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:156-181 [...]	Coverage (incl. loops): 0.62% \| (excl. loops): 0.00%

/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/Platforms/CPU/SIMD/inner_product.hpp: 82 - 155

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

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

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

[...]

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223

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

223:     return X[i];

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h: 173 - 173

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

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 63 - 94

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

63:     return (a * b);

[...]

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

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp: 156 - 181

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

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: }

0x2751c0 PUSH	%RBP

0x2751c1 MOV	%RSP,%RBP

0x2751c4 PUSH	%R15

0x2751c6 PUSH	%R14

0x2751c8 PUSH	%R13

0x2751ca PUSH	%R12

0x2751cc PUSH	%RBX

0x2751cd SUB	$0x38,%RSP

0x2751d1 CMPL	$0,0xc(%RDI)

0x2751d5 MOV	%RCX,%RBX

0x2751d8 MOV	%RDX,%R15

0x2751db MOV	%RDI,%R14

0x2751de JNE	275233

0x2751e0 MOV	0x468(%R14),%RDI

0x2751e7 MOV	%RSI,%R12

0x2751ea CALL	2a2310 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv>

0x2751ef MOV	0x470(%R14),%RDI

0x2751f6 MOV	0x478(%R14),%EDX

0x2751fd MOV	0x47c(%R14),%ECX

0x275204 LEA	0x90(%R14),%R8

0x27520b LEA	0x110(%R14),%R9

0x275212 LEA	0x150(%R14),%RAX

0x275219 MOV	%R12,%RSI

0x27521c MOV	(%RDI),%R10

0x27521f MOV	%RAX,(%RSP)

0x275223 CALLQ	0x28(%R10)

0x275227 MOV	0x468(%R14),%RDI

0x27522e CALL	2a2400 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv>

0x275233 MOVSXD	0x484(%R14),%RAX

0x27523a TEST	%RAX,%RAX

0x27523d JE	275945

0x275243 CMP	$0x1,%EAX

0x275246 JNE	2752b9

0x275248 MOV	0x100(%R14),%RAX

0x27524f MOV	0x140(%R14),%RCX

0x275256 MOV	0x18(%R15),%RDX

0x27525a VMOVDDUP	(%RAX),%XMM0

0x27525e MOVSXD	0x478(%R14),%RAX

0x275265 VMULPD	(%RCX),%XMM0,%XMM2

0x275269 VMULSD	0x10(%RCX),%XMM0,%XMM1

0x27526e LEA	(%RAX,%RAX,2),%RSI

0x275272 VADDPD	(%RDX,%RSI,8),%XMM2,%XMM3

0x275277 VMULPD	%XMM2,%XMM2,%XMM2

0x27527b VMOVUPD	%XMM3,(%RDX,%RSI,8)

0x275280 VADDSD	0x10(%RDX,%RSI,8),%XMM1,%XMM3

0x275286 VMOVSD	%XMM3,0x10(%RDX,%RSI,8)

0x27528c VSHUFPD	$0x1,%XMM2,%XMM2,%XMM3

0x275291 MOV	0x180(%R14),%RCX

0x275298 VADDSD	%XMM2,%XMM3,%XMM2

0x27529c MOV	0x18(%RBX),%RDX

0x2752a0 VFMADD231SD	%XMM1,%XMM1,%XMM2

0x2752a5 VFMSUB231SD	(%RCX),%XMM0,%XMM2

0x2752aa VADDSD	(%RDX,%RAX,8),%XMM2,%XMM0

0x2752af VMOVSD	%XMM0,(%RDX,%RAX,8)

0x2752b4 JMP	275945

0x2752b9 MOV	0x480(%R14),%ECX

0x2752c0 TEST	%ECX,%ECX

0x2752c2 JLE	275940

0x2752c8 MOV	0x18(%RBX),%RBX

0x2752cc MOV	0x118(%R14),%RDX

0x2752d3 VMOVAPD	-0x70cbb(%RIP),%YMM1

0x2752db VMOVAPD	-0x70c43(%RIP),%YMM2

0x2752e3 VMOVAPD	-0x70ceb(%RIP),%YMM3

0x2752eb VMOVAPD	-0x6a2b5(%RIP),%ZMM4

0x2752f5 VMOVAPD	-0x6a27f(%RIP),%ZMM5

0x2752ff VMOVAPD	-0x6a249(%RIP),%ZMM6

0x275309 VMOVAPD	-0x6a213(%RIP),%ZMM7

0x275313 VMOVAPD	-0x6a1dd(%RIP),%ZMM8

0x27531d VMOVAPD	-0x6a1a7(%RIP),%ZMM9

0x275327 MOV	0x158(%R14),%R11

0x27532e MOV	0xd8(%R14),%R9

0x275335 MOV	0x100(%R14),%RSI

0x27533c MOV	0x180(%R14),%RDI

0x275343 MOV	0x18(%R15),%R10

0x275347 MOV	0x140(%R14),%R8

0x27534e MOV	%ECX,%R13D

0x275351 SHR	$0x5,%R13D

0x275355 MOV	%ECX,%R15D

0x275358 AND	$-0x4,%R15D

0x27535c VXORPD	%XMM24,%XMM24,%XMM24

0x275362 SAL	$0x8,%R13

0x275366 MOV	%RBX,-0x40(%RBP)

0x27536a MOVSXD	0x478(%R14),%RBX

0x275371 SAL	$0x3,%RDX

0x275375 SAL	$0x3,%R11

0x275379 MOV	%ECX,%R14D

0x27537c AND	$-0x20,%R14D

0x275380 SAL	$0x3,%R9

0x275384 LEA	0xc0(%RSI),%R12

0x27538b LEA	(%RDX,%RDX,2),%RDX

0x27538f MOV	%R11,-0x48(%RBP)

0x275393 LEA	0xc0(%RDI),%R11

0x27539a MOV	%R14,-0x30(%RBP)

0x27539e XOR	%R14D,%R14D

0x2753a1 MOV	%R9,-0x50(%RBP)

0x2753a5 MOV	%RDX,-0x38(%RBP)

0x2753a9 JMP	27541f

0x2753ab NOPL	(%RAX,%RAX,1)

(1071) 0x2753b0 LEA	(%RBX,%RBX,2),%RDX

(1071) 0x2753b4 MOV	-0x48(%RBP),%R9

(1071) 0x2753b8 ADD	-0x38(%RBP),%R8

(1071) 0x2753bc INC	%R14

(1071) 0x2753bf VADDPD	(%R10,%RDX,8),%XMM11,%XMM12

(1071) 0x2753c5 ADD	%R9,%R11

(1071) 0x2753c8 ADD	%R9,%RDI

(1071) 0x2753cb VMOVUPD	%XMM12,(%R10,%RDX,8)

(1071) 0x2753d1 VADDSD	0x10(%R10,%RDX,8),%XMM0,%XMM12

(1071) 0x2753d8 VBLENDPD	$0x1,%XMM0,%XMM11,%XMM0

(1071) 0x2753de VMULPD	%XMM0,%XMM0,%XMM0

(1071) 0x2753e2 VMOVSD	%XMM12,0x10(%R10,%RDX,8)

(1071) 0x2753e9 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM12

(1071) 0x2753ee MOV	-0x40(%RBP),%RDX

(1071) 0x2753f2 VFMADD231SD	%XMM11,%XMM11,%XMM12

(1071) 0x2753f7 VADDSD	%XMM0,%XMM12,%XMM0

(1071) 0x2753fb VSUBSD	%XMM0,%XMM10,%XMM0

(1071) 0x2753ff VADDSD	(%RDX,%RBX,8),%XMM0,%XMM0

(1071) 0x275404 VMOVSD	%XMM0,(%RDX,%RBX,8)

(1071) 0x275409 MOV	-0x50(%RBP),%RDX

(1071) 0x27540d INC	%RBX

(1071) 0x275410 ADD	%RDX,%R12

(1071) 0x275413 ADD	%RDX,%RSI

(1071) 0x275416 CMP	%RAX,%R14

(1071) 0x275419 JE	275945

(1071) 0x27541f CMP	$0x4,%ECX

(1071) 0x275422 JAE	275430

(1071) 0x275424 VXORPD	%XMM10,%XMM10,%XMM10

(1071) 0x275429 XOR	%EDX,%EDX

(1071) 0x27542b JMP	275540

(1071) 0x275430 CMP	$0x20,%ECX

(1071) 0x275433 JAE	275450

(1071) 0x275435 VXORPD	%XMM10,%XMM10,%XMM10

(1071) 0x27543a XOR	%R9D,%R9D

(1071) 0x27543d JMP	2754fd

0x275442 NOPW	%CS:(%RAX,%RAX,1)

(1071) 0x275450 VXORPD	%XMM0,%XMM0,%XMM0

(1071) 0x275454 VXORPD	%XMM10,%XMM10,%XMM10

(1071) 0x275459 VXORPD	%XMM11,%XMM11,%XMM11

(1071) 0x27545e VXORPD	%XMM12,%XMM12,%XMM12

(1071) 0x275463 XOR	%EDX,%EDX

(1071) 0x275465 NOPW	%CS:(%RAX,%RAX,1)

  (1069) 0x275470 VMOVUPD	-0xc0(%R11,%RDX,1),%ZMM13

  (1069) 0x275478 VMOVUPD	-0x80(%R11,%RDX,1),%ZMM14

  (1069) 0x275480 VMOVUPD	-0x40(%R11,%RDX,1),%ZMM15

  (1069) 0x275488 VMOVUPD	(%R11,%RDX,1),%ZMM16

  (1069) 0x27548f VFMADD231PD	-0xc0(%R12,%RDX,1),%ZMM13,%ZMM0

  (1069) 0x275497 VFMADD231PD	-0x80(%R12,%RDX,1),%ZMM14,%ZMM10

  (1069) 0x27549f VFMADD231PD	-0x40(%R12,%RDX,1),%ZMM15,%ZMM11

  (1069) 0x2754a7 VFMADD231PD	(%R12,%RDX,1),%ZMM16,%ZMM12

  (1069) 0x2754ae ADD	$0x100,%RDX

  (1069) 0x2754b5 CMP	%RDX,%R13

  (1069) 0x2754b8 JNE	275470

(1071) 0x2754ba VADDPD	%ZMM0,%ZMM10,%ZMM0

(1071) 0x2754c0 VADDPD	%ZMM11,%ZMM12,%ZMM11

(1071) 0x2754c6 MOV	-0x30(%RBP),%RDX

(1071) 0x2754ca VADDPD	%ZMM0,%ZMM11,%ZMM0

(1071) 0x2754d0 VEXTRACTF64X4	$0x1,%ZMM0,%YMM10

(1071) 0x2754d7 VADDPD	%ZMM10,%ZMM0,%ZMM0

(1071) 0x2754dd VEXTRACTF128	$0x1,%YMM0,%XMM10

(1071) 0x2754e3 VADDPD	%XMM0,%XMM10,%XMM0

(1071) 0x2754e7 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM10

(1071) 0x2754ec VADDSD	%XMM0,%XMM10,%XMM10

(1071) 0x2754f0 CMP	%RCX,%RDX

(1071) 0x2754f3 JE	275553

(1071) 0x2754f5 MOV	%RDX,%R9

(1071) 0x2754f8 TEST	$0x1c,%CL

(1071) 0x2754fb JE	275540

(1071) 0x2754fd VMOVQ	%XMM10,%XMM0

(1071) 0x275501 NOPW	%CS:(%RAX,%RAX,1)

  (1075) 0x275510 VMOVUPD	(%RDI,%R9,8),%YMM10

  (1075) 0x275516 VFMADD231PD	(%RSI,%R9,8),%YMM10,%YMM0

  (1075) 0x27551c ADD	$0x4,%R9

  (1075) 0x275520 CMP	%R9,%R15

  (1075) 0x275523 JNE	275510

(1071) 0x275525 VEXTRACTF128	$0x1,%YMM0,%XMM10

(1071) 0x27552b MOV	%R15,%RDX

(1071) 0x27552e VADDPD	%XMM0,%XMM10,%XMM0

(1071) 0x275532 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM10

(1071) 0x275537 VADDSD	%XMM0,%XMM10,%XMM10

(1071) 0x27553b CMP	%RCX,%R15

(1071) 0x27553e JE	275553

  (1074) 0x275540 VMOVSD	(%RDI,%RDX,8),%XMM0

  (1074) 0x275545 VFMADD231SD	(%RSI,%RDX,8),%XMM0,%XMM10

  (1074) 0x27554b INC	%RDX

  (1074) 0x27554e CMP	%RDX,%RCX

  (1074) 0x275551 JNE	275540

(1071) 0x275553 CMP	$0x4,%ECX

(1071) 0x275556 JAE	275570

(1071) 0x275558 VXORPD	%XMM11,%XMM11,%XMM11

(1071) 0x27555d XOR	%R9D,%R9D

(1071) 0x275560 JMP	2758fc

0x275565 NOPW	%CS:(%RAX,%RAX,1)

(1071) 0x275570 CMP	$0x20,%ECX

(1071) 0x275573 JAE	275590

(1071) 0x275575 VXORPD	%XMM11,%XMM11,%XMM11

(1071) 0x27557a XOR	%EDX,%EDX

(1071) 0x27557c JMP	275841

0x275581 NOPW	%CS:(%RAX,%RAX,1)

(1071) 0x275590 VXORPD	%XMM11,%XMM11,%XMM11

(1071) 0x275595 VXORPD	%XMM12,%XMM12,%XMM12

(1071) 0x27559a VXORPD	%XMM13,%XMM13,%XMM13

(1071) 0x27559f VXORPD	%XMM14,%XMM14,%XMM14

(1071) 0x2755a4 VXORPD	%XMM15,%XMM15,%XMM15

(1071) 0x2755a9 VXORPD	%XMM16,%XMM16,%XMM16

(1071) 0x2755af VXORPD	%XMM17,%XMM17,%XMM17

(1071) 0x2755b5 VXORPD	%XMM18,%XMM18,%XMM18

(1071) 0x2755bb VXORPD	%XMM19,%XMM19,%XMM19

(1071) 0x2755c1 VXORPD	%XMM20,%XMM20,%XMM20

(1071) 0x2755c7 VXORPD	%XMM21,%XMM21,%XMM21

(1071) 0x2755cd VXORPD	%XMM22,%XMM22,%XMM22

(1071) 0x2755d3 XOR	%EDX,%EDX

(1071) 0x2755d5 MOV	%R8,%R9

(1071) 0x2755d8 NOPL	(%RAX,%RAX,1)

  (1070) 0x2755e0 VMOVUPD	(%R9),%ZMM0

  (1070) 0x2755e6 VMOVUPD	0x40(%R9),%ZMM23

  (1070) 0x2755ed VMOVUPD	0x80(%R9),%ZMM28

  (1070) 0x2755f4 VMOVUPD	-0xc0(%R12,%RDX,1),%ZMM27

  (1070) 0x2755fc VMOVUPD	-0x80(%R12,%RDX,1),%ZMM29

  (1070) 0x275604 VMOVAPD	%ZMM0,%ZMM25

  (1070) 0x27560a VPERMT2PD	%ZMM23,%ZMM4,%ZMM25

  (1070) 0x275610 VMOVAPD	%ZMM0,%ZMM26

  (1070) 0x275616 VPERMT2PD	%ZMM23,%ZMM6,%ZMM26

  (1070) 0x27561c VPERMT2PD	%ZMM0,%ZMM8,%ZMM23

  (1070) 0x275622 VPERMT2PD	%ZMM28,%ZMM5,%ZMM25

  (1070) 0x275628 VPERMT2PD	%ZMM28,%ZMM7,%ZMM26

  (1070) 0x27562e VPERMT2PD	%ZMM28,%ZMM9,%ZMM23

  (1070) 0x275634 VMOVUPD	0xc0(%R9),%ZMM28

  (1070) 0x27563b VFMADD231PD	%ZMM25,%ZMM27,%ZMM11

  (1070) 0x275641 VMOVUPD	0x100(%R9),%ZMM25

  (1070) 0x275648 VFMADD231PD	%ZMM23,%ZMM27,%ZMM19

  (1070) 0x27564e VFMADD231PD	%ZMM26,%ZMM27,%ZMM15

  (1070) 0x275654 VMOVUPD	0x140(%R9),%ZMM27

  (1070) 0x27565b VMOVAPD	%ZMM28,%ZMM0

  (1070) 0x275661 VMOVAPD	%ZMM28,%ZMM23

  (1070) 0x275667 VPERMT2PD	%ZMM25,%ZMM4,%ZMM0

  (1070) 0x27566d VPERMT2PD	%ZMM25,%ZMM6,%ZMM23

  (1070) 0x275673 VPERMT2PD	%ZMM28,%ZMM8,%ZMM25

  (1070) 0x275679 VMOVUPD	0x180(%R9),%ZMM28

  (1070) 0x275680 VPERMT2PD	%ZMM27,%ZMM5,%ZMM0

  (1070) 0x275686 VPERMT2PD	%ZMM27,%ZMM9,%ZMM25

  (1070) 0x27568c VPERMT2PD	%ZMM27,%ZMM7,%ZMM23

  (1070) 0x275692 VMOVUPD	0x200(%R9),%ZMM27

  (1070) 0x275699 VMOVAPD	%ZMM28,%ZMM26

  (1070) 0x27569f VFMADD231PD	%ZMM0,%ZMM29,%ZMM12

  (1070) 0x2756a5 VMOVUPD	0x1c0(%R9),%ZMM0

  (1070) 0x2756ac VFMADD231PD	%ZMM25,%ZMM29,%ZMM20

  (1070) 0x2756b2 VMOVAPD	%ZMM28,%ZMM25

  (1070) 0x2756b8 VFMADD231PD	%ZMM23,%ZMM29,%ZMM16

  (1070) 0x2756be VPERMT2PD	%ZMM0,%ZMM4,%ZMM25

  (1070) 0x2756c4 VPERMT2PD	%ZMM0,%ZMM6,%ZMM26

  (1070) 0x2756ca VPERMT2PD	%ZMM28,%ZMM8,%ZMM0

  (1070) 0x2756d0 VMOVUPD	-0x40(%R12,%RDX,1),%ZMM28

  (1070) 0x2756d8 VPERMT2PD	%ZMM27,%ZMM5,%ZMM25

  (1070) 0x2756de VPERMT2PD	%ZMM27,%ZMM7,%ZMM26

  (1070) 0x2756e4 VPERMT2PD	%ZMM27,%ZMM9,%ZMM0

  (1070) 0x2756ea VMOVUPD	0x240(%R9),%ZMM27

  (1070) 0x2756f1 VFMADD231PD	%ZMM25,%ZMM28,%ZMM13

  (1070) 0x2756f7 VMOVUPD	0x280(%R9),%ZMM25

  (1070) 0x2756fe VFMADD231PD	%ZMM0,%ZMM28,%ZMM21

  (1070) 0x275704 VFMADD231PD	%ZMM26,%ZMM28,%ZMM17

  (1070) 0x27570a VMOVUPD	0x2c0(%R9),%ZMM28

  (1070) 0x275711 ADD	$0x300,%R9

  (1070) 0x275718 VMOVAPD	%ZMM27,%ZMM0

  (1070) 0x27571e VMOVAPD	%ZMM27,%ZMM23

  (1070) 0x275724 VPERMT2PD	%ZMM25,%ZMM4,%ZMM0

  (1070) 0x27572a VPERMT2PD	%ZMM25,%ZMM6,%ZMM23

  (1070) 0x275730 VPERMT2PD	%ZMM27,%ZMM8,%ZMM25

  (1070) 0x275736 VMOVUPD	(%R12,%RDX,1),%ZMM27

  (1070) 0x27573d ADD	$0x100,%RDX

  (1070) 0x275744 VPERMT2PD	%ZMM28,%ZMM5,%ZMM0

  (1070) 0x27574a VPERMT2PD	%ZMM28,%ZMM7,%ZMM23

  (1070) 0x275750 VPERMT2PD	%ZMM28,%ZMM9,%ZMM25

  (1070) 0x275756 VFMADD231PD	%ZMM0,%ZMM27,%ZMM14

  (1070) 0x27575c VFMADD231PD	%ZMM23,%ZMM27,%ZMM18

  (1070) 0x275762 VFMADD231PD	%ZMM25,%ZMM27,%ZMM22

  (1070) 0x275768 CMP	%RDX,%R13

  (1070) 0x27576b JNE	2755e0

(1071) 0x275771 VADDPD	%ZMM15,%ZMM16,%ZMM15

(1071) 0x275777 VADDPD	%ZMM17,%ZMM18,%ZMM16

(1071) 0x27577d VADDPD	%ZMM11,%ZMM12,%ZMM11

(1071) 0x275783 VADDPD	%ZMM13,%ZMM14,%ZMM13

(1071) 0x275789 VADDPD	%ZMM19,%ZMM20,%ZMM0

(1071) 0x27578f VADDPD	%ZMM21,%ZMM22,%ZMM19

(1071) 0x275795 MOV	-0x30(%RBP),%R9

(1071) 0x275799 VADDPD	%ZMM15,%ZMM16,%ZMM15

(1071) 0x27579f VADDPD	%ZMM11,%ZMM13,%ZMM11

(1071) 0x2757a5 VADDPD	%ZMM0,%ZMM19,%ZMM0

(1071) 0x2757ab VEXTRACTF64X4	$0x1,%ZMM15,%YMM16

(1071) 0x2757b2 VEXTRACTF64X4	$0x1,%ZMM11,%YMM12

(1071) 0x2757b9 VEXTRACTF64X4	$0x1,%ZMM0,%YMM19

(1071) 0x2757c0 VADDPD	%ZMM16,%ZMM15,%ZMM15

(1071) 0x2757c6 VADDPD	%ZMM12,%ZMM11,%ZMM11

(1071) 0x2757cc VADDPD	%ZMM19,%ZMM0,%ZMM0

(1071) 0x2757d2 VEXTRACTF32X4	$0x1,%YMM15,%XMM16

(1071) 0x2757d9 VEXTRACTF128	$0x1,%YMM11,%XMM12

(1071) 0x2757df VEXTRACTF32X4	$0x1,%YMM0,%XMM19

(1071) 0x2757e6 VADDPD	%XMM16,%XMM15,%XMM15

(1071) 0x2757ec VADDPD	%XMM12,%XMM11,%XMM11

(1071) 0x2757f1 VADDPD	%XMM19,%XMM0,%XMM0

(1071) 0x2757f7 VSHUFPD	$0x1,%XMM15,%XMM15,%XMM16

(1071) 0x2757fe VSHUFPD	$0x1,%XMM11,%XMM11,%XMM12

(1071) 0x275804 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM19

(1071) 0x27580b VADDSD	%XMM16,%XMM15,%XMM15

(1071) 0x275811 VADDSD	%XMM12,%XMM11,%XMM11

(1071) 0x275816 VADDSD	%XMM19,%XMM0,%XMM0

(1071) 0x27581c VUNPCKLPD	%XMM15,%XMM11,%XMM11

(1071) 0x275821 CMP	%RCX,%R9

(1071) 0x275824 JE	2753b0

(1071) 0x27582a VINSERTF128	$0x1,%XMM0,%YMM11,%YMM0

(1071) 0x275830 MOV	%R9,%RDX

(1071) 0x275833 VSHUFPD	$0x2,%YMM0,%YMM0,%YMM11

(1071) 0x275838 TEST	$0x1c,%CL

(1071) 0x27583b JE	2758fc

(1071) 0x275841 LEA	(%RDX,%RDX,2),%R9

(1071) 0x275845 VEXTRACTF128	$0x1,%YMM11,%XMM0

(1071) 0x27584b VMOVQ	%XMM11,%XMM12

(1071) 0x275850 VUNPCKHPD	%XMM24,%XMM11,%XMM13

(1071) 0x275856 LEA	(%R8,%R9,8),%R9

(1071) 0x27585a VMOVQ	%XMM0,%XMM0

(1071) 0x27585e XCHG	%AX,%AX

  (1073) 0x275860 VMOVUPD	(%R9),%ZMM14

  (1073) 0x275866 VMOVUPD	0x40(%R9),%YMM15

  (1073) 0x27586c VMOVUPD	(%RSI,%RDX,8),%YMM11

  (1073) 0x275871 ADD	$0x4,%RDX

  (1073) 0x275875 ADD	$0x60,%R9

  (1073) 0x275879 VMOVAPD	%ZMM14,%ZMM16

  (1073) 0x27587f VMOVAPD	%ZMM14,%ZMM17

  (1073) 0x275885 VPERMT2PD	%ZMM15,%ZMM1,%ZMM16

  (1073) 0x27588b VPERMT2PD	%ZMM15,%ZMM2,%ZMM17

  (1073) 0x275891 VPERMT2PD	%ZMM15,%ZMM3,%ZMM14

  (1073) 0x275897 VFMADD231PD	%YMM16,%YMM11,%YMM12

  (1073) 0x27589d VFMADD231PD	%YMM17,%YMM11,%YMM13

  (1073) 0x2758a3 VFMADD231PD	%YMM14,%YMM11,%YMM0

  (1073) 0x2758a8 CMP	%RDX,%R15

  (1073) 0x2758ab JNE	275860

(1071) 0x2758ad VEXTRACTF128	$0x1,%YMM0,%XMM11

(1071) 0x2758b3 VADDPD	%YMM0,%YMM11,%YMM0

(1071) 0x2758b7 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM11

(1071) 0x2758bc VADDPD	%YMM0,%YMM11,%YMM0

(1071) 0x2758c0 VEXTRACTF128	$0x1,%YMM13,%XMM11

(1071) 0x2758c6 VADDPD	%XMM11,%XMM13,%XMM11

(1071) 0x2758cb VEXTRACTF128	$0x1,%YMM12,%XMM13

(1071) 0x2758d1 VADDPD	%XMM13,%XMM12,%XMM12

(1071) 0x2758d6 VUNPCKHPD	%XMM11,%XMM12,%XMM13

(1071) 0x2758db VUNPCKLPD	%XMM11,%XMM12,%XMM11

(1071) 0x2758e0 VADDPD	%XMM13,%XMM11,%XMM11

(1071) 0x2758e5 CMP	%RCX,%R15

(1071) 0x2758e8 JE	2753b0

(1071) 0x2758ee VBROADCASTSD	%XMM0,%YMM0

(1071) 0x2758f3 MOV	%R15,%R9

(1071) 0x2758f6 VBLENDPD	$0xc,%YMM0,%YMM11,%YMM11

(1071) 0x2758fc LEA	(%R9,%R9,2),%RDX

(1071) 0x275900 LEA	(%R8,%RDX,8),%RDX

(1071) 0x275904 NOPW	%CS:(%RAX,%RAX,1)

  (1072) 0x275910 VPERMILPD	$0x2,(%RDX),%YMM0

  (1072) 0x275916 ADD	$0x18,%RDX

  (1072) 0x27591a VFMADD231PD	(%RSI,%R9,8){1to4},%YMM0,%YMM11

  (1072) 0x275921 INC	%R9

  (1072) 0x275924 CMP	%R9,%RCX

  (1072) 0x275927 JNE	275910

(1071) 0x275929 VEXTRACTF128	$0x1,%YMM11,%XMM0

(1071) 0x27592f JMP	2753b0

0x275934 NOPW	%CS:(%RAX,%RAX,1)

(1068) 0x275940 DEC	%RAX

(1068) 0x275943 JNE	275940

0x275945 ADD	$0x38,%RSP

0x275949 POP	%RBX

0x27594a POP	%R12

0x27594c POP	%R13

0x27594e POP	%R14

0x275950 POP	%R15

0x275952 POP	%RBP

0x275953 VZEROUPPER

0x275956 RET

0x275957 INT	$0x3

0x275958 INT	$0x3

0x275959 INT	$0x3

0x27595a INT	$0x3

0x27595b INT	$0x3

0x27595c INT	$0x3

0x27595d INT	$0x3

0x27595e INT	$0x3

0x27595f INT	$0x3

Coverage (%)	Name	Source Location	Module
►48.47+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:250	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►47.84+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:249	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►1.53+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:250	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
►1.49+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:249	exec
○	main.omp_outlined.64	stl_vector.h:1046	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		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 orig_0

Source file and lines	DiracDeterminantRef.cpp:156-181
Module	exec

The function is defined in:

/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/Platforms/CPU/SIMD/inner_product.hpp:82-83,155
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h:173
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,94
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:156-181

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 13.88 to 5.50 cycles (2.52x 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 28% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 13.88 to 10.52 cycles (1.32x speedup).

Details

36% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

55% of SSE/AVX loads are used in vector version.
11% of SSE/AVX stores are used in vector version.
25% of SSE/AVX addition or subtraction instructions are used in vector version.
66% of SSE/AVX multiply instructions are used in vector version.
0% of SSE/AVX fused multiply-add instructions are used in vector version.
23% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

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

Execution units bottlenecks

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

FMA

Detected 2 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.

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

Type of elements and instruction set

6 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 3 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 (2 inside FMA instructions)
7: multiply (2 inside FMA instructions)

The binary function is loading 724 bytes (90 double precision FP elements). The binary function is storing 80 bytes (10 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	120
nb uops	111
loop length	575
used x86 registers	16
used mmx registers	0
used xmm registers	5
used ymm registers	3
used zmm registers	6
nb stack references	6
ADD-SUB / MUL ratio	1.33

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.88 cycles
front end	13.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.50	5.50	5.50	5.50	5.50	5.50	13.25	13.25	13.25	13.25	2.75	2.75	2.75	2.75	1.50	1.50
cycles	5.50	5.50	5.50	5.50	5.50	5.50	13.25	13.25	13.25	13.25	2.75	2.75	2.75	2.75	1.50	1.50

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	13.88
Dispatch	13.25
Overall L1	13.88

Vectorization ratios

INT

all	5%
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	9%

all	62%
load	68%
store	33%
mul	66%
add-sub	25%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	36%
load	55%
store	11%
mul	66%
add-sub	25%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	23%

Vector efficiency ratios

INT

all	11%
load	10%
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)
other	10%

all	42%
load	53%
store	16%
mul	20%
add-sub	15%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	28%
load	45%
store	13%
mul	20%
add-sub	15%
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 13.88 cycles. At this rate:

20% of peak load performance is reached (52.18 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.77 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).

ASM code

In the binary file, the address of the function is: 2751c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
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 %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x38,%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
CMPL $0,0xc(%RDI)	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	scal (6.3%)
MOV %RCX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JNE 275233 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x73>	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 0x468(%R14),%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	scal (12.5%)
CALL 2a2310 <_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 0x470(%R14),%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 0x478(%R14),%EDX	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(%R14),%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
LEA 0x90(%R14),%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
LEA 0x110(%R14),%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 0x150(%R14),%RAX	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 %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV (%RDI),%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
MOV %RAX,(%RSP)	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%)
CALLQ 0x28(%R10)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	2.20	N/A
MOV 0x468(%R14),%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
CALL 2a2400 <_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
MOVSXD 0x484(%R14),%RAX	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
TEST %RAX,%RAX	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%)
JE 275945 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x785>	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 $0x1,%EAX	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%)
JNE 2752b9 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xf9>	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 0x100(%R14),%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 0x140(%R14),%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 0x18(%R15),%RDX	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
VMOVDDUP (%RAX),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
MOVSXD 0x478(%R14),%RAX	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
VMULPD (%RCX),%XMM0,%XMM2	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%)
VMULSD 0x10(%RCX),%XMM0,%XMM1	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%)
LEA (%RAX,%RAX,2),%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
VADDPD (%RDX,%RSI,8),%XMM2,%XMM3	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%)
VMULPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
VMOVUPD %XMM3,(%RDX,%RSI,8)	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%)
VADDSD 0x10(%RDX,%RSI,8),%XMM1,%XMM3	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 %XMM3,0x10(%RDX,%RSI,8)	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%)
VSHUFPD $0x1,%XMM2,%XMM2,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
MOV 0x180(%R14),%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
VADDSD %XMM2,%XMM3,%XMM2	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%)
MOV 0x18(%RBX),%RDX	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
VFMADD231SD %XMM1,%XMM1,%XMM2	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%)
VFMSUB231SD (%RCX),%XMM0,%XMM2	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%)
VADDSD (%RDX,%RAX,8),%XMM2,%XMM0	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 %XMM0,(%RDX,%RAX,8)	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 275945 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x785>	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 0x480(%R14),%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
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%)
JLE 275940 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x780>	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 0x18(%RBX),%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 0x118(%R14),%RDX	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
VMOVAPD -0x70cbb(%RIP),%YMM1	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%)
VMOVAPD -0x70c43(%RIP),%YMM2	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%)
VMOVAPD -0x70ceb(%RIP),%YMM3	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%)
VMOVAPD -0x6a2b5(%RIP),%ZMM4	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 (100.0%)
VMOVAPD -0x6a27f(%RIP),%ZMM5	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 (100.0%)
VMOVAPD -0x6a249(%RIP),%ZMM6	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 (100.0%)
VMOVAPD -0x6a213(%RIP),%ZMM7	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 (100.0%)
VMOVAPD -0x6a1dd(%RIP),%ZMM8	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 (100.0%)
VMOVAPD -0x6a1a7(%RIP),%ZMM9	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 (100.0%)
MOV 0x158(%R14),%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	scal (12.5%)
MOV 0xd8(%R14),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x100(%R14),%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 0x180(%R14),%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 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
MOV 0x140(%R14),%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	scal (12.5%)
MOV %ECX,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SHR $0x5,%R13D	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (6.3%)
MOV %ECX,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R15D	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
VXORPD %XMM24,%XMM24,%XMM24	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SAL $0x8,%R13	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %RBX,-0x40(%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%)
MOVSXD 0x478(%R14),%RBX	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
SAL $0x3,%RDX	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,%R11	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
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
AND $-0x20,%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
SAL $0x3,%R9	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
LEA 0xc0(%RSI),%R12	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 (%RDX,%RDX,2),%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
MOV %R11,-0x48(%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%)
LEA 0xc0(%RDI),%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	0.25	N/A
MOV %R14,-0x30(%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%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %R9,-0x50(%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 %RDX,-0x38(%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%)
JMP 27541f <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x25f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	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
NOPW %CS:(%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
NOPW %CS:(%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
NOPW %CS:(%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
NOPW %CS:(%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
ADD $0x38,%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
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 %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
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
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
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	DiracDeterminantRef.cpp:156-181
Module	exec

The function is defined in:

/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/Platforms/CPU/SIMD/inner_product.hpp:82-83,155
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/unique_ptr.h:173
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:63,94
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/DiracDeterminantRef.cpp:156-181

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 13.88 to 5.50 cycles (2.52x speedup).

Workaround

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

Vectorization

Details

36% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

55% of SSE/AVX loads are used in vector version.
11% of SSE/AVX stores are used in vector version.
25% of SSE/AVX addition or subtraction instructions are used in vector version.
66% of SSE/AVX multiply instructions are used in vector version.
0% of SSE/AVX fused multiply-add instructions are used in vector version.
23% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized function can use their full power.

Workaround

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

Execution units bottlenecks

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

FMA

Detected 2 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

CALL instructions

Detected function call instructions.

Details

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

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 (2 inside FMA instructions)
7: multiply (2 inside FMA instructions)

The binary function is loading 724 bytes (90 double precision FP elements). The binary function is storing 80 bytes (10 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	120
nb uops	111
loop length	575
used x86 registers	16
used mmx registers	0
used xmm registers	5
used ymm registers	3
used zmm registers	6
nb stack references	6
ADD-SUB / MUL ratio	1.33

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.88 cycles
front end	13.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.50	5.50	5.50	5.50	5.50	5.50	13.25	13.25	13.25	13.25	2.75	2.75	2.75	2.75	1.50	1.50
cycles	5.50	5.50	5.50	5.50	5.50	5.50	13.25	13.25	13.25	13.25	2.75	2.75	2.75	2.75	1.50	1.50

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	13.88
Dispatch	13.25
Overall L1	13.88

Vectorization ratios

INT

all	5%
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	9%

all	62%
load	68%
store	33%
mul	66%
add-sub	25%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	36%
load	55%
store	11%
mul	66%
add-sub	25%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	23%

Vector efficiency ratios

INT

all	11%
load	10%
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)
other	10%

all	42%
load	53%
store	16%
mul	20%
add-sub	15%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	28%
load	45%
store	13%
mul	20%
add-sub	15%
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 13.88 cycles. At this rate:

20% of peak load performance is reached (52.18 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.77 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).

ASM code

In the binary file, the address of the function is: 2751c0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
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 %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x38,%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
CMPL $0,0xc(%RDI)	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	scal (6.3%)
MOV %RCX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JNE 275233 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x73>	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 0x468(%R14),%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	scal (12.5%)
CALL 2a2310 <_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 0x470(%R14),%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 0x478(%R14),%EDX	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(%R14),%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
LEA 0x90(%R14),%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
LEA 0x110(%R14),%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 0x150(%R14),%RAX	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 %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV (%RDI),%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
MOV %RAX,(%RSP)	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%)
CALLQ 0x28(%R10)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	2.20	N/A
MOV 0x468(%R14),%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
CALL 2a2400 <_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
MOVSXD 0x484(%R14),%RAX	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
TEST %RAX,%RAX	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%)
JE 275945 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x785>	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 $0x1,%EAX	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%)
JNE 2752b9 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0xf9>	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 0x100(%R14),%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 0x140(%R14),%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 0x18(%R15),%RDX	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
VMOVDDUP (%RAX),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
MOVSXD 0x478(%R14),%RAX	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
VMULPD (%RCX),%XMM0,%XMM2	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%)
VMULSD 0x10(%RCX),%XMM0,%XMM1	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%)
LEA (%RAX,%RAX,2),%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
VADDPD (%RDX,%RSI,8),%XMM2,%XMM3	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%)
VMULPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	vect (25.0%)
VMOVUPD %XMM3,(%RDX,%RSI,8)	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%)
VADDSD 0x10(%RDX,%RSI,8),%XMM1,%XMM3	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 %XMM3,0x10(%RDX,%RSI,8)	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%)
VSHUFPD $0x1,%XMM2,%XMM2,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
MOV 0x180(%R14),%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
VADDSD %XMM2,%XMM3,%XMM2	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%)
MOV 0x18(%RBX),%RDX	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
VFMADD231SD %XMM1,%XMM1,%XMM2	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%)
VFMSUB231SD (%RCX),%XMM0,%XMM2	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%)
VADDSD (%RDX,%RAX,8),%XMM2,%XMM0	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 %XMM0,(%RDX,%RAX,8)	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 275945 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x785>	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 0x480(%R14),%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
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%)
JLE 275940 <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x780>	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 0x18(%RBX),%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 0x118(%R14),%RDX	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
VMOVAPD -0x70cbb(%RIP),%YMM1	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%)
VMOVAPD -0x70c43(%RIP),%YMM2	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%)
VMOVAPD -0x70ceb(%RIP),%YMM3	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%)
VMOVAPD -0x6a2b5(%RIP),%ZMM4	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 (100.0%)
VMOVAPD -0x6a27f(%RIP),%ZMM5	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 (100.0%)
VMOVAPD -0x6a249(%RIP),%ZMM6	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 (100.0%)
VMOVAPD -0x6a213(%RIP),%ZMM7	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 (100.0%)
VMOVAPD -0x6a1dd(%RIP),%ZMM8	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 (100.0%)
VMOVAPD -0x6a1a7(%RIP),%ZMM9	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 (100.0%)
MOV 0x158(%R14),%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	scal (12.5%)
MOV 0xd8(%R14),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x100(%R14),%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 0x180(%R14),%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 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
MOV 0x140(%R14),%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	scal (12.5%)
MOV %ECX,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SHR $0x5,%R13D	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (6.3%)
MOV %ECX,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R15D	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
VXORPD %XMM24,%XMM24,%XMM24	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SAL $0x8,%R13	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %RBX,-0x40(%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%)
MOVSXD 0x478(%R14),%RBX	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
SAL $0x3,%RDX	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,%R11	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
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
AND $-0x20,%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
SAL $0x3,%R9	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
LEA 0xc0(%RSI),%R12	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 (%RDX,%RDX,2),%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
MOV %R11,-0x48(%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%)
LEA 0xc0(%RDI),%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	0.25	N/A
MOV %R14,-0x30(%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%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %R9,-0x50(%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 %RDX,-0x38(%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%)
JMP 27541f <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x25f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	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
NOPW %CS:(%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
NOPW %CS:(%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
NOPW %CS:(%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
NOPW %CS:(%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
ADD $0x38,%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
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 %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
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
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
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::DiracDeterminantRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus:...–	0.62	1.03
▼Loop 1071 - inner_product.hpp:82-155 - exec–	0.01	0.01
○Loop 1070 - inner_product.hpp:155-155 - exec	0.38	0.63
○Loop 1069 - inner_product.hpp:82-83 - exec	0.23	0.39
○Loop 1073 - inner_product.hpp:155-155 - exec	0.00	0.00
○Loop 1075 - inner_product.hpp:82-83 - exec	0.00	0.00
○Loop 1072 - inner_product.hpp:155-155 - exec	0.00	0.00
○Loop 1074 - inner_product.hpp:82-83 - exec	0.00	0.00
○Loop 1068 - DiracDeterminantRef.cpp:173-173 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

CALL 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

FMA

Workaround

CALL 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