OV - bt.A.x - Function initialize_._omp

	Function: initialize_._omp_fn.0	Module: bt.A.x	Source: initialize.f90:23-197 [...]	Coverage (incl. loops): 0.02% \| (excl. loops): 0.00%

/home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90: 23 - 197

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

23: !$omp& private(i,j,k,m,zeta,eta,xi,ix,iy,iz,Pface,Pxi,Peta,Pzeta,temp)

[...]

30: !$omp do schedule(static) collapse(2)

31:       do k = 0, grid_points(3)-1

32:          do j = 0, grid_points(2)-1

33:             do i = 0, grid_points(1)-1

34:                do m = 1, 5

35:                   u(m,i,j,k) = 1.0

[...]

51:             zeta = dble(k) * dnzm1

52:             eta = dble(j) * dnym1

53:             do i = 0, grid_points(1)-1

54:                xi = dble(i) * dnxm1

55:

56:                do ix = 1, 2

57:                   call exact_solution(dble(ix-1), eta, zeta,   &

58:      &                    Pface(1,1,ix))

59:                enddo

60:

61:                do iy = 1, 2

62:                   call exact_solution(xi, dble(iy-1) , zeta,   &

63:      &                    Pface(1,2,iy))

64:                enddo

65:

66:                do iz = 1, 2

67:                   call exact_solution(xi, eta, dble(iz-1),     &

68:      &                    Pface(1,3,iz))

69:                enddo

70:

71:                do m = 1, 5

72:                   Pxi   = xi   * Pface(m,1,2) +   &

73:      &                    (1.0d0-xi)   * Pface(m,1,1)

74:                   Peta  = eta  * Pface(m,2,2) +   &

75:      &                    (1.0d0-eta)  * Pface(m,2,1)

76:                   Pzeta = zeta * Pface(m,3,2) +   &

77:      &                    (1.0d0-zeta) * Pface(m,3,1)

78:

79:                   u(m,i,j,k) = Pxi + Peta + Pzeta -   &

80:      &                    Pxi*Peta - Pxi*Pzeta - Peta*Pzeta +   &

81:      &                    Pxi*Peta*Pzeta

[...]

97:       xi = 0.0d0

98: !$omp do schedule(static) collapse(2)

99:       do k = 0, grid_points(3)-1

100:          do j = 0, grid_points(2)-1

101:             zeta = dble(k) * dnzm1

102:             eta = dble(j) * dnym1

103:             call exact_solution(xi, eta, zeta, temp)

104:             do m = 1, 5

105:                u(m,i,j,k) = temp(m)

[...]

115:       i = grid_points(1)-1

116:       xi = 1.0d0

117: !$omp do schedule(static) collapse(2)

118:       do k = 0, grid_points(3)-1

119:          do j = 0, grid_points(2)-1

120:             zeta = dble(k) * dnzm1

121:             eta = dble(j) * dnym1

122:             call exact_solution(xi, eta, zeta, temp)

123:             do m = 1, 5

124:                u(m,i,j,k) = temp(m)

[...]

134:       eta = 0.0d0

135: !$omp do schedule(static) collapse(2)

136:       do k = 0, grid_points(3)-1

137:          do i = 0, grid_points(1)-1

138:             zeta = dble(k) * dnzm1

139:             xi = dble(i) * dnxm1

140:             call exact_solution(xi, eta, zeta, temp)

141:             do m = 1, 5

142:                u(m,i,j,k) = temp(m)

[...]

152:       j = grid_points(2)-1

153:       eta = 1.0d0

154: !$omp do schedule(static) collapse(2)

155:       do k = 0, grid_points(3)-1

156:          do i = 0, grid_points(1)-1

157:             zeta = dble(k) * dnzm1

158:             xi = dble(i) * dnxm1

159:             call exact_solution(xi, eta, zeta, temp)

160:             do m = 1, 5

161:                u(m,i,j,k) = temp(m)

[...]

171:       zeta = 0.0d0

172: !$omp do schedule(static) collapse(2)

173:       do j = 0, grid_points(2)-1

174:          do i =0, grid_points(1)-1

175:             eta = dble(j) * dnym1

176:             xi = dble(i) *dnxm1

177:             call exact_solution(xi, eta, zeta, temp)

178:             do m = 1, 5

179:                u(m,i,j,k) = temp(m)

[...]

188:       k = grid_points(3)-1

189:       zeta = 1.0d0

190: !$omp do schedule(static) collapse(2)

191:       do j = 0, grid_points(2)-1

192:          do i =0, grid_points(1)-1

193:             eta = dble(j) * dnym1

194:             xi = dble(i) * dnxm1

195:             call exact_solution(xi, eta, zeta, temp)

196:             do m = 1, 5

197:                u(m,i,j,k) = temp(m)

0x3870 PUSH	%RBP

0x3871 MOV	%RSP,%RBP

0x3874 PUSH	%R15

0x3876 PUSH	%R14

0x3878 PUSH	%R13

0x387a PUSH	%R12

0x387c PUSH	%RBX

0x387d AND	$-0x20,%RSP

0x3881 SUB	$0x1e0,%RSP

0x3888 MOV	0x26ca9(%RIP),%R12D

0x388f MOV	0x26c9f(%RIP),%ESI

0x3895 TEST	%R12D,%R12D

0x3898 JLE	4a6a

0x389e TEST	%ESI,%ESI

0x38a0 JLE	4a6a

0x38a6 MOV	%ESI,0x78(%RSP)

0x38aa MOV	%R12D,%EBX

0x38ad CALL	2050 <@plt_start@+0x30>

0x38b2 MOV	%EAX,%R14D

0x38b5 MOV	%EAX,(%RSP)

0x38b8 CALL	20d0 <@plt_start@+0xb0>

0x38bd MOV	0x78(%RSP),%ESI

0x38c1 XOR	%EDX,%EDX

0x38c3 MOV	%EAX,%EDI

0x38c5 MOV	%EAX,0x4(%RSP)

0x38c9 IMUL	%ESI,%EBX

0x38cc MOV	%EBX,%EAX

0x38ce DIV	%R14D

0x38d1 MOV	%EAX,%R10D

0x38d4 CMP	%EDX,%EDI

0x38d6 JB	4a15

0x38dc MOV	0x4(%RSP),%EAX

0x38e0 IMUL	%R10D,%EAX

0x38e4 LEA	(%RAX,%RDX,1),%EDI

0x38e7 LEA	(%R10,%RDI,1),%EAX

0x38eb MOV	%EAX,0x14(%RSP)

0x38ef CMP	%EAX,%EDI

0x38f1 JB	3a7b

0x38f7 VMOVSD	0x246a1(%RIP),%XMM2

0x38ff MOVQ	$0,0x88(%RSP)

0x390b MOV	%R12D,%EAX

0x390e XOR	%EDX,%EDX

0x3910 IMUL	%ESI,%EAX

0x3913 DIVL	(%RSP)

0x3916 MOV	%EAX,%ECX

0x3918 CMP	%EDX,0x4(%RSP)

0x391c JB	4a0b

0x3922 MOV	0x4(%RSP),%EAX

0x3926 IMUL	%ECX,%EAX

0x3929 ADD	%EDX,%EAX

0x392b LEA	(%RCX,%RAX,1),%EDX

0x392e CMP	%EDX,%EAX

0x3930 JAE	48ce

0x3936 XOR	%EDX,%EDX

0x3938 VXORPD	%XMM4,%XMM4,%XMM4

0x393c XOR	%R13D,%R13D

0x393f VMOVSD	%XMM2,0x40(%RSP)

0x3945 DIV	%ESI

0x3947 LEA	-0x1(%RCX),%EBX

0x394a MOV	%EBX,0x58(%RSP)

0x394e LEA	0xa0(%RSP),%RBX

0x3956 MOV	%RBX,0x68(%RSP)

0x395b LEA	0x98(%RSP),%RBX

0x3963 LEA	0x88(%RSP),%R12

0x396b MOV	%RBX,0x70(%RSP)

0x3970 LEA	0x90(%RSP),%RBX

0x3978 MOV	%R12,0x50(%RSP)

0x397d MOV	%R13D,%R12D

0x3980 MOV	%ESI,%R13D

0x3983 MOV	%RBX,0x78(%RSP)

0x3988 LEA	0x268b1(%RIP),%RBX

0x398f VCVTSI2SD	%EAX,%XMM4,%XMM0

0x3993 MOV	%EDX,%R15D

0x3996 MOV	%EAX,0x48(%RSP)

0x399a MOVSXD	%EAX,%R14

0x399d VMOVSD	%XMM0,0x60(%RSP)

0x39a3 JMP	39af

0x39a5 NOPL	(%RAX)

(11) 0x39a8 ADD	$0x1,%R12D

(11) 0x39ac VZEROUPPER

(11) 0x39af VMOVSD	0x60(%RSP),%XMM6

(11) 0x39b5 VXORPD	%XMM7,%XMM7,%XMM7

(11) 0x39b9 VMULSD	0x26d5f(%RIP),%XMM6,%XMM0

(11) 0x39c1 MOV	0x68(%RSP),%RCX

(11) 0x39c6 MOV	0x70(%RSP),%RDX

(11) 0x39cb MOV	0x78(%RSP),%RSI

(11) 0x39d0 MOV	0x50(%RSP),%RDI

(11) 0x39d5 VMOVSD	%XMM0,0x98(%RSP)

(11) 0x39de VCVTSI2SD	%R15D,%XMM7,%XMM0

(11) 0x39e3 VMULSD	0x26d3d(%RIP),%XMM0,%XMM0

(11) 0x39eb VMOVSD	%XMM0,0x90(%RSP)

(11) 0x39f4 CALL	4aa0 <exact_solution_>

(11) 0x39f9 MOV	0x268b0(%RIP),%RAX

(11) 0x3a00 MOVSXD	%R15D,%RCX

(11) 0x3a03 IMUL	0x2688d(%RIP),%RCX

(11) 0x3a0b MOV	(%RBX),%RDX

(11) 0x3a0e VMOVAPD	0xa0(%RSP),%YMM5

(11) 0x3a17 VMOVSD	0xc0(%RSP),%XMM0

(11) 0x3a20 IMUL	%R14,%RAX

(11) 0x3a24 ADD	0x2681d(%RIP),%RAX

(11) 0x3a2b ADD	%RCX,%RAX

(11) 0x3a2e VMOVUPD	%XMM5,0x8(%RDX,%RAX,8)

(11) 0x3a34 VEXTRACTF128	$0x1,%YMM5,0x18(%RDX,%RAX,8)

(11) 0x3a3c VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

(11) 0x3a42 CMP	%R12D,0x58(%RSP)

(11) 0x3a47 JE	3f58

(11) 0x3a4d ADD	$0x1,%R15D

(11) 0x3a51 CMP	%R15D,%R13D

(11) 0x3a54 JG	39a8

(11) 0x3a5a ADDL	$0x1,0x48(%RSP)

(11) 0x3a5f VXORPD	%XMM6,%XMM6,%XMM6

(11) 0x3a63 XOR	%R15D,%R15D

(11) 0x3a66 MOVSXD	0x48(%RSP),%R14

(11) 0x3a6b VCVTSI2SD	%R14D,%XMM6,%XMM0

(11) 0x3a70 VMOVSD	%XMM0,0x60(%RSP)

(11) 0x3a76 JMP	39a8

0x3a7b MOV	%EDI,%EAX

0x3a7d XOR	%EDX,%EDX

0x3a7f MOV	0x26aaa(%RIP),%R8D

0x3a86 DIV	%ESI

0x3a88 MOV	0x267b1(%RIP),%RBX

0x3a8f MOV	0x267b2(%RIP),%R12

0x3a96 MOV	0x26813(%RIP),%R13

0x3a9d MOV	0x267f4(%RIP),%R14

0x3aa4 MOV	0x267d5(%RIP),%RCX

0x3aab VMOVSD	0x244ed(%RIP),%XMM2

0x3ab3 MOV	%EDX,%R9D

0x3ab6 MOV	%EAX,0x78(%RSP)

0x3aba TEST	%R8D,%R8D

0x3abd JLE	3b4e

0x3ac3 LEA	-0x1(%R10),%R15D

0x3ac7 SAL	$0x3,%RCX

0x3acb XOR	%R10D,%R10D

0x3ace MOV	%EDI,0x70(%RSP)

0x3ad2 VMOVSD	0x244c6(%RIP),%XMM2

0x3ada MOVSXD	%EAX,%R11

0x3add MOV	%EAX,0x68(%RSP)

0x3ae1 VBROADCASTSD	0x244b6(%RIP),%YMM0

0x3aea NOPW	(%RAX,%RAX,1)

(16) 0x3af0 MOV	%R11,%RDI

(16) 0x3af3 MOVSXD	%R9D,%RAX

(16) 0x3af6 IMUL	%R13,%RDI

(16) 0x3afa IMUL	%R14,%RAX

(16) 0x3afe ADD	%R12,%RDI

(16) 0x3b01 LEA	0x1(%RDI,%RAX,1),%RAX

(16) 0x3b06 XOR	%EDI,%EDI

(16) 0x3b08 LEA	(%RBX,%RAX,8),%RAX

(16) 0x3b0c NOPL	(%RAX)

  (15) 0x3b10 ADD	$0x1,%EDI

  (15) 0x3b13 VMOVUPD	%XMM0,(%RAX)

  (15) 0x3b17 VEXTRACTF128	$0x1,%YMM0,0x10(%RAX)

  (15) 0x3b1e VMOVSD	%XMM2,0x20(%RAX)

  (15) 0x3b23 ADD	%RCX,%RAX

  (15) 0x3b26 CMP	%EDI,%R8D

  (15) 0x3b29 JNE	3b10

(16) 0x3b2b CMP	%R10D,%R15D

(16) 0x3b2e JE	3b43

(16) 0x3b30 ADD	$0x1,%R9D

(16) 0x3b34 CMP	%R9D,%ESI

(16) 0x3b37 JLE	48e2

(16) 0x3b3d ADD	$0x1,%R10D

(16) 0x3b41 JMP	3af0

0x3b43 MOV	0x70(%RSP),%EDI

0x3b47 MOV	0x68(%RSP),%EAX

0x3b4b VZEROUPPER

0x3b4e VXORPD	%XMM3,%XMM3,%XMM3

0x3b52 VCVTSI2SD	%EAX,%XMM3,%XMM0

0x3b56 MOV	%EDX,%ECX

0x3b58 MOV	%EDI,0x1c(%RSP)

0x3b5c LEA	0xa0(%RSP),%R15

0x3b64 MOV	%EAX,0x18(%RSP)

0x3b68 MOV	%ESI,0x10(%RSP)

0x3b6c VMOVSD	%XMM2,0x78(%RSP)

0x3b72 VMOVSD	%XMM0,0x8(%RSP)

0x3b78 NOPL	(%RAX,%RAX,1)

(12) 0x3b80 VMOVSD	0x8(%RSP),%XMM7

(12) 0x3b86 LEA	0x269a3(%RIP),%RAX

(12) 0x3b8d VXORPD	%XMM5,%XMM5,%XMM5

(12) 0x3b91 VMULSD	0x26b87(%RIP),%XMM7,%XMM0

(12) 0x3b99 MOV	(%RAX),%EDX

(12) 0x3b9b VMOVSD	%XMM0,0x98(%RSP)

(12) 0x3ba4 VCVTSI2SD	%ECX,%XMM5,%XMM0

(12) 0x3ba8 VMULSD	0x26b78(%RIP),%XMM0,%XMM0

(12) 0x3bb0 VMOVSD	%XMM0,0x90(%RSP)

(12) 0x3bb9 TEST	%EDX,%EDX

(12) 0x3bbb JLE	3f29

(12) 0x3bc1 MOVSXD	0x18(%RSP),%RAX

(12) 0x3bc6 XOR	%EBX,%EBX

(12) 0x3bc8 MOV	%ECX,0x24(%RSP)

(12) 0x3bcc LEA	0x98(%RSP),%R14

(12) 0x3bd4 MOV	%EDX,0x20(%RSP)

(12) 0x3bd8 LEA	0x90(%RSP),%R13

(12) 0x3be0 LEA	0x88(%RSP),%R12

(12) 0x3be8 MOV	%RAX,0x70(%RSP)

(12) 0x3bed MOVSXD	%ECX,%RAX

(12) 0x3bf0 MOV	%RAX,0x68(%RSP)

(12) 0x3bf5 MOVSXD	%EDX,%RAX

(12) 0x3bf8 MOV	%RAX,0x60(%RSP)

(12) 0x3bfd LEA	0x2663c(%RIP),%RAX

(12) 0x3c04 MOV	%RAX,0x28(%RSP)

(12) 0x3c09 LEA	0xe0(%RSP),%RAX

(12) 0x3c11 MOV	%RAX,0x38(%RSP)

(12) 0x3c16 LEA	0x158(%RSP),%RAX

(12) 0x3c1e MOV	%RAX,0x50(%RSP)

(12) 0x3c23 LEA	0x108(%RSP),%RAX

(12) 0x3c2b MOV	%RAX,0x30(%RSP)

(12) 0x3c30 LEA	0x180(%RSP),%RAX

(12) 0x3c38 MOV	%RAX,0x48(%RSP)

(12) 0x3c3d LEA	0x130(%RSP),%RAX

(12) 0x3c45 MOV	%RAX,0x58(%RSP)

(12) 0x3c4a LEA	0x1a8(%RSP),%RAX

(12) 0x3c52 MOV	%RAX,0x40(%RSP)

(12) 0x3c57 JMP	3c63

0x3c59 NOPL	(%RAX)

  (14) 0x3c60 VZEROUPPER

  (14) 0x3c63 VXORPD	%XMM7,%XMM7,%XMM7

  (14) 0x3c67 VCVTSI2SD	%EBX,%XMM7,%XMM0

  (14) 0x3c6b MOV	0x38(%RSP),%RCX

  (14) 0x3c70 MOV	%R14,%RDX

  (14) 0x3c73 VMULSD	0x26ab5(%RIP),%XMM0,%XMM0

  (14) 0x3c7b MOV	%R13,%RSI

  (14) 0x3c7e MOV	%R15,%RDI

  (14) 0x3c81 MOVQ	$0,0xa0(%RSP)

  (14) 0x3c8d VMOVSD	%XMM0,0x88(%RSP)

  (14) 0x3c96 CALL	4aa0 <exact_solution_>

  (14) 0x3c9b MOV	0x50(%RSP),%RCX

  (14) 0x3ca0 MOV	%R14,%RDX

  (14) 0x3ca3 MOV	%R13,%RSI

  (14) 0x3ca6 VMOVSD	0x78(%RSP),%XMM2

  (14) 0x3cac MOV	%R15,%RDI

  (14) 0x3caf VMOVSD	%XMM2,0xa0(%RSP)

  (14) 0x3cb8 CALL	4aa0 <exact_solution_>

  (14) 0x3cbd MOV	0x30(%RSP),%RCX

  (14) 0x3cc2 MOV	%R14,%RDX

  (14) 0x3cc5 MOV	%R15,%RSI

  (14) 0x3cc8 MOVQ	$0,0xa0(%RSP)

  (14) 0x3cd4 MOV	%R12,%RDI

  (14) 0x3cd7 CALL	4aa0 <exact_solution_>

  (14) 0x3cdc MOV	0x48(%RSP),%RCX

  (14) 0x3ce1 MOV	%R14,%RDX

  (14) 0x3ce4 MOV	%R15,%RSI

  (14) 0x3ce7 VMOVSD	0x78(%RSP),%XMM2

  (14) 0x3ced MOV	%R12,%RDI

  (14) 0x3cf0 VMOVSD	%XMM2,0xa0(%RSP)

  (14) 0x3cf9 CALL	4aa0 <exact_solution_>

  (14) 0x3cfe MOV	0x58(%RSP),%RCX

  (14) 0x3d03 MOV	%R15,%RDX

  (14) 0x3d06 MOV	%R13,%RSI

  (14) 0x3d09 MOVQ	$0,0xa0(%RSP)

  (14) 0x3d15 MOV	%R12,%RDI

  (14) 0x3d18 CALL	4aa0 <exact_solution_>

  (14) 0x3d1d MOV	0x40(%RSP),%RCX

  (14) 0x3d22 MOV	%R15,%RDX

  (14) 0x3d25 MOV	%R13,%RSI

  (14) 0x3d28 VMOVSD	0x78(%RSP),%XMM2

  (14) 0x3d2e MOV	%R12,%RDI

  (14) 0x3d31 VMOVSD	%XMM2,0xa0(%RSP)

  (14) 0x3d3a CALL	4aa0 <exact_solution_>

  (14) 0x3d3f VMOVSD	0x78(%RSP),%XMM2

  (14) 0x3d45 VMOVSD	0x88(%RSP),%XMM4

  (14) 0x3d4e VMOVSD	0x90(%RSP),%XMM3

  (14) 0x3d57 VSUBSD	%XMM4,%XMM2,%XMM9

  (14) 0x3d5b VMOVDDUP	%XMM4,%XMM1

  (14) 0x3d5f VINSERTF128	$0x1,%XMM1,%YMM1,%YMM1

  (14) 0x3d65 VMOVUPD	0x158(%RSP),%XMM7

  (14) 0x3d6e VINSERTF128	$0x1,0x168(%RSP),%YMM7,%YMM0

  (14) 0x3d79 VSUBSD	%XMM3,%XMM2,%XMM7

  (14) 0x3d7d VMULPD	%YMM1,%YMM0,%YMM0

  (14) 0x3d81 VMOVUPD	0x108(%RSP),%XMM5

  (14) 0x3d8a VMOVDDUP	%XMM3,%XMM8

  (14) 0x3d8e VINSERTF128	$0x1,%XMM8,%YMM8,%YMM8

  (14) 0x3d94 MOV	0x28(%RSP),%RAX

  (14) 0x3d99 VMULPD	0x180(%RSP),%YMM8,%YMM8

  (14) 0x3da2 VMOVDDUP	%XMM9,%XMM10

  (14) 0x3da7 VINSERTF128	$0x1,%XMM10,%YMM10,%YMM10

  (14) 0x3dad VMULPD	0xe0(%RSP),%YMM10,%YMM10

  (14) 0x3db6 VADDPD	%YMM0,%YMM10,%YMM10

  (14) 0x3dba VMOVDDUP	%XMM7,%XMM1

  (14) 0x3dbe VINSERTF128	$0x1,%XMM1,%YMM1,%YMM1

  (14) 0x3dc4 MOV	0x68(%RSP),%RCX

  (14) 0x3dc9 VINSERTF128	$0x1,0x118(%RSP),%YMM5,%YMM0

  (14) 0x3dd4 VMULPD	%YMM1,%YMM0,%YMM0

  (14) 0x3dd8 VADDPD	%YMM0,%YMM8,%YMM8

  (14) 0x3ddc VMOVSD	0x98(%RSP),%XMM0

  (14) 0x3de5 VMOVAPD	0x130(%RSP),%XMM6

  (14) 0x3dee VINSERTF128	$0x1,0x140(%RSP),%YMM6,%YMM6

  (14) 0x3df9 VSUBSD	%XMM0,%XMM2,%XMM5

  (14) 0x3dfd VMOVDDUP	%XMM0,%XMM12

  (14) 0x3e01 MOV	(%RAX),%RDX

  (14) 0x3e04 VINSERTF128	$0x1,%XMM12,%YMM12,%YMM12

  (14) 0x3e0a VMOVUPD	0x1a8(%RSP),%XMM2

  (14) 0x3e13 VMULPD	%YMM10,%YMM8,%YMM11

  (14) 0x3e18 IMUL	0x26478(%RIP),%RCX

  (14) 0x3e20 VMOVDDUP	%XMM5,%XMM1

  (14) 0x3e24 VINSERTF128	$0x1,%XMM1,%YMM1,%YMM1

  (14) 0x3e2a VMULPD	%YMM1,%YMM6,%YMM6

  (14) 0x3e2e VINSERTF128	$0x1,0x1b8(%RSP),%YMM2,%YMM1

  (14) 0x3e39 VMULPD	%YMM12,%YMM1,%YMM1

  (14) 0x3e3e VADDPD	%YMM1,%YMM6,%YMM6

  (14) 0x3e42 MOV	0x70(%RSP),%RAX

  (14) 0x3e47 IMUL	0x26461(%RIP),%RAX

  (14) 0x3e4f VADDPD	%YMM10,%YMM8,%YMM1

  (14) 0x3e54 ADD	0x263ed(%RIP),%RAX

  (14) 0x3e5b VMULPD	%YMM6,%YMM10,%YMM10

  (14) 0x3e5f VMULPD	%YMM6,%YMM8,%YMM8

  (14) 0x3e63 VMULSD	0x178(%RSP),%XMM4,%XMM4

  (14) 0x3e6c VADDPD	%YMM6,%YMM1,%YMM1

  (14) 0x3e70 VMULSD	0x100(%RSP),%XMM9,%XMM9

  (14) 0x3e79 VMULSD	0x1a0(%RSP),%XMM3,%XMM3

  (14) 0x3e82 ADD	%RCX,%RAX

  (14) 0x3e85 VSUBPD	%YMM11,%YMM1,%YMM1

  (14) 0x3e8a MOV	0x263ef(%RIP),%RCX

  (14) 0x3e91 VMULPD	%YMM6,%YMM11,%YMM11

  (14) 0x3e95 VMULSD	0x128(%RSP),%XMM7,%XMM7

  (14) 0x3e9e VMULSD	0x150(%RSP),%XMM5,%XMM5

  (14) 0x3ea7 VMULSD	0x1c8(%RSP),%XMM0,%XMM0

  (14) 0x3eb0 VSUBPD	%YMM10,%YMM1,%YMM1

  (14) 0x3eb5 IMUL	%RBX,%RCX

  (14) 0x3eb9 VADDSD	%XMM9,%XMM4,%XMM4

  (14) 0x3ebe ADD	$0x1,%RBX

  (14) 0x3ec2 VSUBPD	%YMM8,%YMM1,%YMM1

  (14) 0x3ec7 VADDSD	%XMM7,%XMM3,%XMM3

  (14) 0x3ecb VADDSD	%XMM5,%XMM0,%XMM0

  (14) 0x3ecf VADDPD	%YMM11,%YMM1,%YMM1

  (14) 0x3ed4 ADD	%RCX,%RAX

  (14) 0x3ed7 VMULSD	%XMM3,%XMM4,%XMM5

  (14) 0x3edb VMOVUPD	%XMM1,0x8(%RDX,%RAX,8)

  (14) 0x3ee1 VEXTRACTF128	$0x1,%YMM1,0x18(%RDX,%RAX,8)

  (14) 0x3ee9 VADDSD	%XMM3,%XMM4,%XMM1

  (14) 0x3eed VMULSD	%XMM0,%XMM4,%XMM4

  (14) 0x3ef1 VMULSD	%XMM0,%XMM3,%XMM3

  (14) 0x3ef5 VADDSD	%XMM0,%XMM1,%XMM1

  (14) 0x3ef9 VMULSD	%XMM5,%XMM0,%XMM0

  (14) 0x3efd VSUBSD	%XMM5,%XMM1,%XMM1

  (14) 0x3f01 VSUBSD	%XMM4,%XMM1,%XMM1

  (14) 0x3f05 VSUBSD	%XMM3,%XMM1,%XMM1

  (14) 0x3f09 VADDSD	%XMM0,%XMM1,%XMM0

  (14) 0x3f0d VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

  (14) 0x3f13 CMP	%RBX,0x60(%RSP)

  (14) 0x3f18 JNE	3c60

(12) 0x3f1e MOV	0x24(%RSP),%ECX

(12) 0x3f22 MOV	0x20(%RSP),%EDX

(12) 0x3f26 VZEROUPPER

(12) 0x3f29 MOV	0x1c(%RSP),%EAX

(12) 0x3f2d ADD	$0x1,%EAX

(12) 0x3f30 CMP	%EAX,0x14(%RSP)

(12) 0x3f34 JE	49bc

(12) 0x3f3a ADD	$0x1,%ECX

(12) 0x3f3d CMP	%ECX,0x10(%RSP)

(12) 0x3f41 JLE	48f4

(12) 0x3f47 TEST	%EDX,%EDX

(12) 0x3f49 JLE	4915

(12) 0x3f4f MOV	%EAX,0x1c(%RSP)

(12) 0x3f53 JMP	3b80

0x3f58 MOV	0x265d9(%RIP),%R12D

0x3f5f VMOVSD	0x40(%RSP),%XMM2

0x3f65 MOV	0x265c9(%RIP),%ESI

0x3f6b VMOVSD	%XMM2,0x88(%RSP)

0x3f74 MOV	0x265b6(%RIP),%EBX

0x3f7a TEST	%R12D,%R12D

0x3f7d JLE	4a4c

0x3f83 TEST	%ESI,%ESI

0x3f85 JLE	4a4c

0x3f8b VZEROUPPER

0x3f8e VMOVSD	%XMM2,0x70(%RSP)

0x3f94 MOV	%ESI,0x78(%RSP)

0x3f98 CALL	2050 <@plt_start@+0x30>

0x3f9d MOV	%EAX,%R13D

0x3fa0 CALL	20d0 <@plt_start@+0xb0>

0x3fa5 MOV	0x78(%RSP),%ESI

0x3fa9 XOR	%EDX,%EDX

0x3fab MOV	%EAX,%ECX

0x3fad VMOVSD	0x70(%RSP),%XMM2

0x3fb3 IMUL	%ESI,%R12D

0x3fb7 MOV	%R12D,%EAX

0x3fba DIV	%R13D

0x3fbd CMP	%EDX,%ECX

0x3fbf MOV	%EAX,%R12D

0x3fc2 JB	4a00

0x3fc8 IMUL	%R12D,%ECX

0x3fcc LEA	(%RCX,%RDX,1),%EAX

0x3fcf LEA	(%R12,%RAX,1),%EDX

0x3fd3 CMP	%EDX,%EAX

0x3fd5 JAE	4148

0x3fdb XOR	%EDX,%EDX

0x3fdd SUB	$0x1,%EBX

0x3fe0 VXORPD	%XMM6,%XMM6,%XMM6

0x3fe4 XOR	%R15D,%R15D

0x3fe7 DIV	%ESI

0x3fe9 MOVSXD	%EBX,%RBX

0x3fec VMOVSD	%XMM2,0x38(%RSP)

0x3ff2 MOV	%ESI,%R13D

0x3ff5 MOV	%RBX,0x58(%RSP)

0x3ffa LEA	-0x1(%R12),%EBX

0x3fff MOV	%EBX,0x50(%RSP)

0x4003 LEA	0xa0(%RSP),%RBX

0x400b MOV	%RBX,0x68(%RSP)

0x4010 LEA	0x98(%RSP),%RBX

0x4018 LEA	0x88(%RSP),%R12

0x4020 MOV	%RBX,0x70(%RSP)

0x4025 LEA	0x90(%RSP),%RBX

0x402d MOV	%R12,0x48(%RSP)

0x4032 MOV	%R15D,%R12D

0x4035 MOV	%RBX,0x78(%RSP)

0x403a LEA	0x261ff(%RIP),%RBX

0x4041 VCVTSI2SD	%EAX,%XMM6,%XMM0

0x4045 MOVSXD	%EAX,%R14

0x4048 MOV	%EAX,0x40(%RSP)

0x404c MOV	%EDX,%R15D

0x404f VMOVSD	%XMM0,0x60(%RSP)

0x4055 JMP	4067

0x4057 NOPW	(%RAX,%RAX,1)

(10) 0x4060 ADD	$0x1,%R12D

(10) 0x4064 VZEROUPPER

(10) 0x4067 VMOVSD	0x60(%RSP),%XMM5

(10) 0x406d VXORPD	%XMM6,%XMM6,%XMM6

(10) 0x4071 VMULSD	0x266a7(%RIP),%XMM5,%XMM0

(10) 0x4079 MOV	0x68(%RSP),%RCX

(10) 0x407e MOV	0x70(%RSP),%RDX

(10) 0x4083 MOV	0x78(%RSP),%RSI

(10) 0x4088 MOV	0x48(%RSP),%RDI

(10) 0x408d VMOVSD	%XMM0,0x98(%RSP)

(10) 0x4096 VCVTSI2SD	%R15D,%XMM6,%XMM0

(10) 0x409b VMULSD	0x26685(%RIP),%XMM0,%XMM0

(10) 0x40a3 VMOVSD	%XMM0,0x90(%RSP)

(10) 0x40ac CALL	4aa0 <exact_solution_>

(10) 0x40b1 MOV	0x261f8(%RIP),%RAX

(10) 0x40b8 MOVSXD	%R15D,%RCX

(10) 0x40bb IMUL	0x261d5(%RIP),%RCX

(10) 0x40c3 MOV	(%RBX),%RDX

(10) 0x40c6 VMOVAPD	0xa0(%RSP),%YMM7

(10) 0x40cf VMOVSD	0xc0(%RSP),%XMM0

(10) 0x40d8 IMUL	%R14,%RAX

(10) 0x40dc ADD	0x26165(%RIP),%RAX

(10) 0x40e3 ADD	%RCX,%RAX

(10) 0x40e6 MOV	0x58(%RSP),%RCX

(10) 0x40eb IMUL	0x2618d(%RIP),%RCX

(10) 0x40f3 ADD	%RCX,%RAX

(10) 0x40f6 VMOVUPD	%XMM7,0x8(%RDX,%RAX,8)

(10) 0x40fc VEXTRACTF128	$0x1,%YMM7,0x18(%RDX,%RAX,8)

(10) 0x4104 VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

(10) 0x410a CMP	%R12D,0x50(%RSP)

(10) 0x410f JE	413f

(10) 0x4111 ADD	$0x1,%R15D

(10) 0x4115 CMP	%R15D,%R13D

(10) 0x4118 JG	4060

(10) 0x411e ADDL	$0x1,0x40(%RSP)

(10) 0x4123 VXORPD	%XMM3,%XMM3,%XMM3

(10) 0x4127 XOR	%R15D,%R15D

(10) 0x412a MOVSXD	0x40(%RSP),%R14

(10) 0x412f VCVTSI2SD	%R14D,%XMM3,%XMM0

(10) 0x4134 VMOVSD	%XMM0,0x60(%RSP)

(10) 0x413a JMP	4060

0x413f VMOVSD	0x38(%RSP),%XMM2

0x4145 VZEROUPPER

0x4148 VMOVSD	%XMM2,0x78(%RSP)

0x414e CALL	2160 <@plt_start@+0x140>

0x4153 MOV	0x263df(%RIP),%EBX

0x4159 MOVQ	$0,0x90(%RSP)

0x4165 MOV	0x263c4(%RIP),%R8D

0x416c VMOVSD	0x78(%RSP),%XMM2

0x4172 TEST	%EBX,%EBX

0x4174 JLE	4a5c

0x417a TEST	%R8D,%R8D

0x417d JLE	4a5c

0x4183 VMOVSD	%XMM2,0x70(%RSP)

0x4189 MOV	%EBX,%R14D

0x418c MOV	%R8D,0x78(%RSP)

0x4191 CALL	2050 <@plt_start@+0x30>

0x4196 MOV	%EAX,%R15D

0x4199 MOV	%EAX,0x48(%RSP)

0x419d CALL	20d0 <@plt_start@+0xb0>

0x41a2 MOV	0x78(%RSP),%R8D

0x41a7 XOR	%EDX,%EDX

0x41a9 MOV	%EAX,%ECX

0x41ab VMOVSD	0x70(%RSP),%XMM2

0x41b1 IMUL	%R8D,%R14D

0x41b5 MOV	%R14D,%EAX

0x41b8 DIV	%R15D

0x41bb CMP	%EDX,%ECX

0x41bd MOV	%EAX,%R14D

0x41c0 JB	4a41

0x41c6 MOV	%R14D,%EAX

0x41c9 IMUL	%ECX,%EAX

0x41cc ADD	%EDX,%EAX

0x41ce LEA	(%R14,%RAX,1),%EDX

0x41d2 CMP	%EDX,%EAX

0x41d4 JAE	48b7

0x41da XOR	%EDX,%EDX

0x41dc VXORPD	%XMM3,%XMM3,%XMM3

0x41e0 SUB	$0x1,%R14D

0x41e4 XOR	%R15D,%R15D

0x41e7 DIV	%R8D

0x41ea MOV	%ECX,0x38(%RSP)

0x41ee MOV	%R8D,0x50(%RSP)

0x41f3 VMOVSD	%XMM2,0x30(%RSP)

0x41f9 LEA	0xa0(%RSP),%RBX

0x4201 MOV	%RBX,0x68(%RSP)

0x4206 LEA	0x98(%RSP),%RBX

0x420e MOV	%RBX,0x70(%RSP)

0x4213 LEA	0x90(%RSP),%RBX

0x421b LEA	0x88(%RSP),%R12

0x4223 MOV	%RBX,0x78(%RSP)

0x4228 LEA	0x26011(%RIP),%RBX

0x422f MOV	%R12,0x58(%RSP)

0x4234 MOV	%RBX,%R12

0x4237 VCVTSI2SD	%EAX,%XMM3,%XMM0

0x423b MOVSXD	%EAX,%RSI

0x423e MOV	%EAX,0x40(%RSP)

0x4242 MOV	%EDX,%R13D

0x4245 MOV	%RSI,%RBX

0x4248 VMOVSD	%XMM0,0x60(%RSP)

0x424e JMP	4257

(9) 0x4250 ADD	$0x1,%R15D

(9) 0x4254 VZEROUPPER

(9) 0x4257 VMOVSD	0x60(%RSP),%XMM7

(9) 0x425d VXORPD	%XMM5,%XMM5,%XMM5

(9) 0x4261 VMULSD	0x264b7(%RIP),%XMM7,%XMM0

(9) 0x4269 MOV	0x68(%RSP),%RCX

(9) 0x426e MOV	0x70(%RSP),%RDX

(9) 0x4273 MOV	0x78(%RSP),%RSI

(9) 0x4278 MOV	0x58(%RSP),%RDI

(9) 0x427d VMOVSD	%XMM0,0x98(%RSP)

(9) 0x4286 VCVTSI2SD	%R13D,%XMM5,%XMM0

(9) 0x428b VMULSD	0x2649d(%RIP),%XMM0,%XMM0

(9) 0x4293 VMOVSD	%XMM0,0x88(%RSP)

(9) 0x429c CALL	4aa0 <exact_solution_>

(9) 0x42a1 MOV	0x26008(%RIP),%RAX

(9) 0x42a8 MOVSXD	%R13D,%RCX

(9) 0x42ab IMUL	0x25fcd(%RIP),%RCX

(9) 0x42b3 MOV	(%R12),%RDX

(9) 0x42b7 VMOVAPD	0xa0(%RSP),%YMM6

(9) 0x42c0 VMOVSD	0xc0(%RSP),%XMM0

(9) 0x42c9 IMUL	%RBX,%RAX

(9) 0x42cd ADD	0x25f74(%RIP),%RAX

(9) 0x42d4 ADD	%RCX,%RAX

(9) 0x42d7 VMOVUPD	%XMM6,0x8(%RDX,%RAX,8)

(9) 0x42dd VEXTRACTF128	$0x1,%YMM6,0x18(%RDX,%RAX,8)

(9) 0x42e5 VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

(9) 0x42eb CMP	%R15D,%R14D

(9) 0x42ee JE	431f

(9) 0x42f0 ADD	$0x1,%R13D

(9) 0x42f4 CMP	%R13D,0x50(%RSP)

(9) 0x42f9 JG	4250

(9) 0x42ff ADDL	$0x1,0x40(%RSP)

(9) 0x4304 VXORPD	%XMM4,%XMM4,%XMM4

(9) 0x4308 XOR	%R13D,%R13D

(9) 0x430b MOVSXD	0x40(%RSP),%RBX

(9) 0x4310 VCVTSI2SD	%EBX,%XMM4,%XMM0

(9) 0x4314 VMOVSD	%XMM0,0x60(%RSP)

(9) 0x431a JMP	4250

0x431f MOV	0x26213(%RIP),%EAX

0x4325 VMOVSD	0x30(%RSP),%XMM2

0x432b MOV	0x38(%RSP),%ECX

0x432f VMOVSD	%XMM2,0x90(%RSP)

0x4338 MOV	0x261f1(%RIP),%R8D

0x433f MOV	0x261ee(%RIP),%R9D

0x4346 TEST	%EAX,%EAX

0x4348 JLE	4a54

0x434e TEST	%R8D,%R8D

0x4351 JLE	4a54

0x4357 VZEROUPPER

0x435a IMUL	%R8D,%EAX

0x435e XOR	%EDX,%EDX

0x4360 DIVL	0x48(%RSP)

0x4364 MOV	%EAX,%R15D

0x4367 CMP	%EDX,%ECX

0x4369 JB	4a36

0x436f MOV	%ECX,%ESI

0x4371 IMUL	%R15D,%ESI

0x4375 LEA	(%RSI,%RDX,1),%EAX

0x4378 LEA	(%R15,%RAX,1),%EDX

0x437c CMP	%EDX,%EAX

0x437e JAE	44f0

0x4384 XOR	%EDX,%EDX

0x4386 SUB	$0x1,%R9D

0x438a VXORPD	%XMM4,%XMM4,%XMM4

0x438e VMOVSD	%XMM2,0x38(%RSP)

0x4394 DIV	%R8D

0x4397 MOVSXD	%R9D,%RBX

0x439a MOV	%R8D,%R13D

0x439d MOV	%RBX,0x58(%RSP)

0x43a2 LEA	-0x1(%R15),%EBX

0x43a6 XOR	%R15D,%R15D

0x43a9 MOV	%EBX,0x50(%RSP)

0x43ad LEA	0xa0(%RSP),%RBX

0x43b5 MOV	%RBX,0x68(%RSP)

0x43ba LEA	0x98(%RSP),%RBX

0x43c2 LEA	0x88(%RSP),%R12

0x43ca MOV	%RBX,0x70(%RSP)

0x43cf LEA	0x90(%RSP),%RBX

0x43d7 MOV	%R12,0x48(%RSP)

0x43dc MOV	%R15D,%R12D

0x43df MOV	%RBX,0x78(%RSP)

0x43e4 LEA	0x25e55(%RIP),%RBX

0x43eb VCVTSI2SD	%EAX,%XMM4,%XMM0

0x43ef MOVSXD	%EAX,%R14

0x43f2 MOV	%EAX,0x40(%RSP)

0x43f6 MOV	%EDX,%R15D

0x43f9 VMOVSD	%XMM0,0x60(%RSP)

0x43ff JMP	440f

0x4401 NOPL	(%RAX)

(8) 0x4408 ADD	$0x1,%R12D

(8) 0x440c VZEROUPPER

(8) 0x440f VMOVSD	0x60(%RSP),%XMM7

(8) 0x4415 VXORPD	%XMM5,%XMM5,%XMM5

(8) 0x4419 VMULSD	0x262ff(%RIP),%XMM7,%XMM0

(8) 0x4421 MOV	0x68(%RSP),%RCX

(8) 0x4426 MOV	0x70(%RSP),%RDX

(8) 0x442b MOV	0x78(%RSP),%RSI

(8) 0x4430 MOV	0x48(%RSP),%RDI

(8) 0x4435 VMOVSD	%XMM0,0x98(%RSP)

(8) 0x443e VCVTSI2SD	%R15D,%XMM5,%XMM0

(8) 0x4443 VMULSD	0x262e5(%RIP),%XMM0,%XMM0

(8) 0x444b VMOVSD	%XMM0,0x88(%RSP)

(8) 0x4454 CALL	4aa0 <exact_solution_>

(8) 0x4459 MOV	0x25e50(%RIP),%RAX

(8) 0x4460 MOV	0x58(%RSP),%RCX

(8) 0x4465 IMUL	0x25e2b(%RIP),%RCX

(8) 0x446d MOV	(%RBX),%RDX

(8) 0x4470 VMOVAPD	0xa0(%RSP),%YMM7

(8) 0x4479 IMUL	%R14,%RAX

(8) 0x447d ADD	0x25dc4(%RIP),%RAX

(8) 0x4484 VMOVSD	0xc0(%RSP),%XMM0

(8) 0x448d ADD	%RCX,%RAX

(8) 0x4490 MOVSXD	%R15D,%RCX

(8) 0x4493 IMUL	0x25de5(%RIP),%RCX

(8) 0x449b ADD	%RCX,%RAX

(8) 0x449e VMOVUPD	%XMM7,0x8(%RDX,%RAX,8)

(8) 0x44a4 VEXTRACTF128	$0x1,%YMM7,0x18(%RDX,%RAX,8)

(8) 0x44ac VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

(8) 0x44b2 CMP	%R12D,0x50(%RSP)

(8) 0x44b7 JE	44e7

(8) 0x44b9 ADD	$0x1,%R15D

(8) 0x44bd CMP	%R13D,%R15D

(8) 0x44c0 JL	4408

(8) 0x44c6 ADDL	$0x1,0x40(%RSP)

(8) 0x44cb VXORPD	%XMM6,%XMM6,%XMM6

(8) 0x44cf XOR	%R15D,%R15D

(8) 0x44d2 MOVSXD	0x40(%RSP),%R14

(8) 0x44d7 VCVTSI2SD	%R14D,%XMM6,%XMM0

(8) 0x44dc VMOVSD	%XMM0,0x60(%RSP)

(8) 0x44e2 JMP	4408

0x44e7 VMOVSD	0x38(%RSP),%XMM2

0x44ed VZEROUPPER

0x44f0 VMOVSD	%XMM2,0x78(%RSP)

0x44f6 CALL	2160 <@plt_start@+0x140>

0x44fb MOV	0x26032(%RIP),%R12D

0x4502 MOVQ	$0,0x98(%RSP)

0x450e MOV	0x2601b(%RIP),%R13D

0x4515 VMOVSD	0x78(%RSP),%XMM2

0x451b TEST	%R12D,%R12D

0x451e JLE	46d2

0x4524 VMOVSD	%XMM2,0x78(%RSP)

0x452a TEST	%R13D,%R13D

0x452d JLE	46d2

0x4533 CALL	2050 <@plt_start@+0x30>

0x4538 MOV	%R12D,%R14D

0x453b IMUL	%R13D,%R14D

0x453f MOV	%EAX,%EBX

0x4541 MOV	%EAX,0x48(%RSP)

0x4545 CALL	20d0 <@plt_start@+0xb0>

0x454a XOR	%EDX,%EDX

0x454c VMOVSD	0x78(%RSP),%XMM2

0x4552 MOV	%EAX,%ESI

0x4554 MOV	%R14D,%EAX

0x4557 DIV	%EBX

0x4559 CMP	%EDX,%ESI

0x455b MOV	%EAX,%R14D

0x455e JB	4a2b

0x4564 MOV	%R14D,%EAX

0x4567 IMUL	%ESI,%EAX

0x456a ADD	%EDX,%EAX

0x456c LEA	(%R14,%RAX,1),%EDX

0x4570 CMP	%EDX,%EAX

0x4572 JAE	48a3

0x4578 LEA	-0x1(%R14),%EBX

0x457c XOR	%EDX,%EDX

0x457e VXORPD	%XMM4,%XMM4,%XMM4

0x4582 XOR	%R14D,%R14D

0x4585 DIV	%R13D

0x4588 MOV	%EBX,0x58(%RSP)

0x458c MOV	%ESI,0x38(%RSP)

0x4590 VMOVSD	%XMM2,0x30(%RSP)

0x4596 LEA	0xa0(%RSP),%RBX

0x459e MOV	%RBX,0x68(%RSP)

0x45a3 LEA	0x98(%RSP),%RBX

0x45ab MOV	%RBX,0x70(%RSP)

0x45b0 LEA	0x90(%RSP),%RBX

0x45b8 LEA	0x88(%RSP),%R12

0x45c0 MOV	%RBX,0x78(%RSP)

0x45c5 LEA	0x25c74(%RIP),%RBX

0x45cc MOV	%R12,0x50(%RSP)

0x45d1 MOV	%RBX,%R12

0x45d4 VCVTSI2SD	%EAX,%XMM4,%XMM0

0x45d8 MOVSXD	%EAX,%RDI

0x45db MOV	%EAX,0x40(%RSP)

0x45df MOV	%R14D,%EAX

0x45e2 MOV	%EDX,%R15D

0x45e5 MOV	%R13D,%R14D

0x45e8 MOV	%RDI,%RBX

0x45eb MOV	%EAX,%R13D

0x45ee VMOVSD	%XMM0,0x60(%RSP)

0x45f4 JMP	4607

0x45f6 NOPW	%CS:(%RAX,%RAX,1)

(7) 0x4600 ADD	$0x1,%R13D

(7) 0x4604 VZEROUPPER

(7) 0x4607 VMOVSD	0x60(%RSP),%XMM7

(7) 0x460d VXORPD	%XMM5,%XMM5,%XMM5

(7) 0x4611 VMULSD	0x2610f(%RIP),%XMM7,%XMM0

(7) 0x4619 MOV	0x68(%RSP),%RCX

(7) 0x461e MOV	0x70(%RSP),%RDX

(7) 0x4623 MOV	0x78(%RSP),%RSI

(7) 0x4628 MOV	0x50(%RSP),%RDI

(7) 0x462d VMOVSD	%XMM0,0x90(%RSP)

(7) 0x4636 VCVTSI2SD	%R15D,%XMM5,%XMM0

(7) 0x463b VMULSD	0x260ed(%RIP),%XMM0,%XMM0

(7) 0x4643 VMOVSD	%XMM0,0x88(%RSP)

(7) 0x464c CALL	4aa0 <exact_solution_>

(7) 0x4651 MOV	0x25c40(%RIP),%RAX

(7) 0x4658 MOVSXD	%R15D,%RCX

(7) 0x465b IMUL	0x25c1d(%RIP),%RCX

(7) 0x4663 MOV	(%R12),%RDX

(7) 0x4667 VMOVAPD	0xa0(%RSP),%YMM7

(7) 0x4670 VMOVSD	0xc0(%RSP),%XMM0

(7) 0x4679 IMUL	%RBX,%RAX

(7) 0x467d ADD	0x25bc4(%RIP),%RAX

(7) 0x4684 ADD	%RCX,%RAX

(7) 0x4687 VMOVUPD	%XMM7,0x8(%RDX,%RAX,8)

(7) 0x468d VEXTRACTF128	$0x1,%YMM7,0x18(%RDX,%RAX,8)

(7) 0x4695 VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

(7) 0x469b CMP	%R13D,0x58(%RSP)

(7) 0x46a0 JE	46e1

(7) 0x46a2 ADD	$0x1,%R15D

(7) 0x46a6 CMP	%R15D,%R14D

(7) 0x46a9 JG	4600

(7) 0x46af ADDL	$0x1,0x40(%RSP)

(7) 0x46b4 VXORPD	%XMM3,%XMM3,%XMM3

(7) 0x46b8 XOR	%R15D,%R15D

(7) 0x46bb MOVSXD	0x40(%RSP),%RBX

(7) 0x46c0 VCVTSI2SD	%EBX,%XMM3,%XMM0

(7) 0x46c4 VMOVSD	%XMM0,0x60(%RSP)

(7) 0x46ca JMP	4600

0x46cf VZEROUPPER

0x46d2 LEA	-0x28(%RBP),%RSP

0x46d6 POP	%RBX

0x46d7 POP	%R12

0x46d9 POP	%R13

0x46db POP	%R14

0x46dd POP	%R15

0x46df POP	%RBP

0x46e0 RET

0x46e1 MOV	0x25e4c(%RIP),%R12D

0x46e8 VMOVSD	0x30(%RSP),%XMM2

0x46ee MOV	0x38(%RSP),%ESI

0x46f2 VMOVSD	%XMM2,0x98(%RSP)

0x46fb MOV	0x25e2e(%RIP),%R13D

0x4702 MOV	0x25e30(%RIP),%EDI

0x4708 TEST	%R12D,%R12D

0x470b JLE	46cf

0x470d TEST	%R13D,%R13D

0x4710 JLE	46cf

0x4712 VZEROUPPER

0x4715 IMUL	%R13D,%R12D

0x4719 XOR	%EDX,%EDX

0x471b MOV	%R12D,%EAX

0x471e DIVL	0x48(%RSP)

0x4722 MOV	%EAX,%R12D

0x4725 CMP	%EDX,%ESI

0x4727 JB	4a20

0x472d IMUL	%R12D,%ESI

0x4731 LEA	(%RSI,%RDX,1),%EAX

0x4734 LEA	(%R12,%RAX,1),%EDX

0x4738 CMP	%EDX,%EAX

0x473a JAE	46d2

0x473c XOR	%EDX,%EDX

0x473e SUB	$0x1,%EDI

0x4741 VXORPD	%XMM4,%XMM4,%XMM4

0x4745 XOR	%R14D,%R14D

0x4748 DIV	%R13D

0x474b MOVSXD	%EDI,%RBX

0x474e MOV	%RBX,0x50(%RSP)

0x4753 LEA	-0x1(%R12),%EBX

0x4758 MOV	%EBX,0x58(%RSP)

0x475c LEA	0xa0(%RSP),%RBX

0x4764 MOV	%RBX,0x68(%RSP)

0x4769 LEA	0x98(%RSP),%RBX

0x4771 MOV	%RBX,0x70(%RSP)

0x4776 LEA	0x90(%RSP),%RBX

0x477e LEA	0x88(%RSP),%R12

0x4786 MOV	%RBX,0x78(%RSP)

0x478b LEA	0x25aae(%RIP),%RBX

0x4792 MOV	%R12,0x48(%RSP)

0x4797 MOV	%RBX,%R12

0x479a VCVTSI2SD	%EAX,%XMM4,%XMM0

0x479e MOVSXD	%EAX,%RSI

0x47a1 MOV	%EAX,0x40(%RSP)

0x47a5 MOV	%R14D,%EAX

0x47a8 MOV	%EDX,%R15D

0x47ab MOV	%R13D,%R14D

0x47ae MOV	%RSI,%RBX

0x47b1 MOV	%EAX,%R13D

0x47b4 VMOVSD	%XMM0,0x60(%RSP)

0x47ba JMP	47c7

0x47bc NOPL	(%RAX)

(6) 0x47c0 ADD	$0x1,%R13D

(6) 0x47c4 VZEROUPPER

(6) 0x47c7 VMOVSD	0x60(%RSP),%XMM7

(6) 0x47cd VMULSD	0x25f53(%RIP),%XMM7,%XMM0

(6) 0x47d5 VXORPD	%XMM7,%XMM7,%XMM7

(6) 0x47d9 MOV	0x68(%RSP),%RCX

(6) 0x47de MOV	0x70(%RSP),%RDX

(6) 0x47e3 MOV	0x78(%RSP),%RSI

(6) 0x47e8 MOV	0x48(%RSP),%RDI

(6) 0x47ed VMOVSD	%XMM0,0x90(%RSP)

(6) 0x47f6 VCVTSI2SD	%R15D,%XMM7,%XMM0

(6) 0x47fb VMULSD	0x25f2d(%RIP),%XMM0,%XMM0

(6) 0x4803 VMOVSD	%XMM0,0x88(%RSP)

(6) 0x480c CALL	4aa0 <exact_solution_>

(6) 0x4811 MOV	0x25a80(%RIP),%RCX

(6) 0x4818 MOV	0x50(%RSP),%RAX

(6) 0x481d IMUL	0x25a8b(%RIP),%RAX

(6) 0x4825 ADD	0x25a1c(%RIP),%RAX

(6) 0x482c MOV	(%R12),%RDX

(6) 0x4830 VMOVAPD	0xa0(%RSP),%YMM7

(6) 0x4839 IMUL	%RBX,%RCX

(6) 0x483d VMOVSD	0xc0(%RSP),%XMM0

(6) 0x4846 ADD	%RCX,%RAX

(6) 0x4849 MOVSXD	%R15D,%RCX

(6) 0x484c IMUL	0x25a2c(%RIP),%RCX

(6) 0x4854 ADD	%RCX,%RAX

(6) 0x4857 VMOVUPD	%XMM7,0x8(%RDX,%RAX,8)

(6) 0x485d VEXTRACTF128	$0x1,%YMM7,0x18(%RDX,%RAX,8)

(6) 0x4865 VMOVSD	%XMM0,0x28(%RDX,%RAX,8)

(6) 0x486b CMP	%R13D,0x58(%RSP)

(6) 0x4870 JE	46cf

(6) 0x4876 ADD	$0x1,%R15D

(6) 0x487a CMP	%R14D,%R15D

(6) 0x487d JL	47c0

(6) 0x4883 ADDL	$0x1,0x40(%RSP)

(6) 0x4888 VXORPD	%XMM3,%XMM3,%XMM3

(6) 0x488c XOR	%R15D,%R15D

(6) 0x488f MOVSXD	0x40(%RSP),%RBX

(6) 0x4894 VCVTSI2SD	%EBX,%XMM3,%XMM0

(6) 0x4898 VMOVSD	%XMM0,0x60(%RSP)

(6) 0x489e JMP	47c0

0x48a3 VMOVSD	%XMM2,0x98(%RSP)

0x48ac MOV	0x25c86(%RIP),%EDI

0x48b2 JMP	4715

0x48b7 MOV	0x25c76(%RIP),%R9D

0x48be MOV	%EBX,%EAX

0x48c0 VMOVSD	%XMM2,0x90(%RSP)

0x48c9 JMP	435a

0x48ce VMOVSD	%XMM2,0x88(%RSP)

0x48d7 MOV	0x25c53(%RIP),%EBX

0x48dd JMP	3f8e

(16) 0x48e2 ADDL	$0x1,0x78(%RSP)

(16) 0x48e7 XOR	%R9D,%R9D

(16) 0x48ea MOVSXD	0x78(%RSP),%R11

(16) 0x48ef JMP	3b3d

(12) 0x48f4 ADDL	$0x1,0x18(%RSP)

(12) 0x48f9 VXORPD	%XMM7,%XMM7,%XMM7

(12) 0x48fd XOR	%ECX,%ECX

(12) 0x48ff MOV	0x18(%RSP),%EBX

(12) 0x4903 VCVTSI2SD	%EBX,%XMM7,%XMM0

(12) 0x4907 VMOVSD	%XMM0,0x8(%RSP)

(12) 0x490d TEST	%EDX,%EDX

(12) 0x490f JG	3f4f

0x4915 VMOVSD	0x25e03(%RIP),%XMM3

0x491d VXORPD	%XMM6,%XMM6,%XMM6

0x4921 VMULSD	0x8(%RSP),%XMM3,%XMM0

0x4927 VMOVSD	0x25df9(%RIP),%XMM1

0x492f MOV	0x1c(%RSP),%EDI

0x4933 MOV	0x14(%RSP),%EBX

0x4937 MOV	0x18(%RSP),%R10D

0x493c VMOVSD	%XMM0,0x98(%RSP)

0x4945 MOV	0x10(%RSP),%ESI

0x4949 VCVTSI2SD	%ECX,%XMM6,%XMM0

0x494d ADD	$0x2,%EDI

0x4950 VMOVSD	0x78(%RSP),%XMM2

0x4956 VMULSD	%XMM1,%XMM0,%XMM0

0x495a VMOVSD	%XMM0,0x90(%RSP)

0x4963 CMP	%EBX,%EDI

0x4965 JAE	49c2

0x4967 SUB	$0x1,%EBX

0x496a MOV	%EBX,%EDX

0x496c SUB	%EAX,%EDX

0x496e XOR	%EAX,%EAX

0x4970 JMP	497f

0x4972 NOPW	(%RAX,%RAX,1)

(13) 0x4978 ADD	$0x1,%EAX

(13) 0x497b CMP	%EAX,%EDX

(13) 0x497d JE	4993

(13) 0x497f ADD	$0x1,%ECX

(13) 0x4982 CMP	%ECX,%ESI

(13) 0x4984 JG	4978

(13) 0x4986 ADD	$0x1,%EAX

(13) 0x4989 ADD	$0x1,%R10D

(13) 0x498d XOR	%ECX,%ECX

(13) 0x498f CMP	%EAX,%EDX

(13) 0x4991 JNE	497f

0x4993 VXORPD	%XMM6,%XMM6,%XMM6

0x4997 VCVTSI2SD	%R10D,%XMM6,%XMM0

0x499c VMULSD	%XMM3,%XMM0,%XMM0

0x49a0 VMOVSD	%XMM0,0x98(%RSP)

0x49a9 VCVTSI2SD	%ECX,%XMM6,%XMM0

0x49ad VMULSD	%XMM1,%XMM0,%XMM0

0x49b1 VMOVSD	%XMM0,0x90(%RSP)

0x49ba JMP	49c2

0x49bc VMOVSD	0x78(%RSP),%XMM2

0x49c2 MOV	0x25b6f(%RIP),%R12D

0x49c9 MOVQ	$0,0x88(%RSP)

0x49d5 MOV	0x25b59(%RIP),%ESI

0x49db TEST	%R12D,%R12D

0x49de JLE	49e8

0x49e0 TEST	%ESI,%ESI

0x49e2 JG	390b

0x49e8 VMOVSD	%XMM2,0x88(%RSP)

0x49f1 JMP	4148

0x49f6 NOPW	%CS:(%RAX,%RAX,1)

0x4a00 ADD	$0x1,%R12D

0x4a04 XOR	%EDX,%EDX

0x4a06 JMP	3fc8

0x4a0b ADD	$0x1,%ECX

0x4a0e XOR	%EDX,%EDX

0x4a10 JMP	3922

0x4a15 ADD	$0x1,%R10D

0x4a19 XOR	%EDX,%EDX

0x4a1b JMP	38dc

0x4a20 ADD	$0x1,%R12D

0x4a24 XOR	%EDX,%EDX

0x4a26 JMP	472d

0x4a2b ADD	$0x1,%R14D

0x4a2f XOR	%EDX,%EDX

0x4a31 JMP	4564

0x4a36 ADD	$0x1,%R15D

0x4a3a XOR	%EDX,%EDX

0x4a3c JMP	436f

0x4a41 ADD	$0x1,%R14D

0x4a45 XOR	%EDX,%EDX

0x4a47 JMP	41c6

0x4a4c VZEROUPPER

0x4a4f JMP	4148

0x4a54 VZEROUPPER

0x4a57 JMP	44f0

0x4a5c VMOVSD	%XMM2,0x90(%RSP)

0x4a65 JMP	44f0

0x4a6a VMOVSD	0x2352e(%RIP),%XMM2

0x4a72 JMP	49e8

0x4a77 NOPW	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►50.00+	omp_fulfill_event		libgomp.so.1.0.0
○	pthread_condattr_setpshared		libc.so.6
○	__clone		libc.so.6
►50.00+	GOMP_parallel		libgomp.so.1.0.0
○	bt	bt.f90:134	bt.A.x
○	main	bt.f90:47	bt.A.x
○	__libc_init_first		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	bt.f90:47	bt.A.x

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 run_0

Source file and lines	initialize.f90:23-197
Module	bt.A.x

The function is defined in /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:23,30-35,51-81,97-105,115-124,134-142,152-161,171-179,188-197.

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 198.00 to 43.25 cycles (4.58x 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 32% 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 198.00 to 117.95 cycles (1.68x 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

Performance is limited by execution of divide and square root operations (the divide/square root unit is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 198.00 to 161.00 cycles (1.23x speedup).

Workaround

Reduce the number of division or square root instructions:
- If denominator is constant over iterations, use reciprocal (replace x/y with x*(1/y)). Check precision impact. This will be done by your compiler with ffast-math or Ofast
Check whether you really need double precision. If not, switch to single precision to speedup execution

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 198.00 to 137.00 cycles (1.45x speedup).

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.

unknown: 10 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:30
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:30
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:172
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:172

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.

DIV: 11 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:30
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:105
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:142
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:152
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:172
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:197
RET: 1 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:23
VBROADCASTSD: 1 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:35
VCVTSI2SD: 10 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:105
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:142
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:197
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:51
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52
VZEROUPPER: 9 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:152
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:188
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 10 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:105
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:142
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:197
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:51
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52

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

4 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 4 FP arithmetical operations:

4: multiply

The binary function is loading 352 bytes (44 double precision FP elements). The binary function is storing 600 bytes (75 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	489
nb uops	644
loop length	2188
used x86 registers	16
used mmx registers	0
used xmm registers	6
used ymm registers	1
used zmm registers	0
nb stack references	22

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	161.00 cycles
front end	161.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5
uops	70.67	70.67	86.00	86.00	105.00	70.67
cycles	70.67	70.67	86.00	86.00	105.00	70.67

Execution ports to units layout:

P0 (256 bits): VPU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (128 bits): store address, load
P3 (128 bits): store address, load
P4 (128 bits): store data
P5: ALU, BRU

Cycles executing div or sqrt instructions

121.00-198.00

Cycles summary

Front-end	161.00
Dispatch	105.00
DIV/SQRT	121.00-198.00
Overall L1	161.00-198.00

Vectorization ratios

INT

all	5%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	14%
load	0%
store	0%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	90%

INT+FP

all	8%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	23%

Vector efficiency ratios

INT

all	34%
load	27%
store	36%
mul	25%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
other	34%

all	28%
load	25%
store	25%
mul	25%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	47%

INT+FP

all	32%
load	26%
store	32%
mul	25%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	25%
other	37%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 198.00 cycles. At this rate:

5% of peak load performance is reached (1.78 out of 32.00 bytes loaded per cycle (GB/s @ 1GHz))
18% of peak store performance is reached (3.03 out of 16.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 3870

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0.50	0.50	1	0	3	1	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0.25	N/A
PUSH %R15	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %R14	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %R13	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %R12	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %RBX	1	0	0	0.50	0.50	1	0	3	1	N/A
AND $-0x20,%RSP	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
SUB $0x1e0,%RSP	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV 0x26ca9(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x26c9f(%RIP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a6a <initialize_._omp_fn.0+0x11fa>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %ESI,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a6a <initialize_._omp_fn.0+0x11fa>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %ESI,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R12D,%EBX	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x78(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,%EDI	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,0x4(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
IMUL %ESI,%EBX	1	0	1	0	0	0	0	3	1	scal (25.0%)
MOV %EBX,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R14D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV %EAX,%R10D	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 4a15 <initialize_._omp_fn.0+0x11a5>	1	0	0	0	0	0	1	0	1-2	N/A
MOV 0x4(%RSP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
IMUL %R10D,%EAX	1	0	1	0	0	0	0	3	1	N/A
LEA (%RAX,%RDX,1),%EDI	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R10,%RDI,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EAX,0x14(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CMP %EAX,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 3a7b <initialize_._omp_fn.0+0x20b>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD 0x246a1(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOVQ $0,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %ESI,%EAX	1	0	1	0	0	0	0	3	1	N/A
DIVL (%RSP)										scal (25.0%)
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,0x4(%RSP)	1	0.33	0.33	0.50	0.50	0	0.33	1	0.50	scal (25.0%)
JB 4a0b <initialize_._omp_fn.0+0x119b>	1	0	0	0	0	0	1	0	1-2	N/A
MOV 0x4(%RSP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
IMUL %ECX,%EAX	1	0	1	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
LEA (%RCX,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 48ce <initialize_._omp_fn.0+0x105e>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
VMOVSD %XMM2,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
DIV %ESI	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
LEA -0x1(%RCX),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %R13D,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %ESI,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x268b1(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOVSXD %EAX,%R14	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 39af <initialize_._omp_fn.0+0x13f>	1	0	0	0	0	0	1	0	2	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDI,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV 0x26aaa(%RIP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
DIV %ESI	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV 0x267b1(%RIP),%RBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (50.0%)
MOV 0x267b2(%RIP),%R12	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x26813(%RIP),%R13	1	0	0	0.50	0.50	0	0	2	0.50	scal (50.0%)
MOV 0x267f4(%RIP),%R14	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x267d5(%RIP),%RCX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x244ed(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV %EDX,%R9D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %EAX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
TEST %R8D,%R8D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 3b4e <initialize_._omp_fn.0+0x2de>	1	0	0	0	0	0	1	0	1-2	N/A
LEA -0x1(%R10),%R15D	1	0.50	0.50	0	0	0	0	1	0.50	N/A
SAL $0x3,%RCX	1	0.50	0	0	0	0	0.50	1	0.50	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDI,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD 0x244c6(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOVSXD %EAX,%R11	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VBROADCASTSD 0x244b6(%RIP),%YMM0	2	0	0	0.50	0.50	0	1	5	1	scal (25.0%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
MOV 0x70(%RSP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x68(%RSP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VCVTSI2SD %EAX,%XMM3,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOV %EDX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDI,0x1c(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%R15	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EAX,0x18(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,0x10(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM0,0x8(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
MOV 0x265d9(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x40(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x265c9(%RIP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM2,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x265b6(%RIP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a4c <initialize_._omp_fn.0+0x11dc>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %ESI,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a4c <initialize_._omp_fn.0+0x11dc>	1	0	0	0	0	0	1	0	1-2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VMOVSD %XMM2,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %EAX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x78(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x70(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
IMUL %ESI,%R12D	1	0	1	0	0	0	0	3	1	N/A
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R13D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
CMP %EDX,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
JB 4a00 <initialize_._omp_fn.0+0x1190>	1	0	0	0	0	0	1	0	1-2	N/A
IMUL %R12D,%ECX	1	0	1	0	0	0	0	3	1	N/A
LEA (%RCX,%RDX,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R12,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 4148 <initialize_._omp_fn.0+0x8d8>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB $0x1,%EBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
VXORPD %XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %ESI	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOVSXD %EBX,%RBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
VMOVSD %XMM2,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA -0x1(%R12),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EBX,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %R15D,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x261ff(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
VCVTSI2SD %EAX,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%R14	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4067 <initialize_._omp_fn.0+0x7f7>	1	0	0	0	0	0	1	0	2	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x38(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2160 <@plt_start@+0x140>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x263df(%RIP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOVQ $0,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x263c4(%RIP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
TEST %EBX,%EBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a5c <initialize_._omp_fn.0+0x11ec>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %R8D,%R8D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a5c <initialize_._omp_fn.0+0x11ec>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD %XMM2,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EBX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R8D,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %EAX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x78(%RSP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x70(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
IMUL %R8D,%R14D	1	0	1	0	0	0	0	3	1	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R15D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
CMP %EDX,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
JB 4a41 <initialize_._omp_fn.0+0x11d1>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %ECX,%EAX	1	0	1	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
LEA (%R14,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 48b7 <initialize_._omp_fn.0+0x1047>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
SUB $0x1,%R14D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R8D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV %ECX,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R8D,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM2,0x30(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x26011(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0.25	N/A
VCVTSI2SD %EAX,%XMM3,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%RSI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EDX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0.25	scal (50.0%)
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4257 <initialize_._omp_fn.0+0x9e7>	1	0	0	0	0	0	1	0	2	N/A
MOV 0x26213(%RIP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x30(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x38(%RSP),%ECX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM2,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x261f1(%RIP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV 0x261ee(%RIP),%R9D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
TEST %EAX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a54 <initialize_._omp_fn.0+0x11e4>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %R8D,%R8D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a54 <initialize_._omp_fn.0+0x11e4>	1	0	0	0	0	0	1	0	1-2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
IMUL %R8D,%EAX	1	0	1	0	0	0	0	3	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
DIVL 0x48(%RSP)										scal (25.0%)
MOV %EAX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 4a36 <initialize_._omp_fn.0+0x11c6>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %ECX,%ESI	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %R15D,%ESI	1	0	1	0	0	0	0	3	1	N/A
LEA (%RSI,%RDX,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R15,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 44f0 <initialize_._omp_fn.0+0xc80>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB $0x1,%R9D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VMOVSD %XMM2,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
DIV %R8D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOVSXD %R9D,%RBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %R8D,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA -0x1(%R15),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EBX,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %R15D,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x25e55(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%R14	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 440f <initialize_._omp_fn.0+0xb9f>	1	0	0	0	0	0	1	0	2	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x38(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2160 <@plt_start@+0x140>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x26032(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOVQ $0,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x2601b(%RIP),%R13D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46d2 <initialize_._omp_fn.0+0xe62>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
TEST %R13D,%R13D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46d2 <initialize_._omp_fn.0+0xe62>	1	0	0	0	0	0	1	0	1-2	N/A
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %R12D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %R13D,%R14D	1	0	1	0	0	0	0	3	1	N/A
MOV %EAX,%EBX	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %EAX,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %EBX	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
CMP %EDX,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
JB 4a2b <initialize_._omp_fn.0+0x11bb>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %ESI,%EAX	1	0	1	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
LEA (%R14,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 48a3 <initialize_._omp_fn.0+0x1033>	1	0	0	0	0	0	1	0	1-2	N/A
LEA -0x1(%R14),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R13D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV %EBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM2,0x30(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x25c74(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0.25	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%RDI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R13D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0.25	scal (50.0%)
MOV %EAX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4607 <initialize_._omp_fn.0+0xd97>	1	0	0	0	0	0	1	0	2	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
LEA -0x28(%RBP),%RSP	1	0.50	0.50	0	0	0	0	1	0.50	N/A
POP %RBX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R12	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R13	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R14	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R15	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %RBP	1	0	0	0.50	0.50	0	0	2	0.50	N/A
RET	2	0	0	0.50	0.50	0	1	0	2	N/A
MOV 0x25e4c(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x30(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x38(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM2,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25e2e(%RIP),%R13D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV 0x25e30(%RIP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46cf <initialize_._omp_fn.0+0xe5f>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %R13D,%R13D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46cf <initialize_._omp_fn.0+0xe5f>	1	0	0	0	0	0	1	0	1-2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
IMUL %R13D,%R12D	1	0	1	0	0	0	0	3	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIVL 0x48(%RSP)										scal (25.0%)
MOV %EAX,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 4a20 <initialize_._omp_fn.0+0x11b0>	1	0	0	0	0	0	1	0	1-2	N/A
IMUL %R12D,%ESI	1	0	1	0	0	0	0	3	1	N/A
LEA (%RSI,%RDX,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R12,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 46d2 <initialize_._omp_fn.0+0xe62>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB $0x1,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R13D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOVSXD %EDI,%RBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %RBX,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA -0x1(%R12),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x25aae(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0.25	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%RSI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R13D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0.25	scal (50.0%)
MOV %EAX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 47c7 <initialize_._omp_fn.0+0xf57>	1	0	0	0	0	0	1	0	2	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM2,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25c86(%RIP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
JMP 4715 <initialize_._omp_fn.0+0xea5>	1	0	0	0	0	0	1	0	2	N/A
MOV 0x25c76(%RIP),%R9D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV %EBX,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM2,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 435a <initialize_._omp_fn.0+0xaea>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD %XMM2,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25c53(%RIP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
JMP 3f8e <initialize_._omp_fn.0+0x71e>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD 0x25e03(%RIP),%XMM3	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VXORPD %XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VMULSD 0x8(%RSP),%XMM3,%XMM0	1	1	0	0.50	0.50	0	0	5	1	scal (25.0%)
VMOVSD 0x25df9(%RIP),%XMM1	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x1c(%RSP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x14(%RSP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV 0x18(%RSP),%R10D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM0,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x10(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VCVTSI2SD %ECX,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
ADD $0x2,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VMULSD %XMM1,%XMM0,%XMM0	1	1	0	0	0	0	0	5	1	scal (25.0%)
VMOVSD %XMM0,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CMP %EBX,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 49c2 <initialize_._omp_fn.0+0x1152>	1	0	0	0	0	0	1	0	1-2	N/A
SUB $0x1,%EBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EBX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB %EAX,%EDX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 497f <initialize_._omp_fn.0+0x110f>	1	0	0	0	0	0	1	0	2	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VCVTSI2SD %R10D,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
VMULSD %XMM3,%XMM0,%XMM0	1	1	0	0	0	0	0	5	1	scal (25.0%)
VMOVSD %XMM0,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VCVTSI2SD %ECX,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
VMULSD %XMM1,%XMM0,%XMM0	1	1	0	0	0	0	0	5	1	scal (25.0%)
VMOVSD %XMM0,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 49c2 <initialize_._omp_fn.0+0x1152>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x25b6f(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOVQ $0,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25b59(%RIP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 49e8 <initialize_._omp_fn.0+0x1178>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %ESI,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JG 390b <initialize_._omp_fn.0+0x9b>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD %XMM2,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4148 <initialize_._omp_fn.0+0x8d8>	1	0	0	0	0	0	1	0	2	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
ADD $0x1,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 3fc8 <initialize_._omp_fn.0+0x758>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 3922 <initialize_._omp_fn.0+0xb2>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R10D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 38dc <initialize_._omp_fn.0+0x6c>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 472d <initialize_._omp_fn.0+0xebd>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R14D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 4564 <initialize_._omp_fn.0+0xcf4>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R15D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 436f <initialize_._omp_fn.0+0xaff>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R14D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 41c6 <initialize_._omp_fn.0+0x956>	1	0	0	0	0	0	1	0	2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
JMP 4148 <initialize_._omp_fn.0+0x8d8>	1	0	0	0	0	0	1	0	2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
JMP 44f0 <initialize_._omp_fn.0+0xc80>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD %XMM2,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 44f0 <initialize_._omp_fn.0+0xc80>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD 0x2352e(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
JMP 49e8 <initialize_._omp_fn.0+0x1178>	1	0	0	0	0	0	1	0	2	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run run_0

Source file and lines	initialize.f90:23-197
Module	bt.A.x

The function is defined in /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:23,30-35,51-81,97-105,115-124,134-142,152-161,171-179,188-197.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Workaround

Reduce the number of division or square root instructions:
- If denominator is constant over iterations, use reciprocal (replace x/y with x*(1/y)). Check precision impact. This will be done by your compiler with ffast-math or Ofast
Check whether you really need double precision. If not, switch to single precision to speedup execution

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 198.00 to 137.00 cycles (1.45x speedup).

CALL instructions

Detected function call instructions.

Details

unknown: 10 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:30
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:30
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:172
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:172

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.

DIV: 11 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:30
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:105
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:142
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:152
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:172
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:197
RET: 1 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:23
VBROADCASTSD: 1 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:35
VCVTSI2SD: 10 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:105
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:142
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:197
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:51
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52
VZEROUPPER: 9 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:115
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:152
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:188
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:135

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 10 occurrences►
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:105
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:33
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:124
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:142
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:161
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:179
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:197
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:51
- /home/eoseret/Applications/NPB3.4.3/NPB3.4-OMP/BT/initialize.f90:52

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

4 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 4 FP arithmetical operations:

4: multiply

The binary function is loading 352 bytes (44 double precision FP elements). The binary function is storing 600 bytes (75 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	489
nb uops	644
loop length	2188
used x86 registers	16
used mmx registers	0
used xmm registers	6
used ymm registers	1
used zmm registers	0
nb stack references	22

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	161.00 cycles
front end	161.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5
uops	70.67	70.67	86.00	86.00	105.00	70.67
cycles	70.67	70.67	86.00	86.00	105.00	70.67

Execution ports to units layout:

P0 (256 bits): VPU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (128 bits): store address, load
P3 (128 bits): store address, load
P4 (128 bits): store data
P5: ALU, BRU

Cycles executing div or sqrt instructions

121.00-198.00

Cycles summary

Front-end	161.00
Dispatch	105.00
DIV/SQRT	121.00-198.00
Overall L1	161.00-198.00

Vectorization ratios

INT

all	5%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	14%
load	0%
store	0%
mul	0%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	90%

INT+FP

all	8%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	23%

Vector efficiency ratios

INT

all	34%
load	27%
store	36%
mul	25%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
other	34%

all	28%
load	25%
store	25%
mul	25%
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	47%

INT+FP

all	32%
load	26%
store	32%
mul	25%
add-sub	25%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	25%
other	37%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 198.00 cycles. At this rate:

5% of peak load performance is reached (1.78 out of 32.00 bytes loaded per cycle (GB/s @ 1GHz))
18% of peak store performance is reached (3.03 out of 16.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 3870

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0.50	0.50	1	0	3	1	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0.25	N/A
PUSH %R15	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %R14	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %R13	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %R12	1	0	0	0.50	0.50	1	0	3	1	N/A
PUSH %RBX	1	0	0	0.50	0.50	1	0	3	1	N/A
AND $-0x20,%RSP	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
SUB $0x1e0,%RSP	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV 0x26ca9(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x26c9f(%RIP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a6a <initialize_._omp_fn.0+0x11fa>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %ESI,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a6a <initialize_._omp_fn.0+0x11fa>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %ESI,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R12D,%EBX	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x78(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,%EDI	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,0x4(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
IMUL %ESI,%EBX	1	0	1	0	0	0	0	3	1	scal (25.0%)
MOV %EBX,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R14D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV %EAX,%R10D	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 4a15 <initialize_._omp_fn.0+0x11a5>	1	0	0	0	0	0	1	0	1-2	N/A
MOV 0x4(%RSP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
IMUL %R10D,%EAX	1	0	1	0	0	0	0	3	1	N/A
LEA (%RAX,%RDX,1),%EDI	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R10,%RDI,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EAX,0x14(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CMP %EAX,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 3a7b <initialize_._omp_fn.0+0x20b>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD 0x246a1(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOVQ $0,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %ESI,%EAX	1	0	1	0	0	0	0	3	1	N/A
DIVL (%RSP)										scal (25.0%)
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,0x4(%RSP)	1	0.33	0.33	0.50	0.50	0	0.33	1	0.50	scal (25.0%)
JB 4a0b <initialize_._omp_fn.0+0x119b>	1	0	0	0	0	0	1	0	1-2	N/A
MOV 0x4(%RSP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
IMUL %ECX,%EAX	1	0	1	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
LEA (%RCX,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 48ce <initialize_._omp_fn.0+0x105e>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R13D,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
VMOVSD %XMM2,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
DIV %ESI	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
LEA -0x1(%RCX),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %R13D,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %ESI,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x268b1(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOVSXD %EAX,%R14	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 39af <initialize_._omp_fn.0+0x13f>	1	0	0	0	0	0	1	0	2	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDI,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV 0x26aaa(%RIP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
DIV %ESI	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV 0x267b1(%RIP),%RBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (50.0%)
MOV 0x267b2(%RIP),%R12	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x26813(%RIP),%R13	1	0	0	0.50	0.50	0	0	2	0.50	scal (50.0%)
MOV 0x267f4(%RIP),%R14	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x267d5(%RIP),%RCX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x244ed(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV %EDX,%R9D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %EAX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
TEST %R8D,%R8D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 3b4e <initialize_._omp_fn.0+0x2de>	1	0	0	0	0	0	1	0	1-2	N/A
LEA -0x1(%R10),%R15D	1	0.50	0.50	0	0	0	0	1	0.50	N/A
SAL $0x3,%RCX	1	0.50	0	0	0	0	0.50	1	0.50	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDI,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD 0x244c6(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOVSXD %EAX,%R11	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VBROADCASTSD 0x244b6(%RIP),%YMM0	2	0	0	0.50	0.50	0	1	5	1	scal (25.0%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
MOV 0x70(%RSP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x68(%RSP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VCVTSI2SD %EAX,%XMM3,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOV %EDX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDI,0x1c(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%R15	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EAX,0x18(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,0x10(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM0,0x8(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
MOV 0x265d9(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x40(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x265c9(%RIP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM2,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x265b6(%RIP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a4c <initialize_._omp_fn.0+0x11dc>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %ESI,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a4c <initialize_._omp_fn.0+0x11dc>	1	0	0	0	0	0	1	0	1-2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VMOVSD %XMM2,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %EAX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x78(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x70(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
IMUL %ESI,%R12D	1	0	1	0	0	0	0	3	1	N/A
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R13D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
CMP %EDX,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
JB 4a00 <initialize_._omp_fn.0+0x1190>	1	0	0	0	0	0	1	0	1-2	N/A
IMUL %R12D,%ECX	1	0	1	0	0	0	0	3	1	N/A
LEA (%RCX,%RDX,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R12,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 4148 <initialize_._omp_fn.0+0x8d8>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB $0x1,%EBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
VXORPD %XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %ESI	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOVSXD %EBX,%RBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
VMOVSD %XMM2,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA -0x1(%R12),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EBX,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %R15D,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x261ff(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
VCVTSI2SD %EAX,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%R14	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4067 <initialize_._omp_fn.0+0x7f7>	1	0	0	0	0	0	1	0	2	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x38(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2160 <@plt_start@+0x140>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x263df(%RIP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOVQ $0,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x263c4(%RIP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
TEST %EBX,%EBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a5c <initialize_._omp_fn.0+0x11ec>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %R8D,%R8D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a5c <initialize_._omp_fn.0+0x11ec>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD %XMM2,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EBX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R8D,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %EAX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x78(%RSP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EAX,%ECX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x70(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
IMUL %R8D,%R14D	1	0	1	0	0	0	0	3	1	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R15D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
CMP %EDX,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
JB 4a41 <initialize_._omp_fn.0+0x11d1>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %ECX,%EAX	1	0	1	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
LEA (%R14,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 48b7 <initialize_._omp_fn.0+0x1047>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM3,%XMM3,%XMM3	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
SUB $0x1,%R14D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R8D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV %ECX,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R8D,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM2,0x30(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x26011(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0.25	N/A
VCVTSI2SD %EAX,%XMM3,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%RSI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EDX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0.25	scal (50.0%)
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4257 <initialize_._omp_fn.0+0x9e7>	1	0	0	0	0	0	1	0	2	N/A
MOV 0x26213(%RIP),%EAX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x30(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x38(%RSP),%ECX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM2,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x261f1(%RIP),%R8D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV 0x261ee(%RIP),%R9D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
TEST %EAX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a54 <initialize_._omp_fn.0+0x11e4>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %R8D,%R8D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 4a54 <initialize_._omp_fn.0+0x11e4>	1	0	0	0	0	0	1	0	1-2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
IMUL %R8D,%EAX	1	0	1	0	0	0	0	3	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
DIVL 0x48(%RSP)										scal (25.0%)
MOV %EAX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 4a36 <initialize_._omp_fn.0+0x11c6>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %ECX,%ESI	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %R15D,%ESI	1	0	1	0	0	0	0	3	1	N/A
LEA (%RSI,%RDX,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R15,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 44f0 <initialize_._omp_fn.0+0xc80>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB $0x1,%R9D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VMOVSD %XMM2,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
DIV %R8D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOVSXD %R9D,%RBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %R8D,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %RBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA -0x1(%R15),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EBX,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %R15D,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x25e55(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%R14	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 440f <initialize_._omp_fn.0+0xb9f>	1	0	0	0	0	0	1	0	2	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x38(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 2160 <@plt_start@+0x140>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV 0x26032(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOVQ $0,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x2601b(%RIP),%R13D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46d2 <initialize_._omp_fn.0+0xe62>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD %XMM2,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
TEST %R13D,%R13D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46d2 <initialize_._omp_fn.0+0xe62>	1	0	0	0	0	0	1	0	1-2	N/A
CALL 2050 <@plt_start@+0x30>	3	0	0	0.50	0.50	1	1	0	2	N/A
MOV %R12D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %R13D,%R14D	1	0	1	0	0	0	0	3	1	N/A
MOV %EAX,%EBX	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
MOV %EAX,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CALL 20d0 <@plt_start@+0xb0>	3	0	0	0.50	0.50	1	1	0	2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIV %EBX	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
CMP %EDX,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
JB 4a2b <initialize_._omp_fn.0+0x11bb>	1	0	0	0	0	0	1	0	1-2	N/A
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
IMUL %ESI,%EAX	1	0	1	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
LEA (%R14,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 48a3 <initialize_._omp_fn.0+0x1033>	1	0	0	0	0	0	1	0	1-2	N/A
LEA -0x1(%R14),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R13D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOV %EBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %ESI,0x38(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VMOVSD %XMM2,0x30(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x25c74(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0.25	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%RDI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R13D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0.25	scal (50.0%)
MOV %EAX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4607 <initialize_._omp_fn.0+0xd97>	1	0	0	0	0	0	1	0	2	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
LEA -0x28(%RBP),%RSP	1	0.50	0.50	0	0	0	0	1	0.50	N/A
POP %RBX	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R12	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R13	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R14	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %R15	1	0	0	0.50	0.50	0	0	2	0.50	N/A
POP %RBP	1	0	0	0.50	0.50	0	0	2	0.50	N/A
RET	2	0	0	0.50	0.50	0	1	0	2	N/A
MOV 0x25e4c(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD 0x30(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x38(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM2,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25e2e(%RIP),%R13D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV 0x25e30(%RIP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46cf <initialize_._omp_fn.0+0xe5f>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %R13D,%R13D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 46cf <initialize_._omp_fn.0+0xe5f>	1	0	0	0	0	0	1	0	1-2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
IMUL %R13D,%R12D	1	0	1	0	0	0	0	3	1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
DIVL 0x48(%RSP)										scal (25.0%)
MOV %EAX,%R12D	1	0	0	0	0	0	0	0	0.25	N/A
CMP %EDX,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JB 4a20 <initialize_._omp_fn.0+0x11b0>	1	0	0	0	0	0	1	0	1-2	N/A
IMUL %R12D,%ESI	1	0	1	0	0	0	0	3	1	N/A
LEA (%RSI,%RDX,1),%EAX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA (%R12,%RAX,1),%EDX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
CMP %EDX,%EAX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 46d2 <initialize_._omp_fn.0+0xe62>	1	0	0	0	0	0	1	0	1-2	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB $0x1,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
VXORPD %XMM4,%XMM4,%XMM4	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
DIV %R13D	10	0	0	0	0	0	0	20-28	11-18	scal (25.0%)
MOVSXD %EDI,%RBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %RBX,0x50(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA -0x1(%R12),%EBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %EBX,0x58(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
LEA 0xa0(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x68(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x98(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x90(%RSP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
LEA 0x88(%RSP),%R12	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
LEA 0x25aae(%RIP),%RBX	1	0.50	0.50	0	0	0	0	1	0.50	N/A
MOV %R12,0x48(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (50.0%)
MOV %RBX,%R12	1	0	0	0	0	0	0	0	0.25	N/A
VCVTSI2SD %EAX,%XMM4,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
MOVSXD %EAX,%RSI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
MOV %EAX,0x40(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV %R14D,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
MOV %EDX,%R15D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %R13D,%R14D	1	0	0	0	0	0	0	0	0.25	N/A
MOV %RSI,%RBX	1	0	0	0	0	0	0	0	0.25	scal (50.0%)
MOV %EAX,%R13D	1	0	0	0	0	0	0	0	0.25	scal (25.0%)
VMOVSD %XMM0,0x60(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 47c7 <initialize_._omp_fn.0+0xf57>	1	0	0	0	0	0	1	0	2	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM2,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25c86(%RIP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
JMP 4715 <initialize_._omp_fn.0+0xea5>	1	0	0	0	0	0	1	0	2	N/A
MOV 0x25c76(%RIP),%R9D	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV %EBX,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
VMOVSD %XMM2,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 435a <initialize_._omp_fn.0+0xaea>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD %XMM2,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25c53(%RIP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
JMP 3f8e <initialize_._omp_fn.0+0x71e>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD 0x25e03(%RIP),%XMM3	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VXORPD %XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VMULSD 0x8(%RSP),%XMM3,%XMM0	1	1	0	0.50	0.50	0	0	5	1	scal (25.0%)
VMOVSD 0x25df9(%RIP),%XMM1	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x1c(%RSP),%EDI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOV 0x14(%RSP),%EBX	1	0	0	0.50	0.50	0	0	2	0.50	scal (25.0%)
MOV 0x18(%RSP),%R10D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VMOVSD %XMM0,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x10(%RSP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
VCVTSI2SD %ECX,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
ADD $0x2,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
VMULSD %XMM1,%XMM0,%XMM0	1	1	0	0	0	0	0	5	1	scal (25.0%)
VMOVSD %XMM0,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
CMP %EBX,%EDI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JAE 49c2 <initialize_._omp_fn.0+0x1152>	1	0	0	0	0	0	1	0	1-2	N/A
SUB $0x1,%EBX	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
MOV %EBX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
SUB %EAX,%EDX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 497f <initialize_._omp_fn.0+0x110f>	1	0	0	0	0	0	1	0	2	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
VXORPD %XMM6,%XMM6,%XMM6	1	0	0	0	0	0	0	0	0.25	vect (50.0%)
VCVTSI2SD %R10D,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
VMULSD %XMM3,%XMM0,%XMM0	1	1	0	0	0	0	0	5	1	scal (25.0%)
VMOVSD %XMM0,0x98(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
VCVTSI2SD %ECX,%XMM6,%XMM0	2	1	1	0	0	0	0	4	1.50	scal (25.0%)
VMULSD %XMM1,%XMM0,%XMM0	1	1	0	0	0	0	0	5	1	scal (25.0%)
VMOVSD %XMM0,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 49c2 <initialize_._omp_fn.0+0x1152>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD 0x78(%RSP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
MOV 0x25b6f(%RIP),%R12D	1	0	0	0.50	0.50	0	0	2	0.50	N/A
MOVQ $0,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
MOV 0x25b59(%RIP),%ESI	1	0	0	0.50	0.50	0	0	2	0.50	N/A
TEST %R12D,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JLE 49e8 <initialize_._omp_fn.0+0x1178>	1	0	0	0	0	0	1	0	1-2	N/A
TEST %ESI,%ESI	1	0.33	0.33	0	0	0	0.33	1	0.33	scal (25.0%)
JG 390b <initialize_._omp_fn.0+0x9b>	1	0	0	0	0	0	1	0	1-2	N/A
VMOVSD %XMM2,0x88(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 4148 <initialize_._omp_fn.0+0x8d8>	1	0	0	0	0	0	1	0	2	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A
ADD $0x1,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 3fc8 <initialize_._omp_fn.0+0x758>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%ECX	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 3922 <initialize_._omp_fn.0+0xb2>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R10D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 38dc <initialize_._omp_fn.0+0x6c>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R12D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 472d <initialize_._omp_fn.0+0xebd>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R14D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 4564 <initialize_._omp_fn.0+0xcf4>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R15D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 436f <initialize_._omp_fn.0+0xaff>	1	0	0	0	0	0	1	0	2	N/A
ADD $0x1,%R14D	1	0.33	0.33	0	0	0	0.33	1	0.33	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0.25	N/A
JMP 41c6 <initialize_._omp_fn.0+0x956>	1	0	0	0	0	0	1	0	2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
JMP 4148 <initialize_._omp_fn.0+0x8d8>	1	0	0	0	0	0	1	0	2	N/A
VZEROUPPER	4	0	0	0	0	0	0	2	1	vect (100.0%)
JMP 44f0 <initialize_._omp_fn.0+0xc80>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD %XMM2,0x90(%RSP)	1	0	0	0.50	0.50	1	0	3	1	scal (25.0%)
JMP 44f0 <initialize_._omp_fn.0+0xc80>	1	0	0	0	0	0	1	0	2	N/A
VMOVSD 0x2352e(%RIP),%XMM2	1	0	0	0.50	0.50	0	0	3	0.50	scal (25.0%)
JMP 49e8 <initialize_._omp_fn.0+0x1178>	1	0	0	0	0	0	1	0	2	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0.25	N/A

Name	Coverage (%)	Time (s)
▼initialize_._omp_fn.0–	0.02	0.00
○Loop 6 - initialize.f90:193-197 - bt.A.x	0.00	0.00
○Loop 13 - initialize.f90:52-52 - bt.A.x	0.00	0.00
▼Loop 12 - initialize.f90:33-105 - bt.A.x–	0.00	0.00
○Loop 14 - initialize.f90:53-81 - bt.A.x	0.02	0.00
○Loop 10 - initialize.f90:120-124 - bt.A.x	0.00	0.00
▼Loop 16 - initialize.f90:33-115 - bt.A.x–	0.00	0.00
○Loop 15 - initialize.f90:33-35 - bt.A.x	0.00	0.00
○Loop 7 - initialize.f90:175-179 - bt.A.x	0.00	0.00
○Loop 9 - initialize.f90:138-142 - bt.A.x	0.00	0.00
○Loop 8 - initialize.f90:157-161 - bt.A.x	0.00	0.00
○Loop 11 - initialize.f90:101-105 - bt.A.x	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Expensive FP math instructions/calls

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

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

Workaround

Expensive FP math instructions/calls

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

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