OV - exec - Loop 405

	Loop Id: 405	Module: exec	Source: BsplineFunctor.h:236-260 [...]	Coverage: 0.02%

0x423b46 VXORPD	%XMM20,%XMM20,%XMM20

0x423b4c XOR	%R9D,%R9D

0x423b4f VPBROADCASTQ	%R9,%YMM21

0x423b55 VPSUBQ	%YMM21,%YMM18,%YMM18

0x423b5b VPCMPNLEUQ	%YMM27,%YMM18,%K1

0x423b62 VMOVUPD	(%RDX,%R9,8),%YMM18{%K1}{z}

0x423b69 VMULPD	%YMM18,%YMM19,%YMM18

0x423b6f VCVTTPD2DQ	%YMM18,%XMM19

0x423b75 VRNDSCALEPD	$0xb,%YMM18,%YMM21

0x423b7c VXORPD	%XMM22,%XMM22,%XMM22

0x423b82 KMOVQ	%K1,%K2

0x423b87 VGATHERDPD	(%R11,%XMM19,8),%YMM22{%K2}

0x423b8e VSUBPD	%YMM21,%YMM18,%YMM18

0x423b94 VMULPD	%YMM18,%YMM18,%YMM21

0x423b9a VMULPD	%YMM18,%YMM21,%YMM23

0x423ba0 VFMADD231PD	%YMM17,%YMM21,%YMM2

0x423ba6 VXORPD	%XMM17,%XMM17,%XMM17

0x423bac KMOVQ	%K1,%K2

0x423bb1 VGATHERDPD	0x8(%R11,%XMM19,8),%YMM17{%K2}

0x423bb9 VFMADD231PD	%YMM3,%YMM23,%YMM2

0x423bbf VFMADD231PD	%YMM5,%YMM18,%YMM2

0x423bc5 VFMADD231PD	%YMM10,%YMM23,%YMM16

0x423bcb VFMADD231PD	%YMM14,%YMM21,%YMM16

0x423bd1 VFMADD231PD	%YMM15,%YMM18,%YMM16

0x423bd7 VMULPD	%YMM17,%YMM16,%YMM3

0x423bdd VFMADD231PD	%YMM22,%YMM2,%YMM3

0x423be3 VFMADD231PD	%YMM13,%YMM23,%YMM9

0x423be9 VFMADD231PD	%YMM12,%YMM21,%YMM9

0x423bef VFMADD231PD	%YMM11,%YMM18,%YMM9

0x423bf5 VXORPD	%XMM2,%XMM2,%XMM2

0x423bf9 KMOVQ	%K1,%K2

0x423bfe VGATHERDPD	0x10(%R11,%XMM19,8),%YMM2{%K2}

0x423c06 VFMADD213PD	%YMM3,%YMM9,%YMM2

0x423c0b VFMADD231PD	%YMM8,%YMM23,%YMM4

0x423c11 VFMADD231PD	%YMM7,%YMM21,%YMM4

0x423c17 VFMADD231PD	%YMM6,%YMM18,%YMM4

0x423c1d VXORPD	%XMM3,%XMM3,%XMM3

0x423c21 KMOVQ	%K1,%K2

0x423c26 VGATHERDPD	0x18(%R11,%XMM19,8),%YMM3{%K2}

0x423c2e VFMADD213PD	%YMM2,%YMM4,%YMM3{%K1}{z}

0x423c34 VEXTRACTF128	$0x1,%YMM3,%XMM2

0x423c3a VADDPD	%XMM2,%XMM3,%XMM2

0x423c3e VSHUFPD	$0x1,%XMM2,%XMM2,%XMM3

0x423c43 VADDSD	%XMM3,%XMM2,%XMM2

0x423c47 VADDSD	%XMM2,%XMM20,%XMM20

0x423c4d VADDSD	%XMM0,%XMM20,%XMM0

0x423c53 LEA	0x1(%R8),%RCX

0x423c57 CMP	%R12,%R8

0x423c5a MOV	%RCX,%R8

0x423c5d JE	423a24

0x423c63 MOV	0x268(%R13),%RSI

0x423c6a MOV	0x18(%RSI),%RSI

0x423c6e MOVSXD	(%RSI,%R8,4),%R15

0x423c72 MOV	0x4(%RSI,%R8,4),%ESI

0x423c77 SUB	%R15D,%ESI

0x423c7a VXORPD	%XMM20,%XMM20,%XMM20

0x423c80 TEST	%ESI,%ESI

0x423c82 JLE	423c4d

0x423c84 MOV	-0x80(%RBP),%RCX

0x423c88 LEA	(%R8,%RCX,1),%RDI

0x423c8c MOV	(%RAX,%RDI,8),%R9

0x423c90 VMOVSD	0x8(%R9),%XMM2

0x423c96 MOV	%ESI,%R14D

0x423c99 MOV	%R14,%R11

0x423c9c AND	$0x7ffffff0,%R11

0x423ca3 JE	423cc0

0x423ca5 CMP	$0x7,%ESI

0x423ca8 JA	423ccb

0x423caa XOR	%R10D,%R10D

0x423cad XOR	%R11D,%R11D

0x423cb0 JMP	423e18

0x423cc0 XOR	%R10D,%R10D

0x423cc3 XOR	%R11D,%R11D

0x423cc6 JMP	423dff

0x423ccb VBROADCASTSD	%XMM2,%YMM3

0x423cd0 MOV	%R15D,%R12D

0x423cd3 MOV	%RBX,%RAX

0x423cd6 LEA	(%RBX,%R15,8),%R13

0x423cda XOR	%R10D,%R10D

0x423cdd XOR	%ESI,%ESI

0x423cdf NOP

  (408) 0x423ce0 VMOVUPD	(%R13,%RSI,8),%YMM4

  (408) 0x423ce7 VMOVUPD	0x20(%R13,%RSI,8),%YMM5

  (408) 0x423cee VMOVUPD	0x40(%R13,%RSI,8),%YMM6

  (408) 0x423cf5 VMOVUPD	0x60(%R13,%RSI,8),%YMM7

  (408) 0x423cfc LEA	(%R12,%RSI,1),%EDI

  (408) 0x423d00 VPBROADCASTD	%EDI,%YMM8

  (408) 0x423d06 VPADDD	%YMM24,%YMM8,%YMM9

  (408) 0x423d0c VPADDD	%YMM31,%YMM8,%YMM8

  (408) 0x423d12 VPCMPNEQD	%YMM1,%YMM8,%K0

  (408) 0x423d19 VPCMPNEQD	%YMM1,%YMM9,%K2

  (408) 0x423d20 VCMPPD	$0x1,%YMM3,%YMM4,%K5

  (408) 0x423d27 VCMPPD	$0x1,%YMM3,%YMM5,%K1

  (408) 0x423d2e KMOVW	%K1,-0x2a(%RBP)

  (408) 0x423d33 KSHIFTLB	$0x4,%K1,%K3

  (408) 0x423d39 KORB	%K3,%K5,%K3

  (408) 0x423d3d VCMPPD	$0x1,%YMM3,%YMM6,%K6

  (408) 0x423d44 VCMPPD	$0x1,%YMM3,%YMM7,%K4

  (408) 0x423d4b MOVSXD	%R10D,%R10

  (408) 0x423d4e LEA	(%RDX,%R10,8),%RDI

  (408) 0x423d52 KANDB	%K0,%K3,%K7

  (408) 0x423d56 KMOVB	%K7,%EBX

  (408) 0x423d5a KANDW	%K2,%K6,%K7

  (408) 0x423d5e POPCNT	%EBX,%EBX

  (408) 0x423d62 VCOMPRESSPD	%YMM6,(%RDI,%RBX,8){%K7}

  (408) 0x423d69 KANDW	%K0,%K5,%K5

  (408) 0x423d6d VCOMPRESSPD	%YMM4,(%RDX,%R10,8){%K5}

  (408) 0x423d74 KSHIFTLB	$0x4,%K4,%K1

  (408) 0x423d7a KORB	%K1,%K6,%K1

  (408) 0x423d7e KMOVB	%K7,-0x2d(%RBP)

  (408) 0x423d83 KSHIFTRB	$0x4,%K2,%K6

  (408) 0x423d89 KANDW	%K6,%K4,%K4

  (408) 0x423d8d LEA	(%RDI,%RBX,8),%RBX

  (408) 0x423d91 MOVZX	-0x2d(%RBP),%ECX

  (408) 0x423d95 POPCNT	%ECX,%ECX

  (408) 0x423d99 VCOMPRESSPD	%YMM7,(%RBX,%RCX,8){%K4}

  (408) 0x423da0 KUNPCKBW	%K3,%K1,%K1

  (408) 0x423da4 KMOVB	%K5,-0x2e(%RBP)

  (408) 0x423da9 KUNPCKBW	%K0,%K2,%K2

  (408) 0x423dad KSHIFTRB	$0x4,%K0,%K0

  (408) 0x423db3 KMOVW	-0x2a(%RBP),%K3

  (408) 0x423db8 KANDW	%K0,%K3,%K3

  (408) 0x423dbc MOVZX	-0x2e(%RBP),%ECX

  (408) 0x423dc0 POPCNT	%ECX,%ECX

  (408) 0x423dc4 VCOMPRESSPD	%YMM5,(%RDI,%RCX,8){%K3}

  (408) 0x423dcb KANDW	%K2,%K1,%K0

  (408) 0x423dcf KMOVW	%K0,%ECX

  (408) 0x423dd3 POPCNT	%ECX,%ECX

  (408) 0x423dd7 ADD	%ECX,%R10D

  (408) 0x423dda ADD	$0x10,%RSI

  (408) 0x423dde CMP	%R11,%RSI

  (408) 0x423de1 JB	423ce0

0x423de7 CMP	%R14D,%R11D

0x423dea MOV	-0x70(%RBP),%R13

0x423dee MOV	-0x68(%RBP),%R12

0x423df2 MOV	%RAX,%RBX

0x423df5 MOV	-0x60(%RBP),%RAX

0x423df9 JE	423fe0

0x423dff VMOVQ	%R14,%XMM4

0x423e04 VMOVD	%R11D,%XMM3

0x423e09 VPSUBQ	%YMM3,%YMM4,%YMM4

0x423e0d VMOVQ	%XMM4,%RSI

0x423e12 CMP	$0x8,%RSI

0x423e16 JAE	423e5b

0x423e18 MOV	-0x78(%RBP),%RSI

0x423e1c SUB	%R15D,%ESI

0x423e1f LEA	(%RBX,%R15,8),%RDI

0x423e23 JMP	423e3c

  (407) 0x423e30 INC	%R11

  (407) 0x423e33 CMP	%R11,%R14

  (407) 0x423e36 JE	423fe0

  (407) 0x423e3c VMOVSD	(%RDI,%R11,8),%XMM3

  (407) 0x423e42 VUCOMISD	%XMM3,%XMM2

  (407) 0x423e46 JBE	423e30

  (407) 0x423e48 CMP	%R11D,%ESI

  (407) 0x423e4b JE	423e30

  (407) 0x423e4d MOVSXD	%R10D,%R10

  (407) 0x423e50 VMOVSD	%XMM3,(%RDX,%R10,8)

  (407) 0x423e56 INC	%R10D

  (407) 0x423e59 JMP	423e30

0x423e5b VPBROADCASTQ	%XMM4,%YMM4

0x423e60 VPCMPNLEUQ	%YMM27,%YMM4,%K2

0x423e67 VPCMPNLEUQ	%YMM28,%YMM4,%K3

0x423e6e KSHIFTLB	$0x4,%K3,%K0

0x423e74 KORB	%K0,%K2,%K1

0x423e78 KMOVW	%K1,-0x2a(%RBP)

0x423e7d VPCMPNLEUQ	%YMM29,%YMM4,%K4

0x423e84 VPCMPNLEUQ	%YMM30,%YMM4,%K5

0x423e8b KSHIFTLB	$0x4,%K5,%K0

0x423e91 KORB	%K0,%K4,%K0

0x423e95 ADD	%R15,%R11

0x423e98 VMOVUPD	0x60(%RBX,%R11,8),%YMM4{%K5}{z}

0x423ea0 VMOVUPD	0x40(%RBX,%R11,8),%YMM5{%K4}{z}

0x423ea8 VMOVUPD	0x20(%RBX,%R11,8),%YMM6{%K3}{z}

0x423eb0 VMOVUPD	(%RBX,%R11,8),%YMM7{%K2}{z}

0x423eb7 VPBROADCASTD	%R15D,%YMM8

0x423ebd VPMOVQD	%YMM3,%XMM3

0x423ec3 VPBROADCASTD	%XMM3,%YMM3

0x423ec8 VPORD	%YMM31,%YMM3,%YMM9

0x423ece VPORD	%YMM24,%YMM3,%YMM3

0x423ed4 VPADDD	%YMM3,%YMM8,%YMM3

0x423ed8 VPADDD	%YMM9,%YMM8,%YMM8

0x423edd VPCMPNEQD	%YMM1,%YMM8,%K3

0x423ee4 VPCMPNEQD	%YMM1,%YMM3,%K4

0x423eeb VBROADCASTSD	%XMM2,%YMM2

0x423ef0 VCMPPD	$0x1,%YMM2,%YMM7,%K2

0x423ef7 VCMPPD	$0x1,%YMM2,%YMM6,%K5

0x423efe KSHIFTLB	$0x4,%K5,%K5

0x423f04 KORB	%K5,%K2,%K2

0x423f08 VCMPPD	$0x1,%YMM2,%YMM5,%K5

0x423f0f VCMPPD	$0x1,%YMM2,%YMM4,%K6

0x423f16 KSHIFTLB	$0x4,%K6,%K6

0x423f1c KORB	%K6,%K5,%K5

0x423f20 MOVSXD	%R10D,%RSI

0x423f23 LEA	(%RDX,%RSI,8),%RDI

0x423f27 KANDB	%K3,%K1,%K6

0x423f2b KANDB	%K2,%K6,%K6

0x423f2f VCOMPRESSPD	%YMM7,(%RDX,%RSI,8){%K6}

0x423f36 KANDB	%K4,%K0,%K7

0x423f3a KMOVQ	%K0,%K1

0x423f3f KANDB	%K5,%K7,%K7

0x423f43 KMOVB	%K6,%ECX

0x423f47 POPCNT	%ECX,%ECX

0x423f4b VCOMPRESSPD	%YMM5,(%RDI,%RCX,8){%K7}

0x423f52 KSHIFTLB	$0x4,%K7,%K0

0x423f58 KSHIFTRB	$0x4,%K0,%K0

0x423f5e KMOVB	%K0,-0x2b(%RBP)

0x423f63 LEA	(%RDI,%RCX,8),%RCX

0x423f67 KSHIFTRB	$0x4,%K7,%K7

0x423f6d MOVZX	-0x2b(%RBP),%R11D

0x423f72 POPCNT	%R11D,%R11D

0x423f77 VCOMPRESSPD	%YMM4,(%RCX,%R11,8){%K7}

0x423f7e KUNPCKBW	%K3,%K4,%K0

0x423f82 KSHIFTLB	$0x4,%K6,%K3

0x423f88 KSHIFTRB	$0x4,%K3,%K3

0x423f8e KMOVB	%K3,-0x2c(%RBP)

0x423f93 KSHIFTRB	$0x4,%K6,%K3

0x423f99 MOVZX	-0x2c(%RBP),%ECX

0x423f9d POPCNT	%ECX,%ECX

0x423fa1 VCOMPRESSPD	%YMM6,(%RDI,%RCX,8){%K3}

0x423fa8 KUNPCKBW	%K2,%K5,%K2

0x423fac KMOVW	-0x2a(%RBP),%K4

0x423fb1 KUNPCKBW	%K4,%K1,%K3

0x423fb5 KANDW	%K0,%K3,%K0

0x423fb9 KANDW	%K0,%K3,%K0

0x423fbd KANDW	%K2,%K0,%K0

0x423fc1 KMOVW	%K0,%ECX

0x423fc5 VMOVD	%R10D,%XMM2

0x423fca POPCNT	%ECX,%ECX

0x423fce ADD	%ECX,%ESI

0x423fd0 VMOVD	%ESI,%XMM3

0x423fd4 VINSERTI32X4	$0,%XMM3,%YMM0,%YMM2{%K4}

0x423fdb VMOVD	%XMM2,%R10D

0x423fe0 VXORPD	%XMM20,%XMM20,%XMM20

0x423fe6 TEST	%R10D,%R10D

0x423fe9 JLE	423c4d

0x423fef VMOVSD	0x238(%R9),%XMM3

0x423ff8 MOV	0x218(%R9),%R11

0x423fff VMOVSD	0x18(%R9),%XMM20

0x424006 VMOVSD	0x20(%R9),%XMM17

0x42400d VMOVSD	0x28(%R9),%XMM5

0x424013 VMOVSD	0x30(%R9),%XMM2

0x424019 VMOVSD	0x38(%R9),%XMM10

0x42401f VMOVSD	0x40(%R9),%XMM14

0x424025 VMOVSD	0x48(%R9),%XMM15

0x42402b VMOVSD	0x50(%R9),%XMM16

0x424032 VMOVSD	0x58(%R9),%XMM13

0x424038 VMOVSD	0x60(%R9),%XMM12

0x42403e VMOVSD	0x68(%R9),%XMM11

0x424044 VMOVSD	0x70(%R9),%XMM9

0x42404a VMOVSD	0x78(%R9),%XMM8

0x424050 VMOVSD	0x80(%R9),%XMM7

0x424059 VMOVSD	0x88(%R9),%XMM6

0x424062 VMOVSD	0x90(%R9),%XMM4

0x42406b MOV	%R10D,%R10D

0x42406e MOV	%R10,%R9

0x424071 VPBROADCASTQ	%R10,%YMM18

0x424077 VBROADCASTSD	%XMM3,%YMM19

0x42407d VBROADCASTSD	%XMM20,%YMM3

0x424083 VBROADCASTSD	%XMM17,%YMM17

0x424089 VBROADCASTSD	%XMM5,%YMM5

0x42408e VBROADCASTSD	%XMM2,%YMM2

0x424093 VBROADCASTSD	%XMM10,%YMM10

0x424098 VBROADCASTSD	%XMM14,%YMM14

0x42409d VBROADCASTSD	%XMM15,%YMM15

0x4240a2 VBROADCASTSD	%XMM16,%YMM16

0x4240a8 VBROADCASTSD	%XMM13,%YMM13

0x4240ad VBROADCASTSD	%XMM12,%YMM12

0x4240b2 VBROADCASTSD	%XMM11,%YMM11

0x4240b7 VBROADCASTSD	%XMM9,%YMM9

0x4240bc VBROADCASTSD	%XMM8,%YMM8

0x4240c1 VBROADCASTSD	%XMM7,%YMM7

0x4240c6 VBROADCASTSD	%XMM6,%YMM6

0x4240cb VBROADCASTSD	%XMM4,%YMM4

0x4240d0 AND	$0x7ffffffc,%R9

0x4240d7 JE	423b46

0x4240dd VXORPD	%XMM20,%XMM20,%XMM20

0x4240e3 XOR	%ESI,%ESI

0x4240e5 NOPW	%CS:(%RAX,%RAX,1)

  (406) 0x4240f0 VMULPD	(%RDX,%RSI,8),%YMM19,%YMM21

  (406) 0x4240f7 VCVTTPD2DQ	%YMM21,%XMM22

  (406) 0x4240fd VRNDSCALEPD	$0xb,%YMM21,%YMM23

  (406) 0x424104 VSUBPD	%YMM23,%YMM21,%YMM21

  (406) 0x42410a VMULPD	%YMM21,%YMM21,%YMM23

  (406) 0x424110 VMULPD	%YMM21,%YMM23,%YMM24

  (406) 0x424116 VMOVAPD	%YMM23,%YMM25

  (406) 0x42411c VFMADD213PD	%YMM2,%YMM17,%YMM25

  (406) 0x424122 VFMADD231PD	%YMM3,%YMM24,%YMM25

  (406) 0x424128 VFMADD231PD	%YMM21,%YMM5,%YMM25

  (406) 0x42412e VXORPD	%XMM26,%XMM26,%XMM26

  (406) 0x424134 KXNORW	%K0,%K0,%K1

  (406) 0x424138 VGATHERDPD	(%R11,%XMM22,8),%YMM26{%K1}

  (406) 0x42413f VFMADD213PD	%YMM20,%YMM25,%YMM26

  (406) 0x424145 VMOVAPD	%YMM24,%YMM20

  (406) 0x42414b VFMADD213PD	%YMM16,%YMM10,%YMM20

  (406) 0x424151 VFMADD231PD	%YMM23,%YMM14,%YMM20

  (406) 0x424157 VXORPD	%XMM25,%XMM25,%XMM25

  (406) 0x42415d KXNORW	%K0,%K0,%K1

  (406) 0x424161 VGATHERDPD	0x8(%R11,%XMM22,8),%YMM25{%K1}

  (406) 0x424169 VFMADD231PD	%YMM21,%YMM15,%YMM20

  (406) 0x42416f VFMADD213PD	%YMM26,%YMM20,%YMM25

  (406) 0x424175 VMOVAPD	%YMM24,%YMM20

  (406) 0x42417b VFMADD213PD	%YMM9,%YMM13,%YMM20

  (406) 0x424181 VXORPD	%XMM26,%XMM26,%XMM26

  (406) 0x424187 KXNORW	%K0,%K0,%K1

  (406) 0x42418b VGATHERDPD	0x10(%R11,%XMM22,8),%YMM26{%K1}

  (406) 0x424193 VFMADD231PD	%YMM23,%YMM12,%YMM20

  (406) 0x424199 VFMADD231PD	%YMM21,%YMM11,%YMM20

  (406) 0x42419f VFMADD213PD	%YMM25,%YMM20,%YMM26

  (406) 0x4241a5 VXORPD	%XMM20,%XMM20,%XMM20

  (406) 0x4241ab KXNORW	%K0,%K0,%K1

  (406) 0x4241af VGATHERDPD	0x18(%R11,%XMM22,8),%YMM20{%K1}

  (406) 0x4241b7 VFMADD213PD	%YMM4,%YMM8,%YMM24

  (406) 0x4241bd VFMADD231PD	%YMM23,%YMM7,%YMM24

  (406) 0x4241c3 VFMADD231PD	%YMM21,%YMM6,%YMM24

  (406) 0x4241c9 VFMADD213PD	%YMM26,%YMM24,%YMM20

  (406) 0x4241cf ADD	$0x4,%RSI

  (406) 0x4241d3 CMP	%R9,%RSI

  (406) 0x4241d6 JB	4240f0

0x4241dc VEXTRACTF32X4	$0x1,%YMM20,%XMM21

0x4241e3 VADDPD	%XMM21,%XMM20,%XMM20

0x4241e9 VSHUFPD	$0x1,%XMM20,%XMM20,%XMM21

0x4241f0 VADDSD	%XMM21,%XMM20,%XMM20

0x4241f6 CMP	%R10D,%R9D

0x4241f9 VPMOVSXBD	0xda0cd(%RIP),%YMM24

0x424203 JNE	423b4f

0x424209 JMP	423c4d

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h: 1296 - 1296

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

1296:       { return _M_ptr; }

/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);

/home/eoseret/qaas_runs_GNR/173-773-5521/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);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 107 - 132

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

107:     for (int k = 0; k < ratios.size(); ++k)

[...]

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_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223

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

223:     return X[i];

/home/eoseret/qaas_runs_GNR/173-773-5521/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]; }

Coverage (%)	Name	Source Location	Module
►100.00+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

Path /

Metric	Value
CQA speedup if no scalar integer	1.30
CQA speedup if FP arith vectorized	1.38
CQA speedup if fully vectorized	5.11
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.46
Bottlenecks	P5,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	shared_ptr_base.h:1296-1296,stl_vector.h:1064-1064,BsplineFunctor.h:236-240,BsplineFunctor.h:246-252,BsplineFunctor.h:256-260,TwoBodyJastrowRef.h:107-107,TwoBodyJastrowRef.h:127-129,TwoBodyJastrowRef.h:132-132,OhmmsVector.h:223-223,ParticleSet.h:313-313,ParticleSet.h:316-316
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	60.00
CQA cycles if no scalar integer	46.00
CQA cycles if FP arith vectorized	43.38
CQA cycles if fully vectorized	11.75
Front-end cycles	41.00
P0 cycles	35.00
P1 cycles	38.00
P2 cycles	18.00
P3 cycles	18.00
P4 cycles	3.50
P5 cycles	60.00
P6 cycles	11.60
P7 cycles	3.50
P8 cycles	3.50
P9 cycles	3.50
P10 cycles	11.40
P11 cycles	18.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	224.00
Nb uops	246.00
Nb loads	42.00
Nb stores	7.00
Nb stack references	8.00
FLOP/cycle	2.47
Nb FLOP add-sub	12.00
Nb FLOP mul	16.00
Nb FLOP fma	60.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	10.93
Bytes prefetched	0.00
Bytes loaded	524.00
Bytes stored	132.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	53.08
Vectorization ratio load	34.48
Vectorization ratio store	100.00
Vectorization ratio mul	100.00
Vectorization ratio add_sub	63.64
Vectorization ratio fma	100.00
Vectorization ratio div_sqrt	NA
Vectorization ratio other	46.48
Vector-efficiency ratio all	28.65
Vector-efficiency ratio load	24.14
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	50.00
Vector-efficiency ratio add_sub	31.82
Vector-efficiency ratio fma	50.00
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	24.30

Metric	Value
CQA speedup if no scalar integer	1.30
CQA speedup if FP arith vectorized	1.38
CQA speedup if fully vectorized	5.11
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.46
Bottlenecks	P5,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	shared_ptr_base.h:1296-1296,stl_vector.h:1064-1064,BsplineFunctor.h:236-240,BsplineFunctor.h:246-252,BsplineFunctor.h:256-260,TwoBodyJastrowRef.h:107-107,TwoBodyJastrowRef.h:127-129,TwoBodyJastrowRef.h:132-132,OhmmsVector.h:223-223,ParticleSet.h:313-313,ParticleSet.h:316-316
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	60.00
CQA cycles if no scalar integer	46.00
CQA cycles if FP arith vectorized	43.38
CQA cycles if fully vectorized	11.75
Front-end cycles	41.00
P0 cycles	35.00
P1 cycles	38.00
P2 cycles	18.00
P3 cycles	18.00
P4 cycles	3.50
P5 cycles	60.00
P6 cycles	11.60
P7 cycles	3.50
P8 cycles	3.50
P9 cycles	3.50
P10 cycles	11.40
P11 cycles	18.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	224.00
Nb uops	246.00
Nb loads	42.00
Nb stores	7.00
Nb stack references	8.00
FLOP/cycle	2.47
Nb FLOP add-sub	12.00
Nb FLOP mul	16.00
Nb FLOP fma	60.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	10.93
Bytes prefetched	0.00
Bytes loaded	524.00
Bytes stored	132.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	53.08
Vectorization ratio load	34.48
Vectorization ratio store	100.00
Vectorization ratio mul	100.00
Vectorization ratio add_sub	63.64
Vectorization ratio fma	100.00
Vectorization ratio div_sqrt	NA
Vectorization ratio other	46.48
Vector-efficiency ratio all	28.65
Vector-efficiency ratio load	24.14
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	50.00
Vector-efficiency ratio add_sub	31.82
Vector-efficiency ratio fma	50.00
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	24.30

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:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h:1296
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-260
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107,127-132
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 49 paths individually, rerun with max-paths=49
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 49 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 60.00 to 46.00 cycles (1.30x speedup).

Workaround

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

Vectorization

Your loop is partially vectorized. Only 28% of vector register length is used (average across all SSE/AVX instructions).

Details

53% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

34% of SSE/AVX loads are used in vector version.
63% of SSE/AVX addition or subtraction instructions are used in vector version.
46% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

Performance is limited by execution of FP multiply or FMA (fused multiply-add) operations (the FP multiply/FMA unit is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 60.00 to 41.00 cycles (1.46x speedup).

Workaround

Reduce the number of FP multiply/FMA instructions

512-bits vectorization

On some x86 processors supporting 512-bits vectorization, compilers are often too conservative and limit vectorization to 256 bits. Performance can then be improved by enforcing 512-bits vectorization, especially with many vectorized and high trip count loops. 512-bits vectorization performance overhead (compared to 256-bits) is generally lower on newer processors.

Workaround

Recompile with -mprefer-vector-width=512

Masked instructions

Detected masked instructions.

Details

Vector registers are partially exploited, which is expected if your loop is irregular or mixes elements of different sizes.

Workaround

If your loop is irregular, try to remove or hoist conditional structures out of your loop. If it mixes elements of different sizes, try to uniformize them.

FMA

Detected 60 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

KMOVW: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:240
VCOMPRESSPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
VCVTTPD2DQ: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:250
VGATHERDPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:256
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:257
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:258
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:259
VPMOVSXBD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:246
VRNDSCALEPD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:251

Vector unaligned load/store instructions

Detected 1 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:260

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.

Gather/scatter instructions

Detected gather/scatter instructions (typically caused by indirect accesses).

Details

VGATHERDPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:256
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:257
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:258
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:259

Workaround

Try to simplify your code and/or replace indirect accesses with unit-stride ones.

Conversion instructions

Detected expensive conversion instructions.

Details

MOVZX: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
VCVTTPD2DQ (FP64 to INT32, SIMD): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:250
VPMOVQD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236
VPMOVSXBD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:246

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

4 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 2 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time). 25 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 148 FP arithmetical operations:

72: addition or subtraction (60 inside FMA instructions)
76: multiply (60 inside FMA instructions)

The binary loop is loading 524 bytes (65 double precision FP elements). The binary loop is storing 132 bytes (16 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.23 FP operations per loaded or stored byte.

General properties

nb instructions	224
nb uops	246
loop length	1172
used x86 registers	15
used mmx registers	0
used xmm registers	21
used ymm registers	30
used zmm registers	0
nb stack references	8
ADD-SUB / MUL ratio	1.75

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	41.00 cycles
front end	41.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	35.00	38.00	18.00	18.00	3.50	60.00	11.60	3.50	3.50	3.50	11.40	18.00
cycles	35.00	38.00	18.00	18.00	3.50	60.00	11.60	3.50	3.50	3.50	11.40	18.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	41.00
Dispatch	60.00
Overall L1	60.00

Vectorization ratios

INT

all	44%
load	50%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	36%

all	56%
load	33%
store	100%
mul	100%
add-sub	42%
fma	100%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	53%

INT+FP

all	53%
load	34%
store	100%
mul	100%
add-sub	63%
fma	100%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	46%

Vector efficiency ratios

INT

all	25%
load	12%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
other	22%

all	29%
load	25%
store	50%
mul	50%
add-sub	21%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	28%
load	24%
store	50%
mul	50%
add-sub	31%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	24%

Cycles and memory resources usage

Detected masked instructions: assuming all mask elements are active. Assuming all data fit into the L1 cache, each iteration of the binary loop takes 60.00 cycles. At this rate:

4% of peak load performance is reached (8.73 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (2.20 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 423c63

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VPBROADCASTQ %R9,%YMM21	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VPSUBQ %YMM21,%YMM18,%YMM18	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (50.0%)
VPCMPNLEUQ %YMM27,%YMM18,%K1																vect (50.0%)
VMOVUPD (%RDX,%R9,8),%YMM18{%K1}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMULPD %YMM18,%YMM19,%YMM18	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VCVTTPD2DQ %YMM18,%XMM19	2	0.50	0.50	0	0	0	1	0	0	0	0	0	0	7	1	vect (50.0%)
VRNDSCALEPD $0xb,%YMM18,%YMM21	2	1	1	0	0	0	0	0	0	0	0	0	0	8	1	vect (50.0%)
VXORPD %XMM22,%XMM22,%XMM22	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD (%R11,%XMM19,8),%YMM22{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VSUBPD %YMM21,%YMM18,%YMM18	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMULPD %YMM18,%YMM18,%YMM21	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VMULPD %YMM18,%YMM21,%YMM23	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM17,%YMM21,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VXORPD %XMM17,%XMM17,%XMM17	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD 0x8(%R11,%XMM19,8),%YMM17{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VFMADD231PD %YMM3,%YMM23,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM5,%YMM18,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM10,%YMM23,%YMM16	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM14,%YMM21,%YMM16	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM15,%YMM18,%YMM16	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VMULPD %YMM17,%YMM16,%YMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM22,%YMM2,%YMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM13,%YMM23,%YMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM12,%YMM21,%YMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM11,%YMM18,%YMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD 0x10(%R11,%XMM19,8),%YMM2{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VFMADD213PD %YMM3,%YMM9,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM8,%YMM23,%YMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM7,%YMM21,%YMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM6,%YMM18,%YMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD 0x18(%R11,%XMM19,8),%YMM3{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VFMADD213PD %YMM2,%YMM4,%YMM3{%K1}{z}	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VEXTRACTF128 $0x1,%YMM3,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM3,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM2,%XMM2,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM3,%XMM2,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VADDSD %XMM2,%XMM20,%XMM20	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VADDSD %XMM0,%XMM20,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
LEA 0x1(%R8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %R12,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV %RCX,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 423a24 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x44>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x268(%R13),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RSI),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD (%RSI,%R8,4),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x4(%RSI,%R8,4),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %R15D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %ESI,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 423c4d <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x26d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x80(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%R8,%RCX,1),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV (%RAX,%RDI,8),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD 0x8(%R9),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %ESI,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %R14,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7ffffff0,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 423cc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x7,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JA 423ccb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2eb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 423e18 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x438>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 423dff <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x41f>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VBROADCASTSD %XMM2,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
MOV %R15D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%RBX,%R15,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %R14D,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV -0x70(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 423fe0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x600>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVQ %R14,%XMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VMOVD %R11D,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VPSUBQ %YMM3,%YMM4,%YMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (50.0%)
VMOVQ %XMM4,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
CMP $0x8,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JAE 423e5b <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x47b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x78(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %R15D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RBX,%R15,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 423e3c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x45c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VPBROADCASTQ %XMM4,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VPCMPNLEUQ %YMM27,%YMM4,%K2																vect (50.0%)
VPCMPNLEUQ %YMM28,%YMM4,%K3																vect (50.0%)
KSHIFTLB $0x4,%K3,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K0,%K2,%K1	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVW %K1,-0x2a(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	3	0.50	N/A
VPCMPNLEUQ %YMM29,%YMM4,%K4																vect (50.0%)
VPCMPNLEUQ %YMM30,%YMM4,%K5																vect (50.0%)
KSHIFTLB $0x4,%K5,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K0,%K4,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
ADD %R15,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVUPD 0x60(%RBX,%R11,8),%YMM4{%K5}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%RBX,%R11,8),%YMM5{%K4}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%RBX,%R11,8),%YMM6{%K3}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD (%RBX,%R11,8),%YMM7{%K2}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPBROADCASTD %R15D,%YMM8	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VPMOVQD %YMM3,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPBROADCASTD %XMM3,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VPORD %YMM31,%YMM3,%YMM9	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPORD %YMM24,%YMM3,%YMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPADDD %YMM3,%YMM8,%YMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPADDD %YMM9,%YMM8,%YMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPCMPNEQD %YMM1,%YMM8,%K3																vect (50.0%)
VPCMPNEQD %YMM1,%YMM3,%K4																vect (50.0%)
VBROADCASTSD %XMM2,%YMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VCMPPD $0x1,%YMM2,%YMM7,%K2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VCMPPD $0x1,%YMM2,%YMM6,%K5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
KSHIFTLB $0x4,%K5,%K5	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K5,%K2,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
VCMPPD $0x1,%YMM2,%YMM5,%K5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VCMPPD $0x1,%YMM2,%YMM4,%K6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
KSHIFTLB $0x4,%K6,%K6	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K6,%K5,%K5	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
MOVSXD %R10D,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%RDX,%RSI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
KANDB %K3,%K1,%K6	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KANDB %K2,%K6,%K6	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
VCOMPRESSPD %YMM7,(%RDX,%RSI,8){%K6}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KANDB %K4,%K0,%K7	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVQ %K0,%K1	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
KANDB %K5,%K7,%K7	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVB %K6,%ECX	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	N/A
POPCNT %ECX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VCOMPRESSPD %YMM5,(%RDI,%RCX,8){%K7}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KSHIFTLB $0x4,%K7,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KSHIFTRB $0x4,%K0,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KMOVB %K0,-0x2b(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	3	0.50	N/A
LEA (%RDI,%RCX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
KSHIFTRB $0x4,%K7,%K7	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
MOVZX -0x2b(%RBP),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
POPCNT %R11D,%R11D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VCOMPRESSPD %YMM4,(%RCX,%R11,8){%K7}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KUNPCKBW %K3,%K4,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KSHIFTLB $0x4,%K6,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KSHIFTRB $0x4,%K3,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KMOVB %K3,-0x2c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	3	0.50	N/A
KSHIFTRB $0x4,%K6,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
MOVZX -0x2c(%RBP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
POPCNT %ECX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VCOMPRESSPD %YMM6,(%RDI,%RCX,8){%K3}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KUNPCKBW %K2,%K5,%K2	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KMOVW -0x2a(%RBP),%K4	3	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	N/A
KUNPCKBW %K4,%K1,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KANDW %K0,%K3,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KANDW %K0,%K3,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KANDW %K2,%K0,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVW %K0,%ECX	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VMOVD %R10D,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
POPCNT %ECX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %ECX,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVD %ESI,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VINSERTI32X4 $0,%XMM3,%YMM0,%YMM2{%K4}	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VMOVD %XMM2,%R10D	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R10D,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 423c4d <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x26d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD 0x238(%R9),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x218(%R9),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD 0x18(%R9),%XMM20	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x20(%R9),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x28(%R9),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x30(%R9),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x38(%R9),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x40(%R9),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x48(%R9),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x50(%R9),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x58(%R9),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x60(%R9),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x68(%R9),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x70(%R9),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x78(%R9),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x80(%R9),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x88(%R9),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x90(%R9),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VPBROADCASTQ %R10,%YMM18	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM3,%YMM19	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM20,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM17,%YMM17	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM5,%YMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM2,%YMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM10,%YMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM14,%YMM14	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM15,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM16,%YMM16	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM13,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM12,%YMM12	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM11,%YMM11	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM9,%YMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM8,%YMM8	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM7,%YMM7	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM6,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM4,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
AND $0x7ffffffc,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 423b46 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x166>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF32X4 $0x1,%YMM20,%XMM21	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM21,%XMM20,%XMM20	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM20,%XMM20,%XMM21	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM21,%XMM20,%XMM20	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
CMP %R10D,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VPMOVSXBD 0xda0cd(%RIP),%YMM24	2	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	vect (12.5%)
JNE 423b4f <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x16f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 423c4d <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x26d>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h:1296
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-260
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107,127-132
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h:313-316

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 49 paths individually, rerun with max-paths=49
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

Your loop is partially vectorized. Only 28% of vector register length is used (average across all SSE/AVX instructions).

Details

53% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

34% of SSE/AVX loads are used in vector version.
63% of SSE/AVX addition or subtraction instructions are used in vector version.
46% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

Workaround

Reduce the number of FP multiply/FMA instructions

512-bits vectorization

Workaround

Recompile with -mprefer-vector-width=512

Masked instructions

Detected masked instructions.

Details

Vector registers are partially exploited, which is expected if your loop is irregular or mixes elements of different sizes.

Workaround

If your loop is irregular, try to remove or hoist conditional structures out of your loop. If it mixes elements of different sizes, try to uniformize them.

FMA

Detected 60 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

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.

KMOVW: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:240
VCOMPRESSPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
VCVTTPD2DQ: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:250
VGATHERDPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:256
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:257
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:258
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:259
VPMOVSXBD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:246
VRNDSCALEPD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:251

Vector unaligned load/store instructions

Detected 1 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:260

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.

Gather/scatter instructions

Detected gather/scatter instructions (typically caused by indirect accesses).

Details

VGATHERDPD: 4 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:256
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:257
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:258
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:259

Workaround

Try to simplify your code and/or replace indirect accesses with unit-stride ones.

Conversion instructions

Detected expensive conversion instructions.

Details

MOVZX: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:107
VCVTTPD2DQ (FP64 to INT32, SIMD): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:250
VPMOVQD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236
VPMOVSXBD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:246

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

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

The binary loop is composed of 148 FP arithmetical operations:

72: addition or subtraction (60 inside FMA instructions)
76: multiply (60 inside FMA instructions)

The binary loop is loading 524 bytes (65 double precision FP elements). The binary loop is storing 132 bytes (16 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.23 FP operations per loaded or stored byte.

General properties

nb instructions	224
nb uops	246
loop length	1172
used x86 registers	15
used mmx registers	0
used xmm registers	21
used ymm registers	30
used zmm registers	0
nb stack references	8
ADD-SUB / MUL ratio	1.75

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	41.00 cycles
front end	41.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	35.00	38.00	18.00	18.00	3.50	60.00	11.60	3.50	3.50	3.50	11.40	18.00
cycles	35.00	38.00	18.00	18.00	3.50	60.00	11.60	3.50	3.50	3.50	11.40	18.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	41.00
Dispatch	60.00
Overall L1	60.00

Vectorization ratios

INT

all	44%
load	50%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
other	36%

all	56%
load	33%
store	100%
mul	100%
add-sub	42%
fma	100%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	53%

INT+FP

all	53%
load	34%
store	100%
mul	100%
add-sub	63%
fma	100%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	46%

Vector efficiency ratios

INT

all	25%
load	12%
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
other	22%

all	29%
load	25%
store	50%
mul	50%
add-sub	21%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	28%
load	24%
store	50%
mul	50%
add-sub	31%
fma	50%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	24%

Cycles and memory resources usage

Detected masked instructions: assuming all mask elements are active. Assuming all data fit into the L1 cache, each iteration of the binary loop takes 60.00 cycles. At this rate:

4% of peak load performance is reached (8.73 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (2.20 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 423c63

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VPBROADCASTQ %R9,%YMM21	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VPSUBQ %YMM21,%YMM18,%YMM18	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (50.0%)
VPCMPNLEUQ %YMM27,%YMM18,%K1																vect (50.0%)
VMOVUPD (%RDX,%R9,8),%YMM18{%K1}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMULPD %YMM18,%YMM19,%YMM18	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VCVTTPD2DQ %YMM18,%XMM19	2	0.50	0.50	0	0	0	1	0	0	0	0	0	0	7	1	vect (50.0%)
VRNDSCALEPD $0xb,%YMM18,%YMM21	2	1	1	0	0	0	0	0	0	0	0	0	0	8	1	vect (50.0%)
VXORPD %XMM22,%XMM22,%XMM22	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD (%R11,%XMM19,8),%YMM22{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VSUBPD %YMM21,%YMM18,%YMM18	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (50.0%)
VMULPD %YMM18,%YMM18,%YMM21	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VMULPD %YMM18,%YMM21,%YMM23	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM17,%YMM21,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VXORPD %XMM17,%XMM17,%XMM17	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD 0x8(%R11,%XMM19,8),%YMM17{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VFMADD231PD %YMM3,%YMM23,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM5,%YMM18,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM10,%YMM23,%YMM16	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM14,%YMM21,%YMM16	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM15,%YMM18,%YMM16	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VMULPD %YMM17,%YMM16,%YMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM22,%YMM2,%YMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM13,%YMM23,%YMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM12,%YMM21,%YMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM11,%YMM18,%YMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD 0x10(%R11,%XMM19,8),%YMM2{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VFMADD213PD %YMM3,%YMM9,%YMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM8,%YMM23,%YMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM7,%YMM21,%YMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VFMADD231PD %YMM6,%YMM18,%YMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
KMOVQ %K1,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
VGATHERDPD 0x18(%R11,%XMM19,8),%YMM3{%K2}	5	1	1	1.33	1.33	0	1	0	0	0	0	0	1.33	28	2	vect (50.0%)
VFMADD213PD %YMM2,%YMM4,%YMM3{%K1}{z}	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (50.0%)
VEXTRACTF128 $0x1,%YMM3,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM3,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM2,%XMM2,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM3,%XMM2,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VADDSD %XMM2,%XMM20,%XMM20	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VADDSD %XMM0,%XMM20,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
LEA 0x1(%R8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %R12,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV %RCX,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JE 423a24 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x44>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x268(%R13),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RSI),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD (%RSI,%R8,4),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x4(%RSI,%R8,4),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %R15D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %ESI,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 423c4d <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x26d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x80(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%R8,%RCX,1),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV (%RAX,%RDI,8),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD 0x8(%R9),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %ESI,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %R14,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x7ffffff0,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 423cc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2e0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x7,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JA 423ccb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2eb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 423e18 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x438>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 423dff <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x41f>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VBROADCASTSD %XMM2,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
MOV %R15D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%RBX,%R15,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %R14D,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV -0x70(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x68(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 423fe0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x600>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVQ %R14,%XMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
VMOVD %R11D,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VPSUBQ %YMM3,%YMM4,%YMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (50.0%)
VMOVQ %XMM4,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
CMP $0x8,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JAE 423e5b <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x47b>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x78(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB %R15D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RBX,%R15,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 423e3c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x45c>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VPBROADCASTQ %XMM4,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VPCMPNLEUQ %YMM27,%YMM4,%K2																vect (50.0%)
VPCMPNLEUQ %YMM28,%YMM4,%K3																vect (50.0%)
KSHIFTLB $0x4,%K3,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K0,%K2,%K1	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVW %K1,-0x2a(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	3	0.50	N/A
VPCMPNLEUQ %YMM29,%YMM4,%K4																vect (50.0%)
VPCMPNLEUQ %YMM30,%YMM4,%K5																vect (50.0%)
KSHIFTLB $0x4,%K5,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K0,%K4,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
ADD %R15,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVUPD 0x60(%RBX,%R11,8),%YMM4{%K5}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x40(%RBX,%R11,8),%YMM5{%K4}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD 0x20(%RBX,%R11,8),%YMM6{%K3}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVUPD (%RBX,%R11,8),%YMM7{%K2}{z}	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VPBROADCASTD %R15D,%YMM8	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VPMOVQD %YMM3,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VPBROADCASTD %XMM3,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VPORD %YMM31,%YMM3,%YMM9	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPORD %YMM24,%YMM3,%YMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPADDD %YMM3,%YMM8,%YMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPADDD %YMM9,%YMM8,%YMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (50.0%)
VPCMPNEQD %YMM1,%YMM8,%K3																vect (50.0%)
VPCMPNEQD %YMM1,%YMM3,%K4																vect (50.0%)
VBROADCASTSD %XMM2,%YMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VCMPPD $0x1,%YMM2,%YMM7,%K2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VCMPPD $0x1,%YMM2,%YMM6,%K5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
KSHIFTLB $0x4,%K5,%K5	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K5,%K2,%K2	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
VCMPPD $0x1,%YMM2,%YMM5,%K5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VCMPPD $0x1,%YMM2,%YMM4,%K6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
KSHIFTLB $0x4,%K6,%K6	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KORB %K6,%K5,%K5	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
MOVSXD %R10D,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%RDX,%RSI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
KANDB %K3,%K1,%K6	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KANDB %K2,%K6,%K6	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
VCOMPRESSPD %YMM7,(%RDX,%RSI,8){%K6}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KANDB %K4,%K0,%K7	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVQ %K0,%K1	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	N/A
KANDB %K5,%K7,%K7	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVB %K6,%ECX	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	N/A
POPCNT %ECX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VCOMPRESSPD %YMM5,(%RDI,%RCX,8){%K7}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KSHIFTLB $0x4,%K7,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KSHIFTRB $0x4,%K0,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KMOVB %K0,-0x2b(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	3	0.50	N/A
LEA (%RDI,%RCX,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
KSHIFTRB $0x4,%K7,%K7	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
MOVZX -0x2b(%RBP),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
POPCNT %R11D,%R11D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VCOMPRESSPD %YMM4,(%RCX,%R11,8){%K7}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KUNPCKBW %K3,%K4,%K0	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KSHIFTLB $0x4,%K6,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KSHIFTRB $0x4,%K3,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KMOVB %K3,-0x2c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	3	0.50	N/A
KSHIFTRB $0x4,%K6,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
MOVZX -0x2c(%RBP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
POPCNT %ECX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VCOMPRESSPD %YMM6,(%RDI,%RCX,8){%K3}	3	0	0	0	0	0.50	2	0	0.50	0.50	0.50	0	0	3	2	vect (50.0%)
KUNPCKBW %K2,%K5,%K2	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KMOVW -0x2a(%RBP),%K4	3	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	N/A
KUNPCKBW %K4,%K1,%K3	1	0	0	0	0	0	1	0	0	0	0	0	0	4	1	N/A
KANDW %K0,%K3,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KANDW %K0,%K3,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KANDW %K2,%K0,%K0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	N/A
KMOVW %K0,%ECX	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VMOVD %R10D,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
POPCNT %ECX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %ECX,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVD %ESI,%XMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (6.3%)
VINSERTI32X4 $0,%XMM3,%YMM0,%YMM2{%K4}	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VMOVD %XMM2,%R10D	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R10D,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JLE 423c4d <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x26d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD 0x238(%R9),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x218(%R9),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD 0x18(%R9),%XMM20	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x20(%R9),%XMM17	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x28(%R9),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x30(%R9),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x38(%R9),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x40(%R9),%XMM14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x48(%R9),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x50(%R9),%XMM16	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x58(%R9),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x60(%R9),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x68(%R9),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x70(%R9),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x78(%R9),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x80(%R9),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x88(%R9),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x90(%R9),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VPBROADCASTQ %R10,%YMM18	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM3,%YMM19	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM20,%YMM3	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM17,%YMM17	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM5,%YMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM2,%YMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM10,%YMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM14,%YMM14	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM15,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM16,%YMM16	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM13,%YMM13	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM12,%YMM12	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM11,%YMM11	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM9,%YMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM8,%YMM8	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM7,%YMM7	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM6,%YMM6	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
VBROADCASTSD %XMM4,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
AND $0x7ffffffc,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 423b46 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x166>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM20,%XMM20,%XMM20	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF32X4 $0x1,%YMM20,%XMM21	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM21,%XMM20,%XMM20	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM20,%XMM20,%XMM21	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM21,%XMM20,%XMM20	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
CMP %R10D,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VPMOVSXBD 0xda0cd(%RIP),%YMM24	2	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	vect (12.5%)
JNE 423b4f <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x16f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 423c4d <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x26d>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

512-bits vectorization

Workaround

Masked instructions

Details

Workaround

FMA

Workaround

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Gather/scatter instructions

Details

Workaround

Conversion 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

Workaround

512-bits vectorization

Workaround

Masked instructions

Details

Workaround

FMA

Workaround

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Gather/scatter instructions

Details

Workaround

Conversion 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