OV - exec - Function reset_field_kernel_module_mp_reset_field_kernel

	Function: reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2	Module: exec	Source: reset_field_kernel.f90:47-66	Coverage (incl. loops): 5.26% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90: 47 - 66

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

47:     !$OMP PARALLEL

48:     !$OMP DO

49:     DO k=y_min,y_max

50:     !$OMP SIMD

51:       DO j=x_min,x_max

52:         density0(j,k)=density1(j,k)

53:         energy0(j,k)=energy1(j,k)

54:       ENDDO

55:     ENDDO

56:     !$OMP END DO

57:

58:     !$OMP DO

59:     DO k=y_min,y_max+1

60:     !$OMP SIMD

61:       DO j=x_min,x_max+1

62:         xvel0(j,k)=xvel1(j,k)

63:         yvel0(j,k)=yvel1(j,k)

64:       ENDDO

65:     ENDDO

66:   !$OMP END DO

0x435870 PUSH	%RBP

0x435871 MOV	%RSP,%RBP

0x435874 PUSH	%R15

0x435876 PUSH	%R14

0x435878 PUSH	%R13

0x43587a PUSH	%R12

0x43587c PUSH	%RBX

0x43587d SUB	$0x128,%RSP

0x435884 MOV	%R9,-0xd0(%RBP)

0x43588b MOV	%RCX,-0xc8(%RBP)

0x435892 MOV	%RDI,%RBX

0x435895 MOV	0xc8(%RBP),%RAX

0x43589c MOV	%RAX,-0x150(%RBP)

0x4358a3 MOV	0xc0(%RBP),%RAX

0x4358aa MOV	%RAX,-0x148(%RBP)

0x4358b1 MOV	0xb8(%RBP),%RAX

0x4358b8 MOV	%RAX,-0x140(%RBP)

0x4358bf MOV	0xb0(%RBP),%RAX

0x4358c6 MOV	%RAX,-0x138(%RBP)

0x4358cd MOV	0x88(%RBP),%RAX

0x4358d4 MOV	%RAX,-0x98(%RBP)

0x4358db MOV	0x80(%RBP),%RAX

0x4358e2 MOV	%RAX,-0x70(%RBP)

0x4358e6 MOV	0x78(%RBP),%RAX

0x4358ea MOV	%RAX,-0x90(%RBP)

0x4358f1 MOV	0x70(%RBP),%RAX

0x4358f5 MOV	%RAX,-0x88(%RBP)

0x4358fc MOV	0x58(%RBP),%EAX

0x4358ff MOV	0x50(%RBP),%R14D

0x435903 MOV	%EAX,-0x2c(%RBP)

0x435906 SUB	%EAX,%R14D

0x435909 MOV	0x68(%RBP),%RAX

0x43590d MOV	%RAX,-0xb8(%RBP)

0x435914 MOV	0x60(%RBP),%RAX

0x435918 MOV	%RAX,-0xc0(%RBP)

0x43591f MOV	0x48(%RBP),%RAX

0x435923 MOV	%RAX,-0x60(%RBP)

0x435927 MOV	0x40(%RBP),%RAX

0x43592b MOV	%RAX,-0x58(%RBP)

0x43592f MOV	0x38(%RBP),%RAX

0x435933 MOV	%RAX,-0x50(%RBP)

0x435937 MOV	0x30(%RBP),%RAX

0x43593b MOV	%RAX,-0x48(%RBP)

0x43593f MOV	0x28(%RBP),%RAX

0x435943 MOV	%RAX,-0xf8(%RBP)

0x43594a MOV	0x20(%RBP),%RAX

0x43594e MOV	%RAX,-0xf0(%RBP)

0x435955 MOV	0x18(%RBP),%RAX

0x435959 MOV	%RAX,-0xe8(%RBP)

0x435960 MOV	0x10(%RBP),%RAX

0x435964 MOV	%RAX,-0xe0(%RBP)

0x43596b MOVL	$0,-0xa8(%RBP)

0x435975 MOV	%RDI,-0xd8(%RBP)

0x43597c JS	435a07

0x435982 MOV	(%RBX),%ESI

0x435984 MOVL	$0,-0x34(%RBP)

0x43598b MOV	%R14D,-0xa0(%RBP)

0x435992 MOV	%R14D,-0x30(%RBP)

0x435996 MOVL	$0x1,-0xa4(%RBP)

0x4359a0 SUB	$0x8,%RSP

0x4359a4 LEA	-0xa4(%RBP),%RAX

0x4359ab LEA	-0xa8(%RBP),%RCX

0x4359b2 LEA	-0x34(%RBP),%R8

0x4359b6 LEA	-0x30(%RBP),%R9

0x4359ba MOV	$0x53be10,%EDI

0x4359bf MOV	%ESI,-0x9c(%RBP)

0x4359c5 MOV	$0x22,%EDX

0x4359ca PUSH	$0x1

0x4359cc PUSH	$0x1

0x4359ce PUSH	%RAX

0x4359cf CALL	404850 <__kmpc_for_static_init_4@plt>

0x4359d4 ADD	$0x20,%RSP

0x4359d8 MOV	-0x34(%RBP),%EAX

0x4359db MOV	-0x30(%RBP),%ECX

0x4359de SUB	%EAX,%ECX

0x4359e0 JAE	435ac0

0x4359e6 MOV	$0x53be30,%EDI

0x4359eb MOV	-0x9c(%RBP),%ESI

0x4359f1 VZEROUPPER

0x4359f4 CALL	404070 <__kmpc_for_static_fini@plt>

0x4359f9 MOV	-0xd8(%RBP),%RBX

0x435a00 MOV	-0xa0(%RBP),%R14D

0x435a07 MOV	(%RBX),%ESI

0x435a09 MOV	$0x53be50,%EDI

0x435a0e CALL	4047c0 <__kmpc_barrier@plt>

0x435a13 INC	%R14D

0x435a16 MOVL	$0,-0xb0(%RBP)

0x435a20 JS	435a93

0x435a22 MOV	(%RBX),%ESI

0x435a24 MOVL	$0,-0x3c(%RBP)

0x435a2b MOV	%R14D,-0x38(%RBP)

0x435a2f MOVL	$0x1,-0xac(%RBP)

0x435a39 SUB	$0x8,%RSP

0x435a3d LEA	-0xac(%RBP),%RAX

0x435a44 LEA	-0xb0(%RBP),%RCX

0x435a4b LEA	-0x3c(%RBP),%R8

0x435a4f LEA	-0x38(%RBP),%R9

0x435a53 MOV	$0x53be70,%EDI

0x435a58 MOV	%ESI,-0x78(%RBP)

0x435a5b MOV	$0x22,%EDX

0x435a60 PUSH	$0x1

0x435a62 PUSH	$0x1

0x435a64 PUSH	%RAX

0x435a65 CALL	404850 <__kmpc_for_static_init_4@plt>

0x435a6a ADD	$0x20,%RSP

0x435a6e MOV	-0x3c(%RBP),%EAX

0x435a71 MOV	-0x38(%RBP),%ECX

0x435a74 SUB	%EAX,%ECX

0x435a76 JAE	435d40

0x435a7c MOV	$0x53be90,%EDI

0x435a81 MOV	-0x78(%RBP),%ESI

0x435a84 VZEROUPPER

0x435a87 CALL	404070 <__kmpc_for_static_fini@plt>

0x435a8c MOV	-0xd8(%RBP),%RBX

0x435a93 MOV	(%RBX),%ESI

0x435a95 MOV	$0x53beb0,%EDI

0x435a9a ADD	$0x128,%RSP

0x435aa1 POP	%RBX

0x435aa2 POP	%R12

0x435aa4 POP	%R13

0x435aa6 POP	%R14

0x435aa8 POP	%R15

0x435aaa POP	%RBP

0x435aab JMP	4047c0

0x435ab0 NOPW	%CS:(%RAX,%RAX,1)

0x435abf NOP

0x435ac0 MOV	%RAX,%RDI

0x435ac3 MOV	-0xb8(%RBP),%RAX

0x435aca MOVSXD	(%RAX),%RDX

0x435acd MOV	-0xc0(%RBP),%RAX

0x435ad4 MOV	(%RAX),%ESI

0x435ad6 ADD	-0x2c(%RBP),%EDI

0x435ad9 SUB	%EDX,%ESI

0x435adb LEA	0x1(%RSI),%EAX

0x435ade CMP	$0x2,%EAX

0x435ae1 MOV	$0x1,%R9D

0x435ae7 CMOVGE	%EAX,%R9D

0x435aeb MOV	%R9D,%R8D

0x435aee AND	$0x7ffffff8,%R8D

0x435af5 MOVSXD	-0xc8(%RBP),%R10

0x435afc MOVSXD	-0xd0(%RBP),%RAX

0x435b03 MOV	%R9,-0x128(%RBP)

0x435b0a VPBROADCASTQ	%R9,%ZMM0

0x435b10 MOV	%RDX,-0x78(%RBP)

0x435b14 LEA	(,%RDX,8),%RDX

0x435b1c LEA	-0x2(%RAX),%R9

0x435b20 MOV	%R9,-0x130(%RBP)

0x435b27 SAL	$0x3,%RAX

0x435b2b SUB	%RAX,%RDX

0x435b2e MOV	-0x50(%RBP),%RAX

0x435b32 LEA	0x10(%RAX,%RDX,1),%RAX

0x435b37 MOV	%RAX,-0x120(%RBP)

0x435b3e MOV	$0x2,%EAX

0x435b43 SUB	%R10,%RAX

0x435b46 MOV	%RAX,-0x118(%RBP)

0x435b4d ADD	$-0x2,%R10

0x435b51 MOV	%R10,-0x68(%RBP)

0x435b55 MOV	-0x48(%RBP),%RAX

0x435b59 LEA	0x10(%RAX,%RDX,1),%RAX

0x435b5e MOV	%RAX,-0x110(%RBP)

0x435b65 MOV	-0x60(%RBP),%RAX

0x435b69 LEA	0x10(%RAX,%RDX,1),%RAX

0x435b6e MOV	%RAX,-0x108(%RBP)

0x435b75 MOV	-0x58(%RBP),%RAX

0x435b79 LEA	0x10(%RAX,%RDX,1),%RAX

0x435b7e MOV	%RAX,-0x100(%RBP)

0x435b85 XOR	%EDX,%EDX

0x435b87 VPMOVSXBQ	0xc0423(%RIP),%ZMM1

0x435b91 MOV	%RDI,-0x80(%RBP)

0x435b95 MOV	%EDI,%R11D

0x435b98 JMP	435c40

0x435b9d NOPW	%CS:(%RAX,%RAX,1)

0x435bac NOPW	%CS:(%RAX,%RAX,1)

0x435bbb NOPL	(%RAX,%RAX,1)

(287) 0x435bc0 SUB	-0x68(%RBP),%R10

(287) 0x435bc4 IMUL	%R10,%RAX

(287) 0x435bc8 IMUL	%R10,%R14

(287) 0x435bcc IMUL	%R10,%R13

(287) 0x435bd0 IMUL	%RDI,%R10

(287) 0x435bd4 MOV	%R13,%RBX

(287) 0x435bd7 MOV	%R14,%R12

(287) 0x435bda MOV	%RAX,%R15

(287) 0x435bdd XOR	%EAX,%EAX

(287) 0x435bdf VPBROADCASTQ	%RAX,%ZMM2

(287) 0x435be5 VPSUBQ	%ZMM2,%ZMM0,%ZMM2

(287) 0x435beb VPCMPNLEUQ	%ZMM1,%ZMM2,%K1

(287) 0x435bf2 ADD	-0x58(%RBP),%R15

(287) 0x435bf6 ADD	-0x78(%RBP),%RAX

(287) 0x435bfa SUB	-0x130(%RBP),%RAX

(287) 0x435c01 VMOVUPD	(%R15,%RAX,8),%ZMM2{%K1}{z}

(287) 0x435c08 ADD	-0x60(%RBP),%R12

(287) 0x435c0c VMOVUPD	%ZMM2,(%R12,%RAX,8){%K1}

(287) 0x435c13 ADD	-0x48(%RBP),%RBX

(287) 0x435c17 VMOVUPD	(%RBX,%RAX,8),%ZMM2{%K1}{z}

(287) 0x435c1e ADD	-0x50(%RBP),%R10

(287) 0x435c22 VMOVUPD	%ZMM2,(%R10,%RAX,8){%K1}

(287) 0x435c29 JMP	435c30

0x435c2b NOPL	(%RAX,%RAX,1)

(287) 0x435c30 LEA	0x1(%RDX),%EAX

(287) 0x435c33 INC	%R11D

(287) 0x435c36 CMP	%ECX,%EDX

(287) 0x435c38 MOV	%EAX,%EDX

(287) 0x435c3a JE	4359e6

(287) 0x435c40 TEST	%ESI,%ESI

(287) 0x435c42 JS	435c30

(287) 0x435c44 MOV	-0x80(%RBP),%RAX

(287) 0x435c48 LEA	(%RAX,%RDX,1),%R9D

(287) 0x435c4c MOV	-0x88(%RBP),%RAX

(287) 0x435c53 MOV	(%RAX),%RAX

(287) 0x435c56 MOV	-0x90(%RBP),%RDI

(287) 0x435c5d MOV	(%RDI),%R14

(287) 0x435c60 MOV	-0x70(%RBP),%RDI

(287) 0x435c64 MOV	(%RDI),%R13

(287) 0x435c67 MOV	-0x98(%RBP),%RDI

(287) 0x435c6e MOV	(%RDI),%RDI

(287) 0x435c71 MOVSXD	%R9D,%R10

(287) 0x435c74 TEST	%R8,%R8

(287) 0x435c77 JE	435bc0

(287) 0x435c7d MOVSXD	%R11D,%R9

(287) 0x435c80 ADD	-0x118(%RBP),%R9

(287) 0x435c87 SUB	-0x68(%RBP),%R10

(287) 0x435c8b MOV	%RAX,%R15

(287) 0x435c8e IMUL	%R10,%R15

(287) 0x435c92 MOV	%R14,%R12

(287) 0x435c95 IMUL	%R10,%R12

(287) 0x435c99 MOV	%R13,%RBX

(287) 0x435c9c IMUL	%R10,%RBX

(287) 0x435ca0 IMUL	%RDI,%R10

(287) 0x435ca4 IMUL	%R9,%RDI

(287) 0x435ca8 ADD	-0x120(%RBP),%RDI

(287) 0x435caf IMUL	%R9,%R13

(287) 0x435cb3 ADD	-0x110(%RBP),%R13

(287) 0x435cba IMUL	%R9,%R14

(287) 0x435cbe ADD	-0x108(%RBP),%R14

(287) 0x435cc5 IMUL	%RAX,%R9

(287) 0x435cc9 ADD	-0x100(%RBP),%R9

(287) 0x435cd0 XOR	%EAX,%EAX

(287) 0x435cd2 NOPW	%CS:(%RAX,%RAX,1)

  (288) 0x435ce0 VMOVUPS	(%R9,%RAX,8),%ZMM2

  (288) 0x435ce7 VMOVUPS	%ZMM2,(%R14,%RAX,8)

  (288) 0x435cee VMOVUPD	(%R13,%RAX,8),%ZMM2

  (288) 0x435cf6 VMOVUPD	%ZMM2,(%RDI,%RAX,8)

  (288) 0x435cfd ADD	$0x8,%RAX

  (288) 0x435d01 CMP	%R8,%RAX

  (288) 0x435d04 JB	435ce0

(287) 0x435d06 MOV	%R8,%RAX

(287) 0x435d09 CMP	-0x128(%RBP),%R8D

(287) 0x435d10 JNE	435bdf

(287) 0x435d16 JMP	435c30

0x435d1b NOPW	%CS:(%RAX,%RAX,1)

0x435d2a NOPW	%CS:(%RAX,%RAX,1)

0x435d39 NOPL	(%RAX)

0x435d40 MOV	%RAX,%RDI

0x435d43 MOV	-0xb8(%RBP),%RAX

0x435d4a MOVSXD	(%RAX),%RDX

0x435d4d MOV	-0xc0(%RBP),%RAX

0x435d54 MOV	(%RAX),%EAX

0x435d56 ADD	-0x2c(%RBP),%EDI

0x435d59 SUB	%EDX,%EAX

0x435d5b LEA	0x1(%RAX),%ESI

0x435d5e ADD	$0x2,%EAX

0x435d61 CMP	$0x2,%EAX

0x435d64 MOV	$0x1,%R9D

0x435d6a CMOVGE	%EAX,%R9D

0x435d6e MOV	%R9D,%R8D

0x435d71 AND	$0x7ffffff8,%R8D

0x435d78 MOVSXD	-0xc8(%RBP),%R10

0x435d7f MOVSXD	-0xd0(%RBP),%RAX

0x435d86 MOV	%R9,-0x80(%RBP)

0x435d8a VPBROADCASTQ	%R9,%ZMM0

0x435d90 MOV	%RDX,-0x90(%RBP)

0x435d97 LEA	(,%RDX,8),%RDX

0x435d9f LEA	-0x2(%RAX),%R9

0x435da3 MOV	%R9,-0x88(%RBP)

0x435daa SAL	$0x3,%RAX

0x435dae SUB	%RAX,%RDX

0x435db1 MOV	-0xe8(%RBP),%RAX

0x435db8 LEA	0x10(%RAX,%RDX,1),%RAX

0x435dbd MOV	%RAX,-0x68(%RBP)

0x435dc1 MOV	$0x2,%EAX

0x435dc6 SUB	%R10,%RAX

0x435dc9 MOV	%RAX,-0x60(%RBP)

0x435dcd ADD	$-0x2,%R10

0x435dd1 MOV	%R10,-0x70(%RBP)

0x435dd5 MOV	-0xe0(%RBP),%RAX

0x435ddc LEA	0x10(%RAX,%RDX,1),%RAX

0x435de1 MOV	%RAX,-0x58(%RBP)

0x435de5 MOV	-0xf8(%RBP),%RAX

0x435dec LEA	0x10(%RAX,%RDX,1),%RAX

0x435df1 MOV	%RAX,-0x50(%RBP)

0x435df5 MOV	-0xf0(%RBP),%RAX

0x435dfc LEA	0x10(%RAX,%RDX,1),%RAX

0x435e01 MOV	%RAX,-0x48(%RBP)

0x435e05 XOR	%R11D,%R11D

0x435e08 VPMOVSXBQ	0xc01a2(%RIP),%ZMM1

0x435e12 MOV	%RDI,-0x98(%RBP)

0x435e19 MOV	%EDI,%R13D

0x435e1c JMP	435ed3

0x435e21 NOPW	%CS:(%RAX,%RAX,1)

0x435e30 NOPW	%CS:(%RAX,%RAX,1)

0x435e3f NOP

(285) 0x435e40 SUB	-0x70(%RBP),%R14

(285) 0x435e44 IMUL	%R14,%RAX

(285) 0x435e48 IMUL	%R14,%RDX

(285) 0x435e4c IMUL	%R14,%R15

(285) 0x435e50 IMUL	%RDI,%R14

(285) 0x435e54 MOV	%R15,%RBX

(285) 0x435e57 MOV	%RDX,%R10

(285) 0x435e5a MOV	%RAX,%R12

(285) 0x435e5d XOR	%EAX,%EAX

(285) 0x435e5f VPBROADCASTQ	%RAX,%ZMM2

(285) 0x435e65 VPSUBQ	%ZMM2,%ZMM0,%ZMM2

(285) 0x435e6b VPCMPNLEUQ	%ZMM1,%ZMM2,%K1

(285) 0x435e72 ADD	-0xf0(%RBP),%R12

(285) 0x435e79 ADD	-0x90(%RBP),%RAX

(285) 0x435e80 SUB	-0x88(%RBP),%RAX

(285) 0x435e87 VMOVUPD	(%R12,%RAX,8),%ZMM2{%K1}{z}

(285) 0x435e8e ADD	-0xf8(%RBP),%R10

(285) 0x435e95 VMOVUPD	%ZMM2,(%R10,%RAX,8){%K1}

(285) 0x435e9c ADD	-0xe0(%RBP),%RBX

(285) 0x435ea3 VMOVUPD	(%RBX,%RAX,8),%ZMM2{%K1}{z}

(285) 0x435eaa ADD	-0xe8(%RBP),%R14

(285) 0x435eb1 VMOVUPD	%ZMM2,(%R14,%RAX,8){%K1}

(285) 0x435eb8 JMP	435ec0

0x435eba NOPW	(%RAX,%RAX,1)

(285) 0x435ec0 LEA	0x1(%R11),%EAX

(285) 0x435ec4 INC	%R13D

(285) 0x435ec7 CMP	%ECX,%R11D

(285) 0x435eca MOV	%EAX,%R11D

(285) 0x435ecd JE	435a7c

(285) 0x435ed3 TEST	%ESI,%ESI

(285) 0x435ed5 JS	435ec0

(285) 0x435ed7 MOV	-0x98(%RBP),%RAX

(285) 0x435ede LEA	(%RAX,%R11,1),%R9D

(285) 0x435ee2 MOV	-0x138(%RBP),%RAX

(285) 0x435ee9 MOV	(%RAX),%RAX

(285) 0x435eec MOV	-0x140(%RBP),%RDX

(285) 0x435ef3 MOV	(%RDX),%RDX

(285) 0x435ef6 MOV	-0x148(%RBP),%RDI

(285) 0x435efd MOV	(%RDI),%R15

(285) 0x435f00 MOV	-0x150(%RBP),%RDI

(285) 0x435f07 MOV	(%RDI),%RDI

(285) 0x435f0a MOVSXD	%R9D,%R14

(285) 0x435f0d TEST	%R8,%R8

(285) 0x435f10 JE	435e40

(285) 0x435f16 MOVSXD	%R13D,%R9

(285) 0x435f19 ADD	-0x60(%RBP),%R9

(285) 0x435f1d SUB	-0x70(%RBP),%R14

(285) 0x435f21 MOV	%RAX,%R12

(285) 0x435f24 IMUL	%R14,%R12

(285) 0x435f28 MOV	%RDX,%R10

(285) 0x435f2b IMUL	%R14,%R10

(285) 0x435f2f MOV	%R15,%RBX

(285) 0x435f32 IMUL	%R14,%RBX

(285) 0x435f36 IMUL	%RDI,%R14

(285) 0x435f3a IMUL	%R9,%RDI

(285) 0x435f3e ADD	-0x68(%RBP),%RDI

(285) 0x435f42 IMUL	%R9,%R15

(285) 0x435f46 ADD	-0x58(%RBP),%R15

(285) 0x435f4a IMUL	%R9,%RDX

(285) 0x435f4e ADD	-0x50(%RBP),%RDX

(285) 0x435f52 IMUL	%RAX,%R9

(285) 0x435f56 ADD	-0x48(%RBP),%R9

(285) 0x435f5a XOR	%EAX,%EAX

(285) 0x435f5c NOPL	(%RAX)

  (286) 0x435f60 VMOVUPS	(%R9,%RAX,8),%ZMM2

  (286) 0x435f67 VMOVUPS	%ZMM2,(%RDX,%RAX,8)

  (286) 0x435f6e VMOVUPD	(%R15,%RAX,8),%ZMM2

  (286) 0x435f75 VMOVUPD	%ZMM2,(%RDI,%RAX,8)

  (286) 0x435f7c ADD	$0x8,%RAX

  (286) 0x435f80 CMP	%R8,%RAX

  (286) 0x435f83 JB	435f60

(285) 0x435f85 MOV	%R8,%RAX

(285) 0x435f88 CMP	-0x80(%RBP),%R8D

(285) 0x435f8c JNE	435e5f

(285) 0x435f92 JMP	435ec0

0x435f97 NOPW	%CS:(%RAX,%RAX,1)

0x435fa1 NOPW	%CS:(%RAX,%RAX,1)

0x435fab NOPW	%CS:(%RAX,%RAX,1)

0x435fb5 NOPW	%CS:(%RAX,%RAX,1)

0x435fbf NOP

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

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_2

Source file and lines	reset_field_kernel.f90:47-66
Module	exec

The function is defined in /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:47-66.

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 40.33 to 4.00 cycles (10.08x 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 10% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 40.33 to 3.47 cycles (11.63x speedup).

Details

Store and arithmetical SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a 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): do i a(i)%x = b(i)%x (slow, non stride 1) => do 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.

__kmpc_barrier@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:56
__kmpc_for_static_fini@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:56
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:66
__kmpc_for_static_init_4@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:50
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:60

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.

VPMOVSXBQ: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:52
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:62
VZEROUPPER: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:56
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:66

Conversion instructions

Detected expensive conversion instructions.

Details

VPMOVSXBQ: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:52
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:62

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 364 bytes. The binary function is storing 376 bytes.

General properties

nb instructions	233
nb uops	242
loop length	1193
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	2
nb stack references	62

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	40.33 cycles
front end	40.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	10.60	10.60	21.00	21.00	35.00	10.60	10.60	35.00	35.00	35.00	10.60	21.00
cycles	10.60	14.60	21.00	21.00	35.00	10.60	10.60	35.00	35.00	35.00	10.60	21.00

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

Cycles summary

Front-end	40.33
Dispatch	35.00
Overall L1	40.33

Vectorization ratios

all	4%
load	25%
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	8%

Vector efficiency ratios

all	10%
load	7%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 40.33 cycles. At this rate:

4% of peak load performance is reached (9.02 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (9.32 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 40.33 to 35.00 cycles (1.15x speedup).

ASM code

In the binary file, the address of the function is: 435870

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
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
SUB $0x128,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV %R9,-0xd0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0xc8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x150(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xc0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x148(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x140(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x138(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x80(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x78(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x70(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x58(%RBP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x50(%RBP),%R14D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOV %EAX,-0x2c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB %EAX,%R14D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV 0x68(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xb8(%RBP)	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(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x38(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x30(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xf8(%RBP)	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(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xf0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x18(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x10(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVL $0,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %RDI,-0xd8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JS 435a07 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x197>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVL $0,-0x34(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R14D,-0xa0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R14D,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0xa4(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xa4(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0xa8(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x34(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x30(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x53be10,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV %ESI,-0x9c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 404850 <__kmpc_for_static_init_4@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x34(%RBP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x30(%RBP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
SUB %EAX,%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%)
JAE 435ac0 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x250>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x53be30,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV -0x9c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404070 <__kmpc_for_static_fini@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0xd8(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xa0(%RBP),%R14D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53be50,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
CALL 4047c0 <__kmpc_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
INC %R14D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOVL $0,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JS 435a93 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x223>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVL $0,-0x3c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R14D,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0xac(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xac(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0xb0(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x3c(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x38(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x53be70,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV %ESI,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 404850 <__kmpc_for_static_init_4@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x3c(%RBP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
SUB %EAX,%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%)
JAE 435d40 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x4d0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x53be90,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV -0x78(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404070 <__kmpc_for_static_fini@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0xd8(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53beb0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD $0x128,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
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
JMP 4047c0 <__kmpc_barrier@plt>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0xb8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD (%RAX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RAX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD -0x2c(%RBP),%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	scal (6.3%)
SUB %EDX,%ESI	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
CMP $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV $0x1,%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%)
CMOVGE %EAX,%R9D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (6.3%)
MOV %R9D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
AND $0x7ffffff8,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
MOVSXD -0xc8(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD -0xd0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x128(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VPBROADCASTQ %R9,%ZMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
MOV %RDX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RDX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x2(%RAX),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,-0x130(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SUB %RAX,%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 -0x50(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x120(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB %R10,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RAX,-0x118(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $-0x2,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x110(%RBP)	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(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x58(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x100(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VPMOVSXBQ 0xc0423(%RIP),%ZMM1	2	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	vect (12.5%)
MOV %RDI,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %EDI,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JMP 435c40 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x3d0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0xb8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD (%RAX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RAX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD -0x2c(%RBP),%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	scal (6.3%)
SUB %EDX,%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),%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
ADD $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV $0x1,%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%)
CMOVGE %EAX,%R9D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (6.3%)
MOV %R9D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
AND $0x7ffffff8,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
MOVSXD -0xc8(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD -0xd0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VPBROADCASTQ %R9,%ZMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
MOV %RDX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RDX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x2(%RAX),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SUB %RAX,%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 -0xe8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB %R10,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $-0x2,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xe0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xf8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xf0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VPMOVSXBQ 0xc01a2(%RIP),%ZMM1	2	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	vect (12.5%)
MOV %RDI,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %EDI,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JMP 435ed3 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x663>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	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 0.00% of application time for run icx_2

Source file and lines	reset_field_kernel.f90:47-66
Module	exec

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)
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

Details

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): do i a(i)%x = b(i)%x (slow, non stride 1) => do 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

__kmpc_barrier@plt: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:56
__kmpc_for_static_fini@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:56
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:66
__kmpc_for_static_init_4@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:50
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:60

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.

VPMOVSXBQ: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:52
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:62
VZEROUPPER: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:56
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:66

Conversion instructions

Detected expensive conversion instructions.

Details

VPMOVSXBQ: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:52
- /home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/reset_field_kernel.f90:62

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 364 bytes. The binary function is storing 376 bytes.

General properties

nb instructions	233
nb uops	242
loop length	1193
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	2
nb stack references	62

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	40.33 cycles
front end	40.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	10.60	10.60	21.00	21.00	35.00	10.60	10.60	35.00	35.00	35.00	10.60	21.00
cycles	10.60	14.60	21.00	21.00	35.00	10.60	10.60	35.00	35.00	35.00	10.60	21.00

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

Cycles summary

Front-end	40.33
Dispatch	35.00
Overall L1	40.33

Vectorization ratios

all	4%
load	25%
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	8%

Vector efficiency ratios

all	10%
load	7%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	9%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	8%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 40.33 cycles. At this rate:

4% of peak load performance is reached (9.02 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (9.32 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: 435870

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
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
SUB $0x128,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV %R9,-0xd0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0xc8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x150(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xc0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x148(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x140(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x138(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x80(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x78(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x70(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x58(%RBP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x50(%RBP),%R14D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOV %EAX,-0x2c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB %EAX,%R14D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV 0x68(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xb8(%RBP)	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(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x40(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x38(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x30(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x28(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xf8(%RBP)	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(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xf0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x18(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0x10(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0xe0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVL $0,-0xa8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %RDI,-0xd8(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
JS 435a07 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x197>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVL $0,-0x34(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R14D,-0xa0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R14D,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0xa4(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xa4(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0xa8(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x34(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x30(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x53be10,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV %ESI,-0x9c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 404850 <__kmpc_for_static_init_4@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x34(%RBP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x30(%RBP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
SUB %EAX,%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%)
JAE 435ac0 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x250>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x53be30,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV -0x9c(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404070 <__kmpc_for_static_fini@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0xd8(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xa0(%RBP),%R14D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53be50,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
CALL 4047c0 <__kmpc_barrier@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
INC %R14D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOVL $0,-0xb0(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
JS 435a93 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x223>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVL $0,-0x3c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %R14D,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0x1,-0xac(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
LEA -0xac(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0xb0(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x3c(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x38(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x53be70,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV %ESI,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 404850 <__kmpc_for_static_init_4@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x3c(%RBP),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
SUB %EAX,%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%)
JAE 435d40 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x4d0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x53be90,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV -0x78(%RBP),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 404070 <__kmpc_for_static_fini@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV -0xd8(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RBX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV $0x53beb0,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD $0x128,%RSP	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
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
JMP 4047c0 <__kmpc_barrier@plt>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0xb8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD (%RAX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RAX),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD -0x2c(%RBP),%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	scal (6.3%)
SUB %EDX,%ESI	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
CMP $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV $0x1,%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%)
CMOVGE %EAX,%R9D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (6.3%)
MOV %R9D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
AND $0x7ffffff8,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
MOVSXD -0xc8(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD -0xd0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x128(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VPBROADCASTQ %R9,%ZMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
MOV %RDX,-0x78(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RDX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x2(%RAX),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,-0x130(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SUB %RAX,%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 -0x50(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x120(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB %R10,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RAX,-0x118(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $-0x2,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x110(%RBP)	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(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x58(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x100(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VPMOVSXBQ 0xc0423(%RIP),%ZMM1	2	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	vect (12.5%)
MOV %RDI,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %EDI,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JMP 435c40 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x3d0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0xb8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD (%RAX),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RAX),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD -0x2c(%RBP),%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	scal (6.3%)
SUB %EDX,%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),%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
ADD $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
MOV $0x1,%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%)
CMOVGE %EAX,%R9D	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (6.3%)
MOV %R9D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
AND $0x7ffffff8,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (6.3%)
MOVSXD -0xc8(%RBP),%R10	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD -0xd0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R9,-0x80(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VPBROADCASTQ %R9,%ZMM0	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	scal (12.5%)
MOV %RDX,-0x90(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RDX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x2(%RAX),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,-0x88(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SAL $0x3,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
SUB %RAX,%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 -0xe8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x2,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SUB %R10,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $-0x2,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,-0x70(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xe0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xf8(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xf0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x10(%RAX,%RDX,1),%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VPMOVSXBQ 0xc01a2(%RIP),%ZMM1	2	0	0	0.33	0.33	0	1	0	0	0	0	0	0.33	3	1	vect (12.5%)
MOV %RDI,-0x98(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %EDI,%R13D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JMP 435ed3 <reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2+0x663>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	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
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼reset_field_kernel_module_mp_reset_field_kernel_.DIR.OMP.PARALLEL.2–	5.26	1.94
▼Loop 285 - reset_field_kernel.f90:49-63 - exec–	0.00	0.01
○Loop 286 - reset_field_kernel.f90:61-63 - exec	2.58	0.95
▼Loop 287 - reset_field_kernel.f90:49-53 - exec–	0.00	0.01
○Loop 288 - reset_field_kernel.f90:51-53 - exec	2.67	0.98

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

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

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