OV - exec - Function clover_unpack_message_top(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_top(global_variables&, int, int, int, int, clover::Buffer2D<double>& ...	Module: exec	Source: pack_kernel.cpp:227-230 [...]	Coverage (incl. loops): 0.02% \| (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: 227 - 230

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

227: #pragma omp parallel for simd

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

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

230:       field(j, y_max + y_inc + k + 2) = top_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]; }

0x445460 PUSH	%RBP

0x445461 MOV	%RSP,%RBP

0x445464 PUSH	%R15

0x445466 PUSH	%R14

0x445468 PUSH	%R13

0x44546a MOV	%RDI,%R13

0x44546d PUSH	%R12

0x44546f PUSH	%RBX

0x445470 AND	$-0x40,%RSP

0x445474 ADD	$-0x80,%RSP

0x445478 MOV	0x1c(%RDI),%EBX

0x44547b MOVSXD	0x10(%RDI),%R12

0x44547f CALL	404630 <omp_get_num_threads@plt>

0x445484 MOV	%EAX,%R14D

0x445487 CALL	404520 <omp_get_thread_num@plt>

0x44548c MOV	%EAX,%ECX

0x44548e MOV	0x14(%R13),%EAX

0x445492 MOV	%R12D,%R15D

0x445495 SUB	%EBX,%R15D

0x445498 ADD	0x24(%R13),%EAX

0x44549c INC	%R15D

0x44549f LEA	0x2(%RBX,%RAX,1),%EAX

0x4454a3 SUB	%R15D,%EAX

0x4454a6 CLTD

0x4454a7 IDIV	%R14D

0x4454aa CMP	%EDX,%ECX

0x4454ac JL	445c80

0x4454b2 IMUL	%EAX,%ECX

0x4454b5 LEA	(%RDX,%RCX,1),%ESI

0x4454b8 LEA	(%RAX,%RSI,1),%EDI

0x4454bb CMP	%EDI,%ESI

0x4454bd JGE	445769

0x4454c3 ADD	%R15D,%EDI

0x4454c6 MOV	%EDI,0x78(%RSP)

0x4454ca MOV	0x18(%R13),%EDI

0x4454ce MOVSXD	0x2c(%R13),%R8

0x4454d2 MOV	0x20(%R13),%R11D

0x4454d6 ADD	0x28(%R13),%EDI

0x4454da MOV	0x8(%R13),%R9

0x4454de MOV	(%R13),%R10

0x4454e2 LEA	0x2(%R8,%RDI,1),%R13D

0x4454e7 MOV	%R11D,0x7c(%RSP)

0x4454ec MOVSXD	%R13D,%R13

0x4454ef LEA	(%R8,%R11,1),%R11D

0x4454f3 MOV	0x8(%R9),%R14

0x4454f7 ADD	%R15D,%ESI

0x4454fa IMUL	(%R10),%R13

0x4454fe MOV	%R11D,0x74(%RSP)

0x445503 MOV	0x10(%R10),%R15

0x445507 LEA	-0x1(%RAX),%R9D

0x44550b CMP	$0x1,%EBX

0x44550e JNE	445780

0x445514 CMP	$0x6,%R9D

0x445518 JBE	445cf6

0x44551e MOVSXD	0x7c(%RSP),%R10

0x445523 MOVSXD	%EDX,%RDI

0x445526 MOVSXD	%R12D,%RBX

0x445529 LEA	-0x1(%RBX,%RDI,1),%RBX

0x44552e MOVSXD	%ECX,%R9

0x445531 MOVSXD	%R8D,%R11

0x445534 ADD	%R9,%RBX

0x445537 LEA	0x1(%R11,%R10,1),%RDI

0x44553c ADD	%RBX,%RDI

0x44553f LEA	0x1(%R13,%RBX,1),%RBX

0x445544 LEA	(%R15,%RBX,8),%R10

0x445548 MOV	%EAX,%EBX

0x44554a SHR	$0x3,%EBX

0x44554d SAL	$0x6,%RBX

0x445551 LEA	-0x40(%RBX),%R9

0x445555 SHR	$0x6,%R9

0x445559 INC	%R9

0x44555c LEA	(%R14,%RDI,8),%R11

0x445560 XOR	%EDI,%EDI

0x445562 AND	$0x7,%R9D

0x445566 JE	445609

0x44556c CMP	$0x1,%R9

0x445570 JE	4455ee

0x445572 CMP	$0x2,%R9

0x445576 JE	4455dc

0x445578 CMP	$0x3,%R9

0x44557c JE	4455ca

0x44557e CMP	$0x4,%R9

0x445582 JE	4455b8

0x445584 CMP	$0x5,%R9

0x445588 JE	4455a6

0x44558a CMP	$0x6,%R9

0x44558e JNE	445ce0

0x445594 VMOVUPD	(%R11,%RDI,1),%ZMM6

0x44559b VMOVUPD	%ZMM6,(%R10,%RDI,1)

0x4455a2 ADD	$0x40,%RDI

0x4455a6 VMOVUPD	(%R11,%RDI,1),%ZMM7

0x4455ad VMOVUPD	%ZMM7,(%R10,%RDI,1)

0x4455b4 ADD	$0x40,%RDI

0x4455b8 VMOVUPD	(%R11,%RDI,1),%ZMM8

0x4455bf VMOVUPD	%ZMM8,(%R10,%RDI,1)

0x4455c6 ADD	$0x40,%RDI

0x4455ca VMOVUPD	(%R11,%RDI,1),%ZMM9

0x4455d1 VMOVUPD	%ZMM9,(%R10,%RDI,1)

0x4455d8 ADD	$0x40,%RDI

0x4455dc VMOVUPD	(%R11,%RDI,1),%ZMM10

0x4455e3 VMOVUPD	%ZMM10,(%R10,%RDI,1)

0x4455ea ADD	$0x40,%RDI

0x4455ee VMOVUPD	(%R11,%RDI,1),%ZMM11

0x4455f5 VMOVUPD	%ZMM11,(%R10,%RDI,1)

0x4455fc ADD	$0x40,%RDI

0x445600 CMP	%RDI,%RBX

0x445603 JE	445697

(327) 0x445609 VMOVUPD	(%R11,%RDI,1),%ZMM12

(327) 0x445610 VMOVUPD	%ZMM12,(%R10,%RDI,1)

(327) 0x445617 VMOVUPD	0x40(%R11,%RDI,1),%ZMM13

(327) 0x44561f VMOVUPD	%ZMM13,0x40(%R10,%RDI,1)

(327) 0x445627 VMOVUPD	0x80(%R11,%RDI,1),%ZMM14

(327) 0x44562f VMOVUPD	%ZMM14,0x80(%R10,%RDI,1)

(327) 0x445637 VMOVUPD	0xc0(%R11,%RDI,1),%ZMM15

(327) 0x44563f VMOVUPD	%ZMM15,0xc0(%R10,%RDI,1)

(327) 0x445647 VMOVUPD	0x100(%R11,%RDI,1),%ZMM3

(327) 0x44564f VMOVUPD	%ZMM3,0x100(%R10,%RDI,1)

(327) 0x445657 VMOVUPD	0x140(%R11,%RDI,1),%ZMM0

(327) 0x44565f VMOVUPD	%ZMM0,0x140(%R10,%RDI,1)

(327) 0x445667 VMOVUPD	0x180(%R11,%RDI,1),%ZMM2

(327) 0x44566f VMOVUPD	%ZMM2,0x180(%R10,%RDI,1)

(327) 0x445677 VMOVUPD	0x1c0(%R11,%RDI,1),%ZMM4

(327) 0x44567f VMOVUPD	%ZMM4,0x1c0(%R10,%RDI,1)

(327) 0x445687 ADD	$0x200,%RDI

(327) 0x44568e CMP	%RDI,%RBX

(327) 0x445691 JNE	445609

0x445697 MOV	%EAX,%R11D

0x44569a AND	$-0x8,%R11D

0x44569e ADD	%R11D,%ESI

0x4456a1 TEST	$0x7,%AL

0x4456a3 JE	445c64

0x4456a9 SUB	%R11D,%EAX

0x4456ac LEA	-0x1(%RAX),%R10D

0x4456b0 CMP	$0x2,%R10D

0x4456b4 JBE	4456fb

0x4456b6 MOVSXD	%EDX,%RDX

0x4456b9 LEA	-0x1(%R12,%RDX,1),%R12

0x4456be MOVSXD	%ECX,%RCX

0x4456c1 ADD	%RCX,%R12

0x4456c4 LEA	(%R12,%R11,1),%R9

0x4456c8 MOVSXD	0x7c(%RSP),%RBX

0x4456cd ADD	%R8,%R9

0x4456d0 LEA	0x1(%RBX,%R9,1),%R8

0x4456d5 ADD	%R13,%R12

0x4456d8 LEA	0x1(%R11,%R12,1),%RDI

0x4456dd VMOVUPD	(%R14,%R8,8),%YMM1

0x4456e3 MOV	%EAX,%R11D

0x4456e6 AND	$-0x4,%R11D

0x4456ea VMOVUPD	%YMM1,(%R15,%RDI,8)

0x4456f0 ADD	%R11D,%ESI

0x4456f3 TEST	$0x3,%AL

0x4456f5 JE	445c64

0x4456fb MOV	0x74(%RSP),%R10D

0x445700 MOVSXD	%ESI,%RDX

0x445703 LEA	(%R10,%RSI,1),%EAX

0x445707 CLTQ

0x445709 VMOVSD	(%R14,%RAX,8),%XMM5

0x44570f MOV	0x78(%RSP),%R12D

0x445714 ADD	%R13,%RDX

0x445717 LEA	0x1(%RSI),%EAX

0x44571a VMOVSD	%XMM5,(%R15,%RDX,8)

0x445720 CMP	%EAX,%R12D

0x445723 JLE	445c64

0x445729 LEA	(%RAX,%R10,1),%ECX

0x44572d MOVSXD	%ECX,%RBX

0x445730 VMOVSD	(%R14,%RBX,8),%XMM6

0x445736 CLTQ

0x445738 ADD	%R13,%RAX

0x44573b ADD	$0x2,%ESI

0x44573e VMOVSD	%XMM6,(%R15,%RAX,8)

0x445744 CMP	%ESI,%R12D

0x445747 JLE	445c64

0x44574d MOV	%R10D,%EAX

0x445750 ADD	%ESI,%EAX

0x445752 CLTQ

0x445754 VMOVSD	(%R14,%RAX,8),%XMM7

0x44575a MOVSXD	%ESI,%RSI

0x44575d ADD	%R13,%RSI

0x445760 VMOVSD	%XMM7,(%R15,%RSI,8)

0x445766 VZEROUPPER

0x445769 LEA	-0x28(%RBP),%RSP

0x44576d POP	%RBX

0x44576e POP	%R12

0x445770 POP	%R13

0x445772 POP	%R14

0x445774 POP	%R15

0x445776 POP	%RBP

0x445777 RET

0x445778 NOPL	(%RAX,%RAX,1)

0x445780 CMP	$0x6,%R9D

0x445784 JBE	445cfe

0x44578a MOVSXD	%EBX,%R9

0x44578d MOV	%R9,%R10

0x445790 SAL	$0x6,%R10

0x445794 MOV	%R10,0x50(%RSP)

0x445799 MOV	%R13,%R10

0x44579c MOVSXD	%R12D,%RDI

0x44579f SUB	%R9,%R10

0x4457a2 MOV	%R9,0x68(%RSP)

0x4457a7 LEA	(,%R9,8),%R11

0x4457af LEA	0x1(%R10,%RDI,1),%R9

0x4457b4 MOVSXD	%EDX,%RDI

0x4457b7 ADD	%R9,%RDI

0x4457ba MOVSXD	%ECX,%R10

0x4457bd ADD	%R10,%RDI

0x4457c0 LEA	(%R15,%RDI,8),%R9

0x4457c4 MOV	%EBX,%EDI

0x4457c6 IMUL	%ESI,%EDI

0x4457c9 MOV	%R9,0x60(%RSP)

0x4457ce MOVSXD	0x7c(%RSP),%R9

0x4457d3 MOVSXD	%R8D,%R10

0x4457d6 ADD	%R9,%R10

0x4457d9 MOVSXD	%EDI,%RDI

0x4457dc ADD	%R10,%RDI

0x4457df LEA	(%R11,%RDI,8),%RDI

0x4457e3 MOV	%EAX,%R10D

0x4457e6 NEG	%R11

0x4457e9 MOV	%R11,0x40(%RSP)

0x4457ee MOV	0x60(%RSP),%R9

0x4457f3 MOV	0x68(%RSP),%R11

0x4457f8 SHR	$0x3,%R10D

0x4457fc SAL	$0x6,%R10

0x445800 ADD	%R10,%R9

0x445803 MOV	%R10,0x20(%RSP)

0x445808 MOV	%R11,%R10

0x44580b SAL	$0x4,%R10

0x44580f MOV	%R9,0x28(%RSP)

0x445814 MOV	%R11,%R9

0x445817 LEA	(%R11,%R11,2),%R11

0x44581b MOV	%R10,0x48(%RSP)

0x445820 LEA	(,%R11,8),%R10

0x445828 SAL	$0x4,%R11

0x44582c SAL	$0x5,%R9

0x445830 MOV	%R11,0x30(%RSP)

0x445835 MOV	0x20(%RSP),%R11

0x44583a MOV	%R9,0x58(%RSP)

0x44583f MOV	0x68(%RSP),%R9

0x445844 SUB	$0x40,%R11

0x445848 LEA	(%R9,%R9,4),%R9

0x44584c SHR	$0x6,%R11

0x445850 SAL	$0x3,%R9

0x445854 INC	%R11

0x445857 MOV	%R9,0x38(%RSP)

0x44585c ADD	%R14,%RDI

0x44585f AND	$0x3,%R11D

0x445863 JE	4459f9

0x445869 CMP	$0x1,%R11

0x44586d JE	44596e

0x445873 CMP	$0x2,%R11

0x445877 JE	4458f1

0x445879 VMOVSD	(%RDI,%R9,1),%XMM0

0x44587f MOV	0x30(%RSP),%R11

0x445884 VMOVSD	(%RDI,%R10,1),%XMM1

0x44588a VMOVHPD	(%RDI,%R11,1),%XMM0,%XMM2

0x445890 MOV	0x68(%RSP),%R11

0x445895 MOV	0x58(%RSP),%R9

0x44589a VMOVSD	(%RDI,%R11,8),%XMM5

0x4458a0 MOV	0x40(%RSP),%R11

0x4458a5 VMOVHPD	(%RDI,%R9,1),%XMM1,%XMM3

0x4458ab VMOVSD	(%RDI,%R11,1),%XMM7

0x4458b1 MOV	0x48(%RSP),%R9

0x4458b6 VMOVHPD	(%RDI),%XMM7,%XMM8

0x4458ba VMOVHPD	(%RDI,%R9,1),%XMM5,%XMM6

0x4458c0 VINSERTF64X2	$0x1,%XMM2,%YMM3,%YMM4

0x4458c7 MOV	0x60(%RSP),%R9

0x4458cc VINSERTF64X2	$0x1,%XMM6,%YMM8,%YMM9

0x4458d3 VINSERTF64X4	$0x1,%YMM4,%ZMM9,%ZMM10

0x4458da VMOVUPD	%ZMM10,(%R9)

0x4458e0 ADD	$0x40,%R9

0x4458e4 MOV	0x50(%RSP),%R11

0x4458e9 MOV	%R9,0x60(%RSP)

0x4458ee ADD	%R11,%RDI

0x4458f1 MOV	0x38(%RSP),%R9

0x4458f6 MOV	0x30(%RSP),%R11

0x4458fb VMOVSD	(%RDI,%R9,1),%XMM11

0x445901 VMOVSD	(%RDI,%R10,1),%XMM13

0x445907 VMOVHPD	(%RDI,%R11,1),%XMM11,%XMM12

0x44590d MOV	0x68(%RSP),%R11

0x445912 MOV	0x58(%RSP),%R9

0x445917 VMOVSD	(%RDI,%R11,8),%XMM0

0x44591d MOV	0x40(%RSP),%R11

0x445922 VMOVHPD	(%RDI,%R9,1),%XMM13,%XMM14

0x445928 VMOVSD	(%RDI,%R11,1),%XMM1

0x44592e MOV	0x48(%RSP),%R9

0x445933 VMOVHPD	(%RDI),%XMM1,%XMM3

0x445937 VMOVHPD	(%RDI,%R9,1),%XMM0,%XMM2

0x44593d VINSERTF64X2	$0x1,%XMM12,%YMM14,%YMM15

0x445944 MOV	0x60(%RSP),%R9

0x445949 VINSERTF64X2	$0x1,%XMM2,%YMM3,%YMM4

0x445950 VINSERTF64X4	$0x1,%YMM15,%ZMM4,%ZMM5

0x445957 VMOVUPD	%ZMM5,(%R9)

0x44595d ADD	$0x40,%R9

0x445961 MOV	0x50(%RSP),%R11

0x445966 MOV	%R9,0x60(%RSP)

0x44596b ADD	%R11,%RDI

0x44596e MOV	0x38(%RSP),%R9

0x445973 MOV	0x30(%RSP),%R11

0x445978 VMOVSD	(%RDI,%R9,1),%XMM6

0x44597e VMOVSD	(%RDI,%R10,1),%XMM8

0x445984 VMOVHPD	(%RDI,%R11,1),%XMM6,%XMM7

0x44598a MOV	0x68(%RSP),%R11

0x44598f MOV	0x58(%RSP),%R9

0x445994 VMOVSD	(%RDI,%R11,8),%XMM11

0x44599a MOV	0x40(%RSP),%R11

0x44599f VMOVHPD	(%RDI,%R9,1),%XMM8,%XMM9

0x4459a5 VMOVSD	(%RDI,%R11,1),%XMM13

0x4459ab MOV	0x48(%RSP),%R9

0x4459b0 VMOVHPD	(%RDI),%XMM13,%XMM14

0x4459b4 VMOVHPD	(%RDI,%R9,1),%XMM11,%XMM12

0x4459ba MOV	0x50(%RSP),%R9

0x4459bf MOV	0x60(%RSP),%R11

0x4459c4 VINSERTF64X2	$0x1,%XMM7,%YMM9,%YMM10

0x4459cb VINSERTF64X2	$0x1,%XMM12,%YMM14,%YMM15

0x4459d2 VINSERTF64X4	$0x1,%YMM10,%ZMM15,%ZMM0

0x4459d9 ADD	%R9,%RDI

0x4459dc MOV	0x28(%RSP),%R9

0x4459e1 VMOVUPD	%ZMM0,(%R11)

0x4459e7 ADD	$0x40,%R11

0x4459eb MOV	%R11,0x60(%RSP)

0x4459f0 CMP	%R9,%R11

0x4459f3 JE	445b9c

0x4459f9 MOV	%EAX,0x20(%RSP)

0x4459fd MOV	0x60(%RSP),%RAX

0x445a02 MOV	%ESI,0x60(%RSP)

0x445a06 MOV	%EDX,0x70(%RSP)

0x445a0a MOV	%R8D,0x1c(%RSP)

0x445a0f MOV	%EBX,0x18(%RSP)

0x445a13 MOV	%R12D,0x14(%RSP)

0x445a18 MOV	%ECX,0x10(%RSP)

0x445a1c MOV	0x58(%RSP),%RDX

0x445a21 MOV	0x68(%RSP),%R9

0x445a26 MOV	0x50(%RSP),%RCX

0x445a2b MOV	0x48(%RSP),%R8

0x445a30 MOV	0x40(%RSP),%R11

0x445a35 MOV	0x38(%RSP),%RBX

0x445a3a MOV	0x30(%RSP),%R12

(326) 0x445a3f VMOVSD	(%RDI,%RBX,1),%XMM2

(326) 0x445a44 VMOVSD	(%RDI,%R10,1),%XMM1

(326) 0x445a4a VMOVSD	(%RDI,%R9,8),%XMM6

(326) 0x445a50 VMOVSD	(%RDI,%R11,1),%XMM8

(326) 0x445a56 VMOVHPD	(%RDI,%R12,1),%XMM2,%XMM3

(326) 0x445a5c VMOVHPD	(%RDI,%RDX,1),%XMM1,%XMM4

(326) 0x445a61 VMOVHPD	(%RDI,%R8,1),%XMM6,%XMM7

(326) 0x445a67 VMOVHPD	(%RDI),%XMM8,%XMM9

(326) 0x445a6b VINSERTF64X2	$0x1,%XMM3,%YMM4,%YMM5

(326) 0x445a72 VINSERTF64X2	$0x1,%XMM7,%YMM9,%YMM10

(326) 0x445a79 VINSERTF64X4	$0x1,%YMM5,%ZMM10,%ZMM11

(326) 0x445a80 VMOVUPD	%ZMM11,(%RAX)

(326) 0x445a86 ADD	%RCX,%RDI

(326) 0x445a89 VMOVSD	(%RDI,%RBX,1),%XMM12

(326) 0x445a8e VMOVSD	(%RDI,%R10,1),%XMM14

(326) 0x445a94 VMOVSD	(%RDI,%R9,8),%XMM0

(326) 0x445a9a VMOVSD	(%RDI,%R11,1),%XMM1

(326) 0x445aa0 VMOVHPD	(%RDI,%R12,1),%XMM12,%XMM13

(326) 0x445aa6 VMOVHPD	(%RDI,%RDX,1),%XMM14,%XMM15

(326) 0x445aab VMOVHPD	(%RDI,%R8,1),%XMM0,%XMM2

(326) 0x445ab1 VMOVHPD	(%RDI),%XMM1,%XMM4

(326) 0x445ab5 VINSERTF64X2	$0x1,%XMM13,%YMM15,%YMM3

(326) 0x445abc VINSERTF64X2	$0x1,%XMM2,%YMM4,%YMM5

(326) 0x445ac3 VINSERTF64X4	$0x1,%YMM3,%ZMM5,%ZMM6

(326) 0x445aca VMOVUPD	%ZMM6,0x40(%RAX)

(326) 0x445ad1 ADD	%RCX,%RDI

(326) 0x445ad4 VMOVSD	(%RDI,%RBX,1),%XMM7

(326) 0x445ad9 VMOVSD	(%RDI,%R10,1),%XMM9

(326) 0x445adf VMOVSD	(%RDI,%R9,8),%XMM12

(326) 0x445ae5 VMOVSD	(%RDI,%R11,1),%XMM14

(326) 0x445aeb VMOVHPD	(%RDI,%RDX,1),%XMM9,%XMM10

(326) 0x445af0 VMOVHPD	(%RDI,%R12,1),%XMM7,%XMM8

(326) 0x445af6 VMOVHPD	(%RDI,%R8,1),%XMM12,%XMM13

(326) 0x445afc VMOVHPD	(%RDI),%XMM14,%XMM15

(326) 0x445b00 VINSERTF64X2	$0x1,%XMM8,%YMM10,%YMM11

(326) 0x445b07 VINSERTF64X2	$0x1,%XMM13,%YMM15,%YMM3

(326) 0x445b0e VINSERTF64X4	$0x1,%YMM11,%ZMM3,%ZMM0

(326) 0x445b15 ADD	%RCX,%RDI

(326) 0x445b18 VMOVUPD	%ZMM0,0x80(%RAX)

(326) 0x445b1f VMOVSD	(%RDI,%RBX,1),%XMM2

(326) 0x445b24 VMOVSD	(%RDI,%R10,1),%XMM1

(326) 0x445b2a VMOVSD	(%RDI,%R9,8),%XMM7

(326) 0x445b30 VMOVHPD	(%RDI,%R12,1),%XMM2,%XMM4

(326) 0x445b36 VMOVHPD	(%RDI,%RDX,1),%XMM1,%XMM5

(326) 0x445b3b VMOVHPD	(%RDI,%R8,1),%XMM7,%XMM8

(326) 0x445b41 VMOVSD	(%RDI,%R11,1),%XMM9

(326) 0x445b47 VINSERTF64X2	$0x1,%XMM4,%YMM5,%YMM6

(326) 0x445b4e VMOVHPD	(%RDI),%XMM9,%XMM10

(326) 0x445b52 VINSERTF64X2	$0x1,%XMM8,%YMM10,%YMM11

(326) 0x445b59 VINSERTF64X4	$0x1,%YMM6,%ZMM11,%ZMM12

(326) 0x445b60 MOV	0x28(%RSP),%RSI

(326) 0x445b65 VMOVUPD	%ZMM12,0xc0(%RAX)

(326) 0x445b6c ADD	$0x100,%RAX

(326) 0x445b72 ADD	%RCX,%RDI

(326) 0x445b75 CMP	%RSI,%RAX

(326) 0x445b78 JNE	445a3f

0x445b7e MOV	0x20(%RSP),%EAX

0x445b82 MOV	0x70(%RSP),%EDX

0x445b86 MOVSXD	0x1c(%RSP),%R8

0x445b8b MOV	0x18(%RSP),%EBX

0x445b8f MOVSXD	0x14(%RSP),%R12

0x445b94 MOV	0x10(%RSP),%ECX

0x445b98 MOV	0x60(%RSP),%ESI

0x445b9c MOV	%EAX,%R9D

0x445b9f AND	$-0x8,%R9D

0x445ba3 LEA	(%R9,%RSI,1),%EDI

0x445ba7 TEST	$0x7,%AL

0x445ba9 JE	445c64

0x445baf SUB	%R9D,%EAX

0x445bb2 LEA	-0x1(%RAX),%R10D

0x445bb6 CMP	$0x2,%R10D

0x445bba JBE	445c33

0x445bbc IMUL	%EBX,%ESI

0x445bbf MOVSXD	0x7c(%RSP),%R11

0x445bc4 MOVSXD	%EBX,%R10

0x445bc7 MOVSXD	%ESI,%RSI

0x445bca ADD	%R11,%R8

0x445bcd ADD	%RSI,%R8

0x445bd0 MOV	%R9,%RSI

0x445bd3 IMUL	%R10,%RSI

0x445bd7 SUB	%R10,%R12

0x445bda ADD	%R13,%R9

0x445bdd ADD	%RSI,%R8

0x445be0 LEA	(%R14,%R8,8),%R11

0x445be4 LEA	(,%R10,8),%RSI

0x445bec LEA	(%R11,%RSI,1),%R8

0x445bf0 ADD	%R8,%RSI

0x445bf3 VMOVSD	(%RSI),%XMM13

0x445bf7 VMOVSD	(%R11),%XMM15

0x445bfc VMOVHPD	(%RSI,%R10,8),%XMM13,%XMM14

0x445c02 MOVSXD	%EDX,%R10

0x445c05 LEA	0x1(%R12,%R9,1),%RDX

0x445c0a VMOVHPD	(%R8),%XMM15,%XMM3

0x445c0f MOVSXD	%ECX,%RCX

0x445c12 ADD	%R10,%RDX

0x445c15 MOV	%EAX,%R12D

0x445c18 VINSERTF64X2	$0x1,%XMM14,%YMM3,%YMM0

0x445c1f ADD	%RCX,%RDX

0x445c22 AND	$-0x4,%R12D

0x445c26 VMOVUPD	%YMM0,(%R15,%RDX,8)

0x445c2c ADD	%R12D,%EDI

0x445c2f TEST	$0x3,%AL

0x445c31 JE	445c64

0x445c33 MOV	%EBX,%R9D

0x445c36 IMUL	%EDI,%R9D

0x445c3a MOV	0x74(%RSP),%R11D

0x445c3f MOVSXD	%EDI,%RSI

0x445c42 LEA	(%R11,%R9,1),%EAX

0x445c46 CLTQ

0x445c48 VMOVSD	(%R14,%RAX,8),%XMM2

0x445c4e MOV	0x78(%RSP),%R8D

0x445c53 ADD	%R13,%RSI

0x445c56 LEA	0x1(%RDI),%EAX

0x445c59 VMOVSD	%XMM2,(%R15,%RSI,8)

0x445c5f CMP	%EAX,%R8D

0x445c62 JG	445c90

0x445c64 VZEROUPPER

0x445c67 LEA	-0x28(%RBP),%RSP

0x445c6b POP	%RBX

0x445c6c POP	%R12

0x445c6e POP	%R13

0x445c70 POP	%R14

0x445c72 POP	%R15

0x445c74 POP	%RBP

0x445c75 RET

0x445c76 NOPW	%CS:(%RAX,%RAX,1)

0x445c80 INC	%EAX

0x445c82 XOR	%EDX,%EDX

0x445c84 JMP	4454b2

0x445c89 NOPL	(%RAX)

0x445c90 LEA	(%RBX,%R9,1),%R10D

0x445c94 LEA	(%R10,%R11,1),%ECX

0x445c98 MOVSXD	%ECX,%RDX

0x445c9b VMOVSD	(%R14,%RDX,8),%XMM4

0x445ca1 CLTQ

0x445ca3 ADD	%R13,%RAX

0x445ca6 ADD	$0x2,%EDI

0x445ca9 VMOVSD	%XMM4,(%R15,%RAX,8)

0x445caf CMP	%EDI,%R8D

0x445cb2 JLE	445c64

0x445cb4 LEA	(%RBX,%R10,1),%EAX

0x445cb8 ADD	%R11D,%EAX

0x445cbb CLTQ

0x445cbd VMOVSD	(%R14,%RAX,8),%XMM1

0x445cc3 MOVSXD	%EDI,%R14

0x445cc6 LEA	(%R14,%R13,1),%R13

0x445cca VMOVSD	%XMM1,(%R15,%R13,8)

0x445cd0 VZEROUPPER

0x445cd3 JMP	445769

0x445cd8 NOPL	(%RAX,%RAX,1)

0x445ce0 VMOVUPD	(%R11),%ZMM5

0x445ce6 MOV	$0x40,%EDI

0x445ceb VMOVUPD	%ZMM5,(%R10)

0x445cf1 JMP	445594

0x445cf6 XOR	%R11D,%R11D

0x445cf9 JMP	4456a9

0x445cfe MOV	%ESI,%EDI

0x445d00 XOR	%R9D,%R9D

0x445d03 JMP	445baf

0x445d08 NOPL	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
○99.57	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:227-230
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:227-230
/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 73.17 to 28.17 cycles (2.60x 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 73.17 to 57.10 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:227
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:227

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:228
VZEROUPPER: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230

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:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230

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:228
CLTQ: 6 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230

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 1172 bytes. The binary function is storing 896 bytes.

General properties

nb instructions	421
nb uops	429
loop length	1763
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	73.17 cycles
front end	73.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	41.50	41.30	40.00	40.00	24.50	41.30	41.50	24.50	24.50	24.50	41.40	40.00
cycles	41.50	48.47	40.00	40.00	24.50	41.30	41.50	24.50	24.50	24.50	41.40	40.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

6.00

Cycles summary

Front-end	73.17
Dispatch	48.47
DIV/SQRT	6.00
Overall L1	73.17

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 73.17 cycles. At this rate:

8% of peak load performance is reached (16.02 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.25 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 73.17 to 48.47 cycles (1.51x speedup).

ASM code

In the binary file, the address of the function is: 445460

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 445c80 <_Z25clover_unpack_message_topR16global_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
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 445769 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x309>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	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
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%)
MOV 0x18(%R13),%EDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x2c(%R13),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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
ADD 0x28(%R13),%EDI	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
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 (%R13),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x2(%R8,%RDI,1),%R13D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	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%)
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),%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
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
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 %R11D,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 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),%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
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 445780 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x320>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R9D	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 445cf6 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x896>	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 445609 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x1a9>	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 4455ee <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x18e>	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 4455dc <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x17c>	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 4455ca <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x16a>	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 4455b8 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x158>	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 4455a6 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x146>	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 445ce0 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x880>	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 445697 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x237>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 4456fb <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x29b>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x6,%R9D	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 445cfe <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x89e>	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 4459f9 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x599>	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 44596e <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x50e>	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 4458f1 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x491>	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 445b9c <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x73c>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c33 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7d3>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c90 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x830>	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
NOPW %CS:(%RAX,%RAX,1)	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 4454b2 <_Z25clover_unpack_message_topR16global_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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445769 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x309>	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 445594 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x134>	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 4456a9 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x249>	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 445baf <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x74f>	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:227-230
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:227-230
/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:227
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:227

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:228
VZEROUPPER: 3 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230

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:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230

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:228
CLTQ: 6 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/pack_kernel.cpp:230

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 1172 bytes. The binary function is storing 896 bytes.

General properties

nb instructions	421
nb uops	429
loop length	1763
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	73.17 cycles
front end	73.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	41.50	41.30	40.00	40.00	24.50	41.30	41.50	24.50	24.50	24.50	41.40	40.00
cycles	41.50	48.47	40.00	40.00	24.50	41.30	41.50	24.50	24.50	24.50	41.40	40.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

6.00

Cycles summary

Front-end	73.17
Dispatch	48.47
DIV/SQRT	6.00
Overall L1	73.17

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 73.17 cycles. At this rate:

8% of peak load performance is reached (16.02 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.25 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: 445460

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 445c80 <_Z25clover_unpack_message_topR16global_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
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 445769 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x309>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	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
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%)
MOV 0x18(%R13),%EDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD 0x2c(%R13),%R8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	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
ADD 0x28(%R13),%EDI	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
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 (%R13),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x2(%R8,%RDI,1),%R13D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	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%)
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),%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
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
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 %R11D,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 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),%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
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 445780 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x320>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R9D	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 445cf6 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x896>	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 445609 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x1a9>	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 4455ee <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x18e>	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 4455dc <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x17c>	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 4455ca <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x16a>	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 4455b8 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x158>	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 4455a6 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x146>	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 445ce0 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x880>	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 445697 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x237>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 4456fb <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x29b>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x6,%R9D	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 445cfe <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x89e>	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 4459f9 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x599>	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 44596e <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x50e>	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 4458f1 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x491>	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 445b9c <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x73c>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c33 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x7d3>	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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445c90 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x830>	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
NOPW %CS:(%RAX,%RAX,1)	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 4454b2 <_Z25clover_unpack_message_topR16global_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 445c64 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x804>	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 445769 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x309>	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 445594 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x134>	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 4456a9 <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x249>	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 445baf <_Z25clover_unpack_message_topR16global_variablesiiiiRN6clover8Buffer2DIdEERNS1_8Buffer1DIdEEiiiiiii._omp_fn.0+0x74f>	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_top(global_variables&, int, int, int, int, clover::Buffer2D&, clover::Buffer1D&, int, int, int, int, int, int, int) [clone ._omp_fn.0]–	0.02	0.00
○Loop 326 - pack_kernel.cpp:230-230 - exec	0.01	0.01
○Loop 327 - pack_kernel.cpp:230-230 - 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