49dae3 MOV	%RSI,-0x48(%RBP)

(1112) 0x49dae7 MOV	%R12,%RSI

(1112) 0x49daea CALLQ	0x18(%R10)

(1112) 0x49daee MOV	-0x50(%RBP),%RDI

(1112) 0x49daf2 MOV	-0xc8(%RBP),%RSI

(1112) 0x49daf9 MOVQ	$0x5bf788,-0x60(%RBP)

(1112) 0x49db01 TEST	%RDI,%RDI

(1112) 0x49db04 JNE	49dbb4

(1112) 0x49db0a MOV	-0x80(%RBP),%RCX

(1112) 0x49db0e MOVQ	$0x5beb98,-0x90(%RBP)

(1112) 0x49db19 TEST	%RCX,%RCX

(1112) 0x49db1c JNE	49db90

(1112) 0x49db1e MOV	-0xb0(%RBP),%RAX

(1112) 0x49db25 MOVQ	$0x5bf788,-0xc0(%RBP)

(1112) 0x49db30 TEST	%RAX,%RAX

(1112) 0x49db33 JNE	49db60

(1112) 0x49db35 INC	%R13

(1112) 0x49db38 CMP	%R14,%R13

(1112) 0x49db3b JNE	49da20

0x49db41 MOV	0x468(%RSI),%RDI

0x49db48 MOV	%RSI,-0xc8(%RBP)

0x49db4f CALL	531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x49db54 MOV	-0xc8(%RBP),%R13

0x49db5b JMP	49d13f

(1112) 0x49db60 MOV	-0xa8(%RBP),%RDI

(1112) 0x49db67 MOV	%RSI,-0xc8(%RBP)

(1112) 0x49db6e INC	%R13

(1112) 0x49db71 LEA	(,%RAX,8),%RSI

(1112) 0x49db79 CALL	404070 <_ZdlPvm@plt>

(1112) 0x49db7e CMP	%R14,%R13

(1112) 0x49db81 MOV	-0xc8(%RBP),%RSI

(1112) 0x49db88 JNE	49da20

0x49db8e JMP	49db41

(1112) 0x49db90 MOV	-0x78(%RBP),%RDI

(1112) 0x49db94 MOV	%RSI,-0xc8(%RBP)

(1112) 0x49db9b LEA	(%RCX,%RCX,2),%RSI

(1112) 0x49db9f SAL	$0x3,%RSI

(1112) 0x49dba3 CALL	404070 <_ZdlPvm@plt>

(1112) 0x49dba8 MOV	-0xc8(%RBP),%RSI

(1112) 0x49dbaf JMP	49db1e

(1112) 0x49dbb4 LEA	(,%RDI,8),%RSI

(1112) 0x49dbbc MOV	-0x48(%RBP),%RDI

(1112) 0x49dbc0 CALL	404070 <_ZdlPvm@plt>

(1112) 0x49dbc5 MOV	-0xc8(%RBP),%RSI

(1112) 0x49dbcc JMP	49db0a

(1109) 0x49dbd1 MOV	%EDI,%ESI

(1109) 0x49dbd3 XOR	%EAX,%EAX

(1109) 0x49dbd5 XOR	%EDX,%EDX

(1109) 0x49dbd7 VXORPD	%XMM0,%XMM0,%XMM0

(1109) 0x49dbdb VXORPD	%XMM2,%XMM2,%XMM2

(1109) 0x49dbdf JMP	49d77e

0x49dbe4 SUB	$0x8,%RSP

0x49dbe8 LEA	0x150(%RSI),%RDX

0x49dbef LEA	0x110(%RSI),%R9

0x49dbf6 LEA	0x90(%RSI),%R8

0x49dbfd PUSH	%RDX

0x49dbfe MOV	%RBX,%RDI

0x49dc01 MOV	%R15D,%EDX

0x49dc04 MOV	%RSI,-0xc8(%RBP)

0x49dc0b MOV	%R12,%RSI

0x49dc0e CALL	%R11

0x49dc11 POP	%RAX

0x49dc12 MOV	-0xc8(%RBP),%RSI

0x49dc19 POP	%RDX

0x49dc1a JMP	49db41

0x49dc1f MOV	%RAX,%R12

0x49dc22 MOV	-0x50(%RBP),%RBX

0x49dc26 MOVQ	$0x5bf788,-0x60(%RBP)

0x49dc2e TEST	%RBX,%RBX

0x49dc31 JE	49dc9b

0x49dc33 MOV	-0x48(%RBP),%RDI

0x49dc37 LEA	(,%RBX,8),%RSI

0x49dc3f VZEROUPPER

0x49dc42 CALL	404070 <_ZdlPvm@plt>

(1108) 0x49dc47 MOV	-0x80(%RBP),%R15

(1108) 0x49dc4b MOVQ	$0x5beb98,-0x90(%RBP)

(1108) 0x49dc56 TEST	%R15,%R15

(1108) 0x49dc59 JE	49dc68

(1108) 0x49dc5b MOV	-0x78(%RBP),%RDI

(1108) 0x49dc5f IMUL	$0x18,%R15,%RSI

(1108) 0x49dc63 CALL	404070 <_ZdlPvm@plt>

(1108) 0x49dc68 MOV	-0xb0(%RBP),%R14

(1108) 0x49dc6f MOVQ	$0x5bf788,-0xc0(%RBP)

(1108) 0x49dc7a TEST	%R14,%R14

(1108) 0x49dc7d JE	49dc93

(1108) 0x49dc7f MOV	-0xa8(%RBP),%RDI

(1108) 0x49dc86 LEA	(,%R14,8),%RSI

(1108) 0x49dc8e CALL	404070 <_ZdlPvm@plt>

(1108) 0x49dc93 MOV	%R12,%RDI

(1108) 0x49dc96 CALL	404240 <_Unwind_Resume@plt>

(1108) 0x49dc9b VZEROUPPER

(1108) 0x49dc9e JMP	49dc47

Coverage (%)	Name	Source Location	Module
►48.60+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:250	exec
○	main._omp_fn.1	miniqmc.cpp:469	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►48.11+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:249	exec
○	main._omp_fn.1	miniqmc.cpp:469	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

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:152-181
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h:217
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h:129-131
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:82-83,155-156
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h:106-111
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:56,144,210,221-223,248
/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/new_allocator.h:104,172
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,92-94
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:152-181

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 19.00 to 6.00 cycles (3.17x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 17% of vector register length is used (average across all SSE/AVX instructions).

Details

24% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

53% of SSE/AVX loads are used in vector version.
8% of SSE/AVX stores are used in vector version.
33% of SSE/AVX addition or subtraction instructions are used in vector version.
33% of SSE/AVX multiply instructions are used in vector version.
0% of SSE/AVX fused multiply-add instructions are used in vector version.
16% 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 3 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.

operator delete(void*, unsigned long): 1 occurrences►
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/new_allocator.h:172
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:159
qmcplusplus::TimerType
::stop(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:161
unknown: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:160

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

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

PUSH: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:152

Type of elements and instruction set

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

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

The binary function is composed of 14 FP arithmetical operations:

7: addition or subtraction (3 inside FMA instructions)
7: multiply (3 inside FMA instructions)

The binary function is loading 496 bytes (62 double precision FP elements). The binary function is storing 100 bytes (12 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.02 FP operations per loaded or stored byte.

General properties

nb instructions	148
nb uops	152
loop length	692
used x86 registers	16
used mmx registers	0
used xmm registers	12
used ymm registers	6
used zmm registers	0
nb stack references	9
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	19.00 cycles
front end	19.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.17	8.17	8.17	8.17	8.17	8.17	15.25	15.25	15.25	15.25	3.00	3.00	2.50	2.50	2.50	2.50
cycles	8.17	8.17	8.17	8.17	8.17	8.17	15.25	15.25	15.25	15.25	3.00	3.00	2.50	2.50	2.50	2.50

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	19.00
Dispatch	15.25
Overall L1	19.00

Vectorization ratios

INT

all	25%
load	75%
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	13%

all	23%
load	28%
store	33%
mul	33%
add-sub	33%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	33%

INT+FP

all	24%
load	53%
store	8%
mul	33%
add-sub	33%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Vector efficiency ratios

INT

all	18%
load	40%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	15%
load	16%
store	16%
mul	16%
add-sub	16%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

INT+FP

all	17%
load	29%
store	12%
mul	16%
add-sub	16%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 19.00 cycles. At this rate:

10% of peak load performance is reached (26.11 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.26 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 19.00 to 15.25 cycles (1.25x speedup).

ASM code

In the binary file, the address of the function is: 49d100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
LEA 0x8(%RSP),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND $-0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSHQ -0x8(%R10)	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.71	N/A
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RDI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0xc0,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0xc(%RDI),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDX,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %ECX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 49d9c4 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8c4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x484(%R13),%R11D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSXD 0x478(%R13),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
CMP $0x1,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 49d937 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x837>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD %R11D,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
VMOVQ %RDX,%XMM15	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
TEST %R11D,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 49d8a0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7a0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVQ 0xd8(%R13),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0xe0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xd0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x480(%R13),%EDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x158(%R13),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVQ 0x180(%R13),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x100(%R13),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVDQA 0x1236fb(%RIP),%YMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x123713(%RIP),%YMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x12372b(%RIP),%YMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
LEA (%R9,%R9,2),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R13,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMOVDQA 0x123738(%RIP),%YMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x123170(%RIP),%YMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x123188(%RIP),%YMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
MOV 0x18(%RAX),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RSI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA -0x1(%RDI),%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVQ %XMM13,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %R14D,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
MOV %R10,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
SAL $0x3,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
VMOVQ %XMM11,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVQ %RBX,%XMM14	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
MOV %EDI,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%EBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
SAL $0x3,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%R11,%R9,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R12,%R8,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVQ %R15,%XMM12	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
SAL $0x5,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
VMOVQ %R9,%XMM10	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x30(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA -0x8(%RSI),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV -0xd0(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x140(%R13),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x100(%R13),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xe0(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%R9,%R9,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV 0x180(%R13),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%R8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVSD (%RCX),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDDUP %XMM6,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULPD (%RBX),%XMM4,%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
MOV 0x18(%R15),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMULSD 0x10(%RBX),%XMM6,%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMULSD %XMM9,%XMM9,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
LEA (%R12,%RDI,8),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VADDPD (%R14),%XMM5,%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
LEA (%R10,%R9,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VADDSD 0x10(%R14),%XMM9,%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM12,0x10(%R14)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVAPD %XMM5,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUNPCKHPD %XMM5,%XMM5,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VFMADD132SD %XMM7,%XMM13,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVUPD %XMM10,(%R14)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD (%R9),%XMM14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD132SD (%RAX),%XMM14,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFNMADD132SD %XMM5,%XMM6,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VSUBSD %XMM7,%XMM8,%XMM15	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM15,(%R9)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JMP 49d8a0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7a0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV 0x468(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0xc8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x470(%RSI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x47c(%RSI),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x478(%RSI),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x28(%RAX),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP $0x47dca0,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 49dbe4 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xae4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP %R15D,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 49db41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa41>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %ECX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
SUB %R15D,%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV 0x468(%RSI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RSI,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0xc8(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JMP 49d13f <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x3f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
JMP 49db41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa41>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x150(%RSI),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x110(%RSI),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x90(%RSI),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
PUSH %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15D,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV %RSI,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL %R11	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	2	N/A
POP %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV -0xc8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
POP %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
JMP 49db41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa41>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x50(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVQ $0x5bf788,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
TEST %RBX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 49dc9b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb9b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x48(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (,%RBX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	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:152-181
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h:217
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h:129-131
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:62
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:82-83,155-156
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h:106-111
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:56,144,210,221-223,248
/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/new_allocator.h:104,172
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,92-94
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:152-181

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 19.00 to 6.00 cycles (3.17x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 17% of vector register length is used (average across all SSE/AVX instructions).

Details

24% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

53% of SSE/AVX loads are used in vector version.
8% of SSE/AVX stores are used in vector version.
33% of SSE/AVX addition or subtraction instructions are used in vector version.
33% of SSE/AVX multiply instructions are used in vector version.
0% of SSE/AVX fused multiply-add instructions are used in vector version.
16% 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 3 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

CALL instructions

Detected function call instructions.

Details

operator delete(void*, unsigned long): 1 occurrences►
- /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/new_allocator.h:172
qmcplusplus::TimerType
::start(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:159
qmcplusplus::TimerType
::stop(): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:161
unknown: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:160

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

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

PUSH: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:152

Type of elements and instruction set

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

The binary function is composed of 14 FP arithmetical operations:

7: addition or subtraction (3 inside FMA instructions)
7: multiply (3 inside FMA instructions)

The binary function is loading 496 bytes (62 double precision FP elements). The binary function is storing 100 bytes (12 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.02 FP operations per loaded or stored byte.

General properties

nb instructions	148
nb uops	152
loop length	692
used x86 registers	16
used mmx registers	0
used xmm registers	12
used ymm registers	6
used zmm registers	0
nb stack references	9
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	19.00 cycles
front end	19.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.17	8.17	8.17	8.17	8.17	8.17	15.25	15.25	15.25	15.25	3.00	3.00	2.50	2.50	2.50	2.50
cycles	8.17	8.17	8.17	8.17	8.17	8.17	15.25	15.25	15.25	15.25	3.00	3.00	2.50	2.50	2.50	2.50

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	19.00
Dispatch	15.25
Overall L1	19.00

Vectorization ratios

INT

all	25%
load	75%
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	13%

all	23%
load	28%
store	33%
mul	33%
add-sub	33%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	33%

INT+FP

all	24%
load	53%
store	8%
mul	33%
add-sub	33%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Vector efficiency ratios

INT

all	18%
load	40%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	15%
load	16%
store	16%
mul	16%
add-sub	16%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

INT+FP

all	17%
load	29%
store	12%
mul	16%
add-sub	16%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 19.00 cycles. At this rate:

10% of peak load performance is reached (26.11 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.26 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: 49d100

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
LEA 0x8(%RSP),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
AND $-0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSHQ -0x8(%R10)	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.71	N/A
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RDI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB $0xc0,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0xc(%RDI),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDX,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %ECX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 49d9c4 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x8c4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x484(%R13),%R11D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSXD 0x478(%R13),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
CMP $0x1,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 49d937 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x837>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD %R11D,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
VMOVQ %RDX,%XMM15	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
TEST %R11D,%R11D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 49d8a0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7a0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVQ 0xd8(%R13),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0xe0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xd0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x480(%R13),%EDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x158(%R13),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVQ 0x180(%R13),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x100(%R13),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVDQA 0x1236fb(%RIP),%YMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x123713(%RIP),%YMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x12372b(%RIP),%YMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
LEA (%R9,%R9,2),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R13,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
VMOVDQA 0x123738(%RIP),%YMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x123170(%RIP),%YMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMOVDQA 0x123188(%RIP),%YMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (50.0%)
MOV 0x18(%RAX),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RSI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA -0x1(%RDI),%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVQ %XMM13,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %R14D,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
MOV %R10,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
SAL $0x3,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
VMOVQ %XMM11,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVQ %RBX,%XMM14	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
MOV %EDI,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%EBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
SAL $0x3,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%R11,%R9,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R12,%R8,8),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVQ %R15,%XMM12	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
SAL $0x5,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
VMOVQ %R9,%XMM10	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x30(%RBP),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA -0x8(%RSI),%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV -0xd0(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x140(%R13),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x100(%R13),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xe0(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%R9,%R9,2),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV 0x180(%R13),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%R8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMOVSD (%RCX),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDDUP %XMM6,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VMULPD (%RBX),%XMM4,%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
MOV 0x18(%R15),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
VMULSD 0x10(%RBX),%XMM6,%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VMULSD %XMM9,%XMM9,%XMM13	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
LEA (%R12,%RDI,8),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VADDPD (%R14),%XMM5,%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
LEA (%R10,%R9,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VADDSD 0x10(%R14),%XMM9,%XMM12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM12,0x10(%R14)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVAPD %XMM5,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VUNPCKHPD %XMM5,%XMM5,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
VFMADD132SD %XMM7,%XMM13,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VMOVUPD %XMM10,(%R14)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
VMOVSD (%R9),%XMM14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VFMADD132SD (%RAX),%XMM14,%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VFNMADD132SD %XMM5,%XMM6,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	4	0.50	scal (12.5%)
VSUBSD %XMM7,%XMM8,%XMM15	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM15,(%R9)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
JMP 49d8a0 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x7a0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV 0x468(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 531880 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0xc8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x470(%RSI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x47c(%RSI),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x478(%RSI),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RBX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x28(%RAX),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP $0x47dca0,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JNE 49dbe4 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xae4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP %R15D,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 49db41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa41>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %ECX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
SUB %R15D,%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV 0x468(%RSI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RSI,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CALL 531ac0 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
MOV -0xc8(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JMP 49d13f <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x3f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
JMP 49db41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa41>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x150(%RSI),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x110(%RSI),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x90(%RSI),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
PUSH %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15D,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
MOV %RSI,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL %R11	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	2	N/A
POP %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV -0xc8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
POP %RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
JMP 49db41 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xa41>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x50(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVQ $0x5bf788,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
TEST %RBX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 49dc9b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xb9b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x48(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (,%RBX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404070 <_ZdlPvm@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::DiracDeterminantRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus:...–	0.63	1.04
▼Loop 1109 - DiracDeterminantRef.cpp:173-178 - exec–	0.00	0.01
○Loop 1110 - inner_product.hpp:155-155 - exec	0.38	0.62
○Loop 1111 - inner_product.hpp:82-83 - exec	0.25	0.40
○Loop 1108 - new_allocator.h:104-172 - exec	0.00	0.00
○Loop 1112 - SPOSet.h:106-111 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

FMA

Workaround

CALL instructions

Details

Complex instructions

Details

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

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