OV - exec - Loop 275

	Loop Id: 275	Module: exec	Source: BsplineFunctor.h:236-260 [...]	Coverage: 0.02%

0x23a160 VADDSD	%XMM0,%XMM14,%XMM14

0x23a164 INC	%R10

0x23a167 CMP	%RCX,%R10

0x23a16a JE	23a045

0x23a170 MOV	-0x80(%RBP),%RAX

0x23a174 MOV	%R9D,%EDI

0x23a177 VXORPD	%XMM0,%XMM0,%XMM0

0x23a17b MOV	0x4(%RAX,%R10,4),%R9D

0x23a180 MOV	%R9D,%EDX

0x23a183 SUB	%EDI,%EDX

0x23a185 JLE	23a160

0x23a187 MOV	-0x70(%RBP),%RAX

0x23a18b MOV	-0x68(%RBP),%R11

0x23a18f MOVSXD	%EDI,%RDI

0x23a192 MOV	%EDX,%EBX

0x23a194 ADD	%R10,%RAX

0x23a197 MOV	(%R11,%RAX,8),%RAX

0x23a19b MOV	-0x78(%RBP),%R11

0x23a19f VMOVSD	0x8(%RAX),%XMM2

0x23a1a4 LEA	(%R11,%RDI,8),%R11

0x23a1a8 CMP	$0x1,%EDX

0x23a1ab JNE	23a1c0

0x23a1ad XOR	%R12D,%R12D

0x23a1b0 XOR	%EDX,%EDX

0x23a1b2 JMP	23a2b0

0x23a1c0 VMOVDQA	-0x35ce8(%RIP),%XMM3

0x23a1c8 VMOVDDUP	%XMM2,%XMM0

0x23a1cc MOV	%EBX,%R12D

0x23a1cf AND	$-0x2,%R12D

0x23a1d3 VPBROADCASTQ	%RDI,%XMM1

0x23a1d9 XOR	%R13D,%R13D

0x23a1dc XOR	%EDX,%EDX

0x23a1de XCHG	%AX,%AX

  (276) 0x23a1e0 VMOVUPD	(%R11,%R13,8),%XMM4

  (276) 0x23a1e6 VPADDQ	%XMM1,%XMM3,%XMM5

  (276) 0x23a1ea VPADDQ	-0x36014(%RIP){1to2},%XMM3,%XMM3

  (276) 0x23a1f4 MOVSXD	%EDX,%RDX

  (276) 0x23a1f7 VPCMPNEQQ	%XMM15,%XMM5,%K1

  (276) 0x23a1fe VCMPPD	$0x1,%XMM0,%XMM4,%K1{%K1}

  (276) 0x23a205 KMOVB	%K1,%R15D

  (276) 0x23a209 VCOMPRESSPD	%XMM4,(%RSI,%RDX,8){%K1}

  (276) 0x23a210 POPCNT	%R15D,%R15D

  (276) 0x23a215 KORTESTB	%K1,%K1

  (276) 0x23a219 CMOVE	%R14D,%R15D

  (276) 0x23a21d ADD	$0x2,%R13

  (276) 0x23a221 ADD	%R15D,%EDX

  (276) 0x23a224 CMP	%R13,%R12

  (276) 0x23a227 JNE	23a1e0

0x23a229 CMP	%RBX,%R12

0x23a22c JNE	23a2b0

0x23a232 VXORPD	%XMM0,%XMM0,%XMM0

0x23a236 TEST	%EDX,%EDX

0x23a238 JLE	23a160

0x23a23e VMOVSD	0x238(%RAX),%XMM16

0x23a245 VMOVUPD	0x18(%RAX),%XMM19

0x23a24f VMOVSD	0x28(%RAX),%XMM20

0x23a256 VMOVSD	0x30(%RAX),%XMM21

0x23a25d VMOVSD	0x38(%RAX),%XMM4

0x23a262 VMOVSD	0x40(%RAX),%XMM5

0x23a267 VMOVSD	0x48(%RAX),%XMM2

0x23a26c VMOVSD	0x50(%RAX),%XMM8

0x23a271 VMOVSD	0x58(%RAX),%XMM7

0x23a276 VMOVSD	0x60(%RAX),%XMM9

0x23a27b VMOVSD	0x68(%RAX),%XMM10

0x23a280 VMOVSD	0x70(%RAX),%XMM11

0x23a285 VMOVUPD	0x78(%RAX),%XMM6

0x23a28a VMOVSD	0x88(%RAX),%XMM17

0x23a291 VMOVSD	0x90(%RAX),%XMM18

0x23a298 MOV	0x218(%RAX),%R11

0x23a29f MOV	%EDX,%EAX

0x23a2a1 CMP	$0x4,%EDX

0x23a2a4 JAE	23a2e9

0x23a2a6 XOR	%EBX,%EBX

0x23a2a8 JMP	23a6c5

0x23a2b0 MOV	%R8,%R13

0x23a2b3 SUB	%RDI,%R13

0x23a2b6 JMP	23a2cc

  (279) 0x23a2c0 INC	%R12

  (279) 0x23a2c3 CMP	%R12,%RBX

  (279) 0x23a2c6 JE	23a232

  (279) 0x23a2cc CMP	%R12,%R13

  (279) 0x23a2cf JE	23a2c0

  (279) 0x23a2d1 VMOVSD	(%R11,%R12,8),%XMM0

  (279) 0x23a2d7 VUCOMISD	%XMM2,%XMM0

  (279) 0x23a2db JAE	23a2c0

  (279) 0x23a2dd MOVSXD	%EDX,%RDI

  (279) 0x23a2e0 INC	%EDX

  (279) 0x23a2e2 VMOVSD	%XMM0,(%RSI,%RDI,8)

  (279) 0x23a2e7 JMP	23a2c0

0x23a2e9 MOV	%EAX,%R12D

0x23a2ec VMOVAPD	%XMM17,%XMM0

0x23a2f2 VMOVAPD	%XMM18,%XMM1

0x23a2f8 SHR	$0x2,%R12D

0x23a2fc VMOVAPD	%XMM21,-0x140(%RBP)

0x23a303 VMOVDDUP	%XMM16,%XMM17

0x23a309 VMOVDDUP	%XMM19,%XMM18

0x23a30f VMOVDDUP	%XMM20,%XMM3

0x23a315 VMOVDDUP	%XMM21,%XMM21

0x23a31b VMOVDDUP	%XMM4,%XMM22

0x23a321 VMOVDDUP	%XMM5,%XMM23

0x23a327 VMOVDDUP	%XMM2,%XMM24

0x23a32d VMOVDDUP	%XMM8,%XMM25

0x23a333 VMOVDDUP	%XMM7,%XMM26

0x23a339 VMOVAPD	%XMM9,-0xc0(%RBP)

0x23a341 VMOVDDUP	%XMM9,%XMM27

0x23a347 VMOVAPD	%XMM10,-0xb0(%RBP)

0x23a34f VMOVDDUP	%XMM10,%XMM28

0x23a355 VMOVDDUP	%XMM11,%XMM29

0x23a35b VMOVDDUP	%XMM6,%XMM30

0x23a361 VMOVDDUP	%XMM0,%XMM9

0x23a365 VMOVDDUP	%XMM1,%XMM10

0x23a369 MOV	%EAX,%EBX

0x23a36b VMOVAPD	%XMM19,-0x160(%RBP)

0x23a372 VMOVAPD	%XMM5,-0x100(%RBP)

0x23a37a VMOVAPD	%XMM2,-0xe0(%RBP)

0x23a382 AND	$-0x4,%EBX

0x23a385 VSHUFPD	$0x3,%XMM19,%XMM19,%XMM19

0x23a38c VSHUFPD	$0x3,%XMM6,%XMM6,%XMM31

0x23a393 VXORPD	%XMM2,%XMM2,%XMM2

0x23a397 VXORPD	%XMM5,%XMM5,%XMM5

0x23a39b VMOVSD	%XMM14,-0x60(%RBP)

0x23a3a0 VMOVAPD	%XMM16,-0x170(%RBP)

0x23a3a7 VMOVAPD	%XMM20,-0x150(%RBP)

0x23a3ae VMOVAPD	%XMM4,-0x110(%RBP)

0x23a3b6 VMOVAPD	%XMM8,-0xd0(%RBP)

0x23a3be VMOVAPD	%XMM7,-0xf0(%RBP)

0x23a3c6 VMOVAPD	%XMM11,-0xa0(%RBP)

0x23a3ce VMOVAPD	%XMM0,-0x130(%RBP)

0x23a3d6 VMOVAPD	%XMM1,-0x120(%RBP)

0x23a3de XOR	%EDX,%EDX

0x23a3e0 SAL	$0x5,%R12

0x23a3e4 NOPW	%CS:(%RAX,%RAX,1)

  (277) 0x23a3f0 VMULPD	(%RSI,%RDX,1),%XMM17,%XMM11

  (277) 0x23a3f7 VMULPD	0x10(%RSI,%RDX,1),%XMM17,%XMM13

  (277) 0x23a3ff VMOVAPD	%XMM3,%XMM20

  (277) 0x23a405 VMOVAPD	%XMM3,%XMM8

  (277) 0x23a409 ADD	$0x20,%RDX

  (277) 0x23a40d VROUNDPD	$0xb,%XMM11,%XMM12

  (277) 0x23a413 VROUNDPD	$0xb,%XMM13,%XMM14

  (277) 0x23a419 VCVTTPD2DQ	%XMM11,%XMM1

  (277) 0x23a41e VCVTTPD2DQ	%XMM13,%XMM0

  (277) 0x23a423 VSUBPD	%XMM12,%XMM11,%XMM12

  (277) 0x23a428 VSUBPD	%XMM14,%XMM13,%XMM11

  (277) 0x23a42d VPMOVSXDQ	%XMM1,%XMM4

  (277) 0x23a432 VPMOVSXDQ	%XMM0,%XMM7

  (277) 0x23a437 VMOVQ	%XMM4,%RDI

  (277) 0x23a43c VPEXTRQ	$0x1,%XMM4,%R15

  (277) 0x23a442 VMOVQ	%XMM7,%R13

  (277) 0x23a447 VPEXTRQ	$0x1,%XMM7,%R8

  (277) 0x23a44d VFMADD213PD	%XMM21,%XMM12,%XMM20

  (277) 0x23a453 VMULPD	%XMM12,%XMM12,%XMM16

  (277) 0x23a459 VFMADD213PD	%XMM21,%XMM11,%XMM8

  (277) 0x23a45f VMULPD	%XMM11,%XMM11,%XMM15

  (277) 0x23a464 VMOVSD	(%R11,%RDI,8),%XMM4

  (277) 0x23a46a VMOVSD	(%R11,%R13,8),%XMM7

  (277) 0x23a470 VMOVHPD	(%R11,%R15,8),%XMM4,%XMM4

  (277) 0x23a476 VMOVHPD	(%R11,%R8,8),%XMM7,%XMM7

  (277) 0x23a47c VMULPD	%XMM12,%XMM16,%XMM14

  (277) 0x23a482 VMULPD	%XMM11,%XMM15,%XMM13

  (277) 0x23a487 VFMADD231PD	%XMM19,%XMM16,%XMM20

  (277) 0x23a48d VFMADD231PD	%XMM19,%XMM15,%XMM8

  (277) 0x23a493 VFMADD231PD	%XMM18,%XMM14,%XMM20

  (277) 0x23a499 VFMADD231PD	%XMM18,%XMM13,%XMM8

  (277) 0x23a49f VFMADD213PD	%XMM2,%XMM4,%XMM20

  (277) 0x23a4a5 VPCMPEQD	%XMM4,%XMM4,%XMM4

  (277) 0x23a4a9 VFMADD213PD	%XMM5,%XMM7,%XMM8

  (277) 0x23a4ae VMOVAPD	%XMM24,%XMM5

  (277) 0x23a4b4 VFMADD213PD	%XMM25,%XMM12,%XMM5

  (277) 0x23a4ba VMOVAPD	%XMM24,%XMM7

  (277) 0x23a4c0 VFMADD213PD	%XMM25,%XMM11,%XMM7

  (277) 0x23a4c6 VPSUBD	%XMM4,%XMM1,%XMM2

  (277) 0x23a4ca VPSUBD	%XMM4,%XMM0,%XMM4

  (277) 0x23a4ce VPMOVSXDQ	%XMM2,%XMM2

  (277) 0x23a4d3 VPMOVSXDQ	%XMM4,%XMM4

  (277) 0x23a4d8 VMOVQ	%XMM2,%RDI

  (277) 0x23a4dd VPEXTRQ	$0x1,%XMM2,%R8

  (277) 0x23a4e3 VFMADD231PD	%XMM23,%XMM16,%XMM5

  (277) 0x23a4e9 VMOVQ	%XMM4,%R15

  (277) 0x23a4ee VPEXTRQ	$0x1,%XMM4,%R13

  (277) 0x23a4f4 VFMADD231PD	%XMM23,%XMM15,%XMM7

  (277) 0x23a4fa VMOVSD	(%R11,%RDI,8),%XMM2

  (277) 0x23a500 VMOVSD	(%R11,%R15,8),%XMM4

  (277) 0x23a506 VMOVHPD	(%R11,%R8,8),%XMM2,%XMM2

  (277) 0x23a50c VMOVHPD	(%R11,%R13,8),%XMM4,%XMM4

  (277) 0x23a512 VFMADD231PD	%XMM22,%XMM14,%XMM5

  (277) 0x23a518 VFMADD231PD	%XMM22,%XMM13,%XMM7

  (277) 0x23a51e VFMADD213PD	%XMM20,%XMM2,%XMM5

  (277) 0x23a524 VPBROADCASTD	-0x36481(%RIP),%XMM2

  (277) 0x23a52d VFMADD213PD	%XMM8,%XMM4,%XMM7

  (277) 0x23a532 VMOVAPD	%XMM28,%XMM8

  (277) 0x23a538 VFMADD213PD	%XMM29,%XMM12,%XMM8

  (277) 0x23a53e VMOVAPD	%XMM28,%XMM20

  (277) 0x23a544 VFMADD213PD	%XMM29,%XMM11,%XMM20

  (277) 0x23a54a VFMADD213PD	%XMM10,%XMM9,%XMM12

  (277) 0x23a54f VFMADD213PD	%XMM10,%XMM9,%XMM11

  (277) 0x23a554 VFMADD231PD	%XMM27,%XMM16,%XMM8

  (277) 0x23a55a VFMADD231PD	%XMM27,%XMM15,%XMM20

  (277) 0x23a560 VFMADD231PD	%XMM16,%XMM31,%XMM12

  (277) 0x23a566 VFMADD231PD	%XMM15,%XMM31,%XMM11

  (277) 0x23a56c VPADDD	%XMM2,%XMM1,%XMM4

  (277) 0x23a570 VPADDD	%XMM2,%XMM0,%XMM2

  (277) 0x23a574 VFMADD231PD	%XMM26,%XMM14,%XMM8

  (277) 0x23a57a VFMADD231PD	%XMM26,%XMM13,%XMM20

  (277) 0x23a580 VFMADD231PD	%XMM14,%XMM30,%XMM12

  (277) 0x23a586 VFMADD231PD	%XMM13,%XMM30,%XMM11

  (277) 0x23a58c VPMOVSXDQ	%XMM4,%XMM4

  (277) 0x23a591 VPMOVSXDQ	%XMM2,%XMM2

  (277) 0x23a596 VMOVQ	%XMM4,%RDI

  (277) 0x23a59b VPEXTRQ	$0x1,%XMM4,%R8

  (277) 0x23a5a1 VMOVQ	%XMM2,%R13

  (277) 0x23a5a6 VPEXTRQ	$0x1,%XMM2,%R15

  (277) 0x23a5ac VMOVSD	(%R11,%RDI,8),%XMM2

  (277) 0x23a5b2 VMOVSD	(%R11,%R13,8),%XMM4

  (277) 0x23a5b8 VMOVHPD	(%R11,%R8,8),%XMM2,%XMM2

  (277) 0x23a5be VMOVHPD	(%R11,%R15,8),%XMM4,%XMM4

  (277) 0x23a5c4 VFMADD213PD	%XMM5,%XMM2,%XMM8

  (277) 0x23a5c9 VPBROADCASTD	-0x36522(%RIP),%XMM2

  (277) 0x23a5d2 VFMADD213PD	%XMM7,%XMM4,%XMM20

  (277) 0x23a5d8 VMOVAPD	%XMM11,%XMM5

  (277) 0x23a5dc VPADDD	%XMM2,%XMM1,%XMM1

  (277) 0x23a5e0 VPADDD	%XMM2,%XMM0,%XMM0

  (277) 0x23a5e4 VMOVAPD	%XMM12,%XMM2

  (277) 0x23a5e8 VPMOVSXDQ	%XMM1,%XMM1

  (277) 0x23a5ed VPMOVSXDQ	%XMM0,%XMM0

  (277) 0x23a5f2 VMOVQ	%XMM1,%RDI

  (277) 0x23a5f7 VMOVQ	%XMM0,%R15

  (277) 0x23a5fc VPEXTRQ	$0x1,%XMM1,%R8

  (277) 0x23a602 VPEXTRQ	$0x1,%XMM0,%R13

  (277) 0x23a608 VMOVSD	(%R11,%RDI,8),%XMM0

  (277) 0x23a60e VMOVSD	(%R11,%R15,8),%XMM1

  (277) 0x23a614 VMOVHPD	(%R11,%R8,8),%XMM0,%XMM0

  (277) 0x23a61a VMOVHPD	(%R11,%R13,8),%XMM1,%XMM1

  (277) 0x23a620 VFMADD213PD	%XMM8,%XMM0,%XMM2

  (277) 0x23a625 VFMADD213PD	%XMM20,%XMM1,%XMM5

  (277) 0x23a62b CMP	%RDX,%R12

  (277) 0x23a62e JNE	23a3f0

0x23a634 VADDPD	%XMM2,%XMM5,%XMM0

0x23a638 VMOVSD	-0x60(%RBP),%XMM14

0x23a63d VMOVDQA	-0x90(%RBP),%XMM15

0x23a645 VMOVAPD	-0x170(%RBP),%XMM16

0x23a64c VMOVAPD	-0x160(%RBP),%XMM19

0x23a653 VMOVAPD	-0x150(%RBP),%XMM20

0x23a65a VMOVAPD	-0x140(%RBP),%XMM21

0x23a661 VMOVAPD	-0x130(%RBP),%XMM17

0x23a668 VMOVAPD	-0x120(%RBP),%XMM18

0x23a66f VMOVAPD	-0x110(%RBP),%XMM4

0x23a677 VMOVAPD	-0x100(%RBP),%XMM5

0x23a67f VMOVAPD	-0xf0(%RBP),%XMM7

0x23a687 VMOVAPD	-0xe0(%RBP),%XMM2

0x23a68f VMOVAPD	-0xd0(%RBP),%XMM8

0x23a697 VMOVAPD	-0xc0(%RBP),%XMM9

0x23a69f VMOVAPD	-0xb0(%RBP),%XMM10

0x23a6a7 VMOVAPD	-0xa0(%RBP),%XMM11

0x23a6af MOV	-0x58(%RBP),%R8

0x23a6b3 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

0x23a6b8 VADDSD	%XMM1,%XMM0,%XMM0

0x23a6bc CMP	%RAX,%RBX

0x23a6bf JE	23a160

0x23a6c5 VUNPCKLPD	%XMM10,%XMM2,%XMM1

0x23a6ca VUNPCKLPD	%XMM9,%XMM5,%XMM5

0x23a6cf VUNPCKLPD	%XMM11,%XMM8,%XMM2

0x23a6d4 VUNPCKLPD	%XMM7,%XMM4,%XMM9

0x23a6d8 NOPL	(%RAX,%RAX,1)

  (278) 0x23a6e0 VMULSD	(%RSI,%RBX,8),%XMM16,%XMM3

  (278) 0x23a6e7 INC	%RBX

  (278) 0x23a6ea VROUNDSD	$0xb,%XMM3,%XMM3,%XMM4

  (278) 0x23a6f0 VCVTTSD2SI	%XMM3,%EDX

  (278) 0x23a6f4 MOVSXD	%EDX,%RDX

  (278) 0x23a6f7 VSUBSD	%XMM4,%XMM3,%XMM3

  (278) 0x23a6fb VMOVAPD	%XMM20,%XMM4

  (278) 0x23a701 VMULSD	%XMM3,%XMM3,%XMM8

  (278) 0x23a705 VMOVDDUP	%XMM3,%XMM7

  (278) 0x23a709 VFMADD213SD	%XMM21,%XMM3,%XMM4

  (278) 0x23a70f VFMADD213PD	%XMM2,%XMM1,%XMM7

  (278) 0x23a714 VMULSD	%XMM3,%XMM8,%XMM10

  (278) 0x23a718 VMOVDDUP	%XMM8,%XMM8

  (278) 0x23a71d VFMADD213SD	%XMM18,%XMM17,%XMM3

  (278) 0x23a723 VMOVDDUP	%XMM10,%XMM10

  (278) 0x23a728 VFMADD231PD	%XMM8,%XMM5,%XMM7

  (278) 0x23a72d VUNPCKLPD	%XMM8,%XMM10,%XMM11

  (278) 0x23a732 VMULPD	%XMM19,%XMM11,%XMM12

  (278) 0x23a738 VMULPD	%XMM6,%XMM11,%XMM8

  (278) 0x23a73c VFMADD231PD	%XMM10,%XMM9,%XMM7

  (278) 0x23a741 VMULPD	0x8(%R11,%RDX,8),%XMM7,%XMM7

  (278) 0x23a748 VADDSD	%XMM4,%XMM12,%XMM4

  (278) 0x23a74c VSHUFPD	$0x1,%XMM12,%XMM12,%XMM13

  (278) 0x23a752 VADDSD	%XMM3,%XMM8,%XMM3

  (278) 0x23a756 VSHUFPD	$0x1,%XMM8,%XMM8,%XMM10

  (278) 0x23a75c VADDSD	%XMM4,%XMM13,%XMM4

  (278) 0x23a760 VFMADD132SD	(%R11,%RDX,8),%XMM0,%XMM4

  (278) 0x23a766 VADDSD	%XMM3,%XMM10,%XMM3

  (278) 0x23a76a VSHUFPD	$0x1,%XMM7,%XMM7,%XMM0

  (278) 0x23a76f VADDSD	%XMM0,%XMM7,%XMM0

  (278) 0x23a773 VADDSD	%XMM0,%XMM4,%XMM0

  (278) 0x23a777 VFMADD231SD	0x18(%R11,%RDX,8),%XMM3,%XMM0

  (278) 0x23a77e CMP	%RBX,%RAX

  (278) 0x23a781 JNE	23a6e0

0x23a787 JMP	23a160

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316

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

313:   inline int first(int igroup) const { return (*group_offsets_)[igroup]; }

314:

315:   ///return the last index of a group i

316:   inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 127 - 132

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

127:     for (int jg = 0; jg < NumGroups; ++jg)

128:     {

129:       const FuncType& f2(*F[igt + jg]);

130:       int iStart = P.first(jg);

131:       int iEnd   = P.last(jg);

132:       curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data());

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 260

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

236:   for (int jat = 0; jat < iLimit; jat++)

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

240:     if (r < cutoff_radius && iStart + jat != iat)

241:       distArrayCompressed[iCount++] = distArray[jat];

242:   }

243:

244:   real_type d = 0.0;

245:   //#pragma omp simd reduction(+:d)

246:   for (int jat = 0; jat < iCount; jat++)

247:   {

248:     real_type r = distArrayCompressed[jat];

249:     r *= DeltaRInv;

250:     int i         = (int)r;

251:     real_type t   = r - real_type(i);

252:     real_type tp0 = t * t * t;

253:     real_type tp1 = t * t;

254:     real_type tp2 = t;

255:

256:     real_type d1 = SplineCoefs[i + 0] * (A[0] * tp0 + A[1] * tp1 + A[2] * tp2 + A[3]);

257:     real_type d2 = SplineCoefs[i + 1] * (A[4] * tp0 + A[5] * tp1 + A[6] * tp2 + A[7]);

258:     real_type d3 = SplineCoefs[i + 2] * (A[8] * tp0 + A[9] * tp1 + A[10] * tp2 + A[11]);

259:     real_type d4 = SplineCoefs[i + 3] * (A[12] * tp0 + A[13] * tp1 + A[14] * tp2 + A[15]);

260:     d += (d1 + d2 + d3 + d4);

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1064 - 1064

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

1064: 	return *(this->_M_impl._M_start + __n);

Coverage (%)	Name	Source Location	Module
►96.13+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:272	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	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
►3.04+	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:272	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	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 /

Metric	Value
CQA speedup if no scalar integer	1.28
CQA speedup if FP arith vectorized	1.29
CQA speedup if fully vectorized	6.20
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.17
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	ParticleSet.h:313-313,ParticleSet.h:316-316,TwoBodyJastrowRef.h:127-127,TwoBodyJastrowRef.h:132-132,BsplineFunctor.h:236-236,BsplineFunctor.h:246-246,BsplineFunctor.h:258-258
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	16.38
CQA cycles if no scalar integer	12.75
CQA cycles if FP arith vectorized	12.69
CQA cycles if fully vectorized	2.64
Front-end cycles	16.38
P0 cycles	4.50
P1 cycles	4.50
P2 cycles	4.50
P3 cycles	4.50
P4 cycles	4.50
P5 cycles	4.50
P6 cycles	14.00
P7 cycles	14.00
P8 cycles	14.00
P9 cycles	14.00
P10 cycles	6.75
P11 cycles	6.75
P12 cycles	6.75
P13 cycles	6.75
P14 cycles	7.50
P15 cycles	7.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	133.00
Nb uops	131.00
Nb loads	41.00
Nb stores	15.00
Nb stack references	21.00
FLOP/cycle	0.24
Nb FLOP add-sub	4.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	42.75
Bytes prefetched	0.00
Bytes loaded	468.00
Bytes stored	232.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	41.18
Vectorization ratio load	51.43
Vectorization ratio store	93.33
Vectorization ratio mul	NA
Vectorization ratio add_sub	20.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	19.15
Vector-efficiency ratio all	16.73
Vector-efficiency ratio load	18.75
Vector-efficiency ratio store	24.17
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	13.75
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	13.16

Metric	Value
CQA speedup if no scalar integer	1.28
CQA speedup if FP arith vectorized	1.29
CQA speedup if fully vectorized	6.20
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.17
Bottlenecks	micro-operation queue,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	ParticleSet.h:313-313,ParticleSet.h:316-316,TwoBodyJastrowRef.h:127-127,TwoBodyJastrowRef.h:132-132,BsplineFunctor.h:236-236,BsplineFunctor.h:246-246,BsplineFunctor.h:258-258
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	16.38
CQA cycles if no scalar integer	12.75
CQA cycles if FP arith vectorized	12.69
CQA cycles if fully vectorized	2.64
Front-end cycles	16.38
P0 cycles	4.50
P1 cycles	4.50
P2 cycles	4.50
P3 cycles	4.50
P4 cycles	4.50
P5 cycles	4.50
P6 cycles	14.00
P7 cycles	14.00
P8 cycles	14.00
P9 cycles	14.00
P10 cycles	6.75
P11 cycles	6.75
P12 cycles	6.75
P13 cycles	6.75
P14 cycles	7.50
P15 cycles	7.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	133.00
Nb uops	131.00
Nb loads	41.00
Nb stores	15.00
Nb stack references	21.00
FLOP/cycle	0.24
Nb FLOP add-sub	4.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	42.75
Bytes prefetched	0.00
Bytes loaded	468.00
Bytes stored	232.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	41.18
Vectorization ratio load	51.43
Vectorization ratio store	93.33
Vectorization ratio mul	NA
Vectorization ratio add_sub	20.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	19.15
Vector-efficiency ratio all	16.73
Vector-efficiency ratio load	18.75
Vector-efficiency ratio store	24.17
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	13.75
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	13.16

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	BsplineFunctor.h:236-260
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:127-132
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-260
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=29
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 29 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 16.38 to 12.75 cycles (1.28x speedup).

Workaround

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

Vectorization

Your loop is poorly vectorized. Only 16% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your loop, you can lower the cost of an iteration from 16.38 to 2.64 cycles (6.20x speedup).

Details

41% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

51% of SSE/AVX loads are used in vector version.
93% of SSE/AVX stores are used in vector version.
20% of SSE/AVX addition or subtraction instructions are used in vector version.
19% 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 loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

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.

VPBROADCASTQ: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236

Type of elements and instruction set

2 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 1 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 loop (in the source code) and the binary loop

The binary loop is composed of 4 FP arithmetical operations:

4: addition or subtraction

The binary loop is loading 468 bytes (58 double precision FP elements). The binary loop is storing 232 bytes (29 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	133
nb uops	131
loop length	699
used x86 registers	12
used mmx registers	0
used xmm registers	30
used ymm registers	0
used zmm registers	0
nb stack references	21

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.38 cycles
front end	16.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.50	4.50	4.50	4.50	4.50	4.50	14.00	14.00	14.00	14.00	6.75	6.75	6.75	6.75	7.50	7.50
cycles	4.50	4.50	4.50	4.50	4.50	4.50	14.00	14.00	14.00	14.00	6.75	6.75	6.75	6.75	7.50	7.50

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	16.38
Dispatch	14.00
Overall L1	16.38

Vectorization ratios

INT

all	8%
load	50%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	51%
load	51%
store	93%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	31%

INT+FP

all	41%
load	51%
store	93%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	20%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	19%

Vector efficiency ratios

INT

all	9%
load	17%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	18%
load	18%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	16%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

INT+FP

all	16%
load	18%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 16.38 cycles. At this rate:

11% of peak load performance is reached (28.58 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.17 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 16.38 to 14.00 cycles (1.17x speedup).

ASM code

In the binary file, the address of the loop is: 23a170

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
VADDSD %XMM0,%XMM14,%XMM14	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%)
INC %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	0.17	N/A
CMP %RCX,%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	0.17	scal (12.5%)
JE 23a045 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x45>	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 -0x80(%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 %R9D,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOV 0x4(%RAX,%R10,4),%R9D	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 (6.3%)
MOV %R9D,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %EDI,%EDX	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 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	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 -0x70(%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 -0x68(%RBP),%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
MOVSXD %EDI,%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	0.17	N/A
MOV %EDX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R10,%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	N/A
MOV (%R11,%RAX,8),%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 -0x78(%RBP),%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
VMOVSD 0x8(%RAX),%XMM2	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%)
LEA (%R11,%RDI,8),%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
CMP $0x1,%EDX	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 23a1c0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1c0>	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
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 23a2b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VMOVDQA -0x35ce8(%RIP),%XMM3	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 (25.0%)
VMOVDDUP %XMM2,%XMM0	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%)
MOV %EBX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x2,%R12D	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%)
VPBROADCASTQ %RDI,%XMM1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %RBX,%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	0.17	scal (12.5%)
JNE 23a2b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b0>	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
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %EDX,%EDX	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 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	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
VMOVSD 0x238(%RAX),%XMM16	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%)
VMOVUPD 0x18(%RAX),%XMM19	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 (25.0%)
VMOVSD 0x28(%RAX),%XMM20	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%)
VMOVSD 0x30(%RAX),%XMM21	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%)
VMOVSD 0x38(%RAX),%XMM4	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%)
VMOVSD 0x40(%RAX),%XMM5	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%)
VMOVSD 0x48(%RAX),%XMM2	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%)
VMOVSD 0x50(%RAX),%XMM8	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%)
VMOVSD 0x58(%RAX),%XMM7	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%)
VMOVSD 0x60(%RAX),%XMM9	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%)
VMOVSD 0x68(%RAX),%XMM10	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%)
VMOVSD 0x70(%RAX),%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%)
VMOVUPD 0x78(%RAX),%XMM6	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 (25.0%)
VMOVSD 0x88(%RAX),%XMM17	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%)
VMOVSD 0x90(%RAX),%XMM18	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 0x218(%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 %EDX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x4,%EDX	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%)
JAE 23a2e9 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e9>	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
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 23a6c5 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x6c5>	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 %R8,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RDI,%R13	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%)
JMP 23a2cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2cc>	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 %EAX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VMOVAPD %XMM17,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM18,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SHR $0x2,%R12D	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%)
VMOVAPD %XMM21,-0x140(%RBP)	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%)
VMOVDDUP %XMM16,%XMM17	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%)
VMOVDDUP %XMM19,%XMM18	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%)
VMOVDDUP %XMM20,%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	scal (12.5%)
VMOVDDUP %XMM21,%XMM21	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%)
VMOVDDUP %XMM4,%XMM22	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%)
VMOVDDUP %XMM5,%XMM23	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%)
VMOVDDUP %XMM2,%XMM24	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%)
VMOVDDUP %XMM8,%XMM25	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%)
VMOVDDUP %XMM7,%XMM26	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%)
VMOVAPD %XMM9,-0xc0(%RBP)	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%)
VMOVDDUP %XMM9,%XMM27	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%)
VMOVAPD %XMM10,-0xb0(%RBP)	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%)
VMOVDDUP %XMM10,%XMM28	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%)
VMOVDDUP %XMM11,%XMM29	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%)
VMOVDDUP %XMM6,%XMM30	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%)
VMOVDDUP %XMM0,%XMM9	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%)
VMOVDDUP %XMM1,%XMM10	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%)
MOV %EAX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVAPD %XMM19,-0x160(%RBP)	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%)
VMOVAPD %XMM5,-0x100(%RBP)	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%)
VMOVAPD %XMM2,-0xe0(%RBP)	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%)
AND $-0x4,%EBX	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
VSHUFPD $0x3,%XMM19,%XMM19,%XMM19	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%)
VSHUFPD $0x3,%XMM6,%XMM6,%XMM31	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%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM5,%XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVSD %XMM14,-0x60(%RBP)	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 %XMM16,-0x170(%RBP)	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%)
VMOVAPD %XMM20,-0x150(%RBP)	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%)
VMOVAPD %XMM4,-0x110(%RBP)	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%)
VMOVAPD %XMM8,-0xd0(%RBP)	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%)
VMOVAPD %XMM7,-0xf0(%RBP)	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%)
VMOVAPD %XMM11,-0xa0(%RBP)	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%)
VMOVAPD %XMM0,-0x130(%RBP)	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%)
VMOVAPD %XMM1,-0x120(%RBP)	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%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
SAL $0x5,%R12	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%)
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
VADDPD %XMM2,%XMM5,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
VMOVSD -0x60(%RBP),%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%)
VMOVDQA -0x90(%RBP),%XMM15	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 (25.0%)
VMOVAPD -0x170(%RBP),%XMM16	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 (25.0%)
VMOVAPD -0x160(%RBP),%XMM19	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 (25.0%)
VMOVAPD -0x150(%RBP),%XMM20	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 (25.0%)
VMOVAPD -0x140(%RBP),%XMM21	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 (25.0%)
VMOVAPD -0x130(%RBP),%XMM17	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 (25.0%)
VMOVAPD -0x120(%RBP),%XMM18	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 (25.0%)
VMOVAPD -0x110(%RBP),%XMM4	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 (25.0%)
VMOVAPD -0x100(%RBP),%XMM5	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 (25.0%)
VMOVAPD -0xf0(%RBP),%XMM7	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 (25.0%)
VMOVAPD -0xe0(%RBP),%XMM2	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 (25.0%)
VMOVAPD -0xd0(%RBP),%XMM8	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 (25.0%)
VMOVAPD -0xc0(%RBP),%XMM9	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 (25.0%)
VMOVAPD -0xb0(%RBP),%XMM10	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 (25.0%)
VMOVAPD -0xa0(%RBP),%XMM11	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 (25.0%)
MOV -0x58(%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	scal (12.5%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	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%)
VADDSD %XMM1,%XMM0,%XMM0	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%)
CMP %RAX,%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 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	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
VUNPCKLPD %XMM10,%XMM2,%XMM1	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%)
VUNPCKLPD %XMM9,%XMM5,%XMM5	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%)
VUNPCKLPD %XMM11,%XMM8,%XMM2	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%)
VUNPCKLPD %XMM7,%XMM4,%XMM9	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%)
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
JMP 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	BsplineFunctor.h:236-260
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:127-132
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-260
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=29
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

41% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

51% of SSE/AVX loads are used in vector version.
93% of SSE/AVX stores are used in vector version.
20% of SSE/AVX addition or subtraction instructions are used in vector version.
19% 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 loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

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.

VPBROADCASTQ: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236

Type of elements and instruction set

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

The binary loop is composed of 4 FP arithmetical operations:

4: addition or subtraction

The binary loop is loading 468 bytes (58 double precision FP elements). The binary loop is storing 232 bytes (29 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	133
nb uops	131
loop length	699
used x86 registers	12
used mmx registers	0
used xmm registers	30
used ymm registers	0
used zmm registers	0
nb stack references	21

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.38 cycles
front end	16.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.50	4.50	4.50	4.50	4.50	4.50	14.00	14.00	14.00	14.00	6.75	6.75	6.75	6.75	7.50	7.50
cycles	4.50	4.50	4.50	4.50	4.50	4.50	14.00	14.00	14.00	14.00	6.75	6.75	6.75	6.75	7.50	7.50

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	16.38
Dispatch	14.00
Overall L1	16.38

Vectorization ratios

INT

all	8%
load	50%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	51%
load	51%
store	93%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	33%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	31%

INT+FP

all	41%
load	51%
store	93%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	20%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	19%

Vector efficiency ratios

INT

all	9%
load	17%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	18%
load	18%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	16%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

INT+FP

all	16%
load	18%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	13%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 16.38 cycles. At this rate:

11% of peak load performance is reached (28.58 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.17 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 23a170

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
VADDSD %XMM0,%XMM14,%XMM14	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%)
INC %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	0.17	N/A
CMP %RCX,%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	0.17	scal (12.5%)
JE 23a045 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x45>	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 -0x80(%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 %R9D,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOV 0x4(%RAX,%R10,4),%R9D	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 (6.3%)
MOV %R9D,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %EDI,%EDX	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 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	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 -0x70(%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 -0x68(%RBP),%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
MOVSXD %EDI,%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	0.17	N/A
MOV %EDX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R10,%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	N/A
MOV (%R11,%RAX,8),%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 -0x78(%RBP),%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
VMOVSD 0x8(%RAX),%XMM2	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%)
LEA (%R11,%RDI,8),%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
CMP $0x1,%EDX	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 23a1c0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1c0>	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
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 23a2b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VMOVDQA -0x35ce8(%RIP),%XMM3	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 (25.0%)
VMOVDDUP %XMM2,%XMM0	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%)
MOV %EBX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x2,%R12D	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%)
VPBROADCASTQ %RDI,%XMM1	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %RBX,%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	0.17	scal (12.5%)
JNE 23a2b0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b0>	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
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %EDX,%EDX	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 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	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
VMOVSD 0x238(%RAX),%XMM16	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%)
VMOVUPD 0x18(%RAX),%XMM19	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 (25.0%)
VMOVSD 0x28(%RAX),%XMM20	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%)
VMOVSD 0x30(%RAX),%XMM21	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%)
VMOVSD 0x38(%RAX),%XMM4	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%)
VMOVSD 0x40(%RAX),%XMM5	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%)
VMOVSD 0x48(%RAX),%XMM2	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%)
VMOVSD 0x50(%RAX),%XMM8	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%)
VMOVSD 0x58(%RAX),%XMM7	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%)
VMOVSD 0x60(%RAX),%XMM9	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%)
VMOVSD 0x68(%RAX),%XMM10	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%)
VMOVSD 0x70(%RAX),%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%)
VMOVUPD 0x78(%RAX),%XMM6	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 (25.0%)
VMOVSD 0x88(%RAX),%XMM17	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%)
VMOVSD 0x90(%RAX),%XMM18	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 0x218(%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 %EDX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x4,%EDX	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%)
JAE 23a2e9 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e9>	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
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 23a6c5 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x6c5>	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 %R8,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %RDI,%R13	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%)
JMP 23a2cc <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2cc>	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 %EAX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VMOVAPD %XMM17,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVAPD %XMM18,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SHR $0x2,%R12D	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%)
VMOVAPD %XMM21,-0x140(%RBP)	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%)
VMOVDDUP %XMM16,%XMM17	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%)
VMOVDDUP %XMM19,%XMM18	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%)
VMOVDDUP %XMM20,%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	scal (12.5%)
VMOVDDUP %XMM21,%XMM21	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%)
VMOVDDUP %XMM4,%XMM22	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%)
VMOVDDUP %XMM5,%XMM23	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%)
VMOVDDUP %XMM2,%XMM24	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%)
VMOVDDUP %XMM8,%XMM25	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%)
VMOVDDUP %XMM7,%XMM26	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%)
VMOVAPD %XMM9,-0xc0(%RBP)	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%)
VMOVDDUP %XMM9,%XMM27	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%)
VMOVAPD %XMM10,-0xb0(%RBP)	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%)
VMOVDDUP %XMM10,%XMM28	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%)
VMOVDDUP %XMM11,%XMM29	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%)
VMOVDDUP %XMM6,%XMM30	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%)
VMOVDDUP %XMM0,%XMM9	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%)
VMOVDDUP %XMM1,%XMM10	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%)
MOV %EAX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVAPD %XMM19,-0x160(%RBP)	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%)
VMOVAPD %XMM5,-0x100(%RBP)	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%)
VMOVAPD %XMM2,-0xe0(%RBP)	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%)
AND $-0x4,%EBX	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
VSHUFPD $0x3,%XMM19,%XMM19,%XMM19	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%)
VSHUFPD $0x3,%XMM6,%XMM6,%XMM31	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%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM5,%XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVSD %XMM14,-0x60(%RBP)	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 %XMM16,-0x170(%RBP)	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%)
VMOVAPD %XMM20,-0x150(%RBP)	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%)
VMOVAPD %XMM4,-0x110(%RBP)	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%)
VMOVAPD %XMM8,-0xd0(%RBP)	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%)
VMOVAPD %XMM7,-0xf0(%RBP)	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%)
VMOVAPD %XMM11,-0xa0(%RBP)	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%)
VMOVAPD %XMM0,-0x130(%RBP)	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%)
VMOVAPD %XMM1,-0x120(%RBP)	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%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
SAL $0x5,%R12	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%)
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
VADDPD %XMM2,%XMM5,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	vect (25.0%)
VMOVSD -0x60(%RBP),%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%)
VMOVDQA -0x90(%RBP),%XMM15	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 (25.0%)
VMOVAPD -0x170(%RBP),%XMM16	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 (25.0%)
VMOVAPD -0x160(%RBP),%XMM19	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 (25.0%)
VMOVAPD -0x150(%RBP),%XMM20	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 (25.0%)
VMOVAPD -0x140(%RBP),%XMM21	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 (25.0%)
VMOVAPD -0x130(%RBP),%XMM17	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 (25.0%)
VMOVAPD -0x120(%RBP),%XMM18	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 (25.0%)
VMOVAPD -0x110(%RBP),%XMM4	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 (25.0%)
VMOVAPD -0x100(%RBP),%XMM5	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 (25.0%)
VMOVAPD -0xf0(%RBP),%XMM7	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 (25.0%)
VMOVAPD -0xe0(%RBP),%XMM2	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 (25.0%)
VMOVAPD -0xd0(%RBP),%XMM8	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 (25.0%)
VMOVAPD -0xc0(%RBP),%XMM9	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 (25.0%)
VMOVAPD -0xb0(%RBP),%XMM10	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 (25.0%)
VMOVAPD -0xa0(%RBP),%XMM11	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 (25.0%)
MOV -0x58(%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	scal (12.5%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	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%)
VADDSD %XMM1,%XMM0,%XMM0	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%)
CMP %RAX,%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 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	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
VUNPCKLPD %XMM10,%XMM2,%XMM1	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%)
VUNPCKLPD %XMM9,%XMM5,%XMM5	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%)
VUNPCKLPD %XMM11,%XMM8,%XMM2	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%)
VUNPCKLPD %XMM7,%XMM4,%XMM9	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%)
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
JMP 23a160 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x160>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Complex instructions

Details

Type of elements and instruction set

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

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

Complex instructions

Details

Type of elements and instruction set

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

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