OV - exec - Loop 325

	Loop Id: 325	Module: exec	Source: BsplineFunctor.h:236-260 [...]	Coverage: 0.02%

0x23fb50 VADDSD	%XMM0,%XMM14,%XMM14

0x23fb54 INC	%R12

0x23fb57 CMP	%R9,%R12

0x23fb5a JE	23fa15

0x23fb60 MOV	0x88(%RSP),%RAX

0x23fb68 MOV	%R15D,%EDI

0x23fb6b VXORPD	%XMM0,%XMM0,%XMM0

0x23fb6f MOV	0x4(%RAX,%R12,4),%R15D

0x23fb74 MOV	%R15D,%EDX

0x23fb77 SUB	%EDI,%EDX

0x23fb79 JLE	23fb50

0x23fb7b MOV	0x80(%RSP),%RAX

0x23fb83 MOV	0x78(%RSP),%RCX

0x23fb88 MOVSXD	%EDI,%RDI

0x23fb8b MOV	%R12,0x48(%RSP)

0x23fb90 MOV	%EDX,%EBX

0x23fb92 LEA	(%R10,%RDI,8),%R11

0x23fb96 ADD	%R12,%RAX

0x23fb99 MOV	(%RCX,%RAX,8),%RAX

0x23fb9d VMOVSD	0x8(%RAX),%XMM0

0x23fba2 CMP	$0x8,%EDX

0x23fba5 JAE	23fbc0

0x23fba7 XOR	%R12D,%R12D

0x23fbaa XOR	%EDX,%EDX

0x23fbac JMP	23fcd0

0x23fbc0 VMOVDQA64	-0x36eca(%RIP),%ZMM3

0x23fbca VBROADCASTSD	%XMM0,%ZMM1

0x23fbd0 MOV	%EBX,%R12D

0x23fbd3 AND	$-0x8,%R12D

0x23fbd7 VPBROADCASTQ	%RDI,%ZMM2

0x23fbdd MOV	%R15D,%ECX

0x23fbe0 XOR	%R13D,%R13D

0x23fbe3 XOR	%EDX,%EDX

0x23fbe5 NOPW	%CS:(%RAX,%RAX,1)

  (326) 0x23fbf0 VMOVUPD	(%R11,%R13,8),%ZMM4

  (326) 0x23fbf7 VPADDQ	%ZMM2,%ZMM3,%ZMM5

  (326) 0x23fbfd VPADDQ	-0x3bb0f(%RIP){1to8},%ZMM3,%ZMM3

  (326) 0x23fc07 MOVSXD	%EDX,%RDX

  (326) 0x23fc0a VPCMPNEQQ	%ZMM15,%ZMM5,%K1

  (326) 0x23fc11 VCMPPD	$0x1,%ZMM1,%ZMM4,%K1{%K1}

  (326) 0x23fc18 KMOVB	%K1,%R15D

  (326) 0x23fc1c VCOMPRESSPD	%ZMM4,(%RSI,%RDX,8){%K1}

  (326) 0x23fc23 POPCNT	%R15D,%R15D

  (326) 0x23fc28 KORTESTB	%K1,%K1

  (326) 0x23fc2c CMOVE	%R14D,%R15D

  (326) 0x23fc30 ADD	$0x8,%R13

  (326) 0x23fc34 ADD	%R15D,%EDX

  (326) 0x23fc37 CMP	%R13,%R12

  (326) 0x23fc3a JNE	23fbf0

0x23fc3c MOV	%ECX,%R15D

0x23fc3f CMP	%RBX,%R12

0x23fc42 JNE	23fcd0

0x23fc48 MOV	0x48(%RSP),%R12

0x23fc4d VXORPD	%XMM0,%XMM0,%XMM0

0x23fc51 TEST	%EDX,%EDX

0x23fc53 JLE	23fb50

0x23fc59 VMOVSD	0x238(%RAX),%XMM16

0x23fc60 VMOVUPD	0x18(%RAX),%XMM19

0x23fc6a VMOVSD	0x28(%RAX),%XMM20

0x23fc71 VMOVSD	0x30(%RAX),%XMM21

0x23fc78 VMOVSD	0x38(%RAX),%XMM4

0x23fc7d VMOVSD	0x40(%RAX),%XMM5

0x23fc82 VMOVSD	0x48(%RAX),%XMM2

0x23fc87 VMOVSD	0x50(%RAX),%XMM8

0x23fc8c VMOVSD	0x58(%RAX),%XMM7

0x23fc91 VMOVSD	0x60(%RAX),%XMM9

0x23fc96 VMOVSD	0x68(%RAX),%XMM10

0x23fc9b VMOVSD	0x70(%RAX),%XMM11

0x23fca0 VMOVUPD	0x78(%RAX),%XMM6

0x23fca5 VMOVSD	0x88(%RAX),%XMM17

0x23fcac VMOVSD	0x90(%RAX),%XMM18

0x23fcb3 MOV	0x218(%RAX),%R11

0x23fcba MOV	%EDX,%EAX

0x23fcbc CMP	$0x8,%EDX

0x23fcbf JAE	23fd09

0x23fcc1 XOR	%EBX,%EBX

0x23fcc3 JMP	240241

0x23fcd0 MOV	%R8,%R13

0x23fcd3 SUB	%RDI,%R13

0x23fcd6 JMP	23fcec

  (329) 0x23fce0 INC	%R12

  (329) 0x23fce3 CMP	%R12,%RBX

  (329) 0x23fce6 JE	23fc48

  (329) 0x23fcec CMP	%R12,%R13

  (329) 0x23fcef JE	23fce0

  (329) 0x23fcf1 VMOVSD	(%R11,%R12,8),%XMM1

  (329) 0x23fcf7 VUCOMISD	%XMM0,%XMM1

  (329) 0x23fcfb JAE	23fce0

  (329) 0x23fcfd MOVSXD	%EDX,%RCX

  (329) 0x23fd00 INC	%EDX

  (329) 0x23fd02 VMOVSD	%XMM1,(%RSI,%RCX,8)

  (329) 0x23fd07 JMP	23fce0

0x23fd09 MOV	%EAX,%R12D

0x23fd0c VMOVAPD	%XMM17,%XMM0

0x23fd12 VMOVAPD	%XMM18,%XMM1

0x23fd18 SHR	$0x3,%R12D

0x23fd1c VMOVAPD	%XMM21,0x130(%RSP)

0x23fd24 VBROADCASTSD	%XMM16,%YMM17

0x23fd2a VBROADCASTSD	%XMM19,%YMM18

0x23fd30 VMOVAPD	%YMM19,0x160(%RSP)

0x23fd38 VPERMPD	$0x55,%YMM19,%YMM19

0x23fd3f VBROADCASTSD	%XMM20,%YMM3

0x23fd45 VBROADCASTSD	%XMM21,%YMM21

0x23fd4b VBROADCASTSD	%XMM4,%YMM22

0x23fd51 VBROADCASTSD	%XMM5,%YMM23

0x23fd57 VBROADCASTSD	%XMM2,%YMM24

0x23fd5d VBROADCASTSD	%XMM8,%YMM25

0x23fd63 VBROADCASTSD	%XMM7,%YMM26

0x23fd69 VMOVAPD	%XMM9,0xb0(%RSP)

0x23fd72 VBROADCASTSD	%XMM9,%YMM27

0x23fd78 VMOVAPD	%XMM10,0xa0(%RSP)

0x23fd81 VBROADCASTSD	%XMM10,%YMM28

0x23fd87 VBROADCASTSD	%XMM11,%YMM29

0x23fd8d VBROADCASTSD	%XMM6,%YMM30

0x23fd93 VPERMPD	$0x55,%YMM6,%YMM31

0x23fd9a VBROADCASTSD	%XMM0,%YMM9

0x23fd9f VBROADCASTSD	%XMM1,%YMM10

0x23fda4 MOV	%EAX,%EBX

0x23fda6 VMOVAPD	%XMM5,0xf0(%RSP)

0x23fdaf VMOVAPD	%XMM2,0xd0(%RSP)

0x23fdb8 AND	$-0x8,%EBX

0x23fdbb VXORPD	%XMM2,%XMM2,%XMM2

0x23fdbf VXORPD	%XMM5,%XMM5,%XMM5

0x23fdc3 MOV	%R15D,0x3c(%RSP)

0x23fdc8 VMOVSD	%XMM14,0x70(%RSP)

0x23fdce VMOVAPD	%XMM16,0x150(%RSP)

0x23fdd6 VMOVAPD	%XMM20,0x140(%RSP)

0x23fdde VMOVAPD	%XMM4,0x100(%RSP)

0x23fde7 VMOVAPD	%XMM8,0xc0(%RSP)

0x23fdf0 VMOVAPD	%XMM7,0xe0(%RSP)

0x23fdf9 VMOVAPD	%XMM11,0x90(%RSP)

0x23fe02 VMOVAPD	%XMM0,0x120(%RSP)

0x23fe0b VMOVAPD	%XMM1,0x110(%RSP)

0x23fe14 XOR	%EDX,%EDX

0x23fe16 SAL	$0x6,%R12

0x23fe1a NOPW	(%RAX,%RAX,1)

  (327) 0x23fe20 VMULPD	(%RSI,%RDX,1),%YMM17,%YMM11

  (327) 0x23fe27 VMULPD	0x20(%RSI,%RDX,1),%YMM17,%YMM13

  (327) 0x23fe2f VMOVAPD	%YMM3,%YMM20

  (327) 0x23fe35 ADD	$0x40,%RDX

  (327) 0x23fe39 VCVTTPD2DQ	%YMM11,%XMM1

  (327) 0x23fe3e VCVTTPD2DQ	%YMM13,%XMM0

  (327) 0x23fe43 VROUNDPD	$0xb,%YMM11,%YMM12

  (327) 0x23fe49 VROUNDPD	$0xb,%YMM13,%YMM14

  (327) 0x23fe4f VPMOVSXDQ	%XMM1,%YMM4

  (327) 0x23fe54 VPMOVSXDQ	%XMM0,%YMM7

  (327) 0x23fe59 VSUBPD	%YMM12,%YMM11,%YMM12

  (327) 0x23fe5e VSUBPD	%YMM14,%YMM13,%YMM11

  (327) 0x23fe63 VPEXTRQ	$0x1,%XMM4,%RDI

  (327) 0x23fe69 VMOVQ	%XMM4,%R15

  (327) 0x23fe6e VEXTRACTI128	$0x1,%YMM4,%XMM4

  (327) 0x23fe74 VMOVQ	%XMM7,%RCX

  (327) 0x23fe79 VPEXTRQ	$0x1,%XMM7,%R14

  (327) 0x23fe7f VMOVQ	%XMM4,%R13

  (327) 0x23fe84 VPEXTRQ	$0x1,%XMM4,%R8

  (327) 0x23fe8a VEXTRACTI128	$0x1,%YMM7,%XMM4

  (327) 0x23fe90 VMOVSD	(%R11,%R15,8),%XMM7

  (327) 0x23fe96 VMOVSD	(%R11,%RCX,8),%XMM8

  (327) 0x23fe9c VMULPD	%YMM12,%YMM12,%YMM16

  (327) 0x23fea2 VFMADD213PD	%YMM21,%YMM11,%YMM20

  (327) 0x23fea8 VMULPD	%YMM11,%YMM11,%YMM15

  (327) 0x23fead VMOVQ	%XMM4,%R9

  (327) 0x23feb2 VPEXTRQ	$0x1,%XMM4,%R10

  (327) 0x23feb8 VMOVSD	(%R11,%R13,8),%XMM4

  (327) 0x23febe VMOVHPD	(%R11,%RDI,8),%XMM7,%XMM7

  (327) 0x23fec4 VMOVHPD	(%R11,%R14,8),%XMM8,%XMM8

  (327) 0x23feca VMOVHPD	(%R11,%R8,8),%XMM4,%XMM4

  (327) 0x23fed0 VMULPD	%YMM12,%YMM16,%YMM14

  (327) 0x23fed6 VMULPD	%YMM11,%YMM15,%YMM13

  (327) 0x23fedb VFMADD231PD	%YMM19,%YMM15,%YMM20

  (327) 0x23fee1 VFMADD231PD	%YMM18,%YMM13,%YMM20

  (327) 0x23fee7 VINSERTF128	$0x1,%XMM4,%YMM7,%YMM4

  (327) 0x23feed VMOVSD	(%R11,%R9,8),%XMM7

  (327) 0x23fef3 VMOVHPD	(%R11,%R10,8),%XMM7,%XMM7

  (327) 0x23fef9 VINSERTF128	$0x1,%XMM7,%YMM8,%YMM7

  (327) 0x23feff VMOVAPD	%YMM3,%YMM8

  (327) 0x23ff03 VFMADD213PD	%YMM21,%YMM12,%YMM8

  (327) 0x23ff09 VFMADD213PD	%YMM5,%YMM7,%YMM20

  (327) 0x23ff0f VMOVAPD	%YMM24,%YMM7

  (327) 0x23ff15 VFMADD213PD	%YMM25,%YMM11,%YMM7

  (327) 0x23ff1b VFMADD231PD	%YMM19,%YMM16,%YMM8

  (327) 0x23ff21 VFMADD231PD	%YMM23,%YMM15,%YMM7

  (327) 0x23ff27 VFMADD231PD	%YMM18,%YMM14,%YMM8

  (327) 0x23ff2d VFMADD231PD	%YMM22,%YMM13,%YMM7

  (327) 0x23ff33 VFMADD213PD	%YMM2,%YMM4,%YMM8

  (327) 0x23ff38 VPCMPEQD	%XMM4,%XMM4,%XMM4

  (327) 0x23ff3c VPSUBD	%XMM4,%XMM1,%XMM2

  (327) 0x23ff40 VPSUBD	%XMM4,%XMM0,%XMM4

  (327) 0x23ff44 VPMOVSXDQ	%XMM2,%YMM2

  (327) 0x23ff49 VPMOVSXDQ	%XMM4,%YMM4

  (327) 0x23ff4e VMOVQ	%XMM2,%RCX

  (327) 0x23ff53 VPEXTRQ	$0x1,%XMM2,%RDI

  (327) 0x23ff59 VEXTRACTI128	$0x1,%YMM2,%XMM2

  (327) 0x23ff5f VMOVQ	%XMM4,%R10

  (327) 0x23ff64 VPEXTRQ	$0x1,%XMM4,%R14

  (327) 0x23ff6a VPEXTRQ	$0x1,%XMM2,%R8

  (327) 0x23ff70 VMOVQ	%XMM2,%R9

  (327) 0x23ff75 VEXTRACTI128	$0x1,%YMM4,%XMM2

  (327) 0x23ff7b VMOVSD	(%R11,%RCX,8),%XMM4

  (327) 0x23ff81 VMOVSD	(%R11,%R10,8),%XMM5

  (327) 0x23ff87 VMOVQ	%XMM2,%R15

  (327) 0x23ff8c VPEXTRQ	$0x1,%XMM2,%R13

  (327) 0x23ff92 VMOVSD	(%R11,%R9,8),%XMM2

  (327) 0x23ff98 VMOVHPD	(%R11,%RDI,8),%XMM4,%XMM4

  (327) 0x23ff9e VMOVHPD	(%R11,%R14,8),%XMM5,%XMM5

  (327) 0x23ffa4 VMOVHPD	(%R11,%R8,8),%XMM2,%XMM2

  (327) 0x23ffaa VINSERTF128	$0x1,%XMM2,%YMM4,%YMM2

  (327) 0x23ffb0 VMOVSD	(%R11,%R15,8),%XMM4

  (327) 0x23ffb6 VMOVHPD	(%R11,%R13,8),%XMM4,%XMM4

  (327) 0x23ffbc VINSERTF128	$0x1,%XMM4,%YMM5,%YMM4

  (327) 0x23ffc2 VMOVAPD	%YMM24,%YMM5

  (327) 0x23ffc8 VFMADD213PD	%YMM25,%YMM12,%YMM5

  (327) 0x23ffce VFMADD213PD	%YMM20,%YMM4,%YMM7

  (327) 0x23ffd4 VMOVAPD	%YMM28,%YMM20

  (327) 0x23ffda VFMADD213PD	%YMM29,%YMM11,%YMM20

  (327) 0x23ffe0 VFMADD213PD	%YMM10,%YMM9,%YMM11

  (327) 0x23ffe5 VFMADD231PD	%YMM23,%YMM16,%YMM5

  (327) 0x23ffeb VFMADD231PD	%YMM27,%YMM15,%YMM20

  (327) 0x23fff1 VFMADD231PD	%YMM15,%YMM31,%YMM11

  (327) 0x23fff7 VFMADD231PD	%YMM22,%YMM14,%YMM5

  (327) 0x23fffd VFMADD231PD	%YMM26,%YMM13,%YMM20

  (327) 0x240003 VFMADD231PD	%YMM13,%YMM30,%YMM11

  (327) 0x240009 VFMADD213PD	%YMM8,%YMM2,%YMM5

  (327) 0x24000e VPBROADCASTD	-0x3bf47(%RIP),%XMM2

  (327) 0x240017 VPADDD	%XMM2,%XMM1,%XMM4

  (327) 0x24001b VPADDD	%XMM2,%XMM0,%XMM2

  (327) 0x24001f VPMOVSXDQ	%XMM4,%YMM4

  (327) 0x240024 VPMOVSXDQ	%XMM2,%YMM2

  (327) 0x240029 VMOVQ	%XMM4,%RCX

  (327) 0x24002e VPEXTRQ	$0x1,%XMM4,%RDI

  (327) 0x240034 VEXTRACTI128	$0x1,%YMM4,%XMM4

  (327) 0x24003a VMOVQ	%XMM2,%R14

  (327) 0x24003f VPEXTRQ	$0x1,%XMM2,%R10

  (327) 0x240045 VEXTRACTI128	$0x1,%YMM2,%XMM2

  (327) 0x24004b VMOVQ	%XMM4,%R8

  (327) 0x240050 VPEXTRQ	$0x1,%XMM4,%R9

  (327) 0x240056 VMOVSD	(%R11,%RCX,8),%XMM4

  (327) 0x24005c VMOVQ	%XMM2,%R15

  (327) 0x240061 VPEXTRQ	$0x1,%XMM2,%R13

  (327) 0x240067 VMOVSD	(%R11,%R14,8),%XMM8

  (327) 0x24006d VMOVSD	(%R11,%R8,8),%XMM2

  (327) 0x240073 VMOVHPD	(%R11,%RDI,8),%XMM4,%XMM4

  (327) 0x240079 VMOVHPD	(%R11,%R10,8),%XMM8,%XMM8

  (327) 0x24007f VMOVHPD	(%R11,%R9,8),%XMM2,%XMM2

  (327) 0x240085 VINSERTF128	$0x1,%XMM2,%YMM4,%YMM2

  (327) 0x24008b VMOVSD	(%R11,%R15,8),%XMM4

  (327) 0x240091 VMOVHPD	(%R11,%R13,8),%XMM4,%XMM4

  (327) 0x240097 VINSERTF128	$0x1,%XMM4,%YMM8,%YMM4

  (327) 0x24009d VMOVAPD	%YMM28,%YMM8

  (327) 0x2400a3 VFMADD213PD	%YMM29,%YMM12,%YMM8

  (327) 0x2400a9 VFMADD213PD	%YMM10,%YMM9,%YMM12

  (327) 0x2400ae VFMADD213PD	%YMM7,%YMM4,%YMM20

  (327) 0x2400b4 VFMADD231PD	%YMM27,%YMM16,%YMM8

  (327) 0x2400ba VFMADD231PD	%YMM16,%YMM31,%YMM12

  (327) 0x2400c0 VFMADD231PD	%YMM26,%YMM14,%YMM8

  (327) 0x2400c6 VFMADD231PD	%YMM14,%YMM30,%YMM12

  (327) 0x2400cc VFMADD213PD	%YMM5,%YMM2,%YMM8

  (327) 0x2400d1 VPBROADCASTD	-0x3c006(%RIP),%XMM2

  (327) 0x2400da VMOVAPD	%YMM11,%YMM5

  (327) 0x2400de VPADDD	%XMM2,%XMM1,%XMM1

  (327) 0x2400e2 VPADDD	%XMM2,%XMM0,%XMM0

  (327) 0x2400e6 VPMOVSXDQ	%XMM1,%YMM1

  (327) 0x2400eb VPMOVSXDQ	%XMM0,%YMM0

  (327) 0x2400f0 VMOVQ	%XMM1,%RCX

  (327) 0x2400f5 VPEXTRQ	$0x1,%XMM1,%RDI

  (327) 0x2400fb VEXTRACTI128	$0x1,%YMM1,%XMM1

  (327) 0x240101 VMOVQ	%XMM0,%R10

  (327) 0x240106 VPEXTRQ	$0x1,%XMM0,%R14

  (327) 0x24010c VEXTRACTI128	$0x1,%YMM0,%XMM0

  (327) 0x240112 VMOVQ	%XMM1,%R9

  (327) 0x240117 VPEXTRQ	$0x1,%XMM1,%R8

  (327) 0x24011d VMOVSD	(%R11,%RCX,8),%XMM1

  (327) 0x240123 VMOVQ	%XMM0,%R15

  (327) 0x240128 VPEXTRQ	$0x1,%XMM0,%R13

  (327) 0x24012e VMOVSD	(%R11,%R10,8),%XMM2

  (327) 0x240134 VMOVSD	(%R11,%R9,8),%XMM0

  (327) 0x24013a VMOVHPD	(%R11,%RDI,8),%XMM1,%XMM1

  (327) 0x240140 VMOVHPD	(%R11,%R14,8),%XMM2,%XMM2

  (327) 0x240146 VMOVHPD	(%R11,%R8,8),%XMM0,%XMM0

  (327) 0x24014c VINSERTF128	$0x1,%XMM0,%YMM1,%YMM0

  (327) 0x240152 VMOVSD	(%R11,%R15,8),%XMM1

  (327) 0x240158 VMOVHPD	(%R11,%R13,8),%XMM1,%XMM1

  (327) 0x24015e VINSERTF128	$0x1,%XMM1,%YMM2,%YMM1

  (327) 0x240164 VMOVAPD	%YMM12,%YMM2

  (327) 0x240168 VFMADD213PD	%YMM8,%YMM0,%YMM2

  (327) 0x24016d VFMADD213PD	%YMM20,%YMM1,%YMM5

  (327) 0x240173 CMP	%RDX,%R12

  (327) 0x240176 JNE	23fe20

0x24017c VADDPD	%YMM2,%YMM5,%YMM0

0x240180 VMOVSD	0x70(%RSP),%XMM14

0x240186 VMOVDQA64	0x180(%RSP),%ZMM15

0x24018e VMOVAPD	0x150(%RSP),%XMM16

0x240196 VMOVAPD	0x160(%RSP),%YMM19

0x24019e VMOVAPD	0x140(%RSP),%XMM20

0x2401a6 VMOVAPD	0x130(%RSP),%XMM21

0x2401ae VMOVAPD	0x120(%RSP),%XMM17

0x2401b6 VMOVAPD	0x110(%RSP),%XMM18

0x2401be VMOVAPD	0x100(%RSP),%XMM4

0x2401c7 VMOVAPD	0xf0(%RSP),%XMM5

0x2401d0 VMOVAPD	0xe0(%RSP),%XMM7

0x2401d9 VMOVAPD	0xd0(%RSP),%XMM2

0x2401e2 VMOVAPD	0xc0(%RSP),%XMM8

0x2401eb VMOVAPD	0xb0(%RSP),%XMM9

0x2401f4 VMOVAPD	0xa0(%RSP),%XMM10

0x2401fd VMOVAPD	0x90(%RSP),%XMM11

0x240206 MOV	0x68(%RSP),%R8

0x24020b MOV	0x60(%RSP),%R9

0x240210 MOV	0x58(%RSP),%R10

0x240215 MOV	0x3c(%RSP),%R15D

0x24021a MOV	0x48(%RSP),%R12

0x24021f MOV	$0,%R14D

0x240225 VEXTRACTF128	$0x1,%YMM0,%XMM1

0x24022b VADDPD	%XMM1,%XMM0,%XMM0

0x24022f VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

0x240234 VADDSD	%XMM1,%XMM0,%XMM0

0x240238 CMP	%RAX,%RBX

0x24023b JE	23fb50

0x240241 VUNPCKLPD	%XMM10,%XMM2,%XMM1

0x240246 VUNPCKLPD	%XMM9,%XMM5,%XMM5

0x24024b VUNPCKLPD	%XMM11,%XMM8,%XMM2

0x240250 VUNPCKLPD	%XMM7,%XMM4,%XMM9

0x240254 NOPW	%CS:(%RAX,%RAX,1)

  (328) 0x240260 VMULSD	(%RSI,%RBX,8),%XMM16,%XMM3

  (328) 0x240267 INC	%RBX

  (328) 0x24026a VROUNDSD	$0xb,%XMM3,%XMM3,%XMM4

  (328) 0x240270 VCVTTSD2SI	%XMM3,%ECX

  (328) 0x240274 MOVSXD	%ECX,%RDX

  (328) 0x240277 VSUBSD	%XMM4,%XMM3,%XMM3

  (328) 0x24027b VMOVAPD	%XMM20,%XMM4

  (328) 0x240281 VMULSD	%XMM3,%XMM3,%XMM8

  (328) 0x240285 VMOVDDUP	%XMM3,%XMM7

  (328) 0x240289 VFMADD213SD	%XMM21,%XMM3,%XMM4

  (328) 0x24028f VFMADD213PD	%XMM2,%XMM1,%XMM7

  (328) 0x240294 VMULSD	%XMM3,%XMM8,%XMM10

  (328) 0x240298 VMOVDDUP	%XMM8,%XMM8

  (328) 0x24029d VFMADD213SD	%XMM18,%XMM17,%XMM3

  (328) 0x2402a3 VMOVDDUP	%XMM10,%XMM10

  (328) 0x2402a8 VFMADD231PD	%XMM8,%XMM5,%XMM7

  (328) 0x2402ad VUNPCKLPD	%XMM8,%XMM10,%XMM11

  (328) 0x2402b2 VMULPD	%XMM19,%XMM11,%XMM12

  (328) 0x2402b8 VMULPD	%XMM6,%XMM11,%XMM8

  (328) 0x2402bc VFMADD231PD	%XMM10,%XMM9,%XMM7

  (328) 0x2402c1 VMULPD	0x8(%R11,%RDX,8),%XMM7,%XMM7

  (328) 0x2402c8 VADDSD	%XMM4,%XMM12,%XMM4

  (328) 0x2402cc VSHUFPD	$0x1,%XMM12,%XMM12,%XMM13

  (328) 0x2402d2 VADDSD	%XMM3,%XMM8,%XMM3

  (328) 0x2402d6 VSHUFPD	$0x1,%XMM8,%XMM8,%XMM10

  (328) 0x2402dc VADDSD	%XMM4,%XMM13,%XMM4

  (328) 0x2402e0 VFMADD132SD	(%R11,%RDX,8),%XMM0,%XMM4

  (328) 0x2402e6 VADDSD	%XMM3,%XMM10,%XMM3

  (328) 0x2402ea VSHUFPD	$0x1,%XMM7,%XMM7,%XMM0

  (328) 0x2402ef VADDSD	%XMM0,%XMM7,%XMM0

  (328) 0x2402f3 VADDSD	%XMM0,%XMM4,%XMM0

  (328) 0x2402f7 VFMADD231SD	0x18(%R11,%RDX,8),%XMM3,%XMM0

  (328) 0x2402fe CMP	%RBX,%RAX

  (328) 0x240301 JNE	240260

0x240307 JMP	23fb50

/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
►96.38+	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
►2.75+	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	1.39
CQA speedup if FP arith vectorized	1.31
CQA speedup if fully vectorized	2.02
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.15
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	17.75
CQA cycles if no scalar integer	12.75
CQA cycles if FP arith vectorized	13.53
CQA cycles if fully vectorized	8.81
Front-end cycles	17.75
P0 cycles	4.67
P1 cycles	4.67
P2 cycles	4.67
P3 cycles	4.67
P4 cycles	4.67
P5 cycles	4.67
P6 cycles	15.50
P7 cycles	15.50
P8 cycles	15.50
P9 cycles	15.50
P10 cycles	4.25
P11 cycles	10.50
P12 cycles	10.00
P13 cycles	4.25
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	144.00
Nb uops	142.00
Nb loads	45.00
Nb stores	17.00
Nb stack references	24.00
FLOP/cycle	0.45
Nb FLOP add-sub	8.00
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	48.90
Bytes prefetched	0.00
Bytes loaded	608.00
Bytes stored	260.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	41.90
Vectorization ratio load	47.37
Vectorization ratio store	82.35
Vectorization ratio mul	NA
Vectorization ratio add_sub	33.33
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	22.73
Vector-efficiency ratio all	19.52
Vector-efficiency ratio load	22.70
Vector-efficiency ratio store	23.90
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	19.79
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	15.06

Metric	Value
CQA speedup if no scalar integer	1.39
CQA speedup if FP arith vectorized	1.31
CQA speedup if fully vectorized	2.02
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.15
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	17.75
CQA cycles if no scalar integer	12.75
CQA cycles if FP arith vectorized	13.53
CQA cycles if fully vectorized	8.81
Front-end cycles	17.75
P0 cycles	4.67
P1 cycles	4.67
P2 cycles	4.67
P3 cycles	4.67
P4 cycles	4.67
P5 cycles	4.67
P6 cycles	15.50
P7 cycles	15.50
P8 cycles	15.50
P9 cycles	15.50
P10 cycles	4.25
P11 cycles	10.50
P12 cycles	10.00
P13 cycles	4.25
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	144.00
Nb uops	142.00
Nb loads	45.00
Nb stores	17.00
Nb stack references	24.00
FLOP/cycle	0.45
Nb FLOP add-sub	8.00
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	48.90
Bytes prefetched	0.00
Bytes loaded	608.00
Bytes stored	260.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	41.90
Vectorization ratio load	47.37
Vectorization ratio store	82.35
Vectorization ratio mul	NA
Vectorization ratio add_sub	33.33
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	22.73
Vector-efficiency ratio all	19.52
Vector-efficiency ratio load	22.70
Vector-efficiency ratio store	23.90
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	19.79
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	15.06

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 17.75 to 12.75 cycles (1.39x 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 19% 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 17.75 to 8.81 cycles (2.02x speedup).

Details

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

47% of SSE/AVX loads are used in vector version.
82% of SSE/AVX stores are used in vector version.
33% of SSE/AVX addition or subtraction instructions are used in vector version.
22% 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

Vector unaligned load/store instructions

Detected 1 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:246

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Use vector aligned instructions:
1. align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
2. inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Type of elements and instruction set

2 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 1 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time). 1 AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (four at a time).

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

The binary loop is composed of 8 FP arithmetical operations:

8: addition or subtraction

The binary loop is loading 608 bytes (76 double precision FP elements). The binary loop is storing 260 bytes (32 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	144
nb uops	142
loop length	805
used x86 registers	14
used mmx registers	0
used xmm registers	18
used ymm registers	21
used zmm registers	4
nb stack references	24

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	17.75 cycles
front end	17.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.67	4.67	4.67	4.67	4.67	4.67	15.50	15.50	15.50	15.50	4.25	10.50	10.00	4.25	7.50	7.50
cycles	4.67	4.67	4.67	4.67	4.67	4.67	15.50	15.50	15.50	15.50	4.25	10.50	10.00	4.25	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	17.75
Dispatch	15.50
Overall L1	17.75

Vectorization ratios

INT

all	8%
load	28%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	52%
load	51%
store	93%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	33%

INT+FP

all	41%
load	47%
store	82%
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	22%

Vector efficiency ratios

INT

all	16%
load	35%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
other	8%

all	20%
load	19%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	18%

INT+FP

all	19%
load	22%
store	23%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	19%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 17.75 cycles. At this rate:

13% of peak load performance is reached (34.25 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.65 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 17.75 to 15.50 cycles (1.15x speedup).

ASM code

In the binary file, the address of the loop is: 23fb60

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 %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	N/A
CMP %R9,%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%)
JE 23fa15 <_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 0x88(%RSP),%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 %R15D,%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,%R12,4),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV %R15D,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
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 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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(%RSP),%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(%RSP),%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
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 %R12,0x48(%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%)
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
LEA (%R10,%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
ADD %R12,%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 (%RCX,%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
VMOVSD 0x8(%RAX),%XMM0	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%)
CMP $0x8,%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 23fbc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1f0>	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	N/A
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 23fcd0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x300>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VMOVDQA64 -0x36eca(%RIP),%ZMM3	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%)
VBROADCASTSD %XMM0,%ZMM1	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	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	N/A
AND $-0x8,%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	N/A
VPBROADCASTQ %RDI,%ZMM2	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
MOV %R15D,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	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%)
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
MOV %ECX,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
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 23fcd0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x300>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x48(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
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 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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	scal (12.5%)
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 $0x8,%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 23fd09 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x339>	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 240241 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x871>	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 23fcec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x31c>	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	N/A
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 $0x3,%R12D	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
VMOVAPD %XMM21,0x130(%RSP)	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%)
VBROADCASTSD %XMM16,%YMM17	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM19,%YMM18	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %YMM19,0x160(%RSP)	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 (50.0%)
VPERMPD $0x55,%YMM19,%YMM19	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	vect (50.0%)
VBROADCASTSD %XMM20,%YMM3	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM21,%YMM21	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM4,%YMM22	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM5,%YMM23	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM2,%YMM24	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM8,%YMM25	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM7,%YMM26	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM9,0xb0(%RSP)	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%)
VBROADCASTSD %XMM9,%YMM27	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM10,0xa0(%RSP)	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%)
VBROADCASTSD %XMM10,%YMM28	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM11,%YMM29	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM6,%YMM30	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VPERMPD $0x55,%YMM6,%YMM31	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	vect (50.0%)
VBROADCASTSD %XMM0,%YMM9	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM1,%YMM10	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	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 %XMM5,0xf0(%RSP)	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 %XMM2,0xd0(%RSP)	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 $-0x8,%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
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%)
MOV %R15D,0x3c(%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 (6.3%)
VMOVSD %XMM14,0x70(%RSP)	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 %XMM16,0x150(%RSP)	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 %XMM20,0x140(%RSP)	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 %XMM4,0x100(%RSP)	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 %XMM8,0xc0(%RSP)	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 %XMM7,0xe0(%RSP)	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 %XMM11,0x90(%RSP)	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 %XMM0,0x120(%RSP)	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 %XMM1,0x110(%RSP)	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 $0x6,%R12	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
NOPW (%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 %YMM2,%YMM5,%YMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	vect (50.0%)
VMOVSD 0x70(%RSP),%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%)
VMOVDQA64 0x180(%RSP),%ZMM15	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 0x150(%RSP),%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(%RSP),%YMM19	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 0x140(%RSP),%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 0x130(%RSP),%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 0x120(%RSP),%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 0x110(%RSP),%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 0x100(%RSP),%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 0xf0(%RSP),%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 0xe0(%RSP),%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 0xd0(%RSP),%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 0xc0(%RSP),%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 0xb0(%RSP),%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 0xa0(%RSP),%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 0x90(%RSP),%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 0x68(%RSP),%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 0x60(%RSP),%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 0x58(%RSP),%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 0x3c(%RSP),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV 0x48(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV $0,%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	scal (6.3%)
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	3	0.50	vect (25.0%)
VADDPD %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	vect (25.0%)
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 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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%)
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
JMP 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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):

47% of SSE/AVX loads are used in vector version.
82% of SSE/AVX stores are used in vector version.
33% of SSE/AVX addition or subtraction instructions are used in vector version.
22% 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

Vector unaligned load/store instructions

Detected 1 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:246

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Use vector aligned instructions:
1. align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
2. inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Type of elements and instruction set

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

The binary loop is composed of 8 FP arithmetical operations:

8: addition or subtraction

The binary loop is loading 608 bytes (76 double precision FP elements). The binary loop is storing 260 bytes (32 double precision FP elements).

Arithmetic intensity

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

General properties

nb instructions	144
nb uops	142
loop length	805
used x86 registers	14
used mmx registers	0
used xmm registers	18
used ymm registers	21
used zmm registers	4
nb stack references	24

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	17.75 cycles
front end	17.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.67	4.67	4.67	4.67	4.67	4.67	15.50	15.50	15.50	15.50	4.25	10.50	10.00	4.25	7.50	7.50
cycles	4.67	4.67	4.67	4.67	4.67	4.67	15.50	15.50	15.50	15.50	4.25	10.50	10.00	4.25	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	17.75
Dispatch	15.50
Overall L1	17.75

Vectorization ratios

INT

all	8%
load	28%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	52%
load	51%
store	93%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	33%

INT+FP

all	41%
load	47%
store	82%
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	22%

Vector efficiency ratios

INT

all	16%
load	35%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
other	8%

all	20%
load	19%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	18%

INT+FP

all	19%
load	22%
store	23%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	19%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 17.75 cycles. At this rate:

13% of peak load performance is reached (34.25 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.65 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: 23fb60

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 %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	N/A
CMP %R9,%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%)
JE 23fa15 <_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 0x88(%RSP),%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 %R15D,%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,%R12,4),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV %R15D,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
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 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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(%RSP),%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(%RSP),%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
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 %R12,0x48(%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%)
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
LEA (%R10,%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
ADD %R12,%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 (%RCX,%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
VMOVSD 0x8(%RAX),%XMM0	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%)
CMP $0x8,%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 23fbc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1f0>	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	N/A
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 23fcd0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x300>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VMOVDQA64 -0x36eca(%RIP),%ZMM3	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%)
VBROADCASTSD %XMM0,%ZMM1	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	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	N/A
AND $-0x8,%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	N/A
VPBROADCASTQ %RDI,%ZMM2	2	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (12.5%)
MOV %R15D,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	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%)
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
MOV %ECX,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
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 23fcd0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x300>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x48(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
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 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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	scal (12.5%)
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 $0x8,%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 23fd09 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x339>	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 240241 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x871>	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 23fcec <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x31c>	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	N/A
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 $0x3,%R12D	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
VMOVAPD %XMM21,0x130(%RSP)	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%)
VBROADCASTSD %XMM16,%YMM17	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM19,%YMM18	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %YMM19,0x160(%RSP)	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 (50.0%)
VPERMPD $0x55,%YMM19,%YMM19	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	vect (50.0%)
VBROADCASTSD %XMM20,%YMM3	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM21,%YMM21	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM4,%YMM22	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM5,%YMM23	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM2,%YMM24	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM8,%YMM25	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM7,%YMM26	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM9,0xb0(%RSP)	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%)
VBROADCASTSD %XMM9,%YMM27	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VMOVAPD %XMM10,0xa0(%RSP)	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%)
VBROADCASTSD %XMM10,%YMM28	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM11,%YMM29	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM6,%YMM30	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VPERMPD $0x55,%YMM6,%YMM31	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	4	0.50	vect (50.0%)
VBROADCASTSD %XMM0,%YMM9	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
VBROADCASTSD %XMM1,%YMM10	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	0.50	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 %XMM5,0xf0(%RSP)	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 %XMM2,0xd0(%RSP)	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 $-0x8,%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
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%)
MOV %R15D,0x3c(%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 (6.3%)
VMOVSD %XMM14,0x70(%RSP)	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 %XMM16,0x150(%RSP)	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 %XMM20,0x140(%RSP)	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 %XMM4,0x100(%RSP)	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 %XMM8,0xc0(%RSP)	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 %XMM7,0xe0(%RSP)	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 %XMM11,0x90(%RSP)	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 %XMM0,0x120(%RSP)	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 %XMM1,0x110(%RSP)	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 $0x6,%R12	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
NOPW (%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 %YMM2,%YMM5,%YMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	vect (50.0%)
VMOVSD 0x70(%RSP),%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%)
VMOVDQA64 0x180(%RSP),%ZMM15	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 0x150(%RSP),%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(%RSP),%YMM19	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 0x140(%RSP),%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 0x130(%RSP),%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 0x120(%RSP),%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 0x110(%RSP),%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 0x100(%RSP),%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 0xf0(%RSP),%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 0xe0(%RSP),%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 0xd0(%RSP),%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 0xc0(%RSP),%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 0xb0(%RSP),%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 0xa0(%RSP),%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 0x90(%RSP),%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 0x68(%RSP),%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 0x60(%RSP),%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 0x58(%RSP),%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 0x3c(%RSP),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV 0x48(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV $0,%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	scal (6.3%)
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	3	0.50	vect (25.0%)
VADDPD %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	vect (25.0%)
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 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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%)
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
JMP 23fb50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x180>	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

Vector unaligned load/store instructions

Details

Workaround

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

Vector unaligned load/store instructions

Details

Workaround

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