OV - exec - Function clover_unpack_message_bottom(global_variables&, int, int, int, int, clover::Buffer2D<double>&, clover::Buffer1D<double>&, int, int, int, int, int, int, int) [clone ._omp

	Function: clover_unpack_message_bottom(global_variables&, int, int, int, int, clover::Buffer2D<doubl ...	Module: exec	Source: pack_kernel.cpp:297-300 [...]	Coverage (incl. loops): 0.01% \| (excl. loops): 0.01%

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp: 297 - 300

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

297: #pragma omp parallel for simd

298:     for (int j = (x_min - depth + 1); j < (x_max + x_inc + depth + 2); j++) {

299:       int index = buffer_offset + k + j * depth;

300:       field(j, y_min - k) = bottom_rcv[index];

/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]; }

0x446690 PUSH	%RBP

0x446691 MOV	%RSP,%RBP

0x446694 PUSH	%R15

0x446696 PUSH	%R14

0x446698 PUSH	%R13

0x44669a MOV	%RDI,%R13

0x44669d PUSH	%R12

0x44669f PUSH	%RBX

0x4466a0 AND	$-0x40,%RSP

0x4466a4 ADD	$-0x80,%RSP

0x4466a8 MOV	0x1c(%RDI),%EBX

0x4466ab MOVSXD	0x10(%RDI),%R12

0x4466af CALL	404630 <omp_get_num_threads@plt>

0x4466b4 MOV	%EAX,%R14D

0x4466b7 CALL	404520 <omp_get_thread_num@plt>

0x4466bc MOV	%EAX,%ECX

0x4466be MOV	0x14(%R13),%EAX

0x4466c2 MOV	%R12D,%R15D

0x4466c5 SUB	%EBX,%R15D

0x4466c8 ADD	0x24(%R13),%EAX

0x4466cc INC	%R15D

0x4466cf LEA	0x2(%RBX,%RAX,1),%EAX

0x4466d3 SUB	%R15D,%EAX

0x4466d6 CLTD

0x4466d7 IDIV	%R14D

0x4466da CMP	%EDX,%ECX

0x4466dc JL	446ea0

0x4466e2 IMUL	%EAX,%ECX

0x4466e5 LEA	(%RDX,%RCX,1),%ESI

0x4466e8 LEA	(%RAX,%RSI,1),%EDI

0x4466eb CMP	%EDI,%ESI

0x4466ed JGE	446992

0x4466f3 MOV	0x20(%R13),%R11D

0x4466f7 MOVSXD	0x28(%R13),%R8

0x4466fb MOV	(%R13),%R10

0x4466ff MOV	0x8(%R13),%R9

0x446703 MOV	0x18(%R13),%R13D

0x446707 ADD	%R15D,%EDI

0x44670a SUB	%R8D,%R13D

0x44670d MOV	%EDI,0x78(%RSP)

0x446711 MOVSXD	%R13D,%R13

0x446714 LEA	(%R8,%R11,1),%EDI

0x446718 MOV	%R11D,0x7c(%RSP)

0x44671d ADD	%R15D,%ESI

0x446720 IMUL	(%R10),%R13

0x446724 MOV	%EDI,0x74(%RSP)

0x446728 MOV	0x8(%R9),%R14

0x44672c MOV	0x10(%R10),%R15

0x446730 LEA	-0x1(%RAX),%R11D

0x446734 CMP	$0x1,%EBX

0x446737 JNE	4469a8

0x44673d CMP	$0x6,%R11D

0x446741 JBE	446f16

0x446747 MOVSXD	0x7c(%RSP),%R10

0x44674c MOVSXD	%EDX,%RDI

0x44674f MOVSXD	%R12D,%RBX

0x446752 LEA	-0x1(%RBX,%RDI,1),%RBX

0x446757 MOVSXD	%ECX,%R9

0x44675a MOVSXD	%R8D,%R11

0x44675d ADD	%R9,%RBX

0x446760 LEA	0x1(%R11,%R10,1),%RDI

0x446765 ADD	%RBX,%RDI

0x446768 LEA	0x1(%R13,%RBX,1),%RBX

0x44676d LEA	(%R15,%RBX,8),%R10

0x446771 MOV	%EAX,%EBX

0x446773 SHR	$0x3,%EBX

0x446776 SAL	$0x6,%RBX

0x44677a LEA	-0x40(%RBX),%R9

0x44677e SHR	$0x6,%R9

0x446782 INC	%R9

0x446785 LEA	(%R14,%RDI,8),%R11

0x446789 XOR	%EDI,%EDI

0x44678b AND	$0x7,%R9D

0x44678f JE	446832

0x446795 CMP	$0x1,%R9

0x446799 JE	446817

0x44679b CMP	$0x2,%R9

0x44679f JE	446805

0x4467a1 CMP	$0x3,%R9

0x4467a5 JE	4467f3

0x4467a7 CMP	$0x4,%R9

0x4467ab JE	4467e1

0x4467ad CMP	$0x5,%R9

0x4467b1 JE	4467cf

0x4467b3 CMP	$0x6,%R9

0x4467b7 JNE	446f00

0x4467bd VMOVUPD	(%R11,%RDI,1),%ZMM6

0x4467c4 VMOVUPD	%ZMM6,(%R10,%RDI,1)

0x4467cb ADD	$0x40,%RDI

0x4467cf VMOVUPD	(%R11,%RDI,1),%ZMM7

0x4467d6 VMOVUPD	%ZMM7,(%R10,%RDI,1)

0x4467dd ADD	$0x40,%RDI

0x4467e1 VMOVUPD	(%R11,%RDI,1),%ZMM8

0x4467e8 VMOVUPD	%ZMM8,(%R10,%RDI,1)

0x4467ef ADD	$0x40,%RDI

0x4467f3 VMOVUPD	(%R11,%RDI,1),%ZMM9

0x4467fa VMOVUPD	%ZMM9,(%R10,%RDI,1)

0x446801 ADD	$0x40,%RDI

0x446805 VMOVUPD	(%R11,%RDI,1),%ZMM10

0x44680c VMOVUPD	%ZMM10,(%R10,%RDI,1)

0x446813 ADD	$0x40,%RDI

0x446817 VMOVUPD	(%R11,%RDI,1),%ZMM11

0x44681e VMOVUPD	%ZMM11,(%R10,%RDI,1)

0x446825 ADD	$0x40,%RDI

0x446829 CMP	%RDI,%RBX

0x44682c JE	4468c0

(331) 0x446832 VMOVUPD	(%R11,%RDI,1),%ZMM12

(331) 0x446839 VMOVUPD	%ZMM12,(%R10,%RDI,1)

(331) 0x446840 VMOVUPD	0x40(%R11,%RDI,1),%ZMM13

(331) 0x446848 VMOVUPD	%ZMM13,0x40(%R10,%RDI,1)

(331) 0x446850 VMOVUPD	0x80(%R11,%RDI,1),%ZMM14

(331) 0x446858 VMOVUPD	%ZMM14,0x80(%R10,%RDI,1)

(331) 0x446860 VMOVUPD	0xc0(%R11,%RDI,1),%ZMM15

(331) 0x446868 VMOVUPD	%ZMM15,0xc0(%R10,%RDI,1)

(331) 0x446870 VMOVUPD	0x100(%R11,%RDI,1),%ZMM3

(331) 0x446878 VMOVUPD	%ZMM3,0x100(%R10,%RDI,1)

(331) 0x446880 VMOVUPD	0x140(%R11,%RDI,1),%ZMM0

(331) 0x446888 VMOVUPD	%ZMM0,0x140(%R10,%RDI,1)

(331) 0x446890 VMOVUPD	0x180(%R11,%RDI,1),%ZMM2

(331) 0x446898 VMOVUPD	%ZMM2,0x180(%R10,%RDI,1)

(331) 0x4468a0 VMOVUPD	0x1c0(%R11,%RDI,1),%ZMM4

(331) 0x4468a8 VMOVUPD	%ZMM4,0x1c0(%R10,%RDI,1)

(331) 0x4468b0 ADD	$0x200,%RDI

(331) 0x4468b7 CMP	%RDI,%RBX

(331) 0x4468ba JNE	446832

0x4468c0 MOV	%EAX,%R11D

0x4468c3 AND	$-0x8,%R11D

0x4468c7 ADD	%R11D,%ESI

0x4468ca TEST	$0x7,%AL

0x4468cc JE	446e8c

0x4468d2 SUB	%R11D,%EAX

0x4468d5 LEA	-0x1(%RAX),%R10D

0x4468d9 CMP	$0x2,%R10D

0x4468dd JBE	446924

0x4468df MOVSXD	%EDX,%RDX

0x4468e2 LEA	-0x1(%R12,%RDX,1),%R12

0x4468e7 MOVSXD	%ECX,%RCX

0x4468ea ADD	%RCX,%R12

0x4468ed LEA	(%R12,%R11,1),%R9

0x4468f1 MOVSXD	0x7c(%RSP),%RBX

0x4468f6 ADD	%R8,%R9

0x4468f9 LEA	0x1(%RBX,%R9,1),%R8

0x4468fe ADD	%R13,%R12

0x446901 LEA	0x1(%R11,%R12,1),%RDI

0x446906 VMOVUPD	(%R14,%R8,8),%YMM1

0x44690c MOV	%EAX,%R11D

0x44690f AND	$-0x4,%R11D

0x446913 VMOVUPD	%YMM1,(%R15,%RDI,8)

0x446919 ADD	%R11D,%ESI

0x44691c TEST	$0x3,%AL

0x44691e JE	446e8c

0x446924 MOV	0x74(%RSP),%R10D

0x446929 MOVSXD	%ESI,%RDX

0x44692c LEA	(%R10,%RSI,1),%EAX

0x446930 CLTQ

0x446932 VMOVSD	(%R14,%RAX,8),%XMM5

0x446938 MOV	0x78(%RSP),%R12D

0x44693d ADD	%R13,%RDX

0x446940 LEA	0x1(%RSI),%EAX

0x446943 VMOVSD	%XMM5,(%R15,%RDX,8)

0x446949 CMP	%EAX,%R12D

0x44694c JLE	446e8c

0x446952 LEA	(%RAX,%R10,1),%ECX

0x446956 MOVSXD	%ECX,%RBX

0x446959 VMOVSD	(%R14,%RBX,8),%XMM6

0x44695f CLTQ

0x446961 ADD	%R13,%RAX

0x446964 ADD	$0x2,%ESI

0x446967 VMOVSD	%XMM6,(%R15,%RAX,8)

0x44696d CMP	%ESI,%R12D

0x446970 JLE	446e8c

0x446976 MOV	%R10D,%EAX

0x446979 ADD	%ESI,%EAX

0x44697b CLTQ

0x44697d VMOVSD	(%R14,%RAX,8),%XMM7

0x446983 MOVSXD	%ESI,%RSI

0x446986 ADD	%R13,%RSI

0x446989 VMOVSD	%XMM7,(%R15,%RSI,8)

0x44698f VZEROUPPER

0x446992 LEA	-0x28(%RBP),%RSP

0x446996 POP	%RBX

0x446997 POP	%R12

0x446999 POP	%R13

0x44699b POP	%R14

0x44699d POP	%R15

0x44699f POP	%RBP

0x4469a0 RET

0x4469a1 NOPL	(%RAX)

0x4469a8 CMP	$0x6,%R11D

0x4469ac JBE	446f1e

0x4469b2 MOVSXD	%EBX,%R9

0x4469b5 MOV	%R9,%R10

0x4469b8 SAL	$0x6,%R10

0x4469bc MOV	%R10,0x50(%RSP)

0x4469c1 MOV	%R13,%R10

0x4469c4 MOVSXD	%R12D,%RDI

0x4469c7 SUB	%R9,%R10

0x4469ca MOV	%R9,0x68(%RSP)

0x4469cf LEA	(,%R9,8),%R11

0x4469d7 LEA	0x1(%R10,%RDI,1),%R9

0x4469dc MOVSXD	%EDX,%RDI

0x4469df ADD	%R9,%RDI

0x4469e2 MOVSXD	%ECX,%R10

0x4469e5 ADD	%R10,%RDI

0x4469e8 LEA	(%R15,%RDI,8),%R9

0x4469ec MOV	%EBX,%EDI

0x4469ee IMUL	%ESI,%EDI

0x4469f1 MOV	%R9,0x60(%RSP)

0x4469f6 MOVSXD	0x7c(%RSP),%R9

0x4469fb MOVSXD	%R8D,%R10

0x4469fe ADD	%R9,%R10

0x446a01 MOVSXD	%EDI,%RDI

0x446a04 ADD	%R10,%RDI

0x446a07 LEA	(%R11,%RDI,8),%RDI

0x446a0b MOV	%EAX,%R10D

0x446a0e NEG	%R11

0x446a11 MOV	%R11,0x40(%RSP)

0x446a16 MOV	0x60(%RSP),%R9

0x446a1b MOV	0x68(%RSP),%R11

0x446a20 SHR	$0x3,%R10D

0x446a24 SAL	$0x6,%R10

0x446a28 ADD	%R10,%R9

0x446a2b MOV	%R10,0x20(%RSP)

0x446a30 MOV	%R11,%R10

0x446a33 SAL	$0x4,%R10

0x446a37 MOV	%R9,0x28(%RSP)

0x446a3c MOV	%R11,%R9

0x446a3f LEA	(%R11,%R11,2),%R11

0x446a43 MOV	%R10,0x48(%RSP)

0x446a48 LEA	(,%R11,8),%R10

0x446a50 SAL	$0x4,%R11

0x446a54 SAL	$0x5,%R9

0x446a58 MOV	%R11,0x30(%RSP)

0x446a5d MOV	0x20(%RSP),%R11

0x446a62 MOV	%R9,0x58(%RSP)

0x446a67 MOV	0x68(%RSP),%R9

0x446a6c SUB	$0x40,%R11

0x446a70 LEA	(%R9,%R9,4),%R9

0x446a74 SHR	$0x6,%R11

0x446a78 SAL	$0x3,%R9

0x446a7c INC	%R11

0x446a7f MOV	%R9,0x38(%RSP)

0x446a84 ADD	%R14,%RDI

0x446a87 AND	$0x3,%R11D

0x446a8b JE	446c21

0x446a91 CMP	$0x1,%R11

0x446a95 JE	446b96

0x446a9b CMP	$0x2,%R11

0x446a9f JE	446b19

0x446aa1 VMOVSD	(%RDI,%R9,1),%XMM0

0x446aa7 MOV	0x30(%RSP),%R11

0x446aac VMOVSD	(%RDI,%R10,1),%XMM1

0x446ab2 VMOVHPD	(%RDI,%R11,1),%XMM0,%XMM2

0x446ab8 MOV	0x68(%RSP),%R11

0x446abd MOV	0x58(%RSP),%R9

0x446ac2 VMOVSD	(%RDI,%R11,8),%XMM5

0x446ac8 MOV	0x40(%RSP),%R11

0x446acd VMOVHPD	(%RDI,%R9,1),%XMM1,%XMM3

0x446ad3 VMOVSD	(%RDI,%R11,1),%XMM7

0x446ad9 MOV	0x48(%RSP),%R9

0x446ade VMOVHPD	(%RDI),%XMM7,%XMM8

0x446ae2 VMOVHPD	(%RDI,%R9,1),%XMM5,%XMM6

0x446ae8 VINSERTF64X2	$0x1,%XMM2,%YMM3,%YMM4

0x446aef MOV	0x60(%RSP),%R9

0x446af4 VINSERTF64X2	$0x1,%XMM6,%YMM8,%YMM9

0x446afb VINSERTF64X4	$0x1,%YMM4,%ZMM9,%ZMM10

0x446b02 VMOVUPD	%ZMM10,(%R9)

0x446b08 ADD	$0x40,%R9

0x446b0c MOV	0x50(%RSP),%R11

0x446b11 MOV	%R9,0x60(%RSP)

0x446b16 ADD	%R11,%RDI

0x446b19 MOV	0x38(%RSP),%R9

0x446b1e MOV	0x30(%RSP),%R11

0x446b23 VMOVSD	(%RDI,%R9,1),%XMM11

0x446b29 VMOVSD	(%RDI,%R10,1),%XMM13

0x446b2f VMOVHPD	(%RDI,%R11,1),%XMM11,%XMM12

0x446b35 MOV	0x68(%RSP),%R11

0x446b3a MOV	0x58(%RSP),%R9

0x446b3f VMOVSD	(%RDI,%R11,8),%XMM0

0x446b45 MOV	0x40(%RSP),%R11

0x446b4a VMOVHPD	(%RDI,%R9,1),%XMM13,%XMM14

0x446b50 VMOVSD	(%RDI,%R11,1),%XMM1

0x446b56 MOV	0x48(%RSP),%R9

0x446b5b VMOVHPD	(%RDI),%XMM1,%XMM3

0x446b5f VMOVHPD	(%RDI,%R9,1),%XMM0,%XMM2

0x446b65 VINSERTF64X2	$0x1,%XMM12,%YMM14,%YMM15

0x446b6c MOV	0x60(%RSP),%R9

0x446b71 VINSERTF64X2	$0x1,%XMM2,%YMM3,%YMM4

0x446b78 VINSERTF64X4	$0x1,%YMM15,%ZMM4,%ZMM5

0x446b7f VMOVUPD	%ZMM5,(%R9)

0x446b85 ADD	$0x40,%R9

0x446b89 MOV	0x50(%RSP),%R11

0x446b8e MOV	%R9,0x60(%RSP)

0x446b93 ADD	%R11,%RDI

0x446b96 MOV	0x38(%RSP),%R9

0x446b9b MOV	0x30(%RSP),%R11

0x446ba0 VMOVSD	(%RDI,%R9,1),%XMM6

0x446ba6 VMOVSD	(%RDI,%R10,1),%XMM8

0x446bac VMOVHPD	(%RDI,%R11,1),%XMM6,%XMM7

0x446bb2 MOV	0x68(%RSP),%R11

0x446bb7 MOV	0x58(%RSP),%R9

0x446bbc VMOVSD	(%RDI,%R11,8),%XMM11

0x446bc2 MOV	0x40(%RSP),%R11

0x446bc7 VMOVHPD	(%RDI,%R9,1),%XMM8,%XMM9

0x446bcd VMOVSD	(%RDI,%R11,1),%XMM13

0x446bd3 MOV	0x48(%RSP),%R9

0x446bd8 VMOVHPD	(%RDI),%XMM13,%XMM14

0x446bdc VMOVHPD	(%RDI,%R9,1),%XMM11,%XMM12

0x446be2 MOV	0x50(%RSP),%R9

0x446be7 MOV	0x60(%RSP),%R11

0x446bec VINSERTF64X2	$0x1,%XMM7,%YMM9,%YMM10

0x446bf3 VINSERTF64X2	$0x1,%XMM12,%YMM14,%YMM15

0x446bfa VINSERTF64X4	$0x1,%YMM10,%ZMM15,%ZMM0

0x446c01 ADD	%R9,%RDI

0x446c04 MOV	0x28(%RSP),%R9

0x446c09 VMOVUPD	%ZMM0,(%R11)

0x446c0f ADD	$0x40,%R11

0x446c13 MOV	%R11,0x60(%RSP)

0x446c18 CMP	%R9,%R11

0x446c1b JE	446dc4

0x446c21 MOV	%EAX,0x20(%RSP)

0x446c25 MOV	0x60(%RSP),%RAX

0x446c2a MOV	%ESI,0x60(%RSP)

0x446c2e MOV	%EDX,0x70(%RSP)

0x446c32 MOV	%R8D,0x1c(%RSP)

0x446c37 MOV	%EBX,0x18(%RSP)

0x446c3b MOV	%R12D,0x14(%RSP)

0x446c40 MOV	%ECX,0x10(%RSP)

0x446c44 MOV	0x58(%RSP),%RDX

0x446c49 MOV	0x68(%RSP),%R9

0x446c4e MOV	0x50(%RSP),%RCX

0x446c53 MOV	0x48(%RSP),%R8

0x446c58 MOV	0x40(%RSP),%R11

0x446c5d MOV	0x38(%RSP),%RBX

0x446c62 MOV	0x30(%RSP),%R12

(330) 0x446c67 VMOVSD	(%RDI,%RBX,1),%XMM2

(330) 0x446c6c VMOVSD	(%RDI,%R10,1),%XMM1

(330) 0x446c72 VMOVSD	(%RDI,%R9,8),%XMM6

(330) 0x446c78 VMOVSD	(%RDI,%R11,1),%XMM8

(330) 0x446c7e VMOVHPD	(%RDI,%R12,1),%XMM2,%XMM3

(330) 0x446c84 VMOVHPD	(%RDI,%RDX,1),%XMM1,%XMM4

(330) 0x446c89 VMOVHPD	(%RDI,%R8,1),%XMM6,%XMM7

(330) 0x446c8f VMOVHPD	(%RDI),%XMM8,%XMM9

(330) 0x446c93 VINSERTF64X2	$0x1,%XMM3,%YMM4,%YMM5

(330) 0x446c9a VINSERTF64X2	$0x1,%XMM7,%YMM9,%YMM10

(330) 0x446ca1 VINSERTF64X4	$0x1,%YMM5,%ZMM10,%ZMM11

(330) 0x446ca8 VMOVUPD	%ZMM11,(%RAX)

(330) 0x446cae ADD	%RCX,%RDI

(330) 0x446cb1 VMOVSD	(%RDI,%RBX,1),%XMM12

(330) 0x446cb6 VMOVSD	(%RDI,%R10,1),%XMM14

(330) 0x446cbc VMOVSD	(%RDI,%R9,8),%XMM0

(330) 0x446cc2 VMOVSD	(%RDI,%R11,1),%XMM1

(330) 0x446cc8 VMOVHPD	(%RDI,%R12,1),%XMM12,%XMM13

(330) 0x446cce VMOVHPD	(%RDI,%RDX,1),%XMM14,%XMM15

(330) 0x446cd3 VMOVHPD	(%RDI,%R8,1),%XMM0,%XMM2

(330) 0x446cd9 VMOVHPD	(%RDI),%XMM1,%XMM4

(330) 0x446cdd VINSERTF64X2	$0x1,%XMM13,%YMM15,%YMM3

(330) 0x446ce4 VINSERTF64X2	$0x1,%XMM2,%YMM4,%YMM5

(330) 0x446ceb VINSERTF64X4	$0x1,%YMM3,%ZMM5,%ZMM6

(330) 0x446cf2 VMOVUPD	%ZMM6,0x40(%RAX)

(330) 0x446cf9 ADD	%RCX,%RDI

(330) 0x446cfc VMOVSD	(%RDI,%RBX,1),%XMM7

(330) 0x446d01 VMOVSD	(%RDI,%R10,1),%XMM9

(330) 0x446d07 VMOVSD	(%RDI,%R9,8),%XMM12

(330) 0x446d0d VMOVSD	(%RDI,%R11,1),%XMM14

(330) 0x446d13 VMOVHPD	(%RDI,%RDX,1),%XMM9,%XMM10

(330) 0x446d18 VMOVHPD	(%RDI,%R12,1),%XMM7,%XMM8

(330) 0x446d1e VMOVHPD	(%RDI,%R8,1),%XMM12,%XMM13

(330) 0x446d24 VMOVHPD	(%RDI),%XMM14,%XMM15

(330) 0x446d28 VINSERTF64X2	$0x1,%XMM8,%YMM10,%YMM11

(330) 0x446d2f VINSERTF64X2	$0x1,%XMM13,%YMM15,%YMM3

(330) 0x446d36 VINSERTF64X4	$0x1,%YMM11,%ZMM3,%ZMM0

(330) 0x446d3d ADD	%RCX,%RDI

(330) 0x446d40 VMOVUPD	%ZMM0,0x80(%RAX)

(330) 0x446d47 VMOVSD	(%RDI,%RBX,1),%XMM2

(330) 0x446d4c VMOVSD	(%RDI,%R10,1),%XMM1

(330) 0x446d52 VMOVSD	(%RDI,%R9,8),%XMM7

(330) 0x446d58 VMOVHPD	(%RDI,%R12,1),%XMM2,%XMM4

(330) 0x446d5e VMOVHPD	(%RDI,%RDX,1),%XMM1,%XMM5

(330) 0x446d63 VMOVHPD	(%RDI,%R8,1),%XMM7,%XMM8

(330) 0x446d69 VMOVSD	(%RDI,%R11,1),%XMM9

(330) 0x446d6f VINSERTF64X2	$0x1,%XMM4,%YMM5,%YMM6

(330) 0x446d76 VMOVHPD	(%RDI),%XMM9,%XMM10

(330) 0x446d7a VINSERTF64X2	$0x1,%XMM8,%YMM10,%YMM11

(330) 0x446d81 VINSERTF64X4	$0x1,%YMM6,%ZMM11,%ZMM12

(330) 0x446d88 MOV	0x28(%RSP),%RSI

(330) 0x446d8d VMOVUPD	%ZMM12,0xc0(%RAX)

(330) 0x446d94 ADD	$0x100,%RAX

(330) 0x446d9a ADD	%RCX,%RDI

(330) 0x446d9d CMP	%RSI,%RAX

(330) 0x446da0 JNE	446c67

0x446da6 MOV	0x20(%RSP),%EAX

0x446daa MOV	0x70(%RSP),%EDX

0x446dae MOVSXD	0x1c(%RSP),%R8

0x446db3 MOV	0x18(%RSP),%EBX

0x446db7 MOVSXD	0x14(%RSP),%R12

0x446dbc MOV	0x10(%RSP),%ECX

0x446dc0 MOV	0x60(%RSP),%ESI

0x446dc4 MOV	%EAX,%R9D

0x446dc7 AND	$-0x8,%R9D

0x446dcb LEA	(%R9,%RSI,1),%EDI

0x446dcf TEST	$0x7,%AL

0x446dd1 JE	446e8c

0x446dd7 SUB	%R9D,%EAX

0x446dda LEA	-0x1(%RAX),%R10D

0x446dde CMP	$0x2,%R10D

0x446de2 JBE	446e5b

0x446de4 IMUL	%EBX,%ESI

0x446de7 MOVSXD	0x7c(%RSP),%R11

0x446dec MOVSXD	%EBX,%R10

0x446def MOVSXD	%ESI,%RSI

0x446df2 ADD	%R11,%R8

0x446df5 ADD	%RSI,%R8

0x446df8 MOV	%R9,%RSI

0x446dfb IMUL	%R10,%RSI

0x446dff SUB	%R10,%R12

0x446e02 ADD	%R13,%R9

0x446e05 ADD	%RSI,%R8

0x446e08 LEA	(%R14,%R8,8),%R11

0x446e0c LEA	(,%R10,8),%RSI

0x446e14 LEA	(%R11,%RSI,1),%R8

0x446e18 ADD	%R8,%RSI

0x446e1b VMOVSD	(%RSI),%XMM13

0x446e1f VMOVSD	(%R11),%XMM15

0x446e24 VMOVHPD	(%RSI,%R10,8),%XMM13,%XMM14

0x446e2a MOVSXD	%EDX,%R10

0x446e2d LEA	0x1(%R12,%R9,1),%RDX

0x446e32 VMOVHPD	(%R8),%XMM15,%XMM3

0x446e37 MOVSXD	%ECX,%RCX

0x446e3a ADD	%R10,%RDX

0x446e3d MOV	%EAX,%R12D

0x446e40 VINSERTF64X2	$0x1,%XMM14,%YMM3,%YMM0

0x446e47 ADD	%RCX,%RDX

0x446e4a AND	$-0x4,%R12D

0x446e4e VMOVUPD	%YMM0,(%R15,%RDX,8)

0x446e54 ADD	%R12D,%EDI

0x446e57 TEST	$0x3,%AL

0x446e59 JE	446e8c

0x446e5b MOV	%EBX,%R9D

0x446e5e IMUL	%EDI,%R9D

0x446e62 MOV	0x74(%RSP),%R11D

0x446e67 MOVSXD	%EDI,%RSI

0x446e6a LEA	(%R11,%R9,1),%EAX

0x446e6e CLTQ

0x446e70 VMOVSD	(%R14,%RAX,8),%XMM2

0x446e76 MOV	0x78(%RSP),%R8D

0x446e7b ADD	%R13,%RSI

0x446e7e LEA	0x1(%RDI),%EAX

0x446e81 VMOVSD	%XMM2,(%R15,%RSI,8)

0x446e87 CMP	%EAX,%R8D

0x446e8a JG	446eb0

0x446e8c VZEROUPPER

0x446e8f LEA	-0x28(%RBP),%RSP

0x446e93 POP	%RBX

0x446e94 POP	%R12

0x446e96 POP	%R13

0x446e98 POP	%R14

0x446e9a POP	%R15

0x446e9c POP	%RBP

0x446e9d RET

0x446e9e XCHG	%AX,%AX

0x446ea0 INC	%EAX

0x446ea2 XOR	%EDX,%EDX

0x446ea4 JMP	4466e2

0x446ea9 NOPL	(%RAX)

0x446eb0 LEA	(%RBX,%R9,1),%R10D

0x446eb4 LEA	(%R10,%R11,1),%ECX

0x446eb8 MOVSXD	%ECX,%RDX

0x446ebb VMOVSD	(%R14,%RDX,8),%XMM4

0x446ec1 CLTQ

0x446ec3 ADD	%R13,%RAX

0x446ec6 ADD	$0x2,%EDI

0x446ec9 VMOVSD	%XMM4,(%R15,%RAX,8)

0x446ecf CMP	%EDI,%R8D

0x446ed2 JLE	446e8c

0x446ed4 LEA	(%RBX,%R10,1),%EAX

0x446ed8 ADD	%R11D,%EAX

0x446edb CLTQ

0x446edd VMOVSD	(%R14,%RAX,8),%XMM1

0x446ee3 MOVSXD	%EDI,%R14

0x446ee6 LEA	(%R14,%R13,1),%R13

0x446eea VMOVSD	%XMM1,(%R15,%R13,8)

0x446ef0 VZEROUPPER

0x446ef3 JMP	446992

0x446ef8 NOPL	(%RAX,%RAX,1)

0x446f00 VMOVUPD	(%R11),%ZMM5

0x446f06 MOV	$0x40,%EDI

0x446f0b VMOVUPD	%ZMM5,(%R10)

0x446f11 JMP	4467bd

0x446f16 XOR	%R11D,%R11D

0x446f19 JMP	4468d2

0x446f1e MOV	%ESI,%EDI

0x446f20 XOR	%R9D,%R9D

0x446f23 JMP	446dd7

0x446f28 NOPL	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
○99.44	gomp_thread_start	team.c:130	libgomp.so.1.0.0

Path /

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

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_2

Source file and lines	pack_kernel.cpp:297-300
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:297-300
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 73.00 to 28.17 cycles (2.59x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 26% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 73.00 to 56.93 cycles (1.28x speedup).

Details

26% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

19% of SSE/AVX loads are used in vector version.
29% of SSE/AVX stores are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
31% 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 function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

omp_get_num_threads@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:297
omp_get_thread_num@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:297

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.

IDIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:298
VZEROUPPER: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300

Vector unaligned load/store instructions

Detected 3 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
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.

Conversion instructions

Detected expensive conversion instructions.

Details

CLTD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:298
CLTQ: 6 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300

Workaround

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

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 1168 bytes. The binary function is storing 896 bytes.

General properties

nb instructions	420
nb uops	428
loop length	1747
used x86 registers	16
used mmx registers	0
used xmm registers	15
used ymm registers	9
used zmm registers	10
nb stack references	19

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	73.00 cycles
front end	73.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	41.30	41.20	39.67	39.67	24.50	41.20	41.10	24.50	24.50	24.50	41.20	39.67
cycles	41.30	47.47	39.67	39.67	24.50	41.20	41.10	24.50	24.50	24.50	41.20	39.67

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

6.00

Cycles summary

Front-end	73.00
Dispatch	47.47
DIV/SQRT	6.00
Overall L1	73.00

Vectorization ratios

INT

all	5%
load	NA (no load vectorizable/vectorized instructions)
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	42%
load	19%
store	66%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	26%
load	19%
store	29%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	31%

Vector efficiency ratios

INT

all	10%
load	NA (no load vectorizable/vectorized instructions)
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	38%
load	27%
store	65%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	32%

INT+FP

all	26%
load	27%
store	34%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	6%
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 73.00 cycles. At this rate:

8% of peak load performance is reached (16.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.27 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 73.00 to 47.47 cycles (1.54x speedup).

ASM code

In the binary file, the address of the function is: 446690

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
AND $-0x40,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD $-0x80,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x1c(%RDI),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x10(%RDI),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404630 <omp_get_num_threads@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404520 <omp_get_thread_num@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x14(%R13),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %EBX,%R15D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD 0x24(%R13),%EAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
INC %R15D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x2(%RBX,%RAX,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SUB %R15D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTD	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (6.3%)
IDIV %R14D	4	0	3	0	0	0	0	0	0	0	0	0	0	11-16	6	scal (6.3%)
CMP %EDX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JL 446ea0 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x810>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %EAX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA (%RDX,%RCX,1),%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%RAX,%RSI,1),%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %EDI,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JGE 446992 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x302>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x20(%R13),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x28(%R13),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R13),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%R13),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%R13),%R13D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R15D,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB %R8D,%R13D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %EDI,0x78(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVSXD %R13D,%R13	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R8,%R11,1),%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %R11D,0x7c(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
ADD %R15D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL (%R10),%R13	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV %EDI,0x74(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x8(%R9),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R10),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA -0x1(%RAX),%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x1,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 4469a8 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x318>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446f16 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x886>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD 0x7c(%RSP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %EDX,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOVSXD %R12D,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA -0x1(%RBX,%RDI,1),%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOVSXD %R8D,%R11	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R9,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R11,%R10,1),%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RBX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R13,%RBX,1),%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA (%R15,%RBX,8),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%EBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x6,%RBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA -0x40(%RBX),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x6,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R14,%RDI,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x7,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 446832 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x1a2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%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%)
JE 446817 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x187>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%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%)
JE 446805 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x175>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%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%)
JE 4467f3 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x163>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%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%)
JE 4467e1 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x151>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%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%)
JE 4467cf <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x13f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%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%)
JNE 446f00 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x870>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%R11,%RDI,1),%ZMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM6,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM7,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM8,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM9,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM10,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM11,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDI,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4468c0 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x230>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %EAX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x8,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %R11D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x7,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB %R11D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1(%RAX),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x2,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446924 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x294>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %EDX,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA -0x1(%R12,%RDX,1),%R12	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %ECX,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %RCX,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R12,%R11,1),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVSXD 0x7c(%RSP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R8,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RBX,%R9,1),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R13,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R11,%R12,1),%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VMOVUPD (%R14,%R8,8),%YMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
MOV %EAX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVUPD %YMM1,(%R15,%RDI,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
ADD %R11D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x3,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x74(%RSP),%R10D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %ESI,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R10,%RSI,1),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x78(%RSP),%R12D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R13,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RSI),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVSD %XMM5,(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %EAX,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JLE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RAX,%R10,1),%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOVSXD %ECX,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%R14,%RBX,8),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %R13,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD $0x2,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD %XMM6,(%R15,%RAX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %ESI,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JLE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R10D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %ESI,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVSXD %ESI,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R13,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD %XMM7,(%R15,%RSI,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x28(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x6,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446f1e <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x88e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %EBX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %R9,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x6,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %R10,0x50(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSXD %R12D,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SUB %R9,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R9,0x68(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%R9,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x1(%R10,%RDI,1),%R9	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %EDX,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R9,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOVSXD %ECX,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R10,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R15,%RDI,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EBX,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %ESI,%EDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R9,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVSXD 0x7c(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %R8D,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R9,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOVSXD %EDI,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R10,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R11,%RDI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NEG %R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,0x40(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x60(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SHR $0x3,%R10D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x6,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %R10,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R10,0x20(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x4,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %R9,0x28(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R11,%R11,2),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,0x48(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%R11,8),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %R11,0x30(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x20(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,0x58(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x68(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB $0x40,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R9,%R9,4),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x6,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x3,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,0x38(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND $0x3,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 446c21 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x591>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 446b96 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x506>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 446b19 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x489>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD (%RDI,%R9,1),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x30(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R10,1),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDI,%R11,1),%XMM0,%XMM2	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R11,8),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI,%R9,1),%XMM1,%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVSD (%RDI,%R11,1),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x48(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI),%XMM7,%XMM8	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVHPD (%RDI,%R9,1),%XMM5,%XMM6	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VINSERTF64X2 $0x1,%XMM2,%YMM3,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
MOV 0x60(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VINSERTF64X2 $0x1,%XMM6,%YMM8,%YMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X4 $0x1,%YMM4,%ZMM9,%ZMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VMOVUPD %ZMM10,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x50(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV 0x38(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R9,1),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%RDI,%R10,1),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDI,%R11,1),%XMM11,%XMM12	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R11,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI,%R9,1),%XMM13,%XMM14	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVSD (%RDI,%R11,1),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x48(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI),%XMM1,%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVHPD (%RDI,%R9,1),%XMM0,%XMM2	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VINSERTF64X2 $0x1,%XMM12,%YMM14,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
MOV 0x60(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VINSERTF64X2 $0x1,%XMM2,%YMM3,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X4 $0x1,%YMM15,%ZMM4,%ZMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VMOVUPD %ZMM5,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x50(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV 0x38(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R9,1),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%RDI,%R10,1),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDI,%R11,1),%XMM6,%XMM7	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R11,8),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI,%R9,1),%XMM8,%XMM9	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVSD (%RDI,%R11,1),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x48(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI),%XMM13,%XMM14	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVHPD (%RDI,%R9,1),%XMM11,%XMM12	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x50(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x60(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VINSERTF64X2 $0x1,%XMM7,%YMM9,%YMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X2 $0x1,%XMM12,%YMM14,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X4 $0x1,%YMM10,%ZMM15,%ZMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
ADD %R9,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV 0x28(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVUPD %ZMM0,(%R11)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %R9,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 446dc4 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x734>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %EAX,0x20(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x60(%RSP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %ESI,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EDX,0x70(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R8D,0x1c(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EBX,0x18(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R12D,0x14(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %ECX,0x10(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x58(%RSP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x68(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x50(%RSP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x48(%RSP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x38(%RSP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RSP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RSP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x70(%RSP),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x1c(%RSP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RSP),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x14(%RSP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RSP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x60(%RSP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %EAX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x8,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%R9,%RSI,1),%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
TEST $0x7,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB %R9D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1(%RAX),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x2,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446e5b <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7cb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %EBX,%ESI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD 0x7c(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %EBX,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOVSXD %ESI,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R11,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RSI,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %R10,%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SUB %R10,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %R13,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RSI,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R14,%R8,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (,%R10,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R11,%RSI,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R8,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RSI),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R11),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RSI,%R10,8),%XMM13,%XMM14	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVSXD %EDX,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA 0x1(%R12,%R9,1),%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VMOVHPD (%R8),%XMM15,%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVSXD %ECX,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R10,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %EAX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VINSERTF64X2 $0x1,%XMM14,%YMM3,%YMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
ADD %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND $-0x4,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVUPD %YMM0,(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
ADD %R12D,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x3,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %EBX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %EDI,%R9D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV 0x74(%RSP),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %EDI,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R11,%R9,1),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x78(%RSP),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R13,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RDI),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVSD %XMM2,(%R15,%RSI,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %EAX,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JG 446eb0 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x820>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x28(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 4466e2 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x52>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RBX,%R9,1),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%R10,%R11,1),%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOVSXD %ECX,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%R14,%RDX,8),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %R13,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD $0x2,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD %XMM4,(%R15,%RAX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %EDI,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JLE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RBX,%R10,1),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %R11D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVSXD %EDI,%R14	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R14,%R13,1),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,(%R15,%R13,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP 446992 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x302>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVUPD (%R11),%ZMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
MOV $0x40,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVUPD %ZMM5,(%R10)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
JMP 4467bd <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x12d>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 4468d2 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x242>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV %ESI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 446dd7 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x747>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run gcc_2

Source file and lines	pack_kernel.cpp:297-300
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:297-300
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

26% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

19% of SSE/AVX loads are used in vector version.
29% of SSE/AVX stores are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
31% 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 function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

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

No data for this section

CALL instructions

Detected function call instructions.

Details

omp_get_num_threads@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:297
omp_get_thread_num@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:297

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.

IDIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:298
VZEROUPPER: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300

Vector unaligned load/store instructions

Detected 3 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
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.

Conversion instructions

Detected expensive conversion instructions.

Details

CLTD: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:298
CLTQ: 6 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:300

Workaround

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

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 1168 bytes. The binary function is storing 896 bytes.

General properties

nb instructions	420
nb uops	428
loop length	1747
used x86 registers	16
used mmx registers	0
used xmm registers	15
used ymm registers	9
used zmm registers	10
nb stack references	19

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	73.00 cycles
front end	73.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	41.30	41.20	39.67	39.67	24.50	41.20	41.10	24.50	24.50	24.50	41.20	39.67
cycles	41.30	47.47	39.67	39.67	24.50	41.20	41.10	24.50	24.50	24.50	41.20	39.67

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

6.00

Cycles summary

Front-end	73.00
Dispatch	47.47
DIV/SQRT	6.00
Overall L1	73.00

Vectorization ratios

INT

all	5%
load	NA (no load vectorizable/vectorized instructions)
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	9%

all	42%
load	19%
store	66%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	26%
load	19%
store	29%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	31%

Vector efficiency ratios

INT

all	10%
load	NA (no load vectorizable/vectorized instructions)
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	38%
load	27%
store	65%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	32%

INT+FP

all	26%
load	27%
store	34%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	6%
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 73.00 cycles. At this rate:

8% of peak load performance is reached (16.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.27 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 446690

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RDI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
AND $-0x40,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD $-0x80,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x1c(%RDI),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x10(%RDI),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CALL 404630 <omp_get_num_threads@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404520 <omp_get_thread_num@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x14(%R13),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SUB %EBX,%R15D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD 0x24(%R13),%EAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
INC %R15D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x2(%RBX,%RAX,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SUB %R15D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTD	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (6.3%)
IDIV %R14D	4	0	3	0	0	0	0	0	0	0	0	0	0	11-16	6	scal (6.3%)
CMP %EDX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JL 446ea0 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x810>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %EAX,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA (%RDX,%RCX,1),%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%RAX,%RSI,1),%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %EDI,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JGE 446992 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x302>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x20(%R13),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x28(%R13),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%R13),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%R13),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%R13),%R13D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R15D,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB %R8D,%R13D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %EDI,0x78(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVSXD %R13D,%R13	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R8,%R11,1),%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOV %R11D,0x7c(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
ADD %R15D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL (%R10),%R13	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
MOV %EDI,0x74(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x8(%R9),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%R10),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA -0x1(%RAX),%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x1,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 4469a8 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x318>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446f16 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x886>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD 0x7c(%RSP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %EDX,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOVSXD %R12D,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA -0x1(%RBX,%RDI,1),%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %ECX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOVSXD %R8D,%R11	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R9,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R11,%R10,1),%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RBX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R13,%RBX,1),%RBX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA (%R15,%RBX,8),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x3,%EBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x6,%RBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA -0x40(%RBX),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x6,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R14,%RDI,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x7,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 446832 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x1a2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%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%)
JE 446817 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x187>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%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%)
JE 446805 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x175>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%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%)
JE 4467f3 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x163>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%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%)
JE 4467e1 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x151>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%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%)
JE 4467cf <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x13f>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%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%)
JNE 446f00 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x870>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD (%R11,%RDI,1),%ZMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM6,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM7,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM8,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM9,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM10,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD (%R11,%RDI,1),%ZMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
VMOVUPD %ZMM11,(%R10,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDI,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4468c0 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x230>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %EAX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x8,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %R11D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x7,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB %R11D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1(%RAX),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x2,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446924 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x294>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %EDX,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA -0x1(%R12,%RDX,1),%R12	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %ECX,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %RCX,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R12,%R11,1),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVSXD 0x7c(%RSP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R8,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RBX,%R9,1),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R13,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R11,%R12,1),%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VMOVUPD (%R14,%R8,8),%YMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
MOV %EAX,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVUPD %YMM1,(%R15,%RDI,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
ADD %R11D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x3,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x74(%RSP),%R10D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %ESI,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R10,%RSI,1),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x78(%RSP),%R12D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R13,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RSI),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVSD %XMM5,(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %EAX,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JLE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RAX,%R10,1),%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOVSXD %ECX,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%R14,%RBX,8),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %R13,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD $0x2,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD %XMM6,(%R15,%RAX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %ESI,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JLE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %R10D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %ESI,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVSXD %ESI,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R13,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD %XMM7,(%R15,%RSI,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x28(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x6,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446f1e <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x88e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOVSXD %EBX,%R9	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV %R9,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x6,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %R10,0x50(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R13,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSXD %R12D,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
SUB %R9,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R9,0x68(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%R9,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x1(%R10,%RDI,1),%R9	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD %EDX,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R9,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOVSXD %ECX,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R10,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R15,%RDI,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EBX,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %ESI,%EDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R9,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVSXD 0x7c(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %R8D,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R9,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOVSXD %EDI,%RDI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R10,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R11,%RDI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NEG %R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R11,0x40(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x60(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SHR $0x3,%R10D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x6,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %R10,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R10,0x20(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x4,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %R9,0x28(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %R11,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R11,%R11,2),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,0x48(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%R11,8),%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x5,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV %R11,0x30(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x20(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,0x58(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x68(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SUB $0x40,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R9,%R9,4),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x6,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SAL $0x3,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,0x38(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND $0x3,%R11D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 446c21 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x591>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 446b96 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x506>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 446b19 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x489>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD (%RDI,%R9,1),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x30(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R10,1),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDI,%R11,1),%XMM0,%XMM2	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R11,8),%XMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI,%R9,1),%XMM1,%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVSD (%RDI,%R11,1),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x48(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI),%XMM7,%XMM8	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVHPD (%RDI,%R9,1),%XMM5,%XMM6	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VINSERTF64X2 $0x1,%XMM2,%YMM3,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
MOV 0x60(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VINSERTF64X2 $0x1,%XMM6,%YMM8,%YMM9	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X4 $0x1,%YMM4,%ZMM9,%ZMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VMOVUPD %ZMM10,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x50(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV 0x38(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R9,1),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%RDI,%R10,1),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDI,%R11,1),%XMM11,%XMM12	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R11,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI,%R9,1),%XMM13,%XMM14	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVSD (%RDI,%R11,1),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x48(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI),%XMM1,%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVHPD (%RDI,%R9,1),%XMM0,%XMM2	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VINSERTF64X2 $0x1,%XMM12,%YMM14,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
MOV 0x60(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VINSERTF64X2 $0x1,%XMM2,%YMM3,%YMM4	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X4 $0x1,%YMM15,%ZMM4,%ZMM5	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
VMOVUPD %ZMM5,(%R9)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x50(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV 0x38(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R9,1),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%RDI,%R10,1),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RDI,%R11,1),%XMM6,%XMM7	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x68(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x58(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDI,%R11,8),%XMM11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI,%R9,1),%XMM8,%XMM9	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVSD (%RDI,%R11,1),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x48(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVHPD (%RDI),%XMM13,%XMM14	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
VMOVHPD (%RDI,%R9,1),%XMM11,%XMM12	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOV 0x50(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x60(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VINSERTF64X2 $0x1,%XMM7,%YMM9,%YMM10	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X2 $0x1,%XMM12,%YMM14,%YMM15	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VINSERTF64X4 $0x1,%YMM10,%ZMM15,%ZMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (50.0%)
ADD %R9,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV 0x28(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVUPD %ZMM0,(%R11)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %R9,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 446dc4 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x734>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %EAX,0x20(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x60(%RSP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %ESI,0x60(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EDX,0x70(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R8D,0x1c(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EBX,0x18(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R12D,0x14(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %ECX,0x10(%RSP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0x58(%RSP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x68(%RSP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x50(%RSP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x48(%RSP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x38(%RSP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RSP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x20(%RSP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x70(%RSP),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x1c(%RSP),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x18(%RSP),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x14(%RSP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RSP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x60(%RSP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %EAX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x8,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%R9,%RSI,1),%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
TEST $0x7,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB %R9D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1(%RAX),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP $0x2,%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JBE 446e5b <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7cb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %EBX,%ESI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOVSXD 0x7c(%RSP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %EBX,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOVSXD %ESI,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R11,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RSI,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R9,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %R10,%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
SUB %R10,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %R13,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RSI,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%R14,%R8,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (,%R10,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R11,%RSI,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R8,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RSI),%XMM13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R11),%XMM15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVHPD (%RSI,%R10,8),%XMM13,%XMM14	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVSXD %EDX,%R10	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA 0x1(%R12,%R9,1),%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
VMOVHPD (%R8),%XMM15,%XMM3	1	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	4-12	1	scal (12.5%)
MOVSXD %ECX,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
ADD %R10,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %EAX,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VINSERTF64X2 $0x1,%XMM14,%YMM3,%YMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
ADD %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND $-0x4,%R12D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVUPD %YMM0,(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
ADD %R12D,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x3,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %EBX,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %EDI,%R9D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV 0x74(%RSP),%R11D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %EDI,%RSI	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R11,%R9,1),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x78(%RSP),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R13,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RDI),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
VMOVSD %XMM2,(%R15,%RSI,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %EAX,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JG 446eb0 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x820>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x28(%RBP),%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 4466e2 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x52>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%RBX,%R9,1),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
LEA (%R10,%R11,1),%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
MOVSXD %ECX,%RDX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%R14,%RDX,8),%XMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %R13,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD $0x2,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD %XMM4,(%R15,%RAX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %EDI,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JLE 446e8c <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7fc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RBX,%R10,1),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %R11D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CLTQ	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.33	scal (12.5%)
VMOVSD (%R14,%RAX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOVSXD %EDI,%R14	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
LEA (%R14,%R13,1),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,(%R15,%R13,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP 446992 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x302>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVUPD (%R11),%ZMM5	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
MOV $0x40,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVUPD %ZMM5,(%R10)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
JMP 4467bd <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x12d>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 4468d2 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x242>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV %ESI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 446dd7 <_Z28clover_unpack_message_bottomR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x747>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼clover_unpack_message_bottom(global_variables&, int, int, int, int, clover::Buffer2D&, clover::Buffer1D&, int, int, int, int, int, int, int) [clone ._omp_fn.0]–	0.01	0.00
○Loop 330 - pack_kernel.cpp:300-300 - exec	0.00	0.01
○Loop 331 - pack_kernel.cpp:300-300 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code