OV - exec - Function field_summary_kernel_module_mp_field_summary_kernel

	Function: field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2	Module: exec	Source: field_summary_kernel.f90:54-74	Coverage (incl. loops): 0.29% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90: 54 - 74

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

54:     !$OMP PARALLEL

55:     !$OMP DO PRIVATE(vsqrd,cell_vol,cell_mass) REDUCTION(+ : vol,mass,press,ie,ke)

56:     DO k=y_min,y_max

57:     !$OMP SIMD

58:       DO j=x_min,x_max

59:         vsqrd=0.0

60:         DO kv=k,k+1

61:           DO jv=j,j+1

62:             vsqrd=vsqrd+0.25*(xvel0(jv,kv)**2+yvel0(jv,kv)**2)

63:           ENDDO

64:         ENDDO

65:         cell_vol=volume(j,k)

66:         cell_mass=cell_vol*density0(j,k)

67:         vol=vol+cell_vol

68:         mass=mass+cell_mass

69:         ie=ie+cell_mass*energy0(j,k)

70:         ke=ke+cell_mass*0.5*vsqrd

71:         press=press+cell_vol*pressure(j,k)

72:       ENDDO

73:     ENDDO

74:   !$OMP END DO

0x4261b0 PUSH	%RBP

0x4261b1 MOV	%RSP,%RBP

0x4261b4 PUSH	%R15

0x4261b6 PUSH	%R14

0x4261b8 PUSH	%R13

0x4261ba PUSH	%R12

0x4261bc PUSH	%RBX

0x4261bd SUB	$0xd8,%RSP

0x4261c4 MOV	%R9,-0x98(%RBP)

0x4261cb MOV	%R8,-0x90(%RBP)

0x4261d2 MOV	0x60(%RBP),%EBX

0x4261d5 MOV	0x58(%RBP),%EAX

0x4261d8 SUB	%EBX,%EAX

0x4261da MOVL	$0,-0x60(%RBP)

0x4261e1 JS	42694b

0x4261e7 MOV	%RCX,%R14

0x4261ea MOV	%RDX,%R13

0x4261ed MOV	%RDI,-0x30(%RBP)

0x4261f1 MOV	(%RDI),%ESI

0x4261f3 MOVL	$0,-0x38(%RBP)

0x4261fa MOV	%EAX,-0x34(%RBP)

0x4261fd MOVL	$0x1,-0x5c(%RBP)

0x426204 SUB	$0x8,%RSP

0x426208 LEA	-0x5c(%RBP),%RAX

0x42620c LEA	-0x60(%RBP),%RCX

0x426210 LEA	-0x38(%RBP),%R8

0x426214 LEA	-0x34(%RBP),%R9

0x426218 MOV	$0x5385b0,%EDI

0x42621d MOV	%ESI,-0x54(%RBP)

0x426220 MOV	$0x22,%EDX

0x426225 PUSH	$0x1

0x426227 PUSH	$0x1

0x426229 PUSH	%RAX

0x42622a CALL	404670 <__kmpc_for_static_init_4@plt>

0x42622f ADD	$0x20,%RSP

0x426233 MOV	-0x38(%RBP),%EAX

0x426236 MOV	-0x34(%RBP),%ECX

0x426239 VXORPD	%XMM1,%XMM1,%XMM1

0x42623d VXORPD	%XMM2,%XMM2,%XMM2

0x426241 VXORPD	%XMM3,%XMM3,%XMM3

0x426245 VXORPD	%XMM5,%XMM5,%XMM5

0x426249 VXORPD	%XMM0,%XMM0,%XMM0

0x42624d SUB	%EAX,%ECX

0x42624f MOV	%ECX,-0x58(%RBP)

0x426252 JAE	42634a

0x426258 MOV	0x20(%RBP),%R15

0x42625c MOV	0x18(%RBP),%R13

0x426260 MOV	0x10(%RBP),%R14

0x426264 VMOVSD	%XMM0,-0x88(%RBP)

0x42626c VMOVSD	%XMM5,-0x80(%RBP)

0x426271 VMOVSD	%XMM3,-0x78(%RBP)

0x426276 VMOVSD	%XMM2,-0x70(%RBP)

0x42627b VMOVSD	%XMM1,-0x68(%RBP)

0x426280 MOV	$0x5385d0,%EDI

0x426285 MOV	-0x54(%RBP),%ESI

0x426288 VZEROUPPER

0x42628b CALL	404230 <__kmpc_for_static_fini@plt>

0x426290 MOV	-0x30(%RBP),%RAX

0x426294 MOV	(%RAX),%ESI

0x426296 SUB	$0x8,%RSP

0x42629a MOV	$0x591060,%RAX

0x4262a1 LEA	-0x88(%RBP),%R8

0x4262a8 MOV	$0x538690,%EDI

0x4262ad MOV	$0x426160,%R9D

0x4262b3 MOV	$0x5,%EDX

0x4262b8 MOV	$0x28,%ECX

0x4262bd PUSH	%RAX

0x4262be CALL	404830 <__kmpc_reduce@plt>

0x4262c3 ADD	$0x10,%RSP

0x4262c7 CMP	$0x2,%EAX

0x4262ca JGE	4268a7

0x4262d0 CMP	$0x1,%EAX

0x4262d3 MOV	-0x30(%RBP),%RDI

0x4262d7 JNE	42694b

0x4262dd VMOVSD	-0x88(%RBP),%XMM0

0x4262e5 VADDSD	(%R15),%XMM0,%XMM0

0x4262ea VMOVSD	%XMM0,(%R15)

0x4262ef VMOVSD	-0x80(%RBP),%XMM0

0x4262f4 VADDSD	(%R13),%XMM0,%XMM0

0x4262fa VMOVSD	%XMM0,(%R13)

0x426300 VMOVSD	-0x78(%RBP),%XMM0

0x426305 MOV	-0x90(%RBP),%RAX

0x42630c VADDSD	(%RAX),%XMM0,%XMM0

0x426310 VMOVSD	%XMM0,(%RAX)

0x426314 VMOVSD	-0x70(%RBP),%XMM0

0x426319 VADDSD	(%R14),%XMM0,%XMM0

0x42631e VMOVSD	%XMM0,(%R14)

0x426323 VMOVSD	-0x68(%RBP),%XMM0

0x426328 MOV	-0x98(%RBP),%RAX

0x42632f VADDSD	(%RAX),%XMM0,%XMM0

0x426333 VMOVSD	%XMM0,(%RAX)

0x426337 MOV	(%RDI),%ESI

0x426339 MOV	$0x591060,%RDX

0x426340 MOV	$0x5386b0,%EDI

0x426345 JMP	426942

0x42634a MOV	%RAX,%R9

0x42634d MOV	0x70(%RBP),%RSI

0x426351 MOV	0x68(%RBP),%RDI

0x426355 SAL	$0x20,%R14

0x426359 MOV	$-0x200000000,%RAX

0x426363 LEA	(%R14,%RAX,1),%RCX

0x426367 MOV	%RCX,%RDX

0x42636a SAR	$0x20,%RDX

0x42636e MOV	%RDX,-0xa0(%RBP)

0x426375 SAL	$0x20,%R13

0x426379 ADD	%R13,%RAX

0x42637c MOV	%RAX,%R11

0x42637f SAR	$0x20,%R11

0x426383 ADD	%EBX,%R9D

0x426386 MOVSXD	(%RSI),%RBX

0x426389 MOV	(%RDI),%ESI

0x42638b SUB	%EBX,%ESI

0x42638d MOV	%RSI,-0xf8(%RBP)

0x426394 INC	%ESI

0x426396 CMP	$0x2,%ESI

0x426399 MOV	$0x1,%R10D

0x42639f CMOVGE	%ESI,%R10D

0x4263a3 MOV	%R10,-0x48(%RBP)

0x4263a7 AND	$0x7ffffffc,%R10D

0x4263ae TEST	%RCX,%RCX

0x4263b1 MOV	$-0x1,%RSI

0x4263b8 CMOVNS	%RCX,%RSI

0x4263bc TEST	%RSI,%RSI

0x4263bf MOV	$0x1,%EDI

0x4263c4 CMOVG	%RDI,%RSI

0x4263c8 MOV	$0x200000000,%R15

0x4263d2 MOV	%R15,%R8

0x4263d5 SUB	%R14,%R8

0x4263d8 CMP	%R8,%RCX

0x4263db CMOVG	%RCX,%R8

0x4263df SHR	$0x20,%R8

0x4263e3 IMUL	%RSI,%R8

0x4263e7 LEA	(,%RBX,8),%RCX

0x4263ef SAL	$0x3,%R8

0x4263f3 SUB	%R8,%RCX

0x4263f6 MOV	$0x1,%ESI

0x4263fb MOV	%R11,-0xa8(%RBP)

0x426402 SUB	%R11,%RSI

0x426405 MOV	%RSI,-0xc0(%RBP)

0x42640c MOV	0x28(%RBP),%RSI

0x426410 ADD	%RCX,%RSI

0x426413 MOV	%RSI,-0xb8(%RBP)

0x42641a ADD	0x30(%RBP),%RCX

0x42641e MOV	%RCX,-0xc8(%RBP)

0x426425 TEST	%RAX,%RAX

0x426428 MOV	$-0x1,%RCX

0x42642f CMOVNS	%RAX,%RCX

0x426433 TEST	%RCX,%RCX

0x426436 CMOVG	%RDI,%RCX

0x42643a SUB	%R13,%R15

0x42643d CMP	%R15,%RAX

0x426440 CMOVG	%RAX,%R15

0x426444 SHR	$0x20,%R15

0x426448 IMUL	%RCX,%R15

0x42644c VPBROADCASTD	%EBX,%XMM0

0x426452 VPMOVSXDQ	%XMM0,%YMM4

0x426457 NEG	%R15

0x42645a MOV	%R15,-0xd0(%RBP)

0x426461 SUB	%RDX,%RBX

0x426464 MOV	%RBX,-0xd8(%RBP)

0x42646b VPXOR	%XMM0,%XMM0,%XMM0

0x42646f VMOVSD	0xd4959(%RIP),%XMM6

0x426477 VMOVDQA	0xd0b01(%RIP),%YMM7

0x42647f VBROADCASTSD	0xd4948(%RIP),%YMM8

0x426488 VPBROADCASTQ	0xd4947(%RIP),%YMM9

0x426491 XOR	%EAX,%EAX

0x426493 MOV	%RAX,-0x50(%RBP)

0x426497 MOV	%R9,-0xb0(%RBP)

0x42649e MOV	%R9D,%R13D

0x4264a1 JMP	4264c9

0x4264a3 NOPW	%CS:(%RAX,%RAX,1)

(177) 0x4264b0 MOV	-0x50(%RBP),%RAX

(177) 0x4264b4 LEA	0x1(%RAX),%ECX

(177) 0x4264b7 INC	%R13D

(177) 0x4264ba CMP	-0x58(%RBP),%EAX

(177) 0x4264bd MOV	%ECX,%EAX

(177) 0x4264bf MOV	%RAX,-0x50(%RBP)

(177) 0x4264c3 JE	426258

(177) 0x4264c9 CMPL	$0,-0xf8(%RBP)

(177) 0x4264d0 JS	4264b0

(177) 0x4264d2 MOV	0x78(%RBP),%RCX

(177) 0x4264d6 MOV	(%RCX),%R8

(177) 0x4264d9 MOV	0x80(%RBP),%RCX

(177) 0x4264e0 MOV	(%RCX),%R11

(177) 0x4264e3 MOV	0x88(%RBP),%RCX

(177) 0x4264ea MOV	(%RCX),%RBX

(177) 0x4264ed MOV	0x90(%RBP),%RCX

(177) 0x4264f4 MOV	(%RCX),%R15

(177) 0x4264f7 MOV	0x98(%RBP),%RCX

(177) 0x4264fe MOV	(%RCX),%RDI

(177) 0x426501 MOV	0xa0(%RBP),%RCX

(177) 0x426508 MOV	(%RCX),%RAX

(177) 0x42650b CMPL	$0x4,-0x48(%RBP)

(177) 0x42650f MOV	%R8,-0x40(%RBP)

(177) 0x426513 MOV	%RDI,-0x100(%RBP)

(177) 0x42651a JAE	426530

(177) 0x42651c XOR	%ECX,%ECX

(177) 0x42651e JMP	426751

0x426523 NOPW	%CS:(%RAX,%RAX,1)

(177) 0x426530 MOV	-0xb0(%RBP),%RCX

(177) 0x426537 MOV	%RAX,%RDX

(177) 0x42653a MOV	-0x50(%RBP),%RAX

(177) 0x42653e ADD	%EAX,%ECX

(177) 0x426540 MOVSXD	%ECX,%RCX

(177) 0x426543 SUB	-0xa8(%RBP),%RCX

(177) 0x42654a MOV	%R8,%R12

(177) 0x42654d IMUL	%RCX,%R12

(177) 0x426551 MOV	0x30(%RBP),%R14

(177) 0x426555 ADD	%R14,%R12

(177) 0x426558 MOV	%R11,%RAX

(177) 0x42655b IMUL	%RCX,%R11

(177) 0x42655f MOV	%RDI,%RSI

(177) 0x426562 MOV	0x28(%RBP),%RDI

(177) 0x426566 ADD	%RDI,%R11

(177) 0x426569 LEA	0x1(%RCX),%R9

(177) 0x42656d IMUL	%R9,%R8

(177) 0x426571 ADD	%R14,%R8

(177) 0x426574 MOV	%RAX,-0xe0(%RBP)

(177) 0x42657b IMUL	%RAX,%R9

(177) 0x42657f MOV	%RDX,%RAX

(177) 0x426582 MOV	-0xa0(%RBP),%RDX

(177) 0x426589 ADD	%RDI,%R9

(177) 0x42658c MOV	%RBX,-0xf0(%RBP)

(177) 0x426593 IMUL	%RCX,%RBX

(177) 0x426597 ADD	0x50(%RBP),%RBX

(177) 0x42659b MOV	%R15,-0xe8(%RBP)

(177) 0x4265a2 MOV	%R15,%R14

(177) 0x4265a5 IMUL	%RCX,%R14

(177) 0x4265a9 ADD	0x48(%RBP),%R14

(177) 0x4265ad MOV	%RSI,%RDI

(177) 0x4265b0 IMUL	%RCX,%RDI

(177) 0x4265b4 ADD	0x40(%RBP),%RDI

(177) 0x4265b8 IMUL	%RAX,%RCX

(177) 0x4265bc ADD	0x38(%RBP),%RCX

(177) 0x4265c0 VXORPD	%XMM14,%XMM14,%XMM14

(177) 0x4265c5 VXORPD	%XMM13,%XMM13,%XMM13

(177) 0x4265ca VXORPD	%XMM12,%XMM12,%XMM12

(177) 0x4265cf VXORPD	%XMM11,%XMM11,%XMM11

(177) 0x4265d4 VXORPD	%XMM10,%XMM10,%XMM10

(177) 0x4265d9 XOR	%ESI,%ESI

(177) 0x4265db VMOVDQA	%YMM7,%YMM15

(177) 0x4265df NOP

  (178) 0x4265e0 VPADDQ	%XMM4,%XMM15,%XMM16

  (178) 0x4265e6 VMOVQ	%XMM16,%R15

  (178) 0x4265ec SUB	%RDX,%R15

  (178) 0x4265ef VMOVUPD	(%R12,%R15,8),%YMM16

  (178) 0x4265f6 VMOVUPD	0x8(%R12,%R15,8),%YMM17

  (178) 0x426601 VMOVUPD	(%R11,%R15,8),%YMM18

  (178) 0x426608 VMOVUPD	0x8(%R11,%R15,8),%YMM19

  (178) 0x426613 VMOVUPD	(%R8,%R15,8),%YMM20

  (178) 0x42661a VMOVUPD	0x8(%R8,%R15,8),%YMM21

  (178) 0x426625 VMOVUPD	(%R9,%R15,8),%YMM22

  (178) 0x42662c VMOVUPD	0x8(%R9,%R15,8),%YMM23

  (178) 0x426637 VMOVUPD	(%RBX,%R15,8),%YMM24

  (178) 0x42663e VMULPD	(%R14,%R15,8),%YMM24,%YMM25

  (178) 0x426645 VFMADD231PD	(%RDI,%R15,8),%YMM25,%YMM12

  (178) 0x42664c VFMADD231PD	(%RCX,%R15,8),%YMM24,%YMM14

  (178) 0x426653 VMULPD	%YMM16,%YMM16,%YMM16

  (178) 0x426659 VFMADD213PD	%YMM16,%YMM18,%YMM18

  (178) 0x42665f VFMADD231PD	%YMM17,%YMM17,%YMM18

  (178) 0x426665 VFMADD231PD	%YMM19,%YMM19,%YMM18

  (178) 0x42666b VFMADD213PD	%YMM18,%YMM20,%YMM20

  (178) 0x426671 VFMADD213PD	%YMM20,%YMM22,%YMM22

  (178) 0x426677 VFMADD231PD	%YMM21,%YMM21,%YMM22

  (178) 0x42667d VFMADD231PD	%YMM23,%YMM23,%YMM22

  (178) 0x426683 VADDPD	%YMM24,%YMM10,%YMM10

  (178) 0x426689 VADDPD	%YMM25,%YMM11,%YMM11

  (178) 0x42668f VMULPD	%YMM22,%YMM25,%YMM16

  (178) 0x426695 VFMADD231PD	%YMM8,%YMM16,%YMM13

  (178) 0x42669b VPADDQ	%YMM9,%YMM15,%YMM15

  (178) 0x4266a0 ADD	$0x4,%RSI

  (178) 0x4266a4 CMP	%R10,%RSI

  (178) 0x4266a7 JB	4265e0

(177) 0x4266ad VEXTRACTF128	$0x1,%YMM14,%XMM15

(177) 0x4266b3 VADDPD	%XMM15,%XMM14,%XMM14

(177) 0x4266b8 VSHUFPD	$0x1,%XMM14,%XMM14,%XMM15

(177) 0x4266be VADDSD	%XMM15,%XMM14,%XMM14

(177) 0x4266c3 VADDSD	%XMM3,%XMM14,%XMM3

(177) 0x4266c7 VEXTRACTF128	$0x1,%YMM13,%XMM14

(177) 0x4266cd VADDPD	%XMM14,%XMM13,%XMM13

(177) 0x4266d2 VSHUFPD	$0x1,%XMM13,%XMM13,%XMM14

(177) 0x4266d8 VADDSD	%XMM14,%XMM13,%XMM13

(177) 0x4266dd VADDSD	%XMM1,%XMM13,%XMM1

(177) 0x4266e1 VEXTRACTF128	$0x1,%YMM12,%XMM13

(177) 0x4266e7 VADDPD	%XMM13,%XMM12,%XMM12

(177) 0x4266ec VSHUFPD	$0x1,%XMM12,%XMM12,%XMM13

(177) 0x4266f2 VADDSD	%XMM13,%XMM12,%XMM12

(177) 0x4266f7 VADDSD	%XMM2,%XMM12,%XMM2

(177) 0x4266fb VEXTRACTF128	$0x1,%YMM11,%XMM12

(177) 0x426701 VADDPD	%XMM12,%XMM11,%XMM11

(177) 0x426706 VSHUFPD	$0x1,%XMM11,%XMM11,%XMM12

(177) 0x42670c VADDSD	%XMM12,%XMM11,%XMM11

(177) 0x426711 VADDSD	%XMM5,%XMM11,%XMM5

(177) 0x426715 VEXTRACTF128	$0x1,%YMM10,%XMM11

(177) 0x42671b VADDPD	%XMM11,%XMM10,%XMM10

(177) 0x426720 VSHUFPD	$0x1,%XMM10,%XMM10,%XMM11

(177) 0x426726 VADDSD	%XMM11,%XMM10,%XMM10

(177) 0x42672b VADDSD	%XMM0,%XMM10,%XMM0

(177) 0x42672f MOV	%R10,%RCX

(177) 0x426732 CMP	-0x48(%RBP),%R10

(177) 0x426736 MOV	-0xf0(%RBP),%RBX

(177) 0x42673d MOV	-0xe8(%RBP),%R15

(177) 0x426744 MOV	-0xe0(%RBP),%R11

(177) 0x42674b JE	4264b0

(177) 0x426751 MOVSXD	%R13D,%RDI

(177) 0x426754 MOV	-0xc0(%RBP),%RSI

(177) 0x42675b ADD	%RDI,%RSI

(177) 0x42675e ADD	-0xd0(%RBP),%RDI

(177) 0x426765 MOV	%R11,%R8

(177) 0x426768 IMUL	%RSI,%R8

(177) 0x42676c MOV	%RAX,%RDX

(177) 0x42676f MOV	-0x40(%RBP),%RAX

(177) 0x426773 IMUL	%RAX,%RSI

(177) 0x426777 IMUL	%RDI,%R11

(177) 0x42677b IMUL	%RDI,%RAX

(177) 0x42677f IMUL	%RDI,%RDX

(177) 0x426783 MOV	%R13D,-0x40(%RBP)

(177) 0x426787 MOV	-0x100(%RBP),%R13

(177) 0x42678e IMUL	%RDI,%R13

(177) 0x426792 IMUL	%RDI,%R15

(177) 0x426796 IMUL	%RDI,%RBX

(177) 0x42679a MOV	-0x48(%RBP),%RDI

(177) 0x42679e SUB	%RCX,%RDI

(177) 0x4267a1 LEA	(%R8,%RCX,8),%R8

(177) 0x4267a5 MOV	-0xb8(%RBP),%R14

(177) 0x4267ac ADD	%R14,%R8

(177) 0x4267af LEA	(%RSI,%RCX,8),%R9

(177) 0x4267b3 MOV	%RBX,%R12

(177) 0x4267b6 MOV	-0xc8(%RBP),%RBX

(177) 0x4267bd ADD	%RBX,%R9

(177) 0x4267c0 LEA	(%R11,%RCX,8),%R11

(177) 0x4267c4 ADD	%R14,%R11

(177) 0x4267c7 LEA	(%RAX,%RCX,8),%RSI

(177) 0x4267cb ADD	%RBX,%RSI

(177) 0x4267ce ADD	-0xd8(%RBP),%RCX

(177) 0x4267d5 LEA	(%RDX,%RCX,8),%RBX

(177) 0x4267d9 ADD	0x38(%RBP),%RBX

(177) 0x4267dd LEA	(,%RCX,8),%R14

(177) 0x4267e5 ADD	%R13,%R14

(177) 0x4267e8 MOV	-0x40(%RBP),%R13D

(177) 0x4267ec ADD	0x40(%RBP),%R14

(177) 0x4267f0 LEA	(%R15,%RCX,8),%R15

(177) 0x4267f4 ADD	0x48(%RBP),%R15

(177) 0x4267f8 LEA	(%R12,%RCX,8),%RCX

(177) 0x4267fc ADD	0x50(%RBP),%RCX

(177) 0x426800 XOR	%R12D,%R12D

(177) 0x426803 NOPW	%CS:(%RAX,%RAX,1)

  (179) 0x426810 VMOVSD	(%RSI,%R12,8),%XMM10

  (179) 0x426816 VMOVSD	0x8(%RSI,%R12,8),%XMM11

  (179) 0x42681d VMOVSD	(%R11,%R12,8),%XMM12

  (179) 0x426823 VMOVSD	0x8(%R11,%R12,8),%XMM13

  (179) 0x42682a VMULSD	%XMM10,%XMM10,%XMM10

  (179) 0x42682f VFMADD213SD	%XMM10,%XMM12,%XMM12

  (179) 0x426834 VFMADD231SD	%XMM11,%XMM11,%XMM12

  (179) 0x426839 VFMADD231SD	%XMM13,%XMM13,%XMM12

  (179) 0x42683e VMOVSD	(%R9,%R12,8),%XMM10

  (179) 0x426844 VMOVSD	0x8(%R9,%R12,8),%XMM11

  (179) 0x42684b VMOVSD	(%R8,%R12,8),%XMM13

  (179) 0x426851 VMOVSD	0x8(%R8,%R12,8),%XMM14

  (179) 0x426858 VFMADD213SD	%XMM12,%XMM10,%XMM10

  (179) 0x42685d VFMADD213SD	%XMM10,%XMM13,%XMM13

  (179) 0x426862 VFMADD231SD	%XMM11,%XMM11,%XMM13

  (179) 0x426867 VFMADD231SD	%XMM14,%XMM14,%XMM13

  (179) 0x42686c VMOVSD	(%RCX,%R12,8),%XMM10

  (179) 0x426872 VMULSD	(%R15,%R12,8),%XMM10,%XMM11

  (179) 0x426878 VADDSD	%XMM0,%XMM10,%XMM0

  (179) 0x42687c VADDSD	%XMM5,%XMM11,%XMM5

  (179) 0x426880 VFMADD231SD	(%R14,%R12,8),%XMM11,%XMM2

  (179) 0x426886 VMULSD	%XMM13,%XMM11,%XMM11

  (179) 0x42688b VFMADD231SD	%XMM6,%XMM11,%XMM1

  (179) 0x426890 VFMADD231SD	(%RBX,%R12,8),%XMM10,%XMM3

  (179) 0x426896 INC	%R12

  (179) 0x426899 CMP	%R12,%RDI

  (179) 0x42689c JNE	426810

(177) 0x4268a2 JMP	4264b0

0x4268a7 MOV	-0x30(%RBP),%RDI

0x4268ab JNE	42694b

0x4268b1 VMOVSD	-0x88(%RBP),%XMM0

0x4268b9 MOV	(%RDI),%ESI

0x4268bb MOV	$0x5385f0,%EDI

0x4268c0 MOV	%R15,%RDX

0x4268c3 CALL	404330 <__kmpc_atomic_float8_add@plt>

0x4268c8 VMOVSD	-0x80(%RBP),%XMM0

0x4268cd MOV	-0x30(%RBP),%RAX

0x4268d1 MOV	(%RAX),%ESI

0x4268d3 MOV	$0x538610,%EDI

0x4268d8 MOV	%R13,%RDX

0x4268db CALL	404330 <__kmpc_atomic_float8_add@plt>

0x4268e0 VMOVSD	-0x78(%RBP),%XMM0

0x4268e5 MOV	-0x30(%RBP),%RAX

0x4268e9 MOV	(%RAX),%ESI

0x4268eb MOV	$0x538630,%EDI

0x4268f0 MOV	-0x90(%RBP),%RDX

0x4268f7 CALL	404330 <__kmpc_atomic_float8_add@plt>

0x4268fc VMOVSD	-0x70(%RBP),%XMM0

0x426901 MOV	-0x30(%RBP),%RAX

0x426905 MOV	(%RAX),%ESI

0x426907 MOV	$0x538650,%EDI

0x42690c MOV	%R14,%RDX

0x42690f CALL	404330 <__kmpc_atomic_float8_add@plt>

0x426914 VMOVSD	-0x68(%RBP),%XMM0

0x426919 MOV	-0x30(%RBP),%RAX

0x42691d MOV	(%RAX),%ESI

0x42691f MOV	$0x538670,%EDI

0x426924 MOV	-0x98(%RBP),%RDX

0x42692b CALL	404330 <__kmpc_atomic_float8_add@plt>

0x426930 MOV	-0x30(%RBP),%RAX

0x426934 MOV	(%RAX),%ESI

0x426936 MOV	$0x591060,%RDX

0x42693d MOV	$0x5386d0,%EDI

0x426942 CALL	4049b0 <__kmpc_end_reduce@plt>

0x426947 MOV	-0x30(%RBP),%RDI

0x42694b MOV	(%RDI),%ESI

0x42694d MOV	$0x5386f0,%EDI

0x426952 CALL	404740 <__kmpc_barrier@plt>

0x426957 ADD	$0xd8,%RSP

0x42695e POP	%RBX

0x42695f POP	%R12

0x426961 POP	%R13

0x426963 POP	%R14

0x426965 POP	%R15

0x426967 POP	%RBP

0x426968 RET

0x426969 NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►51.00+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►36.72+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
►5.72+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
►3.28+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	field_summary_kernel	field_summary_kernel.f90:77	exec
○	field_summary	field_summary.f90:70	exec
○	hydro	hydro.f90:81	exec
○	main		exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		exec
►2.40+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

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 0.00% of application time for run icx_0

Source file and lines	field_summary_kernel.f90:54-74
Module	exec

The function is defined in /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:54-74.

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 29.25 to 7.50 cycles (3.90x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)
To reference allocatable arrays, use "allocatable" instead of "pointer" pointers or qualify them with the "contiguous" attribute (Fortran 2008)
For structures, limit to one indirection. For example, use a_b%c instead of a%b%c with a_b set to a%b before this function

Vectorization

Your function is probably not vectorized. Only 12% of vector register length is used (average across all SSE/AVX instructions).

Details

Store and arithmetical SSE/AVX instructions are used in scalar version (process only one data element in vector registers).

Workaround

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

Execution units bottlenecks

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

512-bits vectorization

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

Workaround

Recompile with -qopt-zmm-usage=high

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.

__kmpc_atomic_float8_add@plt: 5 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_barrier@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_end_reduce@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_for_static_fini@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_for_static_init_4@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:57
__kmpc_reduce@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74

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.

CMOVG: 4 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:58
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:58
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:56
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:56
CMOVGE: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:58
VPBROADCASTD: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:56

Type of elements and instruction set

5 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 5 FP arithmetical operations:

5: addition or subtraction

The binary function is loading 404 bytes (50 double precision FP elements). The binary function is storing 216 bytes (27 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	221
nb uops	234
loop length	982
used x86 registers	16
used mmx registers	0
used xmm registers	6
used ymm registers	4
used zmm registers	0
nb stack references	34

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	29.25 cycles
front end	29.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	17.00	17.00	17.00	17.00	17.00	17.00	24.00	24.00	24.00	24.00	0.00	3.00	2.50	2.50	5.00	5.00
cycles	17.00	17.00	17.00	17.00	17.00	17.00	24.00	24.00	24.00	24.00	0.00	3.00	2.50	2.50	5.00	5.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	29.25
Dispatch	24.00
Overall L1	29.25

Vectorization ratios

INT

all	5%
load	16%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	15%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	83%

INT+FP

all	9%
load	4%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	18%

Vector efficiency ratios

INT

all	11%
load	17%
store	10%
mul	12%
add-sub	10%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	14%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

INT+FP

all	12%
load	13%
store	11%
mul	12%
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 29.25 cycles. At this rate:

5% of peak load performance is reached (13.81 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.38 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 29.25 to 24.00 cycles (1.22x speedup).

ASM code

In the binary file, the address of the function is: 4261b0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0xd8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R8,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x60(%RBP),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x58(%RBP),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SUB %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
JS 42694b <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x79b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOVL $0,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
MOV %EAX,-0x34(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
MOVL $0x1,-0x5c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x5c(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x60(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x34(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x5385b0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %ESI,-0x54(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 404670 <__kmpc_for_static_init_4@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV -0x34(%RBP),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (6.3%)
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM5,%XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SUB %EAX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %ECX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
JAE 42634a <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x19a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x20(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VMOVSD %XMM0,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM5,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM3,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM2,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM1,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV $0x5385d0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x54(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404230 <__kmpc_for_static_fini@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x591060,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x88(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x538690,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x426160,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x5,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x28,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 404830 <__kmpc_reduce@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
ADD $0x10,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JGE 4268a7 <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x6f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
JNE 42694b <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x79b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD -0x88(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R15),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%R15)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x80(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R13),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%R13)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x78(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x90(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VADDSD (%RAX),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x70(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R14),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%R14)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x68(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x98(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VADDSD (%RAX),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x591060,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x5386b0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 426942 <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x792>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x70(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x68(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SAL $0x20,%R14	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $-0x200000000,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R14,%RAX,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAR $0x20,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %RDX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
SAL $0x20,%R13	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAR $0x20,%R11	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %EBX,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOVSXD (%RSI),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SUB %EBX,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
INC %ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x2,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x1,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMOVGE %ESI,%R10D	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (6.3%)
MOV %R10,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
AND $0x7ffffffc,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $-0x1,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVNS %RCX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %RSI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %RDI,%RSI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x200000000,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %R14,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMP %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RCX,%R8	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
SHR $0x20,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
IMUL %RSI,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
LEA (,%RBX,8),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
SUB %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x1,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
SUB %R11,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x28(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
ADD %RCX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
ADD 0x30(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $-0x1,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMOVNS %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RDI,%RCX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
SUB %R13,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RAX,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
SHR $0x20,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RCX,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
VPBROADCASTD %EBX,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (6.3%)
VPMOVSXDQ %XMM0,%YMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	2	0.50	vect (25.0%)
NEG %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
SUB %RDX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
VPXOR %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	vect (25.0%)
VMOVSD 0xd4959(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDQA 0xd0b01(%RIP),%YMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.50	vect (50.0%)
VBROADCASTSD 0xd4948(%RIP),%YMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
VPBROADCASTQ 0xd4947(%RIP),%YMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R9,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R9D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 4264c9 <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x319>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
JNE 42694b <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x79b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD -0x88(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x5385f0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x80(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538610,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x78(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538630,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x90(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x70(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538650,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x68(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538670,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x98(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x591060,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x5386d0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4049b0 <__kmpc_end_reduce@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x5386f0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404740 <__kmpc_barrier@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
ADD $0xd8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_0

Source file and lines	field_summary_kernel.f90:54-74
Module	exec

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 29.25 to 7.50 cycles (3.90x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)
To reference allocatable arrays, use "allocatable" instead of "pointer" pointers or qualify them with the "contiguous" attribute (Fortran 2008)
For structures, limit to one indirection. For example, use a_b%c instead of a%b%c with a_b set to a%b before this function

Vectorization

Your function is probably not vectorized. Only 12% of vector register length is used (average across all SSE/AVX instructions).

Details

Store and arithmetical SSE/AVX instructions are used in scalar version (process only one data element in vector registers).

Workaround

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

Execution units bottlenecks

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

512-bits vectorization

Workaround

Recompile with -qopt-zmm-usage=high

CALL instructions

Detected function call instructions.

Details

__kmpc_atomic_float8_add@plt: 5 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_barrier@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_end_reduce@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_for_static_fini@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74
__kmpc_for_static_init_4@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:57
__kmpc_reduce@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:74

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.

CMOVG: 4 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:58
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:58
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:56
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:56
CMOVGE: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:58
VPBROADCASTD: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/174-049-0948/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/field_summary_kernel.f90:56

Type of elements and instruction set

5 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 5 FP arithmetical operations:

5: addition or subtraction

The binary function is loading 404 bytes (50 double precision FP elements). The binary function is storing 216 bytes (27 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	221
nb uops	234
loop length	982
used x86 registers	16
used mmx registers	0
used xmm registers	6
used ymm registers	4
used zmm registers	0
nb stack references	34

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	29.25 cycles
front end	29.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	17.00	17.00	17.00	17.00	17.00	17.00	24.00	24.00	24.00	24.00	0.00	3.00	2.50	2.50	5.00	5.00
cycles	17.00	17.00	17.00	17.00	17.00	17.00	24.00	24.00	24.00	24.00	0.00	3.00	2.50	2.50	5.00	5.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	29.25
Dispatch	24.00
Overall L1	29.25

Vectorization ratios

INT

all	5%
load	16%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	15%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	83%

INT+FP

all	9%
load	4%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	18%

Vector efficiency ratios

INT

all	11%
load	17%
store	10%
mul	12%
add-sub	10%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	14%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

INT+FP

all	12%
load	13%
store	11%
mul	12%
add-sub	11%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 29.25 cycles. At this rate:

5% of peak load performance is reached (13.81 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.38 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: 4261b0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0xd8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R9,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R8,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x60(%RBP),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x58(%RBP),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SUB %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
JS 42694b <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x79b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOVL $0,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
MOV %EAX,-0x34(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
MOVL $0x1,-0x5c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x5c(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x60(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x34(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x5385b0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %ESI,-0x54(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 404670 <__kmpc_for_static_init_4@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV -0x34(%RBP),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (6.3%)
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM2,%XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM5,%XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SUB %EAX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %ECX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (6.3%)
JAE 42634a <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x19a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV 0x20(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VMOVSD %XMM0,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM5,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM3,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM2,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD %XMM1,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV $0x5385d0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x54(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404230 <__kmpc_for_static_fini@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x591060,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x88(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x538690,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x426160,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x5,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x28,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 404830 <__kmpc_reduce@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
ADD $0x10,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JGE 4268a7 <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x6f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
JNE 42694b <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x79b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD -0x88(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R15),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%R15)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x80(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R13),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%R13)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x78(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x90(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VADDSD (%RAX),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x70(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R14),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%R14)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
VMOVSD -0x68(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x98(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
VADDSD (%RAX),%XMM0,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x591060,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x5386b0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 426942 <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x792>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x70(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV 0x68(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SAL $0x20,%R14	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $-0x200000000,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%R14,%RAX,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAR $0x20,%RDX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %RDX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
SAL $0x20,%R13	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAR $0x20,%R11	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD %EBX,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOVSXD (%RSI),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
SUB %EBX,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
INC %ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x2,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x1,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMOVGE %ESI,%R10D	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (6.3%)
MOV %R10,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
AND $0x7ffffffc,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $-0x1,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVNS %RCX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %RSI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVG %RDI,%RSI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x200000000,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %R14,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMP %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RCX,%R8	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
SHR $0x20,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
IMUL %RSI,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
LEA (,%RBX,8),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x3,%R8	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
SUB %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x1,%ESI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R11,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
SUB %R11,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x28(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
ADD %RCX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RSI,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
ADD 0x30(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $-0x1,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CMOVNS %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
TEST %RCX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RDI,%RCX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
SUB %R13,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %RAX,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
SHR $0x20,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.33	N/A
IMUL %RCX,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	0	3	0.33	N/A
VPBROADCASTD %EBX,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	1	1	scal (6.3%)
VPMOVSXDQ %XMM0,%YMM4	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	2	0.50	vect (25.0%)
NEG %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
SUB %RDX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RBX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
VPXOR %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	vect (25.0%)
VMOVSD 0xd4959(%RIP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
VMOVDQA 0xd0b01(%RIP),%YMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.50	vect (50.0%)
VBROADCASTSD 0xd4948(%RIP),%YMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
VPBROADCASTQ 0xd4947(%RIP),%YMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	1	0.50	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R9,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %R9D,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 4264c9 <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x319>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
JNE 42694b <field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2+0x79b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD -0x88(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x5385f0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x80(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538610,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x78(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538630,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x90(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x70(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538650,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x68(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x538670,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x98(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	scal (12.5%)
CALL 404330 <__kmpc_atomic_float8_add@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x591060,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x5386d0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 4049b0 <__kmpc_end_reduce@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	3	0.25	N/A
MOV $0x5386f0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 404740 <__kmpc_barrier@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0.50	N/A
ADD $0xd8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼field_summary_kernel_module_mp_field_summary_kernel_.DIR.OMP.PARALLEL.2–	0.29	0.12
▼Loop 177 - field_summary_kernel.f90:56-71 - exec–	0.00	0.01
○Loop 178 - field_summary_kernel.f90:58-71 - exec	0.29	0.11
○Loop 179 - field_summary_kernel.f90:58-71 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code