OV - exec - Loop 156

	Loop Id: 156	Module: exec	Source: advec_cell.cpp:66-110 [...]	Coverage: 3.95%

0x4205e0 MULPD	%XMM9,%XMM7

0x4205e5 DIVPD	%XMM7,%XMM8

0x4205ea MOVAPD	%XMM12,%XMM7

0x4205ef XORPD	%XMM3,%XMM3

0x4205f3 CMPPD	$0x6,%XMM3,%XMM7

0x4205f8 MOVAPD	0x7afdf(%RIP),%XMM9    [25]

0x420601 MOVAPD	%XMM9,%XMM3

0x420606 SUBPD	%XMM8,%XMM3

0x42060b SUBPD	%XMM9,%XMM8

0x420610 ANDPD	%XMM7,%XMM3

0x420614 ANDNPD	%XMM8,%XMM7

0x420619 ORPD	%XMM3,%XMM7

0x42061d ANDPD	%XMM15,%XMM6

0x420622 ANDPD	%XMM15,%XMM12

0x420627 MOVAPD	%XMM12,%XMM3

0x42062c MINPD	%XMM6,%XMM3

0x420630 MOVAPD	%XMM6,%XMM4

0x420634 CMPPD	$0x3,%XMM6,%XMM4

0x420639 MOVAPD	%XMM12,%XMM8

0x42063e ANDPD	%XMM4,%XMM8

0x420643 ANDNPD	%XMM3,%XMM4

0x420647 ORPD	%XMM8,%XMM4

0x42064c MULPD	%XMM5,%XMM12

0x420651 MULPD	%XMM13,%XMM6

0x420656 ADDPD	%XMM12,%XMM6

0x42065b MOVAPD	0x7af9d(%RIP),%XMM5    [25]

0x420663 MULPD	%XMM5,%XMM6

0x420667 MOVAPD	%XMM6,%XMM0

0x42066b MINPD	%XMM4,%XMM0

0x42066f CMPPD	$0x3,%XMM4,%XMM4

0x420674 ANDPD	%XMM4,%XMM6

0x420678 ANDNPD	%XMM0,%XMM4

0x42067c ORPD	%XMM6,%XMM4

0x420680 MULPD	%XMM7,%XMM4

0x420684 ANDPD	%XMM4,%XMM2

0x420688 ADDPD	%XMM1,%XMM2

0x42068c MULPD	%XMM10,%XMM2

0x420691 MOVDQA	-0x120(%RBP),%XMM3    [14]

0x420699 MOVDQA	%XMM3,%XMM0

0x42069d PSRLQ	$0x20,%XMM0

0x4206a2 PMULUDQ	%XMM11,%XMM0

0x4206a7 MOVDQA	%XMM3,%XMM1

0x4206ab PMULUDQ	%XMM11,%XMM1

0x4206b0 PSRLQ	$0x20,%XMM11

0x4206b6 PMULUDQ	%XMM3,%XMM11

0x4206bb PADDQ	%XMM0,%XMM11

0x4206c0 PADDQ	-0xb0(%RBP),%XMM1    [14]

0x4206c8 PSLLQ	$0x20,%XMM11

0x4206ce PADDQ	%XMM11,%XMM1

0x4206d3 PSLLQ	$0x3,%XMM1

0x4206d8 MOVQ	-0x38(%RBP),%XMM0    [14]

0x4206dd PSHUFD	$0x44,%XMM0,%XMM0

0x4206e2 PADDQ	%XMM1,%XMM0

0x4206e6 MOVQ	%XMM0,%RAX

0x4206eb PSHUFD	$-0x12,%XMM0,%XMM0

0x4206f0 MOVQ	%XMM0,%RDX

0x4206f5 MOVLPD	%XMM2,(%RAX)    [1]

0x4206f9 MOVHPD	%XMM2,(%RDX)    [15]

0x4206fd MOVDQA	-0x1d0(%RBP),%XMM3    [14]

0x420705 PADDQ	0x7ad43(%RIP),%XMM3    [25]

0x42070d ADD	$0x2,%R9

0x420711 CMP	%R8,%R9

0x420714 JAE	420cf2

0x42071a MOVQ	%XMM3,%RAX

0x42071f XOR	%EDX,%EDX

0x420721 DIVQ	-0xc8(%RBP)    [14]

0x420728 MOVQ	%RAX,%XMM0

0x42072d PSHUFD	$-0x12,%XMM3,%XMM1

0x420732 MOVQ	%XMM1,%RAX

0x420737 XOR	%EDX,%EDX

0x420739 DIVQ	-0xc0(%RBP)    [14]

0x420740 MOVQ	%RAX,%XMM1

0x420745 PUNPCKLQDQ	%XMM1,%XMM0

0x420749 MOVDQA	%XMM0,%XMM2

0x42074d PADDQ	-0x1a0(%RBP),%XMM2    [14]

0x420755 PMULUDQ	-0x1b0(%RBP),%XMM0    [14]

0x42075d MOVDQA	%XMM3,-0x1d0(%RBP)    [14]

0x420765 MOVDQA	%XMM3,%XMM1

0x420769 PSUBQ	%XMM0,%XMM1

0x42076d PSHUFD	$-0x18,%XMM1,%XMM14

0x420773 PADDD	-0x190(%RBP),%XMM14    [14]

0x42077c PXOR	%XMM0,%XMM0

0x420780 PCMPGTD	%XMM14,%XMM0

0x420785 MOVDQA	%XMM14,%XMM6

0x42078a PUNPCKLDQ	%XMM0,%XMM6

0x42078e PSHUFD	$-0x18,%XMM2,%XMM11

0x420794 PSLLQ	$0x20,%XMM2

0x420799 PSRAD	$0x1f,%XMM2

0x42079e PSHUFD	$-0x13,%XMM2,%XMM0

0x4207a3 PUNPCKLDQ	%XMM0,%XMM11

0x4207a8 MOVDQA	-0x180(%RBP),%XMM3    [14]

0x4207b0 MOVDQA	%XMM3,%XMM0

0x4207b4 PMULUDQ	%XMM11,%XMM0

0x4207b9 MOVDQA	-0x110(%RBP),%XMM1    [14]

0x4207c1 PMULUDQ	%XMM11,%XMM1

0x4207c6 PSRLQ	$0x20,%XMM2

0x4207cb PMULUDQ	%XMM2,%XMM3

0x4207cf PADDQ	%XMM1,%XMM3

0x4207d3 PSLLQ	$0x20,%XMM3

0x4207d8 PADDQ	%XMM6,%XMM0

0x4207dc PADDQ	%XMM3,%XMM0

0x4207e0 PSLLQ	$0x3,%XMM0

0x4207e5 PADDQ	-0x100(%RBP),%XMM0    [14]

0x4207ed MOVQ	%XMM0,%RAX

0x4207f2 PSHUFD	$-0x12,%XMM0,%XMM0

0x4207f7 MOVQ	%XMM0,%RDX

0x4207fc MOVSD	(%RAX),%XMM0    [3]

0x420800 MOVHPD	(%RDX),%XMM0    [17]

0x420804 XORPD	%XMM12,%XMM12

0x420809 CMPPD	$0x1,%XMM0,%XMM12

0x42080f MOVAPD	%XMM0,%XMM7

0x420813 MOVAPD	%XMM0,-0xb0(%RBP)    [14]

0x42081b MOVDQA	%XMM14,%XMM0

0x420820 PCMPEQD	%XMM3,%XMM3

0x420824 PADDD	%XMM3,%XMM0

0x420828 MOVDQA	%XMM14,%XMM1

0x42082d PSUBD	%XMM3,%XMM1

0x420831 MOVDQA	%XMM1,%XMM5

0x420835 MOVDQA	-0x170(%RBP),%XMM3    [14]

0x42083d PCMPGTD	%XMM3,%XMM5

0x420841 PAND	%XMM5,%XMM3

0x420845 PANDN	%XMM1,%XMM5

0x420849 POR	%XMM3,%XMM5

0x42084d PXOR	%XMM1,%XMM1

0x420851 PCMPGTD	%XMM0,%XMM1

0x420855 PUNPCKLDQ	%XMM1,%XMM0

0x420859 PXOR	%XMM1,%XMM1

0x42085d PCMPGTD	%XMM5,%XMM1

0x420861 PUNPCKLDQ	%XMM1,%XMM5

0x420865 PADDD	0x7ad62(%RIP),%XMM14    [25]

0x42086e PXOR	%XMM1,%XMM1

0x420872 PCMPGTD	%XMM14,%XMM1

0x420877 PUNPCKLDQ	%XMM1,%XMM14

0x42087c MOVAPD	%XMM12,%XMM3

0x420881 ANDNPD	%XMM5,%XMM3

0x420885 PAND	%XMM12,%XMM14

0x42088a POR	%XMM3,%XMM14

0x42088f MOVDQA	%XMM12,%XMM1

0x420894 PANDN	%XMM0,%XMM1

0x420898 PAND	%XMM12,%XMM0

0x42089d POR	%XMM0,%XMM3

0x4208a1 MOVDQA	%XMM6,%XMM4

0x4208a5 PAND	%XMM12,%XMM4

0x4208aa POR	%XMM1,%XMM4

0x4208ae MOVDQA	%XMM4,%XMM10

0x4208b3 MOVDQA	%XMM4,-0x1c0(%RBP)    [14]

0x4208bb PANDN	%XMM6,%XMM12

0x4208c0 POR	%XMM0,%XMM12

0x4208c5 MOVAPD	%XMM7,%XMM1

0x4208c9 ANDPD	%XMM15,%XMM1

0x4208ce MOVDQA	-0x160(%RBP),%XMM7    [14]

0x4208d6 MOVDQA	%XMM7,%XMM0

0x4208da PMULUDQ	%XMM11,%XMM0

0x4208df MOVDQA	%XMM7,%XMM5

0x4208e3 PSRLQ	$0x20,%XMM5

0x4208e8 PMULUDQ	%XMM11,%XMM5

0x4208ed PMULUDQ	%XMM2,%XMM7

0x4208f1 PADDQ	%XMM5,%XMM7

0x4208f5 PSLLQ	$0x20,%XMM7

0x4208fa PADDQ	%XMM0,%XMM7

0x4208fe PADDQ	%XMM12,%XMM7

0x420903 PSLLQ	$0x3,%XMM7

0x420908 MOVQ	-0x58(%RBP),%XMM0    [14]

0x42090d PSHUFD	$0x44,%XMM0,%XMM0

0x420912 PADDQ	%XMM7,%XMM0

0x420916 MOVQ	%XMM0,%RDX

0x42091b PSHUFD	$-0x12,%XMM0,%XMM0

0x420920 MOVQ	%XMM0,%RAX

0x420925 MOVSD	(%RDX),%XMM0    [16]

0x420929 MOVHPD	(%RAX),%XMM0    [2]

0x42092d DIVPD	%XMM0,%XMM1

0x420931 MOVAPD	%XMM1,%XMM5

0x420935 ADDPD	%XMM9,%XMM5

0x42093a MOVDQA	%XMM6,%XMM0

0x42093e PSLLQ	$0x3,%XMM0

0x420943 MOVQ	-0x88(%RBP),%XMM7    [14]

0x42094b PSHUFD	$0x44,%XMM7,%XMM7

0x420950 PADDQ	%XMM7,%XMM0

0x420954 MOVQ	%XMM0,%RSI

0x420959 PSHUFD	$-0x12,%XMM0,%XMM0

0x42095e MOVQ	%XMM0,%RDI

0x420963 MOVSD	(%RSI),%XMM13    [13]

0x420968 MOVHPD	(%RDI),%XMM13    [24]

0x42096d PSLLQ	$0x3,%XMM3

0x420972 PADDQ	%XMM7,%XMM3

0x420976 MOVQ	%XMM3,%RSI

0x42097b PSHUFD	$-0x12,%XMM3,%XMM3

0x420980 MOVQ	%XMM3,%RDI

0x420985 MOVSD	(%RSI),%XMM3    [12]

0x420989 MOVHPD	(%RDI),%XMM3    [23]

0x42098d MULPD	%XMM5,%XMM13

0x420992 DIVPD	%XMM3,%XMM13

0x420997 MOVDQA	-0x150(%RBP),%XMM3    [14]

0x42099f MOVDQA	%XMM3,%XMM5

0x4209a3 PMULUDQ	%XMM11,%XMM5

0x4209a8 MOVDQA	%XMM3,%XMM7

0x4209ac PSRLQ	$0x20,%XMM7

0x4209b1 PMULUDQ	%XMM11,%XMM7

0x4209b6 PMULUDQ	%XMM2,%XMM3

0x4209ba PADDQ	%XMM7,%XMM3

0x4209be PSLLQ	$0x20,%XMM3

0x4209c3 PADDQ	%XMM5,%XMM3

0x4209c7 MOVDQA	%XMM3,%XMM5

0x4209cb PADDQ	%XMM12,%XMM5

0x4209d0 PSLLQ	$0x3,%XMM5

0x4209d5 MOVQ	%R12,%XMM7

0x4209da PSHUFD	$0x44,%XMM7,%XMM7

0x4209df PADDQ	%XMM7,%XMM5

0x4209e3 MOVQ	%XMM5,%RSI

0x4209e8 PSHUFD	$-0x12,%XMM5,%XMM5

0x4209ed MOVQ	%XMM5,%RBX

0x4209f2 MOVAPD	%XMM15,%XMM4

0x4209f7 MOVSD	(%RSI),%XMM15    [11]

0x4209fc MOVHPD	(%RBX),%XMM15    [26]

0x420a01 MOVDQA	%XMM3,%XMM5

0x420a05 PADDQ	%XMM14,%XMM5

0x420a0a PSLLQ	$0x3,%XMM5

0x420a0f PADDQ	%XMM7,%XMM5

0x420a13 MOVQ	%XMM5,%RDI

0x420a18 PSHUFD	$-0x12,%XMM5,%XMM5

0x420a1d MOVQ	%XMM5,%R14

0x420a22 MOVSD	(%RDI),%XMM5    [22]

0x420a26 MOVHPD	(%R14),%XMM5    [8]

0x420a2b MOVAPD	%XMM15,%XMM8

0x420a30 PADDQ	%XMM10,%XMM3

0x420a35 PSLLQ	$0x3,%XMM3

0x420a3a PADDQ	%XMM7,%XMM3

0x420a3e MOVQ	%XMM3,%RDI

0x420a43 PSHUFD	$-0x12,%XMM3,%XMM3

0x420a48 MOVQ	%XMM3,%R14

0x420a4d MOVSD	(%RDI),%XMM10    [21]

0x420a52 MOVHPD	(%R14),%XMM10    [7]

0x420a57 SUBPD	%XMM5,%XMM8

0x420a5c SUBPD	%XMM15,%XMM10

0x420a61 MOVAPD	%XMM10,%XMM5

0x420a66 MULPD	%XMM8,%XMM5

0x420a6b MOVAPD	%XMM9,%XMM0

0x420a70 XORPD	%XMM9,%XMM9

0x420a75 CMPPD	$0x1,%XMM5,%XMM9

0x420a7b ANDPD	%XMM4,%XMM8

0x420a80 MOVAPD	%XMM10,%XMM3

0x420a85 ANDPD	%XMM4,%XMM3

0x420a89 MOVAPD	%XMM3,%XMM5

0x420a8d MINPD	%XMM8,%XMM5

0x420a92 MOVAPD	%XMM8,%XMM7

0x420a97 CMPPD	$0x3,%XMM8,%XMM7

0x420a9d MOVAPD	%XMM3,%XMM4

0x420aa1 ANDPD	%XMM7,%XMM4

0x420aa5 ANDNPD	%XMM5,%XMM7

0x420aa9 ORPD	%XMM4,%XMM7

0x420aad MOVAPD	0x7ab3b(%RIP),%XMM5    [25]

0x420ab5 SUBPD	%XMM1,%XMM5

0x420ab9 MULPD	%XMM5,%XMM3

0x420abd MULPD	%XMM13,%XMM8

0x420ac2 ADDPD	%XMM3,%XMM8

0x420ac7 MULPD	0x7ab30(%RIP),%XMM8    [25]

0x420ad0 MOVAPD	%XMM8,%XMM3

0x420ad5 MINPD	%XMM7,%XMM3

0x420ad9 CMPPD	$0x3,%XMM7,%XMM7

0x420ade ANDPD	%XMM7,%XMM8

0x420ae3 ANDNPD	%XMM3,%XMM7

0x420ae7 ORPD	%XMM8,%XMM7

0x420aec CMPPD	$0x6,0x79caa(%RIP),%XMM10    [25]

0x420af6 MOVAPD	%XMM0,%XMM3

0x420afa SUBPD	%XMM1,%XMM3

0x420afe SUBPD	%XMM0,%XMM1

0x420b02 ANDPD	%XMM10,%XMM3

0x420b07 ANDNPD	%XMM1,%XMM10

0x420b0c ORPD	%XMM3,%XMM10

0x420b11 MULPD	%XMM7,%XMM10

0x420b16 ANDPD	%XMM9,%XMM10

0x420b1b ADDPD	%XMM15,%XMM10

0x420b20 MULPD	-0xb0(%RBP),%XMM10    [14]

0x420b29 MOVDQA	-0x140(%RBP),%XMM4    [14]

0x420b31 MOVDQA	%XMM4,%XMM1

0x420b35 PSRLQ	$0x20,%XMM1

0x420b3a PMULUDQ	%XMM11,%XMM1

0x420b3f MOVDQA	%XMM4,%XMM3

0x420b43 PMULUDQ	%XMM2,%XMM3

0x420b47 PADDQ	%XMM1,%XMM3

0x420b4b MOVDQA	%XMM4,%XMM1

0x420b4f PMULUDQ	%XMM11,%XMM1

0x420b54 PSLLQ	$0x20,%XMM3

0x420b59 MOVDQA	%XMM6,-0xb0(%RBP)    [14]

0x420b61 PADDQ	%XMM6,%XMM1

0x420b65 PADDQ	%XMM3,%XMM1

0x420b69 PSLLQ	$0x3,%XMM1

0x420b6e MOVQ	-0x40(%RBP),%XMM3    [14]

0x420b73 PSHUFD	$0x44,%XMM3,%XMM3

0x420b78 PADDQ	%XMM1,%XMM3

0x420b7c MOVQ	%XMM3,%RDI

0x420b81 MOVLPD	%XMM10,(%RDI)    [20]

0x420b86 PSHUFD	$-0x12,%XMM3,%XMM1

0x420b8b MOVQ	%XMM1,%RDI

0x420b90 MOVHPD	%XMM10,(%RDI)    [19]

0x420b95 MOVDQA	-0x130(%RBP),%XMM3    [14]

0x420b9d MOVDQA	%XMM3,%XMM1

0x420ba1 PSRLQ	$0x20,%XMM1

0x420ba6 PMULUDQ	%XMM11,%XMM1

0x420bab PMULUDQ	%XMM3,%XMM2

0x420baf PADDQ	%XMM1,%XMM2

0x420bb3 MOVDQA	%XMM3,%XMM1

0x420bb7 PMULUDQ	%XMM11,%XMM1

0x420bbc PSLLQ	$0x20,%XMM2

0x420bc1 PADDQ	%XMM1,%XMM2

0x420bc5 PADDQ	%XMM2,%XMM12

0x420bca PSLLQ	$0x3,%XMM12

0x420bd0 MOVQ	%R15,%XMM1

0x420bd5 PSHUFD	$0x44,%XMM1,%XMM3

0x420bda PADDQ	%XMM3,%XMM12

0x420bdf MOVQ	%XMM12,%RDI

0x420be4 PSHUFD	$-0x12,%XMM12,%XMM1

0x420bea MOVQ	%XMM1,%R14

0x420bef MOVSD	(%RDI),%XMM1    [18]

0x420bf3 MOVHPD	(%R14),%XMM1    [6]

0x420bf8 PADDQ	%XMM2,%XMM14

0x420bfd PSLLQ	$0x3,%XMM14

0x420c03 PADDQ	%XMM3,%XMM14

0x420c08 MOVQ	%XMM14,%RDI

0x420c0d PSHUFD	$-0x12,%XMM14,%XMM4

0x420c13 MOVQ	%XMM4,%R14

0x420c18 MOVSD	(%RDI),%XMM4    [10]

0x420c1c MOVHPD	(%R14),%XMM4    [5]

0x420c21 PADDQ	-0x1c0(%RBP),%XMM2    [14]

0x420c29 MOVAPD	%XMM1,%XMM6

0x420c2d PSLLQ	$0x3,%XMM2

0x420c32 PADDQ	%XMM3,%XMM2

0x420c36 MOVQ	%XMM2,%RDI

0x420c3b PSHUFD	$-0x12,%XMM2,%XMM2

0x420c40 MOVQ	%XMM2,%R14

0x420c45 MOVSD	(%RDI),%XMM12    [9]

0x420c4a MOVHPD	(%R14),%XMM12    [4]

0x420c4f SUBPD	%XMM4,%XMM6

0x420c53 SUBPD	%XMM1,%XMM12

0x420c58 MOVAPD	%XMM12,%XMM3

0x420c5d MULPD	%XMM6,%XMM3

0x420c61 PXOR	%XMM2,%XMM2

0x420c65 CMPPD	$0x1,%XMM3,%XMM2

0x420c6a MOVMSKPD	%XMM2,%EDI

0x420c6e TEST	$0x1,%DIL

0x420c72 JNE	420ca0

0x420c74 TEST	$0x2,%DIL

0x420c78 JNE	420caa

0x420c7a MOVAPD	0x79e6d(%RIP),%XMM15    [25]

0x420c83 TEST	$0x1,%DIL

0x420c87 JNE	420cbd

0x420c89 MOVAPD	%XMM10,%XMM8

0x420c8e ANDPD	%XMM15,%XMM8

0x420c93 TEST	$0x2,%DIL

0x420c97 JE	4205e0

0x420c9d JMP	420cd6

0x420ca0 MOVSD	(%RDX),%XMM7    [16]

0x420ca4 TEST	$0x2,%DIL

0x420ca8 JE	420c7a

0x420caa MOVHPD	(%RAX),%XMM7    [2]

0x420cae MOVAPD	0x79e39(%RIP),%XMM15    [25]

0x420cb7 TEST	$0x1,%DIL

0x420cbb JE	420c89

0x420cbd MOVSD	(%RSI),%XMM9    [11]

0x420cc2 MOVAPD	%XMM10,%XMM8

0x420cc7 ANDPD	%XMM15,%XMM8

0x420ccc TEST	$0x2,%DIL

0x420cd0 JE	4205e0

0x420cd6 MOVHPD	(%RBX),%XMM9    [26]

0x420cdb JMP	4205e0

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp: 66 - 110

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

66:     for (int j = (y_min + 1); j < (y_max + 2); j++) {

67:       for (int i = (x_min + 1); i < (x_max + 2 + 2); i++)

68:         ({

69:           int upwind, donor, downwind, dif;

70:           double sigmat, sigma3, sigma4, sigmav, sigmam, diffuw, diffdw, limiter, wind;

71:           if (vol_flux_x(i, j) > 0.0) {

72:             upwind = i - 2;

73:             donor = i - 1;

74:             downwind = i;

75:             dif = donor;

76:           } else {

77:             upwind = std::min(i + 1, x_max + 2);

78:             donor = i;

79:             downwind = i - 1;

80:             dif = upwind;

81:           }

82:           sigmat = std::fabs(vol_flux_x(i, j)) / pre_vol(donor, j);

83:           sigma3 = (1.0 + sigmat) * (vertexdx[i] / vertexdx[dif]);

84:           sigma4 = 2.0 - sigmat;

85:           sigmav = sigmat;

86:           diffuw = density1(donor, j) - density1(upwind, j);

87:           diffdw = density1(downwind, j) - density1(donor, j);

88:           wind = 1.0;

89:           if (diffdw <= 0.0) wind = -1.0;

90:           if (diffuw * diffdw > 0.0) {

91:             limiter = (1.0 - sigmav) * wind *

92:                       std::fmin(std::fmin(std::fabs(diffuw), std::fabs(diffdw)),

93:                                 one_by_six * (sigma3 * std::fabs(diffuw) + sigma4 * std::fabs(diffdw)));

94:           } else {

95:             limiter = 0.0;

96:           }

97:           mass_flux_x(i, j) = vol_flux_x(i, j) * (density1(donor, j) + limiter);

98:           sigmam = std::fabs(mass_flux_x(i, j)) / (density1(donor, j) * pre_vol(donor, j));

99:           diffuw = energy1(donor, j) - energy1(upwind, j);

100:           diffdw = energy1(downwind, j) - energy1(donor, j);

101:           wind = 1.0;

102:           if (diffdw <= 0.0) wind = -1.0;

103:           if (diffuw * diffdw > 0.0) {

104:             limiter = (1.0 - sigmam) * wind *

105:                       std::fmin(std::fmin(std::fabs(diffuw), std::fabs(diffdw)),

106:                                 one_by_six * (sigma3 * std::fabs(diffuw) + sigma4 * std::fabs(diffdw)));

107:           } else {

108:             limiter = 0.0;

109:           }

110:           ener_flux(i, j) = mass_flux_x(i, j) * (energy1(donor, j) + limiter);

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 46 - 69

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

46:   T &operator[](size_t i) const { return data[i]; }

[...]

69:   T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; }

Coverage (%)	Name	Source Location	Module
►100.00+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

Path /

Metric	Value
CQA speedup if no scalar integer	1.02
CQA speedup if FP arith vectorized	1.29
CQA speedup if fully vectorized	3.85
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.36
Bottlenecks	P0, P1, P5,
Function	advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [clone .extracted.27]
Source	advec_cell.cpp:66-110,context.h:46-46,context.h:69-69
Source loop unroll info	unrolled by 2
Source loop unroll confidence level	high
Unroll/vectorization loop type	main
Unroll factor	2
CQA cycles	84.67
CQA cycles if no scalar integer	82.83
CQA cycles if FP arith vectorized	65.42
CQA cycles if fully vectorized	22.00
Front-end cycles	62.33
P0 cycles	84.67
P1 cycles	84.67
P2 cycles	18.33
P3 cycles	18.33
P4 cycles	4.00
P5 cycles	84.67
P6 cycles	8.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	4.00
P10 cycles	8.00
P11 cycles	18.33
DIV/SQRT cycles	32.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	365.00
Nb uops	374.00
Nb loads	55.00
Nb stores	8.00
Nb stack references	21.00
FLOP/cycle	0.73
Nb FLOP add-sub	28.00
Nb FLOP mul	28.00
Nb FLOP fma	0.00
Nb FLOP div	6.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	8.69
Bytes prefetched	0.00
Bytes loaded	640.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	80.64
Vectorization ratio load	45.45
Vectorization ratio store	50.00
Vectorization ratio mul	100.00
Vectorization ratio add_sub	98.21
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	60.00
Vectorization ratio other	84.16
Vector-efficiency ratio all	21.71
Vector-efficiency ratio load	17.95
Vector-efficiency ratio store	18.75
Vector-efficiency ratio mul	17.80
Vector-efficiency ratio add_sub	24.78
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	20.00
Vector-efficiency ratio other	22.71

Metric	Value
CQA speedup if no scalar integer	1.02
CQA speedup if FP arith vectorized	1.29
CQA speedup if fully vectorized	3.85
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.36
Bottlenecks	P0, P1, P5,
Function	advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [clone .extracted.27]
Source	advec_cell.cpp:66-110,context.h:46-46,context.h:69-69
Source loop unroll info	unrolled by 2
Source loop unroll confidence level	high
Unroll/vectorization loop type	main
Unroll factor	2
CQA cycles	84.67
CQA cycles if no scalar integer	82.83
CQA cycles if FP arith vectorized	65.42
CQA cycles if fully vectorized	22.00
Front-end cycles	62.33
P0 cycles	84.67
P1 cycles	84.67
P2 cycles	18.33
P3 cycles	18.33
P4 cycles	4.00
P5 cycles	84.67
P6 cycles	8.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	4.00
P10 cycles	8.00
P11 cycles	18.33
DIV/SQRT cycles	32.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	365.00
Nb uops	374.00
Nb loads	55.00
Nb stores	8.00
Nb stack references	21.00
FLOP/cycle	0.73
Nb FLOP add-sub	28.00
Nb FLOP mul	28.00
Nb FLOP fma	0.00
Nb FLOP div	6.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	8.69
Bytes prefetched	0.00
Bytes loaded	640.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	80.64
Vectorization ratio load	45.45
Vectorization ratio store	50.00
Vectorization ratio mul	100.00
Vectorization ratio add_sub	98.21
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	60.00
Vectorization ratio other	84.16
Vector-efficiency ratio all	21.71
Vector-efficiency ratio load	17.95
Vector-efficiency ratio store	18.75
Vector-efficiency ratio mul	17.80
Vector-efficiency ratio add_sub	24.78
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	20.00
Vector-efficiency ratio other	22.71

Path /

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

Function	advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [clone .extracted.27]
Source file and lines	advec_cell.cpp:66-110
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:66-110
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

It is main loop of related source loop which is unrolled by 2 (including vectorization).
Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=16
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 16 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

Vectorization

Your loop is partially vectorized. Only 21% 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 84.67 to 22.00 cycles (3.85x speedup).

Details

80% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

45% of SSE/AVX loads are used in vector version.
50% of SSE/AVX stores are used in vector version.
98% of SSE/AVX addition or subtraction instructions are used in vector version.
60% of SSE/AVX divide and square root instructions are used in vector version.
84% 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

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.

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 84.67 to 62.33 cycles (1.36x speedup).

Workaround

Reduce the number of FP multiply/FMA instructions

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
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.

CMPPD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:89
DIV: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:66
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:66

Vector unaligned load/store instructions

Detected 14 suboptimal vector unaligned load/store instructions.

Details

MOVHPD: 14 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:110
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:71
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:82
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:83
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:83
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:86
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:86
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:87
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:97
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:99
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:99
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:100
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:98
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:98

Workaround

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

Type of elements and instruction set

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

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

The binary loop is composed of 62 FP arithmetical operations:

28: addition or subtraction
28: multiply
6: divide

The binary loop is loading 640 bytes (80 double precision FP elements). The binary loop is storing 96 bytes (12 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.08 FP operations per loaded or stored byte.

General properties

nb instructions	365
nb uops	374
loop length	1791
used x86 registers	11
used mmx registers	0
used xmm registers	16
used ymm registers	0
used zmm registers	0
nb stack references	21
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	62.33 cycles
front end	62.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	84.67	84.67	18.33	18.33	4.00	84.67	8.00	4.00	4.00	4.00	8.00	18.33
cycles	84.67	84.67	18.33	18.33	4.00	84.67	8.00	4.00	4.00	4.00	8.00	18.33

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

32.00

Cycles summary

Front-end	62.33
Dispatch	84.67
DIV/SQRT	32.00
Overall L1	84.67

Vectorization ratios

INT

all	81%
load	73%
store	100%
mul	100%
add-sub	97%
fma	NA (no fma vectorizable/vectorized instructions)
other	74%

all	79%
load	25%
store	20%
mul	100%
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	100%
other	100%

INT+FP

all	80%
load	45%
store	50%
mul	100%
add-sub	98%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	60%
other	84%

Vector efficiency ratios

INT

all	21%
load	21%
store	25%
mul	12%
add-sub	24%
fma	NA (no fma vectorizable/vectorized instructions)
other	21%

all	22%
load	15%
store	15%
mul	25%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	25%
other	25%

INT+FP

all	21%
load	17%
store	18%
mul	17%
add-sub	24%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	20%
other	22%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 84.67 cycles. At this rate:

3% of peak load performance is reached (7.56 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (1.13 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: 42071a

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
MULPD %XMM9,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
DIVPD %XMM7,%XMM8	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	vect (25.0%)
MOVAPD %XMM12,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
XORPD %XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x6,%XMM3,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD 0x7afdf(%RIP),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVAPD %XMM9,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
SUBPD %XMM8,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM9,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
ANDPD %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM8,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM3,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDPD %XMM15,%XMM6	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDPD %XMM15,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM12,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM6,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM6,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
CMPPD $0x3,%XMM6,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM12,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM4,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM3,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM8,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MULPD %XMM5,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MULPD %XMM13,%XMM6	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ADDPD %XMM12,%XMM6	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVAPD 0x7af9d(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MULPD %XMM5,%XMM6	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM6,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM4,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
CMPPD $0x3,%XMM4,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM4,%XMM6	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM0,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM6,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MULPD %XMM7,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM4,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ADDPD %XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD %XMM10,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVDQA -0x120(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSRLQ $0x20,%XMM11	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM3,%XMM11	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM0,%XMM11	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ -0xb0(%RBP),%XMM1	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM11	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM11,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM1,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM0,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RDX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVLPD %XMM2,(%RAX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
MOVHPD %XMM2,(%RDX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
MOVDQA -0x1d0(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
PADDQ 0x7ad43(%RIP),%XMM3	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
ADD $0x2,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMP %R8,%R9	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 420cf2 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9b2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVQ %XMM3,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
DIVQ -0xc8(%RBP)	5	0	3	0.33	0.33	0	0	0	0	0	0	0	0.33	11-16	10	scal (12.5%)
MOVQ %RAX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM1,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
DIVQ -0xc0(%RBP)	5	0	3	0.33	0.33	0	0	0	0	0	0	0	0.33	11-16	10	scal (12.5%)
MOVQ %RAX,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PUNPCKLQDQ %XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVDQA %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ -0x1a0(%RBP),%XMM2	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PMULUDQ -0x1b0(%RBP),%XMM0	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	5	0.50	vect (12.5%)
MOVDQA %XMM3,-0x1d0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSUBQ %XMM0,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (25.0%)
PSHUFD $-0x18,%XMM1,%XMM14	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDD -0x190(%RBP),%XMM14	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PXOR %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM14,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
MOVDQA %XMM14,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PUNPCKLDQ %XMM0,%XMM6	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
PSHUFD $-0x18,%XMM2,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PSLLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PSRAD $0x1f,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PSHUFD $-0x13,%XMM2,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PUNPCKLDQ %XMM0,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
MOVDQA -0x180(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA -0x110(%RBP),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSRLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM1,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM6,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM3,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ -0x100(%RBP),%XMM0	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
MOVQ %XMM0,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RDX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RAX),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RDX),%XMM0	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
XORPD %XMM12,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x1,%XMM0,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVAPD %XMM0,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVDQA %XMM14,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PCMPEQD %XMM3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PADDD %XMM3,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM14,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSUBD %XMM3,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (25.0%)
MOVDQA %XMM1,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVDQA -0x170(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
PCMPGTD %XMM3,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PAND %XMM5,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PANDN %XMM1,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM3,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PXOR %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM0,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PUNPCKLDQ %XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
PXOR %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM5,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PUNPCKLDQ %XMM1,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
PADDD 0x7ad62(%RIP),%XMM14	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PXOR %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM14,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PUNPCKLDQ %XMM1,%XMM14	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
MOVAPD %XMM12,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDNPD %XMM5,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PAND %XMM12,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM3,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM12,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PANDN %XMM0,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PAND %XMM12,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM0,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM6,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PAND %XMM12,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM1,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM4,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVDQA %XMM4,-0x1c0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PANDN %XMM6,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM0,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM7,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM15,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA -0x160(%RBP),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM7,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM7,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PMULUDQ %XMM2,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM5,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM0,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM12,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x58(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM7,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM0,%RDX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDX),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RAX),%XMM0	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
DIVPD %XMM0,%XMM1	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	vect (25.0%)
MOVAPD %XMM1,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ADDPD %XMM9,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVDQA %XMM6,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSLLQ $0x3,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x88(%RBP),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM7,%XMM7	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM7,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM0,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RSI),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RDI),%XMM13	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
PSLLQ $0x3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM3,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM3,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RSI),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RDI),%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MULPD %XMM5,%XMM13	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
DIVPD %XMM3,%XMM13	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	vect (25.0%)
MOVDQA -0x150(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM3,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PMULUDQ %XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM5,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ %XMM12,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ %R12,%XMM7	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM7,%XMM7	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM7,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM5,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM5,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM5,%RBX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVAPD %XMM15,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVSD (%RSI),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RBX),%XMM15	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVDQA %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ %XMM14,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM7,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM5,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM5,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM5,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM5	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVAPD %XMM15,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ %XMM10,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM3,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM3,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM10	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
SUBPD %XMM5,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM15,%XMM10	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVAPD %XMM10,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MULPD %XMM8,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM9,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
XORPD %XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x1,%XMM5,%XMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM4,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM10,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM4,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM8,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
CMPPD $0x3,%XMM8,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM3,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM7,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM5,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM4,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD 0x7ab3b(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
SUBPD %XMM1,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD %XMM5,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MULPD %XMM13,%XMM8	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ADDPD %XMM3,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD 0x7ab30(%RIP),%XMM8	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
MOVAPD %XMM8,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM7,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
CMPPD $0x3,%XMM7,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM7,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM3,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM8,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
CMPPD $0x6,0x79caa(%RIP),%XMM10	2	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
MOVAPD %XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
SUBPD %XMM1,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
ANDPD %XMM10,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM1,%XMM10	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM3,%XMM10	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MULPD %XMM7,%XMM10	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM9,%XMM10	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ADDPD %XMM15,%XMM10	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD -0xb0(%RBP),%XMM10	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
MOVDQA -0x140(%RBP),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM4,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM1,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSLLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM6,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PADDQ %XMM6,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM3,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x40(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM1,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM3,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVLPD %XMM10,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM1,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVHPD %XMM10,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
MOVDQA -0x130(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PMULUDQ %XMM3,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM1,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSLLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM1,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM2,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ %R15,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM1,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM3,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM12,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM12,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM1,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM1	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
PADDQ %XMM2,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM14	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM3,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM14,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM14,%XMM4	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM4,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM4	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
PADDQ -0x1c0(%RBP),%XMM2	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
MOVAPD %XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSLLQ $0x3,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM3,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM2,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM2,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM2,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM12	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
SUBPD %XMM4,%XMM6	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM1,%XMM12	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVAPD %XMM12,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MULPD %XMM6,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
PXOR %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x1,%XMM3,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVMSKPD %XMM2,%EDI	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 420ca0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x960>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 420caa <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x96a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVAPD 0x79e6d(%RIP),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 420cbd <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x97d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVAPD %XMM10,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM15,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 4205e0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x2a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 420cd6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x996>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOVSD (%RDX),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 420c7a <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x93a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVHPD (%RAX),%XMM7	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVAPD 0x79e39(%RIP),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 420c89 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x949>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSD (%RSI),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVAPD %XMM10,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM15,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 4205e0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x2a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVHPD (%RBX),%XMM9	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
JMP 4205e0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x2a0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A

Function	advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [clone .extracted.27]
Source file and lines	advec_cell.cpp:66-110
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:66-110
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

It is main loop of related source loop which is unrolled by 2 (including vectorization).
Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=16
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

Vectorization

Details

80% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

45% of SSE/AVX loads are used in vector version.
50% of SSE/AVX stores are used in vector version.
98% of SSE/AVX addition or subtraction instructions are used in vector version.
60% of SSE/AVX divide and square root instructions are used in vector version.
84% 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

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.

Execution units bottlenecks

Workaround

Reduce the number of FP multiply/FMA instructions

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
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.

CMPPD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:89
DIV: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:66
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:66

Vector unaligned load/store instructions

Detected 14 suboptimal vector unaligned load/store instructions.

Details

MOVHPD: 14 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:110
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:71
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:82
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:83
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:83
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:86
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:86
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:87
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:97
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:99
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:99
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:100
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:98
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:98

Workaround

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

Type of elements and instruction set

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

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

The binary loop is composed of 62 FP arithmetical operations:

28: addition or subtraction
28: multiply
6: divide

The binary loop is loading 640 bytes (80 double precision FP elements). The binary loop is storing 96 bytes (12 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.08 FP operations per loaded or stored byte.

General properties

nb instructions	365
nb uops	374
loop length	1791
used x86 registers	11
used mmx registers	0
used xmm registers	16
used ymm registers	0
used zmm registers	0
nb stack references	21
ADD-SUB / MUL ratio	1.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	62.33 cycles
front end	62.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	84.67	84.67	18.33	18.33	4.00	84.67	8.00	4.00	4.00	4.00	8.00	18.33
cycles	84.67	84.67	18.33	18.33	4.00	84.67	8.00	4.00	4.00	4.00	8.00	18.33

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

32.00

Cycles summary

Front-end	62.33
Dispatch	84.67
DIV/SQRT	32.00
Overall L1	84.67

Vectorization ratios

INT

all	81%
load	73%
store	100%
mul	100%
add-sub	97%
fma	NA (no fma vectorizable/vectorized instructions)
other	74%

all	79%
load	25%
store	20%
mul	100%
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	100%
other	100%

INT+FP

all	80%
load	45%
store	50%
mul	100%
add-sub	98%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	60%
other	84%

Vector efficiency ratios

INT

all	21%
load	21%
store	25%
mul	12%
add-sub	24%
fma	NA (no fma vectorizable/vectorized instructions)
other	21%

all	22%
load	15%
store	15%
mul	25%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	25%
other	25%

INT+FP

all	21%
load	17%
store	18%
mul	17%
add-sub	24%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	20%
other	22%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 84.67 cycles. At this rate:

3% of peak load performance is reached (7.56 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (1.13 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: 42071a

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
MULPD %XMM9,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
DIVPD %XMM7,%XMM8	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	vect (25.0%)
MOVAPD %XMM12,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
XORPD %XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x6,%XMM3,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD 0x7afdf(%RIP),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVAPD %XMM9,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
SUBPD %XMM8,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM9,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
ANDPD %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM8,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM3,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDPD %XMM15,%XMM6	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDPD %XMM15,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM12,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM6,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM6,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
CMPPD $0x3,%XMM6,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM12,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM4,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM3,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM8,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MULPD %XMM5,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MULPD %XMM13,%XMM6	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ADDPD %XMM12,%XMM6	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVAPD 0x7af9d(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MULPD %XMM5,%XMM6	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM6,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM4,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
CMPPD $0x3,%XMM4,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM4,%XMM6	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM0,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM6,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MULPD %XMM7,%XMM4	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM4,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ADDPD %XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD %XMM10,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVDQA -0x120(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSRLQ $0x20,%XMM11	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM3,%XMM11	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM0,%XMM11	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ -0xb0(%RBP),%XMM1	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM11	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM11,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x38(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM1,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM0,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RDX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVLPD %XMM2,(%RAX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
MOVHPD %XMM2,(%RDX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
MOVDQA -0x1d0(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
PADDQ 0x7ad43(%RIP),%XMM3	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
ADD $0x2,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMP %R8,%R9	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 420cf2 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x9b2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVQ %XMM3,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
DIVQ -0xc8(%RBP)	5	0	3	0.33	0.33	0	0	0	0	0	0	0	0.33	11-16	10	scal (12.5%)
MOVQ %RAX,%XMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM1,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
DIVQ -0xc0(%RBP)	5	0	3	0.33	0.33	0	0	0	0	0	0	0	0.33	11-16	10	scal (12.5%)
MOVQ %RAX,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PUNPCKLQDQ %XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVDQA %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ -0x1a0(%RBP),%XMM2	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PMULUDQ -0x1b0(%RBP),%XMM0	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	5	0.50	vect (12.5%)
MOVDQA %XMM3,-0x1d0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSUBQ %XMM0,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (25.0%)
PSHUFD $-0x18,%XMM1,%XMM14	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDD -0x190(%RBP),%XMM14	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PXOR %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM14,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
MOVDQA %XMM14,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PUNPCKLDQ %XMM0,%XMM6	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
PSHUFD $-0x18,%XMM2,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PSLLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PSRAD $0x1f,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PSHUFD $-0x13,%XMM2,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PUNPCKLDQ %XMM0,%XMM11	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
MOVDQA -0x180(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA -0x110(%RBP),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSRLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM1,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM6,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM3,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ -0x100(%RBP),%XMM0	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
MOVQ %XMM0,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RDX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RAX),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RDX),%XMM0	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
XORPD %XMM12,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x1,%XMM0,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVAPD %XMM0,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVDQA %XMM14,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PCMPEQD %XMM3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PADDD %XMM3,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM14,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSUBD %XMM3,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	0-1	0.33	vect (25.0%)
MOVDQA %XMM1,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVDQA -0x170(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
PCMPGTD %XMM3,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PAND %XMM5,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PANDN %XMM1,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM3,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PXOR %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM0,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PUNPCKLDQ %XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
PXOR %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM5,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PUNPCKLDQ %XMM1,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
PADDD 0x7ad62(%RIP),%XMM14	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
PXOR %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
PCMPGTD %XMM14,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0-1	0.50	vect (25.0%)
PUNPCKLDQ %XMM1,%XMM14	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (12.5%)
MOVAPD %XMM12,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDNPD %XMM5,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PAND %XMM12,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM3,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM12,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PANDN %XMM0,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PAND %XMM12,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM0,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM6,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PAND %XMM12,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM1,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM4,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVDQA %XMM4,-0x1c0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PANDN %XMM6,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
POR %XMM0,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM7,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM15,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA -0x160(%RBP),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM7,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM7,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PMULUDQ %XMM2,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM5,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM0,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM12,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x58(%RBP),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM7,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM0,%RDX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RAX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDX),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RAX),%XMM0	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
DIVPD %XMM0,%XMM1	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	vect (25.0%)
MOVAPD %XMM1,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ADDPD %XMM9,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVDQA %XMM6,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSLLQ $0x3,%XMM0	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x88(%RBP),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM7,%XMM7	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM7,%XMM0	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM0,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM0,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RSI),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RDI),%XMM13	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
PSLLQ $0x3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM3,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM3,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RSI),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RDI),%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MULPD %XMM5,%XMM13	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
DIVPD %XMM3,%XMM13	1	1	0	0	0	0	0	0	0	0	0	0	0	13-15	4	vect (25.0%)
MOVDQA -0x150(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM3,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PMULUDQ %XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM5,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ %XMM12,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ %R12,%XMM7	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM7,%XMM7	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM7,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM5,%RSI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM5,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM5,%RBX	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVAPD %XMM15,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MOVSD (%RSI),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%RBX),%XMM15	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVDQA %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ %XMM14,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM7,%XMM5	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM5,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM5,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM5,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM5	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVAPD %XMM15,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PADDQ %XMM10,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM7,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM3,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM3,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM10	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
SUBPD %XMM5,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM15,%XMM10	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVAPD %XMM10,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MULPD %XMM8,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM9,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
XORPD %XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x1,%XMM5,%XMM9	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM4,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM10,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM4,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD %XMM3,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM8,%XMM5	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
CMPPD $0x3,%XMM8,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVAPD %XMM3,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM7,%XMM4	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM5,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM4,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVAPD 0x7ab3b(%RIP),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
SUBPD %XMM1,%XMM5	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD %XMM5,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MULPD %XMM13,%XMM8	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ADDPD %XMM3,%XMM8	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD 0x7ab30(%RIP),%XMM8	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
MOVAPD %XMM8,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MINPD %XMM7,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
CMPPD $0x3,%XMM7,%XMM7	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM7,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM3,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM8,%XMM7	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
CMPPD $0x6,0x79caa(%RIP),%XMM10	2	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
MOVAPD %XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
SUBPD %XMM1,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
ANDPD %XMM10,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ANDNPD %XMM1,%XMM10	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ORPD %XMM3,%XMM10	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MULPD %XMM7,%XMM10	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
ANDPD %XMM9,%XMM10	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
ADDPD %XMM15,%XMM10	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MULPD -0xb0(%RBP),%XMM10	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	vect (25.0%)
MOVDQA -0x140(%RBP),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
MOVDQA %XMM4,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM2,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM1,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM4,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSLLQ $0x20,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVDQA %XMM6,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
PADDQ %XMM6,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM3,%XMM1	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ -0x40(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
PSHUFD $0x44,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM1,%XMM3	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM3,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVLPD %XMM10,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
PSHUFD $-0x12,%XMM3,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM1,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVHPD %XMM10,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	4-12	0.50	scal (12.5%)
MOVDQA -0x130(%RBP),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSRLQ $0x20,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PMULUDQ %XMM3,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PADDQ %XMM1,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVDQA %XMM3,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PMULUDQ %XMM11,%XMM1	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	5	0.50	vect (12.5%)
PSLLQ $0x20,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM1,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PADDQ %XMM2,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM12	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
MOVQ %R15,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $0x44,%XMM1,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
PADDQ %XMM3,%XMM12	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM12,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM12,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM1,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM1	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
PADDQ %XMM2,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
PSLLQ $0x3,%XMM14	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM3,%XMM14	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM14,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM14,%XMM4	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM4,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM4	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
PADDQ -0x1c0(%RBP),%XMM2	1	0.33	0.33	0.33	0.33	0	0.33	0	0	0	0	0	0.33	1	0.33	vect (25.0%)
MOVAPD %XMM1,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
PSLLQ $0x3,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1-2	0.50	vect (25.0%)
PADDQ %XMM3,%XMM2	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
MOVQ %XMM2,%RDI	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
PSHUFD $-0x12,%XMM2,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
MOVQ %XMM2,%R14	1	1	0	0	0	0	0	0	0	0	0	0	0	1	1	scal (12.5%)
MOVSD (%RDI),%XMM12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVHPD (%R14),%XMM12	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
SUBPD %XMM4,%XMM6	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
SUBPD %XMM1,%XMM12	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	2-3	0.50	vect (25.0%)
MOVAPD %XMM12,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
MULPD %XMM6,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
PXOR %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMPPD $0x1,%XMM3,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	vect (25.0%)
MOVMSKPD %XMM2,%EDI	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 420ca0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x960>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 420caa <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x96a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVAPD 0x79e6d(%RIP),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JNE 420cbd <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x97d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVAPD %XMM10,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM15,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 4205e0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x2a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 420cd6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x996>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOVSD (%RDX),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 420c7a <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x93a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVHPD (%RAX),%XMM7	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVAPD 0x79e39(%RIP),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (25.0%)
TEST $0x1,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 420c89 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x949>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSD (%RSI),%XMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVAPD %XMM10,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0-1	0.17	vect (25.0%)
ANDPD %XMM15,%XMM8	1	0.33	0.33	0	0	0	0.33	0	0	0	0	0	0	1	0.33	vect (25.0%)
TEST $0x2,%DIL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 4205e0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x2a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVHPD (%RBX),%XMM9	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
JMP 4205e0 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.extracted.27+0x2a0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

FMA

Workaround

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

FMA

Workaround

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code