OV - exec - Loop 457

	Loop Id: 457	Module: exec	Source: BsplineFunctor.h:236-260 [...]	Coverage: 0.01%

0x430680 ADDSD	%XMM1,%XMM6

0x430684 LEA	0x1(%R11),%RAX

0x430688 CMP	%RCX,%R11

0x43068b MOV	%RAX,%R11

0x43068e JE	430594

0x430694 MOVSXD	(%R8,%R11,4),%R9

0x430698 MOV	0x4(%R8,%R11,4),%R10D

0x43069d SUB	%R9D,%R10D

0x4306a0 XORPD	%XMM1,%XMM1

0x4306a4 TEST	%R10D,%R10D

0x4306a7 JLE	430680

0x4306a9 LEA	(%R11,%RDI,1),%RAX

0x4306ad MOV	-0x80(%RBP),%RSI

0x4306b1 MOV	(%RSI,%RAX,8),%R13

0x4306b5 MOVSD	0x8(%R13),%XMM1

0x4306bb MOV	%R10D,%EAX

0x4306be XOR	%R14D,%R14D

0x4306c1 CMP	$0x8,%R10D

0x4306c5 JAE	430b90

0x4306cb MOV	%EAX,%R10D

0x4306ce AND	$-0x8,%R10D

0x4306d2 CMP	%RAX,%R10

0x4306d5 JAE	430720

0x4306d7 MOV	-0x70(%RBP),%RBX

0x4306db SUB	%R9D,%EBX

0x4306de MOV	-0x68(%RBP),%RSI

0x4306e2 LEA	(%RSI,%R9,8),%R9

0x4306e6 JMP	4306f8

  (460) 0x4306f0 INC	%R10

  (460) 0x4306f3 CMP	%R10,%RAX

  (460) 0x4306f6 JE	430720

  (460) 0x4306f8 MOVSD	(%R9,%R10,8),%XMM0

  (460) 0x4306fe UCOMISD	%XMM0,%XMM1

  (460) 0x430702 JBE	4306f0

  (460) 0x430704 CMP	%R10D,%EBX

  (460) 0x430707 JE	4306f0

  (460) 0x430709 MOVSXD	%R14D,%R14

  (460) 0x43070c MOVSD	%XMM0,(%RDX,%R14,8)

  (460) 0x430712 INC	%R14D

  (460) 0x430715 JMP	4306f0

0x430720 XORPD	%XMM1,%XMM1

0x430724 TEST	%R14D,%R14D

0x430727 JLE	430680

0x43072d MOVSD	0x238(%R13),%XMM7

0x430736 MOV	0x218(%R13),%R15

0x43073d MOVSD	0x18(%R13),%XMM8

0x430743 MOVSD	0x20(%R13),%XMM9

0x430749 MOVSD	0x28(%R13),%XMM10

0x43074f MOVSD	0x38(%R13),%XMM3

0x430755 MOVSD	0x40(%R13),%XMM5

0x43075b MOVSD	0x48(%R13),%XMM2

0x430761 MOVSD	0x58(%R13),%XMM11

0x430767 MOVSD	0x60(%R13),%XMM12

0x43076d MOVSD	0x68(%R13),%XMM13

0x430773 MOVSD	0x78(%R13),%XMM0

0x430779 MOVSD	0x80(%R13),%XMM1

0x430782 MOVAPS	%XMM1,-0x90(%RBP)

0x430789 MOVSD	0x88(%R13),%XMM1

0x430792 MOVAPS	%XMM1,-0xa0(%RBP)

0x430799 MOVQ	0x30(%R13),%XMM14

0x43079f MOVQ	0x50(%R13),%XMM4

0x4307a5 MOVSD	0x70(%R13),%XMM15

0x4307ab MOV	%R14D,%R9D

0x4307ae MOV	%R9,%R14

0x4307b1 MOVSD	0x90(%R13),%XMM1

0x4307ba MOV	$-0x2,%EAX

0x4307bf AND	%RAX,%R14

0x4307c2 MOVAPD	%XMM1,-0x190(%RBP)

0x4307ca JE	430cd7

0x4307d0 MOVSD	%XMM6,-0x78(%RBP)

0x4307d5 MOVAPD	%XMM7,-0x180(%RBP)

0x4307dd UNPCKLPD	%XMM7,%XMM7

0x4307e1 MOVAPD	%XMM7,-0x240(%RBP)

0x4307e9 MOVAPD	%XMM8,-0x170(%RBP)

0x4307f2 UNPCKLPD	%XMM8,%XMM8

0x4307f7 MOVAPD	%XMM8,-0x230(%RBP)

0x430800 MOVAPD	%XMM9,-0x160(%RBP)

0x430809 UNPCKLPD	%XMM9,%XMM9

0x43080e MOVAPD	%XMM9,-0x220(%RBP)

0x430817 MOVAPD	%XMM10,-0x150(%RBP)

0x430820 UNPCKLPD	%XMM10,%XMM10

0x430825 MOVAPD	%XMM10,-0x210(%RBP)

0x43082e MOVDQA	%XMM14,-0x110(%RBP)

0x430837 PUNPCKLQDQ	%XMM14,%XMM14

0x43083c MOVDQA	%XMM14,-0x200(%RBP)

0x430845 MOVAPD	%XMM0,%XMM10

0x43084a MOVQ	%R15,%XMM0

0x43084f PSHUFD	$0x44,%XMM0,%XMM0

0x430854 MOVDQA	%XMM0,-0x1f0(%RBP)

0x43085c MOVAPD	%XMM3,-0xe0(%RBP)

0x430864 UNPCKLPD	%XMM3,%XMM3

0x430868 MOVAPD	%XMM3,-0x1e0(%RBP)

0x430870 MOVAPD	%XMM5,-0xc0(%RBP)

0x430878 UNPCKLPD	%XMM5,%XMM5

0x43087c MOVAPD	%XMM5,-0x1d0(%RBP)

0x430884 MOVAPD	%XMM2,-0xf0(%RBP)

0x43088c UNPCKLPD	%XMM2,%XMM2

0x430890 MOVAPD	%XMM2,-0x1c0(%RBP)

0x430898 MOVDQA	%XMM4,-0xd0(%RBP)

0x4308a0 PUNPCKLQDQ	%XMM4,%XMM4

0x4308a4 MOVDQA	%XMM4,-0x1b0(%RBP)

0x4308ac MOVAPD	%XMM11,-0x140(%RBP)

0x4308b5 UNPCKLPD	%XMM11,%XMM11

0x4308ba MOVAPD	%XMM11,-0x1a0(%RBP)

0x4308c3 MOVAPD	%XMM12,-0x130(%RBP)

0x4308cc MOVAPD	%XMM12,%XMM6

0x4308d1 UNPCKLPD	%XMM12,%XMM6

0x4308d6 MOVAPD	%XMM13,-0x120(%RBP)

0x4308df MOVAPD	%XMM13,%XMM7

0x4308e4 UNPCKLPD	%XMM13,%XMM7

0x4308e9 MOVAPD	%XMM15,-0x100(%RBP)

0x4308f2 MOVAPD	%XMM15,%XMM9

0x4308f7 UNPCKLPD	%XMM15,%XMM9

0x4308fc MOVAPD	%XMM10,-0xb0(%RBP)

0x430905 UNPCKLPD	%XMM10,%XMM10

0x43090a MOVAPD	-0x90(%RBP),%XMM15

0x430913 UNPCKLPD	%XMM15,%XMM15

0x430918 MOVAPD	-0xa0(%RBP),%XMM11

0x430921 UNPCKLPD	%XMM11,%XMM11

0x430926 UNPCKLPD	%XMM1,%XMM1

0x43092a XOR	%EAX,%EAX

0x43092c PXOR	%XMM0,%XMM0

  (459) 0x430930 MOVAPD	(%RDX,%RAX,8),%XMM2

  (459) 0x430935 MULPD	-0x240(%RBP),%XMM2

  (459) 0x43093d CVTTPD2DQ	%XMM2,%XMM3

  (459) 0x430941 CVTDQ2PD	%XMM3,%XMM4

  (459) 0x430945 SUBPD	%XMM4,%XMM2

  (459) 0x430949 MOVAPD	%XMM2,%XMM8

  (459) 0x43094e MULPD	%XMM2,%XMM8

  (459) 0x430953 MOVAPD	%XMM8,%XMM4

  (459) 0x430958 MOVAPD	-0x220(%RBP),%XMM13

  (459) 0x430961 MULPD	%XMM8,%XMM13

  (459) 0x430966 MOVAPD	-0x210(%RBP),%XMM12

  (459) 0x43096f MULPD	%XMM2,%XMM12

  (459) 0x430974 PXOR	%XMM14,%XMM14

  (459) 0x430979 MULPD	%XMM2,%XMM4

  (459) 0x43097d PCMPGTD	%XMM3,%XMM14

  (459) 0x430982 PUNPCKLDQ	%XMM14,%XMM3

  (459) 0x430987 PSLLQ	$0x3,%XMM3

  (459) 0x43098c ADDPD	%XMM13,%XMM12

  (459) 0x430991 PADDQ	-0x1f0(%RBP),%XMM3

  (459) 0x430999 MOVQ	%XMM3,%RSI

  (459) 0x43099e PSHUFD	$-0x12,%XMM3,%XMM13

  (459) 0x4309a4 MOVAPD	%XMM4,%XMM14

  (459) 0x4309a9 MOVQ	%XMM13,%R10

  (459) 0x4309ae MOVAPD	-0x1d0(%RBP),%XMM13

  (459) 0x4309b7 MULPD	%XMM8,%XMM13

  (459) 0x4309bc MULPD	-0x230(%RBP),%XMM14

  (459) 0x4309c5 MOVAPD	-0x1c0(%RBP),%XMM5

  (459) 0x4309cd MULPD	%XMM2,%XMM5

  (459) 0x4309d1 ADDPD	%XMM13,%XMM5

  (459) 0x4309d6 ADDPD	-0x200(%RBP),%XMM12

  (459) 0x4309df MOVAPD	-0x1e0(%RBP),%XMM13

  (459) 0x4309e8 MULPD	%XMM4,%XMM13

  (459) 0x4309ed ADDPD	-0x1b0(%RBP),%XMM5

  (459) 0x4309f5 ADDPD	%XMM14,%XMM12

  (459) 0x4309fa ADDPD	%XMM13,%XMM5

  (459) 0x4309ff MOVDQA	%XMM3,%XMM14

  (459) 0x430a04 PADDQ	0xf9d03(%RIP),%XMM14

  (459) 0x430a0d MOVSD	(%RSI),%XMM13

  (459) 0x430a12 MOVQ	%XMM14,%RSI

  (459) 0x430a17 PSHUFD	$-0x12,%XMM14,%XMM14

  (459) 0x430a1d MOVHPD	(%R10),%XMM13

  (459) 0x430a22 MOVQ	%XMM14,%R10

  (459) 0x430a27 MOVSD	(%RSI),%XMM14

  (459) 0x430a2c MOVHPD	(%R10),%XMM14

  (459) 0x430a31 MULPD	%XMM5,%XMM14

  (459) 0x430a36 MOVAPD	%XMM6,%XMM5

  (459) 0x430a3a MULPD	%XMM8,%XMM5

  (459) 0x430a3f MULPD	%XMM12,%XMM13

  (459) 0x430a44 MOVAPD	%XMM7,%XMM12

  (459) 0x430a49 MULPD	%XMM2,%XMM12

  (459) 0x430a4e ADDPD	%XMM5,%XMM12

  (459) 0x430a53 MOVAPD	-0x1a0(%RBP),%XMM5

  (459) 0x430a5b MULPD	%XMM4,%XMM5

  (459) 0x430a5f ADDPD	%XMM9,%XMM12

  (459) 0x430a64 ADDPD	%XMM5,%XMM12

  (459) 0x430a69 ADDPD	%XMM0,%XMM13

  (459) 0x430a6e MOVDQA	%XMM3,%XMM0

  (459) 0x430a72 PADDQ	0xf9ca6(%RIP),%XMM0

  (459) 0x430a7a MOVQ	%XMM0,%RSI

  (459) 0x430a7f PSHUFD	$-0x12,%XMM0,%XMM0

  (459) 0x430a84 MOVQ	%XMM0,%R10

  (459) 0x430a89 MOVSD	(%RSI),%XMM5

  (459) 0x430a8d MOVHPD	(%R10),%XMM5

  (459) 0x430a92 MULPD	%XMM12,%XMM5

  (459) 0x430a97 ADDPD	%XMM14,%XMM5

  (459) 0x430a9c ADDPD	%XMM13,%XMM5

  (459) 0x430aa1 MULPD	%XMM15,%XMM8

  (459) 0x430aa6 MULPD	%XMM11,%XMM2

  (459) 0x430aab ADDPD	%XMM8,%XMM2

  (459) 0x430ab0 MULPD	%XMM10,%XMM4

  (459) 0x430ab5 ADDPD	%XMM1,%XMM2

  (459) 0x430ab9 ADDPD	%XMM4,%XMM2

  (459) 0x430abd PADDQ	0xf9c6b(%RIP),%XMM3

  (459) 0x430ac5 MOVQ	%XMM3,%RSI

  (459) 0x430aca PSHUFD	$-0x12,%XMM3,%XMM0

  (459) 0x430acf MOVQ	%XMM0,%R10

  (459) 0x430ad4 MOVSD	(%RSI),%XMM0

  (459) 0x430ad8 MOVHPD	(%R10),%XMM0

  (459) 0x430add MULPD	%XMM2,%XMM0

  (459) 0x430ae1 ADDPD	%XMM5,%XMM0

  (459) 0x430ae5 ADD	$0x2,%RAX

  (459) 0x430ae9 CMP	%R14,%RAX

  (459) 0x430aec JB	430930

0x430af2 MOVAPD	%XMM0,%XMM1

0x430af6 UNPCKHPD	%XMM0,%XMM1

0x430afa ADDSD	%XMM0,%XMM1

0x430afe CMP	%R9,%R14

0x430b01 MOVSD	-0x78(%RBP),%XMM6

0x430b06 MOVAPD	-0x180(%RBP),%XMM7

0x430b0e MOVAPD	-0x170(%RBP),%XMM8

0x430b17 MOVAPD	-0x160(%RBP),%XMM9

0x430b20 MOVAPD	-0x150(%RBP),%XMM10

0x430b29 MOVAPD	-0x140(%RBP),%XMM11

0x430b32 MOVAPD	-0x130(%RBP),%XMM12

0x430b3b MOVAPD	-0x120(%RBP),%XMM13

0x430b44 MOVDQA	-0x110(%RBP),%XMM14

0x430b4d MOVAPD	-0x100(%RBP),%XMM15

0x430b56 MOVAPD	-0xf0(%RBP),%XMM2

0x430b5e MOVAPD	-0xe0(%RBP),%XMM3

0x430b66 MOVDQA	-0xd0(%RBP),%XMM4

0x430b6e MOVAPD	-0xc0(%RBP),%XMM5

0x430b76 MOVAPD	-0xb0(%RBP),%XMM0

0x430b7e JE	430680

0x430b84 JMP	430cde

0x430b90 MOV	%EAX,%R15D

0x430b93 AND	$-0x8,%R15D

0x430b97 MOV	-0x60(%RBP),%RSI

0x430b9b LEA	(%RSI,%R9,8),%R12

0x430b9f MOV	-0x58(%RBP),%RSI

0x430ba3 LEA	(%RSI,%R9,1),%R10D

0x430ba7 XOR	%EBX,%EBX

0x430ba9 XOR	%R14D,%R14D

0x430bac JMP	430bbd

  (461) 0x430bb0 ADD	$0x8,%RBX

  (461) 0x430bb4 CMP	%RBX,%R15

  (461) 0x430bb7 JE	4306cb

  (461) 0x430bbd MOVSD	-0x38(%R12,%RBX,8),%XMM0

  (461) 0x430bc4 UCOMISD	%XMM0,%XMM1

  (461) 0x430bc8 JBE	430bdd

  (461) 0x430bca MOV	%R10D,%ESI

  (461) 0x430bcd ADD	%EBX,%ESI

  (461) 0x430bcf JE	430bdd

  (461) 0x430bd1 MOVSXD	%R14D,%R14

  (461) 0x430bd4 MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430bda INC	%R14D

  (461) 0x430bdd MOVSD	-0x30(%R12,%RBX,8),%XMM0

  (461) 0x430be4 UCOMISD	%XMM0,%XMM1

  (461) 0x430be8 JBE	430bff

  (461) 0x430bea LEA	(%R10,%RBX,1),%ESI

  (461) 0x430bee CMP	$-0x1,%ESI

  (461) 0x430bf1 JE	430bff

  (461) 0x430bf3 MOVSXD	%R14D,%R14

  (461) 0x430bf6 MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430bfc INC	%R14D

  (461) 0x430bff MOVSD	-0x28(%R12,%RBX,8),%XMM0

  (461) 0x430c06 UCOMISD	%XMM0,%XMM1

  (461) 0x430c0a JBE	430c21

  (461) 0x430c0c LEA	(%R10,%RBX,1),%ESI

  (461) 0x430c10 CMP	$-0x2,%ESI

  (461) 0x430c13 JE	430c21

  (461) 0x430c15 MOVSXD	%R14D,%R14

  (461) 0x430c18 MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430c1e INC	%R14D

  (461) 0x430c21 MOVSD	-0x20(%R12,%RBX,8),%XMM0

  (461) 0x430c28 UCOMISD	%XMM0,%XMM1

  (461) 0x430c2c JBE	430c43

  (461) 0x430c2e LEA	(%R10,%RBX,1),%ESI

  (461) 0x430c32 CMP	$-0x3,%ESI

  (461) 0x430c35 JE	430c43

  (461) 0x430c37 MOVSXD	%R14D,%R14

  (461) 0x430c3a MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430c40 INC	%R14D

  (461) 0x430c43 MOVSD	-0x18(%R12,%RBX,8),%XMM0

  (461) 0x430c4a UCOMISD	%XMM0,%XMM1

  (461) 0x430c4e JBE	430c65

  (461) 0x430c50 LEA	(%R10,%RBX,1),%ESI

  (461) 0x430c54 CMP	$-0x4,%ESI

  (461) 0x430c57 JE	430c65

  (461) 0x430c59 MOVSXD	%R14D,%R14

  (461) 0x430c5c MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430c62 INC	%R14D

  (461) 0x430c65 MOVSD	-0x10(%R12,%RBX,8),%XMM0

  (461) 0x430c6c UCOMISD	%XMM0,%XMM1

  (461) 0x430c70 JBE	430c87

  (461) 0x430c72 LEA	(%R10,%RBX,1),%ESI

  (461) 0x430c76 CMP	$-0x5,%ESI

  (461) 0x430c79 JE	430c87

  (461) 0x430c7b MOVSXD	%R14D,%R14

  (461) 0x430c7e MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430c84 INC	%R14D

  (461) 0x430c87 MOVSD	-0x8(%R12,%RBX,8),%XMM0

  (461) 0x430c8e UCOMISD	%XMM0,%XMM1

  (461) 0x430c92 JBE	430ca9

  (461) 0x430c94 LEA	(%R10,%RBX,1),%ESI

  (461) 0x430c98 CMP	$-0x6,%ESI

  (461) 0x430c9b JE	430ca9

  (461) 0x430c9d MOVSXD	%R14D,%R14

  (461) 0x430ca0 MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430ca6 INC	%R14D

  (461) 0x430ca9 MOVSD	(%R12,%RBX,8),%XMM0

  (461) 0x430caf UCOMISD	%XMM0,%XMM1

  (461) 0x430cb3 JBE	430bb0

  (461) 0x430cb9 LEA	(%R10,%RBX,1),%ESI

  (461) 0x430cbd CMP	$-0x7,%ESI

  (461) 0x430cc0 JE	430bb0

  (461) 0x430cc6 MOVSXD	%R14D,%R14

  (461) 0x430cc9 MOVSD	%XMM0,(%RDX,%R14,8)

  (461) 0x430ccf INC	%R14D

  (461) 0x430cd2 JMP	430bb0

0x430cd7 XORPD	%XMM1,%XMM1

0x430cdb XOR	%R14D,%R14D

0x430cde UNPCKLPD	-0x90(%RBP),%XMM11

0x430ce7 UNPCKLPD	%XMM5,%XMM8

0x430cec UNPCKLPD	%XMM0,%XMM12

0x430cf1 UNPCKLPD	%XMM3,%XMM9

0x430cf6 UNPCKLPD	-0xa0(%RBP),%XMM13

0x430cff UNPCKLPD	%XMM2,%XMM10

0x430d04 UNPCKLPD	-0x190(%RBP),%XMM15

0x430d0d PUNPCKLQDQ	%XMM4,%XMM14

0x430d12 NOPW	%CS:(%RAX,%RAX,1)

  (458) 0x430d20 MOVSD	(%RDX,%R14,8),%XMM0

  (458) 0x430d26 MULSD	%XMM7,%XMM0

  (458) 0x430d2a CVTTPD2DQ	%XMM0,%XMM2

  (458) 0x430d2e CVTDQ2PD	%XMM2,%XMM2

  (458) 0x430d32 CVTTSD2SI	%XMM0,%EAX

  (458) 0x430d36 SUBSD	%XMM2,%XMM0

  (458) 0x430d3a MOVAPD	%XMM0,%XMM2

  (458) 0x430d3e MULSD	%XMM0,%XMM2

  (458) 0x430d42 MOVAPD	%XMM2,%XMM3

  (458) 0x430d46 MULSD	%XMM0,%XMM3

  (458) 0x430d4a MOVAPD	%XMM2,%XMM4

  (458) 0x430d4e UNPCKLPD	%XMM3,%XMM4

  (458) 0x430d52 MOVAPD	%XMM12,%XMM5

  (458) 0x430d57 MULPD	%XMM4,%XMM5

  (458) 0x430d5b UNPCKLPD	%XMM2,%XMM3

  (458) 0x430d5f MOVAPD	%XMM3,%XMM2

  (458) 0x430d63 MULPD	%XMM9,%XMM4

  (458) 0x430d68 MULPD	%XMM8,%XMM3

  (458) 0x430d6d ADDPD	%XMM4,%XMM3

  (458) 0x430d71 MULPD	%XMM11,%XMM2

  (458) 0x430d76 ADDPD	%XMM5,%XMM2

  (458) 0x430d7a UNPCKLPD	%XMM0,%XMM0

  (458) 0x430d7e MOVAPD	%XMM10,%XMM4

  (458) 0x430d83 MULPD	%XMM0,%XMM4

  (458) 0x430d87 ADDPD	%XMM14,%XMM4

  (458) 0x430d8c ADDPD	%XMM3,%XMM4

  (458) 0x430d90 CLTQ

  (458) 0x430d92 MULPD	%XMM13,%XMM0

  (458) 0x430d97 ADDPD	%XMM15,%XMM0

  (458) 0x430d9c ADDPD	%XMM2,%XMM0

  (458) 0x430da0 MOVUPD	(%R15,%RAX,8),%XMM2

  (458) 0x430da6 MULPD	%XMM4,%XMM2

  (458) 0x430daa MOVUPD	0x10(%R15,%RAX,8),%XMM3

  (458) 0x430db1 MULPD	%XMM0,%XMM3

  (458) 0x430db5 ADDPD	%XMM2,%XMM3

  (458) 0x430db9 MOVAPD	%XMM3,%XMM0

  (458) 0x430dbd UNPCKHPD	%XMM3,%XMM0

  (458) 0x430dc1 ADDSD	%XMM3,%XMM0

  (458) 0x430dc5 ADDSD	%XMM0,%XMM1

  (458) 0x430dc9 INC	%R14

  (458) 0x430dcc CMP	%R14,%R9

  (458) 0x430dcf JNE	430d20

0x430dd5 JMP	430680

/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: 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_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
►94.99+	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.56+	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stl_uninitialized.h:99	exec
►1.13+	_ZN11qmcplusplus12WaveFunction[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:126	exec
○	main.extracted.107	NewTimer.h:249	exec

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	1.12
CQA speedup if FP arith vectorized	1.07
CQA speedup if fully vectorized	5.22
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.31
Bottlenecks	micro-operation queue, P6, P7, P8, P9,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	ParticleSet.h:313-313,ParticleSet.h:316-316,TwoBodyJastrowRef.h:107-107,TwoBodyJastrowRef.h:127-129,TwoBodyJastrowRef.h:132-132,BsplineFunctor.h:236-236,BsplineFunctor.h:240-241,BsplineFunctor.h:246-246,BsplineFunctor.h:249-249,BsplineFunctor.h:256-260,stl_vector.h:1064-1064
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	19.00
CQA cycles if no scalar integer	17.00
CQA cycles if FP arith vectorized	17.69
CQA cycles if fully vectorized	3.64
Front-end cycles	19.00
P0 cycles	4.83
P1 cycles	4.83
P2 cycles	4.83
P3 cycles	4.83
P4 cycles	4.83
P5 cycles	4.83
P6 cycles	19.00
P7 cycles	19.00
P8 cycles	19.00
P9 cycles	19.00
P10 cycles	7.50
P11 cycles	7.50
P12 cycles	7.50
P13 cycles	7.50
P14 cycles	14.50
P15 cycles	14.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	152.00
Nb uops	152.00
Nb loads	47.00
Nb stores	29.00
Nb stack references	34.00
FLOP/cycle	0.11
Nb FLOP add-sub	2.00
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	51.37
Bytes prefetched	0.00
Bytes loaded	520.00
Bytes stored	456.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	45.76
Vectorization ratio load	39.02
Vectorization ratio store	96.55
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	21.28
Vector-efficiency ratio all	17.64
Vector-efficiency ratio load	17.23
Vector-efficiency ratio store	24.57
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	9.38
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	14.10

Metric	Value
CQA speedup if no scalar integer	1.12
CQA speedup if FP arith vectorized	1.07
CQA speedup if fully vectorized	5.22
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.31
Bottlenecks	micro-operation queue, P6, P7, P8, P9,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	ParticleSet.h:313-313,ParticleSet.h:316-316,TwoBodyJastrowRef.h:107-107,TwoBodyJastrowRef.h:127-129,TwoBodyJastrowRef.h:132-132,BsplineFunctor.h:236-236,BsplineFunctor.h:240-241,BsplineFunctor.h:246-246,BsplineFunctor.h:249-249,BsplineFunctor.h:256-260,stl_vector.h:1064-1064
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	19.00
CQA cycles if no scalar integer	17.00
CQA cycles if FP arith vectorized	17.69
CQA cycles if fully vectorized	3.64
Front-end cycles	19.00
P0 cycles	4.83
P1 cycles	4.83
P2 cycles	4.83
P3 cycles	4.83
P4 cycles	4.83
P5 cycles	4.83
P6 cycles	19.00
P7 cycles	19.00
P8 cycles	19.00
P9 cycles	19.00
P10 cycles	7.50
P11 cycles	7.50
P12 cycles	7.50
P13 cycles	7.50
P14 cycles	14.50
P15 cycles	14.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	152.00
Nb uops	152.00
Nb loads	47.00
Nb stores	29.00
Nb stack references	34.00
FLOP/cycle	0.11
Nb FLOP add-sub	2.00
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	51.37
Bytes prefetched	0.00
Bytes loaded	520.00
Bytes stored	456.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	45.76
Vectorization ratio load	39.02
Vectorization ratio store	96.55
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	21.28
Vector-efficiency ratio all	17.64
Vector-efficiency ratio load	17.23
Vector-efficiency ratio store	24.57
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	9.38
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	14.10

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:107,127-132
/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
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 19.00 to 17.00 cycles (1.12x 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 17% 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 19.00 to 3.64 cycles (5.22x speedup).

Details

45% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

39% of SSE/AVX loads are used in vector version.
96% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
21% 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:
- recompile with ffast-math (included in Ofast) to extend loop vectorization to FP reductions.
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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 19.00 to 14.50 cycles (1.31x speedup).

Workaround

Read less array elements All SSE and/or AVX registers are used: in that case, try to relax register pressure by reducing the unroll factor or splitting your loop
Write less array elements
Provide more information to your compiler:
- hardcode the bounds of the corresponding 'for' loop

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.

MOVQ: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064

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).

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

The binary loop is composed of 2 FP arithmetical operations:

2: addition or subtraction

The binary loop is loading 520 bytes (65 double precision FP elements). The binary loop is storing 456 bytes (57 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	152
nb uops	152
loop length	891
used x86 registers	14
used mmx registers	0
used xmm registers	16
used ymm registers	0
used zmm registers	0
nb stack references	34

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	19.00 cycles
front end	19.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.83	4.83	4.83	4.83	4.83	4.83	19.00	19.00	19.00	19.00	7.50	7.50	7.50	7.50	14.50	14.50
cycles	4.83	4.83	4.83	4.83	4.83	4.83	19.00	19.00	19.00	19.00	7.50	7.50	7.50	7.50	14.50	14.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	19.00
Dispatch	19.00
Overall L1	19.00

Vectorization ratios

INT

all	30%
load	28%
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	12%

all	51%
load	41%
store	95%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	45%
load	39%
store	96%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	21%

Vector efficiency ratios

INT

all	13%
load	15%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	18%
load	17%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

INT+FP

all	17%
load	17%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 19.00 cycles. At this rate:

10% of peak load performance is reached (27.37 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
18% of peak store performance is reached (24.00 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 19.00 to 14.50 cycles (1.31x speedup).

ASM code

In the binary file, the address of the loop is: 430694

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
ADDSD %XMM1,%XMM6	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%)
LEA 0x1(%R11),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %RCX,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RAX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JE 430594 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x44>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD (%R8,%R11,4),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
MOV 0x4(%R8,%R11,4),%R10D	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%)
SUB %R9D,%R10D	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%)
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R10D,%R10D	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 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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
LEA (%R11,%RDI,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x80(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RSI,%RAX,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x8(%R13),%XMM1	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 %R10D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP $0x8,%R10D	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 430b90 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x640>	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 %EAX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x8,%R10D	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%)
CMP %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 430720 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x70(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
SUB %R9D,%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	scal (6.3%)
MOV -0x68(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R9,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JMP 4306f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R14D,%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%)
JLE 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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
MOVSD 0x238(%R13),%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%)
MOV 0x218(%R13),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOVSD 0x18(%R13),%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%)
MOVSD 0x20(%R13),%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%)
MOVSD 0x28(%R13),%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%)
MOVSD 0x38(%R13),%XMM3	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%)
MOVSD 0x40(%R13),%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%)
MOVSD 0x48(%R13),%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%)
MOVSD 0x58(%R13),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x60(%R13),%XMM12	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%)
MOVSD 0x68(%R13),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x78(%R13),%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%)
MOVSD 0x80(%R13),%XMM1	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%)
MOVAPS %XMM1,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVSD 0x88(%R13),%XMM1	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%)
MOVAPS %XMM1,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVQ 0x30(%R13),%XMM14	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%)
MOVQ 0x50(%R13),%XMM4	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%)
MOVSD 0x70(%R13),%XMM15	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 %R14D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVSD 0x90(%R13),%XMM1	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 $-0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND %RAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVAPD %XMM1,-0x190(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
JE 430cd7 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x787>	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
MOVSD %XMM6,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOVAPD %XMM7,-0x180(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM7,-0x240(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM8,-0x170(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM8,%XMM8	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%)
MOVAPD %XMM8,-0x230(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM9,-0x160(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM9,%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%)
MOVAPD %XMM9,-0x220(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM10,-0x150(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM10,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM10,-0x210(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVDQA %XMM14,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
PUNPCKLQDQ %XMM14,%XMM14	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%)
MOVDQA %XMM14,-0x200(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
MOVAPD %XMM0,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ %R15,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	6	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
MOVDQA %XMM0,-0x1f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
MOVAPD %XMM3,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM3,-0x1e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM5,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %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%)
MOVAPD %XMM5,-0x1d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM2,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM2,%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%)
MOVAPD %XMM2,-0x1c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVDQA %XMM4,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
PUNPCKLQDQ %XMM4,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVDQA %XMM4,-0x1b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
MOVAPD %XMM11,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM11,%XMM11	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%)
MOVAPD %XMM11,-0x1a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM12,-0x130(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM12,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM12,%XMM6	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%)
MOVAPD %XMM13,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM13,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM13,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM15,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM15,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM15,%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%)
MOVAPD %XMM10,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM10,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD -0x90(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
UNPCKLPD %XMM15,%XMM15	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%)
MOVAPD -0xa0(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
UNPCKLPD %XMM11,%XMM11	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%)
UNPCKLPD %XMM1,%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%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
PXOR %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	vect (25.0%)
MOVAPD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKHPD %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	scal (12.5%)
ADDSD %XMM0,%XMM1	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 %R9,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSD -0x78(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD -0x180(%RBP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x170(%RBP),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x160(%RBP),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x150(%RBP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x140(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x130(%RBP),%XMM12	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%)
MOVAPD -0x120(%RBP),%XMM13	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%)
MOVDQA -0x110(%RBP),%XMM14	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%)
MOVAPD -0x100(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xf0(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xe0(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVDQA -0xd0(%RBP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xc0(%RBP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xb0(%RBP),%XMM0	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%)
JE 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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
JMP 430cde <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x78e>	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,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x8,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV -0x60(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R9,8),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x58(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R9,1),%R10D	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
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 430bbd <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x66d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
UNPCKLPD -0x90(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
UNPCKLPD %XMM5,%XMM8	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%)
UNPCKLPD %XMM0,%XMM12	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%)
UNPCKLPD %XMM3,%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%)
UNPCKLPD -0xa0(%RBP),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
UNPCKLPD %XMM2,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
UNPCKLPD -0x190(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
PUNPCKLQDQ %XMM4,%XMM14	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 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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:107,127-132
/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
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

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

45% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

39% of SSE/AVX loads are used in vector version.
96% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
21% 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:
- recompile with ffast-math (included in Ofast) to extend loop vectorization to FP reductions.
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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 19.00 to 14.50 cycles (1.31x speedup).

Workaround

Read less array elements All SSE and/or AVX registers are used: in that case, try to relax register pressure by reducing the unroll factor or splitting your loop
Write less array elements
Provide more information to your compiler:
- hardcode the bounds of the corresponding 'for' loop

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.

MOVQ: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1064

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).

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

The binary loop is composed of 2 FP arithmetical operations:

2: addition or subtraction

The binary loop is loading 520 bytes (65 double precision FP elements). The binary loop is storing 456 bytes (57 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	152
nb uops	152
loop length	891
used x86 registers	14
used mmx registers	0
used xmm registers	16
used ymm registers	0
used zmm registers	0
nb stack references	34

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	19.00 cycles
front end	19.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.83	4.83	4.83	4.83	4.83	4.83	19.00	19.00	19.00	19.00	7.50	7.50	7.50	7.50	14.50	14.50
cycles	4.83	4.83	4.83	4.83	4.83	4.83	19.00	19.00	19.00	19.00	7.50	7.50	7.50	7.50	14.50	14.50

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	19.00
Dispatch	19.00
Overall L1	19.00

Vectorization ratios

INT

all	30%
load	28%
store	100%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	12%

all	51%
load	41%
store	95%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	45%
load	39%
store	96%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	21%

Vector efficiency ratios

INT

all	13%
load	15%
store	25%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	18%
load	17%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

INT+FP

all	17%
load	17%
store	24%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	14%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 19.00 cycles. At this rate:

10% of peak load performance is reached (27.37 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
18% of peak store performance is reached (24.00 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: 430694

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
ADDSD %XMM1,%XMM6	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%)
LEA 0x1(%R11),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %RCX,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RAX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JE 430594 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x44>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOVSXD (%R8,%R11,4),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
MOV 0x4(%R8,%R11,4),%R10D	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%)
SUB %R9D,%R10D	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%)
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R10D,%R10D	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 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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
LEA (%R11,%RDI,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x80(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RSI,%RAX,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x8(%R13),%XMM1	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 %R10D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP $0x8,%R10D	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 430b90 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x640>	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 %EAX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x8,%R10D	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%)
CMP %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 430720 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1d0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x70(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
SUB %R9D,%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	scal (6.3%)
MOV -0x68(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R9,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JMP 4306f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x1a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R14D,%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%)
JLE 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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
MOVSD 0x238(%R13),%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%)
MOV 0x218(%R13),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOVSD 0x18(%R13),%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%)
MOVSD 0x20(%R13),%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%)
MOVSD 0x28(%R13),%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%)
MOVSD 0x38(%R13),%XMM3	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%)
MOVSD 0x40(%R13),%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%)
MOVSD 0x48(%R13),%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%)
MOVSD 0x58(%R13),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x60(%R13),%XMM12	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%)
MOVSD 0x68(%R13),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x78(%R13),%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%)
MOVSD 0x80(%R13),%XMM1	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%)
MOVAPS %XMM1,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVSD 0x88(%R13),%XMM1	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%)
MOVAPS %XMM1,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVQ 0x30(%R13),%XMM14	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%)
MOVQ 0x50(%R13),%XMM4	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%)
MOVSD 0x70(%R13),%XMM15	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 %R14D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVSD 0x90(%R13),%XMM1	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 $-0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND %RAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVAPD %XMM1,-0x190(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
JE 430cd7 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x787>	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
MOVSD %XMM6,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOVAPD %XMM7,-0x180(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM7,-0x240(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM8,-0x170(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM8,%XMM8	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%)
MOVAPD %XMM8,-0x230(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM9,-0x160(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM9,%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%)
MOVAPD %XMM9,-0x220(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM10,-0x150(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM10,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM10,-0x210(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVDQA %XMM14,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
PUNPCKLQDQ %XMM14,%XMM14	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%)
MOVDQA %XMM14,-0x200(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
MOVAPD %XMM0,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MOVQ %R15,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	6	1	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
MOVDQA %XMM0,-0x1f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
MOVAPD %XMM3,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM3,-0x1e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM5,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %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%)
MOVAPD %XMM5,-0x1d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM2,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM2,%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%)
MOVAPD %XMM2,-0x1c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVDQA %XMM4,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
PUNPCKLQDQ %XMM4,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVDQA %XMM4,-0x1b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	0.50	vect (25.0%)
MOVAPD %XMM11,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM11,%XMM11	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%)
MOVAPD %XMM11,-0x1a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM12,-0x130(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM12,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM12,%XMM6	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%)
MOVAPD %XMM13,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM13,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM13,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM15,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM15,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM15,%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%)
MOVAPD %XMM10,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM10,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD -0x90(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
UNPCKLPD %XMM15,%XMM15	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%)
MOVAPD -0xa0(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
UNPCKLPD %XMM11,%XMM11	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%)
UNPCKLPD %XMM1,%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%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
PXOR %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	vect (25.0%)
MOVAPD %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKHPD %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	scal (12.5%)
ADDSD %XMM0,%XMM1	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 %R9,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSD -0x78(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD -0x180(%RBP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x170(%RBP),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x160(%RBP),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x150(%RBP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x140(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x130(%RBP),%XMM12	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%)
MOVAPD -0x120(%RBP),%XMM13	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%)
MOVDQA -0x110(%RBP),%XMM14	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%)
MOVAPD -0x100(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xf0(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xe0(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVDQA -0xd0(%RBP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xc0(%RBP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xb0(%RBP),%XMM0	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%)
JE 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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
JMP 430cde <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x78e>	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,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
AND $-0x8,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV -0x60(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R9,8),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x58(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RSI,%R9,1),%R10D	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
XOR %EBX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 430bbd <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x66d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
UNPCKLPD -0x90(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
UNPCKLPD %XMM5,%XMM8	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%)
UNPCKLPD %XMM0,%XMM12	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%)
UNPCKLPD %XMM3,%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%)
UNPCKLPD -0xa0(%RBP),%XMM13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
UNPCKLPD %XMM2,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
UNPCKLPD -0x190(%RBP),%XMM15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
PUNPCKLQDQ %XMM4,%XMM14	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 430680 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x130>	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

Workaround

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code