OV - - Loop 12596 - engine_linuxa64

0x4a56e0 STR	XZR, [X19, X12]

0x4a56e4 STR	W10, [X26, X11]

  (12597) 0x4a56e8 ADD	X12, X12, #8

  (12597) 0x4a56ec ADD	X11, X11, #4

  (12597) 0x4a56f0 ADD	X22, X22, #28

  (12597) 0x4a56f4 CMP	X29, X12

  (12597) 0x4a56f8 B.EQ	4a596c

  (12597) 0x4a56fc LDR	D5, [X19, X12]

  (12597) 0x4a5700 LDR	D6, [X6, X12]

  (12597) 0x4a5704 FMUL	D16, D5, D5

  (12597) 0x4a5708 FMUL	D6, D0, D6

  (12597) 0x4a570c FCMP	D16, D6

  (12597) 0x4a5710 STR	D16, [X20, X12]

  (12597) 0x4a5714 B.MI	4a56e0

  (12597) 0x4a5718 LDR	W3, [X21]

  (12597) 0x4a571c CMP	W3, #1

  (12597) 0x4a5720 B.EQ	4a56e0

  (12597) 0x4a5724 LDR	X3, [SP, #312]

  (12597) 0x4a5728 LDR	D17, [X4, X12]

  (12597) 0x4a572c LDR	D19, [X7, X12]

  (12597) 0x4a5730 FMUL	D26, D1, D19

  (12597) 0x4a5734 LDR	D6, [X3, X12]

  (12597) 0x4a5738 LDR	X3, [SP, #328]

  (12597) 0x4a573c LDR	D25, [X5, X12]

  (12597) 0x4a5740 LDR	D7, [X3, X12]

  (12597) 0x4a5744 LDP	X3, X4, [SP, #344]

  (12597) 0x4a5748 FMUL	D22, D6, D17

  (12597) 0x4a574c FNMUL	D6, D5, D6

  (12597) 0x4a5750 LDR	D20, [X3, X12]

  (12597) 0x4a5754 LDR	X3, [SP, #320]

  (12597) 0x4a5758 LDR	D18, [X4, X12]

  (12597) 0x4a575c ADD	X4, X30, X12

  (12597) 0x4a5760 LDR	D21, [X3, X12]

  (12597) 0x4a5764 LDR	X3, [SP, #456]

  (12597) 0x4a5768 FMUL	D23, D7, D18

  (12597) 0x4a576c FMUL	D17, D17, D20

  (12597) 0x4a5770 FMUL	D7, D5, D7

  (12597) 0x4a5774 FNMUL	D20, D5, D20

  (12597) 0x4a5778 LDR	D24, [X3, X12]

  (12597) 0x4a577c LDR	X3, [SP, #304]

  (12597) 0x4a5780 FSUB	D19, D22, S23

  (12597) 0x4a5784 FMUL	D18, D18, D21

  (12597) 0x4a5788 FMUL	D5, D5, D21

  (12597) 0x4a578c FADD	D22, D26, D19

  (12597) 0x4a5790 FSUB	D19, D26, S19

  (12597) 0x4a5794 ADD	X26, X3, X12

  (12597) 0x4a5798 ADD	X3, SP, #7

  (12597) 0x4a579c LDR	D21, [X26]

  (12597) 0x4a57a0 ADD	X3, X3, #3856

  (12597) 0x4a57a4 FSUB	D18, D17, S18

  (12597) 0x4a57a8 ADD	X24, X3, X12

  (12597) 0x4a57ac FMUL	D23, D16, D24

  (12597) 0x4a57b0 FMUL	D24, D22, D22

  (12597) 0x4a57b4 LDR	X3, [SP, #296]

  (12597) 0x4a57b8 FMUL	D16, D16, D25

  (12597) 0x4a57bc FMUL	D25, D19, D19

  (12597) 0x4a57c0 FADD	D17, D26, D18

  (12597) 0x4a57c4 FSUB	D18, D26, S18

  (12597) 0x4a57c8 FADD	D24, D23, D24

  (12597) 0x4a57cc FADD	D23, D23, D25

  (12597) 0x4a57d0 FMUL	D26, D17, D17

  (12597) 0x4a57d4 FMUL	D25, D18, D18

  (12597) 0x4a57d8 ADD	X3, X3, X12

  (12597) 0x4a57dc FADD	D26, D16, D26

  (12597) 0x4a57e0 STR	D21, [X24]

  (12597) 0x4a57e4 LDR	D21, [X26, #1032]

  (12597) 0x4a57e8 FADD	D16, D16, D25

  (12597) 0x4a57ec FSQRT	D16, D16

  (12597) 0x4a57f0 STR	D21, [X24, #1032]

  (12597) 0x4a57f4 LDR	D21, [X26, #2064]

  (12597) 0x4a57f8 STR	D21, [X24, #3096]

  (12597) 0x4a57fc LDR	D21, [X26, #3096]

  (12597) 0x4a5800 STR	D21, [X24, #4128]

  (12597) 0x4a5804 FSQRT	D21, D24

  (12597) 0x4a5808 FDIV	D16, D2, D16

  (12597) 0x4a580c FDIV	D21, D2, D21

  (12597) 0x4a5810 FNMUL	D25, D5, D16

  (12597) 0x4a5814 STR	D25, [X3, #10320]

  (12597) 0x4a5818 FMUL	D22, D22, D21

  (12597) 0x4a581c STR	D22, [X3, #2064]

  (12597) 0x4a5820 FMUL	D22, D6, D21

  (12597) 0x4a5824 FMUL	D21, D7, D21

  (12597) 0x4a5828 STR	D22, [X3]

  (12597) 0x4a582c FSQRT	D22, D23

  (12597) 0x4a5830 FSQRT	D23, D26

  (12597) 0x4a5834 STR	D21, [X3, #1032]

  (12597) 0x4a5838 FDIV	D22, D2, D22

  (12597) 0x4a583c FDIV	D23, D2, D23

  (12597) 0x4a5840 FNMUL	D6, D6, D22

  (12597) 0x4a5844 FNMUL	D7, D7, D22

  (12597) 0x4a5848 FMUL	D19, D19, D22

  (12597) 0x4a584c LDR	Q22, [X22]

  (12597) 0x4a5850 FMUL	D17, D17, D23

  (12597) 0x4a5854 FMUL	D24, D20, D23

  (12597) 0x4a5858 FMUL	D23, D5, D23

  (12597) 0x4a585c FNMUL	D20, D20, D16

  (12597) 0x4a5860 FMUL	D16, D18, D16

  (12597) 0x4a5864 LDR	D5, [X4, #2064]

  (12597) 0x4a5868 LDR	D18, [X26, #5160]

  (12597) 0x4a586c STR	D6, [X3, #6192]

  (12597) 0x4a5870 STR	D7, [X3, #7224]

  (12597) 0x4a5874 LDR	D6, [X4, #1032]

  (12597) 0x4a5878 STR	D19, [X3, #8256]

  (12597) 0x4a587c STR	D17, [X3, #5160]

  (12597) 0x4a5880 STR	D24, [X3, #3096]

  (12597) 0x4a5884 STR	D23, [X3, #4128]

  (12597) 0x4a5888 STR	D20, [X3, #9288]

  (12597) 0x4a588c STR	D16, [X3, #11352]

  (12597) 0x4a5890 LDR	D7, [X4]

  (12597) 0x4a5894 LDR	D20, [X26, #7224]

  (12597) 0x4a5898 LDR	D19, [X26, #6192]

  (12597) 0x4a589c LDR	D17, [X26, #4128]

  (12597) 0x4a58a0 SMULL2	V21.2D, V22.4S, V3.4S

  (12597) 0x4a58a4 SMULL	V22.2D, V22.2S, V4.2S

  (12597) 0x4a58a8 STR	D18, [X24, #7224]

  (12597) 0x4a58ac FMOV	X3, D22

  (12597) 0x4a58b0 MOV	X4, V22.D[1]

  (12597) 0x4a58b4 STR	D20, [X24, #10320]

  (12597) 0x4a58b8 STR	D19, [X24, #9288]

  (12597) 0x4a58bc MOV	X26, V21.D[1]

  (12597) 0x4a58c0 STR	D17, [X24, #6192]

  (12597) 0x4a58c4 LDR	D22, [X27, X3]

  (12597) 0x4a58c8 LDR	D23, [X23, X3]

  (12597) 0x4a58cc LDR	D16, [X25, X3]

  (12597) 0x4a58d0 FMOV	X3, D21

  (12597) 0x4a58d4 LDR	D17, [X25, X4]

  (12597) 0x4a58d8 LDR	D18, [X27, X4]

  (12597) 0x4a58dc LDR	D21, [X23, X4]

  (12597) 0x4a58e0 LDR	X4, [SP, #472]

  (12597) 0x4a58e4 LDR	D20, [X27, X3]

  (12597) 0x4a58e8 LDR	D19, [X25, X3]

  (12597) 0x4a58ec STR	WZR, [X4, X11]

  (12597) 0x4a58f0 LDR	X4, [SP, #336]

  (12597) 0x4a58f4 FMUL	D22, D22, D6

  (12597) 0x4a58f8 FMUL	D23, D23, D7

  (12597) 0x4a58fc FMUL	D16, D16, D5

  (12597) 0x4a5900 FMUL	D17, D5, D17

  (12597) 0x4a5904 FMUL	D18, D6, D18

  (12597) 0x4a5908 FMUL	D21, D7, D21

  (12597) 0x4a590c FMUL	D20, D6, D20

  (12597) 0x4a5910 FMUL	D19, D5, D19

  (12597) 0x4a5914 FADD	D22, D22, D23

  (12597) 0x4a5918 FADD	D18, D18, D21

  (12597) 0x4a591c FADD	D16, D16, D22

  (12597) 0x4a5920 FADD	D17, D17, D18

  (12597) 0x4a5924 STR	D16, [X24, #2064]

  (12597) 0x4a5928 LDR	D16, [X23, X3]

  (12597) 0x4a592c STR	D17, [X24, #5160]

  (12597) 0x4a5930 FMUL	D16, D7, D16

  (12597) 0x4a5934 FADD	D16, D20, D16

  (12597) 0x4a5938 FADD	D16, D19, D16

  (12597) 0x4a593c STR	D16, [X24, #8256]

  (12597) 0x4a5940 LDR	D16, [X25, X26]

  (12597) 0x4a5944 FMUL	D5, D5, D16

  (12597) 0x4a5948 LDR	D16, [X27, X26]

  (12597) 0x4a594c FMUL	D6, D6, D16

  (12597) 0x4a5950 LDR	D16, [X23, X26]

  (12597) 0x4a5954 LDR	X26, [SP, #472]

  (12597) 0x4a5958 FMUL	D7, D7, D16

  (12597) 0x4a595c FADD	D6, D6, D7

  (12597) 0x4a5960 FADD	D5, D5, D6

  (12597) 0x4a5964 STR	D5, [X24, #11352]

  (12597) 0x4a5968 B	4a56e8

/home/eoseret/OpenRadioss/engine/source/elements/shell/coquez/czcorp5.F: 80 - 150

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

80:             Z2(I)=Z1(I)*Z1(I)

81:             IF (Z2(I)<LL(I)*TOL.OR.NPT == 1) THEN

82:                 Z1(I)=ZERO

83:                 PLAT(I)=.TRUE.

84:             ELSE

85:                 PLAT(I)=.FALSE.

86: C--------------------------------------------------

87: C WARPING SPECIAL TREATMENT

88: C full projection eliminer drilling rotations and rigid rotations

89: C--------------------------------------------------------------------------

90:                 A_4=AREA(I)*FOURTH

91: C

92: C----------  node N ----------

93:                 SZ1=MX13(I)*Y24(I)-MY13(I)*X24(I)

94:                 SZ2=A_4+SZ1

95:                 SZ=Z2(I)*L24(I)

96:                 SL=ONE/SQRT(SZ+SZ2*SZ2)

97:                 VQN(I,1,1)=-Z1(I)*Y24(I)

98:                 VQN(I,2,1)= Z1(I)*X24(I)

99:                 VQN(I,3,1)= SZ2*SL

100:                 VQN(I,1,3)=-VQN(I,1,1)

101:                 VQN(I,2,3)=-VQN(I,2,1)

102:                 VQN(I,1,1)= VQN(I,1,1)*SL

103:                 VQN(I,2,1)= VQN(I,2,1)*SL

104: C

105:                 SZ2=A_4-SZ1

106:                 SL=ONE/SQRT(SZ+SZ2*SZ2)

107:                 VQN(I,1,3)= VQN(I,1,3)*SL

108:                 VQN(I,2,3)= VQN(I,2,3)*SL

109:                 VQN(I,3,3)= SZ2*SL

110: C

111:                 SZ1=MX13(I)*Y13(I)-MY13(I)*X13(I)

112:                 SZ2=A_4+SZ1

113:                 SZ=Z2(I)*L13(I)

114:                 SL=ONE/SQRT(SZ+SZ2*SZ2)

115:                 VQN(I,1,2)=-Z1(I)*Y13(I)

116:                 VQN(I,2,2)= Z1(I)*X13(I)

117:                 VQN(I,3,2)= SZ2*SL

118:                 VQN(I,1,4)=-VQN(I,1,2)

119:                 VQN(I,2,4)=-VQN(I,2,2)

120:                 VQN(I,1,2)= VQN(I,1,2)*SL

121:                 VQN(I,2,2)= VQN(I,2,2)*SL

122: C

123:                 SZ2=A_4-SZ1

124:                 SL=ONE/SQRT(SZ+SZ2*SZ2)

125:                 VQN(I,1,4)= VQN(I,1,4)*SL

126:                 VQN(I,2,4)= VQN(I,2,4)*SL

127:                 VQN(I,3,4)= SZ2*SL

128: C

129:                 K=IXC(2,I)

130:                 RRXYZ(I,1,1) =RLXYZ(I,1,1)

131:                 RRXYZ(I,2,1) =RLXYZ(I,2,1)

132:                 RRXYZ(I,3,1) =VQ(I,1,3)*VR(1,K)+VQ(I,2,3)*VR(2,K)

133:      1               +VQ(I,3,3)*VR(3,K)

134:                 K=IXC(3,I)

135:                 RRXYZ(I,1,2) =RLXYZ(I,1,2)

136:                 RRXYZ(I,2,2) =RLXYZ(I,2,2)

137:                 RRXYZ(I,3,2) =VQ(I,1,3)*VR(1,K)+VQ(I,2,3)*VR(2,K)

138:      1               +VQ(I,3,3)*VR(3,K)

139:                 K=IXC(4,I)

140:                 RRXYZ(I,1,3) =RLXYZ(I,1,3)

141:                 RRXYZ(I,2,3) =RLXYZ(I,2,3)

142:                 RRXYZ(I,3,3) =VQ(I,1,3)*VR(1,K)+VQ(I,2,3)*VR(2,K)

143:      1               +VQ(I,3,3)*VR(3,K)

144:                 K=IXC(5,I)

145:                 RRXYZ(I,1,4) =RLXYZ(I,1,4)

146:                 RRXYZ(I,2,4) =RLXYZ(I,2,4)

147:                 RRXYZ(I,3,4) =VQ(I,1,3)*VR(1,K)+VQ(I,2,3)*VR(2,K)

148:      1               +VQ(I,3,3)*VR(3,K)

149:             ENDIF

150:        ENDDO

Coverage (%)	Name	Source Location	Module

Path /

Metric	Value
CQA speedup if no scalar integer	NA
CQA speedup if FP arith vectorized	NA
CQA speedup if fully vectorized	NA
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	NA
Bottlenecks	NA
Function	czcorp5
Source	czcorp5.F:82-83
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	NA
CQA cycles if no scalar integer	NA
CQA cycles if FP arith vectorized	NA
CQA cycles if fully vectorized	NA
Front-end cycles	NA
P0 cycles	NA
P1 cycles	NA
P2 cycles	NA
P3 cycles	NA
P4 cycles	NA
P5 cycles	NA
P6 cycles	NA
P7 cycles	NA
P8 cycles	NA
P9 cycles	NA
P10 cycles	NA
P11 cycles	NA
P12 cycles	NA
P13 cycles	NA
P14 cycles	NA
P15 cycles	NA
P16 cycles	NA
DIV/SQRT cycles	NA
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	NA
Nb uops	NA
Nb loads	NA
Nb stores	NA
Nb stack references	NA
FLOP/cycle	NA
Nb FLOP add-sub	NA
Nb FLOP mul	NA
Nb FLOP fma	NA
Nb FLOP div	NA
Nb FLOP rcp	NA
Nb FLOP sqrt	NA
Nb FLOP rsqrt	NA
Bytes/cycle	NA
Bytes prefetched	NA
Bytes loaded	NA
Bytes stored	NA
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	NA
Vectorization ratio load	NA
Vectorization ratio store	NA
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	NA
Vector-efficiency ratio load	NA
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Path /

Function	czcorp5
Source file and lines	czcorp5.F:82-83
Module	engine_linuxa64_ompi

The loop is defined in /home/eoseret/OpenRadioss/engine/source/elements/shell/coquez/czcorp5.F:80-150.

Analyzed code is defined in /home/eoseret/OpenRadioss/engine/source/elements/shell/coquez/czcorp5.F:82-83.

Warnings:
get_cqa_results:

Non-innermost loop: analyzing only self part (ignoring child loops).

This loop cannot be analyzed: no jump instruction (loop probably badly detected).

Report Configuration