OV - exec - Loop 24

	Loop Id: 24	Module: exec	Source: cg.cpp:85-90	Coverage: 0.31%

0x411c20 CMP	W10, W15

0x411c24 ADD	W10, W10, #1

0x411c28 ADD	W12, W12, #1

0x411c2c ADD	W8, W23, W5

0x411c30 B.EQ	412050

0x411c34 SBFM	X23, X8, #0, #31

0x411c38 SBFM	X19, X8, #61, #31

0x411c3c CMP	X21, X22

0x411c40 B.CS	411c4c

0x411c44 ORR	X3, XZR, X4

0x411c48 B	411f54

0x411c4c LDUR	W8, [X29, #404]

0x411c50 STUR	W10, [X29, #452]

0x411c54 LDP	X10, X9, [SP, #88]

0x411c58 ORR	X2, XZR, X5

0x411c5c ADD	W8, W8, W12

0x411c60 MUL	W8, W5, W8

0x411c64 STUR	X23, [X29, #456]

0x411c68 STUR	X19, [X29, #440]

0x411c6c ORR	X19, XZR, X4

0x411c70 SBFM	X13, X8, #0, #31

0x411c74 SBFM	X8, X8, #61, #31

0x411c78 ADD	X0, X4, X13

0x411c7c ADD	X14, X5, X13

0x411c80 ADD	X25, X9, X0,LSL #3

0x411c84 LDR	X9, [SP, #104]

0x411c88 ADD	X24, X10, X14,LSL #3

0x411c8c ADD	X4, X18, X0,LSL #3

0x411c90 ADD	X23, X9, X8

0x411c94 LDUR	X9, [X29, #408]

0x411c98 ADD	X1, X9, X13

0x411c9c LDP	X10, X9, [SP, #112]

0x411ca0 ADD	X13, X16, X13

0x411ca4 ORR	X16, XZR, X17

0x411ca8 ADD	X30, X17, X13,LSL #3

0x411cac ADD	X15, X18, X1,LSL #3

0x411cb0 ADD	X27, X17, X1,LSL #3

0x411cb4 ORR	X17, XZR, X18

0x411cb8 SUB	X18, X29, #32

0x411cbc ADD	X22, X10, X8

0x411cc0 ADD	X21, X9, X8

0x411cc4 LDP	X9, X8, [SP, #128]

0x411cc8 LDUR	X10, [X29, #384]

0x411ccc ADD	X6, X8, X14,LSL #3

0x411cd0 LDUR	X8, [X29, #416]

0x411cd4 ADD	X20, X9, X14,LSL #3

0x411cd8 ADD	X5, X8, X0,LSL #3

0x411cdc LDR	X8, [SP, #80]

0x411ce0 ADD	X9, X8, X14,LSL #3

0x411ce4 LDUR	X8, [X29, #464]

0x411ce8 ADD	X11, X8, X0,LSL #3

0x411cec CMP	X11, X6

0x411cf0 CCMP	X5, X9, #2, #3

0x411cf4 CSINC	W8, WZR, WZR, #2

0x411cf8 CMP	X11, X20

0x411cfc CCMP	X4, X9, #2, #3

0x411d00 CSINC	W13, WZR, WZR, #2

0x411d04 CMP	X11, X21

0x411d08 CCMP	X15, X9, #2, #3

0x411d0c CSINC	W14, WZR, WZR, #2

0x411d10 CMP	X11, X22

0x411d14 CCMP	X30, X9, #2, #3

0x411d18 CSINC	W0, WZR, WZR, #2

0x411d1c CMP	X11, X23

0x411d20 CCMP	X27, X9, #2, #3

0x411d24 CSINC	W1, WZR, WZR, #2

0x411d28 CMP	X11, X24

0x411d2c CCMP	X25, X9, #2, #3

0x411d30 CSINC	W3, WZR, WZR, #2

0x411d34 CMP	X18, X6

0x411d38 CCMP	X5, X10, #2, #3

0x411d3c CSINC	W6, WZR, WZR, #2

0x411d40 CMP	X18, X20

0x411d44 CCMP	X4, X10, #2, #3

0x411d48 CSINC	W20, WZR, WZR, #2

0x411d4c CMP	X18, X21

0x411d50 CCMP	X15, X10, #2, #3

0x411d54 CSINC	W21, WZR, WZR, #2

0x411d58 CMP	X18, X22

0x411d5c CCMP	X30, X10, #2, #3

0x411d60 CSINC	W22, WZR, WZR, #2

0x411d64 CMP	X18, X23

0x411d68 CCMP	X27, X10, #2, #3

0x411d6c CSINC	W23, WZR, WZR, #2

0x411d70 CMP	X18, X24

0x411d74 CCMP	X25, X10, #2, #3

0x411d78 CSINC	W24, WZR, WZR, #2

0x411d7c CMP	X18, X9

0x411d80 CCMP	X11, X10, #2, #3

0x411d84 B.CC	412010

0x411d88 LDUR	W15, [X29, #400]

0x411d8c ORR	X5, XZR, X2

0x411d90 ORR	X18, XZR, X17

0x411d94 TBNZ	W8, #0, 412028

0x411d98 ORR	X4, XZR, X19

0x411d9c ORR	X17, XZR, X16

0x411da0 TBNZ	W13, #0, 412008

0x411da4 LDUR	X16, [X29, #376]

0x411da8 LDUR	X19, [X29, #440]

0x411dac TBNZ	W14, #0, 411f40

0x411db0 LDUR	W10, [X29, #452]

0x411db4 TBNZ	W0, #0, 411f44

0x411db8 TBNZ	W1, #0, 411f44

0x411dbc TBNZ	W3, #0, 411f44

0x411dc0 TBNZ	W6, #0, 411f44

0x411dc4 TBNZ	W20, #0, 411f44

0x411dc8 TBNZ	W21, #0, 411f44

0x411dcc TBNZ	W22, #0, 411f44

0x411dd0 TBNZ	W23, #0, 411f44

0x411dd4 TBNZ	W24, #0, 411f44

0x411dd8 LDP	X8, X9, [SP, #64]

0x411ddc LDUR	X2, [X29, #456]

0x411de0 SEL	Z2.D, P0, Z2.D, Z1.D

0x411de4 MOVI	V3.2D, #0

0x411de8 ORR	X3, XZR, XZR

0x411dec ADD	X30, X9, X19

0x411df0 ADD	X13, X8, X19

0x411df4 LDP	X9, X11, [X29, #920]

0x411df8 ADD	X8, X4, X2

0x411dfc ADD	X20, X11, X8,LSL #3

0x411e00 LDR	X11, [SP, #56]

0x411e04 ADD	X9, X9, X2

0x411e08 ADD	X25, X17, X9,LSL #3

0x411e0c ADD	X21, X18, X9,LSL #3

0x411e10 ADD	X23, X11, X8,LSL #3

0x411e14 LDP	X14, X11, [SP, #40]

0x411e18 ADD	X27, X11, X9,LSL #3

0x411e1c ADD	X24, X14, X9,LSL #3

0x411e20 LDR	X9, [SP, #32]

0x411e24 ADD	X0, X14, X8,LSL #3

0x411e28 ADD	X1, X9, X19

0x411e2c ADD	X9, X16, X2

0x411e30 CNTW	X2, ALL

0x411e34 ADD	X14, X17, X9,LSL #3

0x411e38 ADD	X6, X11, X9,LSL #3

0x411e3c LDUR	X9, [X29, #464]

0x411e40 ADD	X22, X9, X8,LSL #3

0x411e44 LDR	X9, [SP, #24]

0x411e48 ADD	X8, X9, X8,LSL #3

  (25) 0x411e4c ADD	X9, X20, X3,LSL #3

  (25) 0x411e50 ADD	X11, X23, X3,LSL #3

  (25) 0x411e54 LD1D	{Z6.D}, P1/Z, [X20, X3,LSL #3]

  (25) 0x411e58 LD1D	{Z16.D}, P1/Z, [X21, X3,LSL #3]

  (25) 0x411e5c FADD	Z22.D, Z6.D, Z16.D

  (25) 0x411e60 LD1D	{Z4.D}, P1/Z, [X9, X28,LSL #3]

  (25) 0x411e64 LD1D	{Z5.D}, P1/Z, [X11, X28,LSL #3]

  (25) 0x411e68 ADD	X9, X30, X3,LSL #3

  (25) 0x411e6c ADD	X11, X13, X3,LSL #3

  (25) 0x411e70 LD1D	{Z24.D}, P1/Z, [X9, X28,LSL #3]

  (25) 0x411e74 LD1D	{Z25.D}, P1/Z, [X11, X28,LSL #3]

  (25) 0x411e78 LD1D	{Z7.D}, P1/Z, [X23, X3,LSL #3]

  (25) 0x411e7c LD1D	{Z17.D}, P1/Z, [X24, X3,LSL #3]

  (25) 0x411e80 LD1D	{Z26.D}, P1/Z, [X9, X26,LSL #3]

  (25) 0x411e84 LD1D	{Z27.D}, P1/Z, [X11, X26,LSL #3]

  (25) 0x411e88 LD1D	{Z28.D}, P1/Z, [X25, X3,LSL #3]

  (25) 0x411e8c LD1D	{Z29.D}, P1/Z, [X27, X3,LSL #3]

  (25) 0x411e90 LD1D	{Z18.D}, P1/Z, [X1, X3,LSL #3]

  (25) 0x411e94 LD1D	{Z19.D}, P1/Z, [X0, X3,LSL #3]

  (25) 0x411e98 MOVPRFX	Z20, Z4

  (25) 0x411e9c FADD	Z20.D, P1/M, Z20.D, #0.0000000

  (25) 0x411ea0 MOVPRFX	Z21, Z5

  (25) 0x411ea4 FADD	Z21.D, P1/M, Z21.D, #0.0000000

  (25) 0x411ea8 LD1D	{Z30.D}, P1/Z, [X14, X3,LSL #3]

  (25) 0x411eac LD1D	{Z31.D}, P1/Z, [X6, X3,LSL #3]

  (25) 0x411eb0 FMUL	Z4.D, Z24.D, Z4.D

  (25) 0x411eb4 FMUL	Z5.D, Z25.D, Z5.D

  (25) 0x411eb8 LD1D	{Z23.D}, P1/Z, [X13, X3,LSL #3]

  (25) 0x411ebc FADD	Z20.D, Z20.D, Z22.D

  (25) 0x411ec0 FADD	Z22.D, Z7.D, Z17.D

  (25) 0x411ec4 FADD	Z21.D, Z21.D, Z22.D

  (25) 0x411ec8 LD1D	{Z22.D}, P1/Z, [X30, X3,LSL #3]

  (25) 0x411ecc FMLA	Z4.D, P1/M, Z26.D, Z6.D

  (25) 0x411ed0 FMLA	Z5.D, P1/M, Z27.D, Z7.D

  (25) 0x411ed4 FADD	Z20.D, Z20.D, Z18.D

  (25) 0x411ed8 LD1D	{Z6.D}, P1/Z, [X30, X3,LSL #3]

  (25) 0x411edc LD1D	{Z7.D}, P1/Z, [X13, X3,LSL #3]

  (25) 0x411ee0 FMLA	Z4.D, P1/M, Z28.D, Z16.D

  (25) 0x411ee4 FMLA	Z5.D, P1/M, Z29.D, Z17.D

  (25) 0x411ee8 FADD	Z21.D, Z21.D, Z19.D

  (25) 0x411eec FMLA	Z4.D, P1/M, Z30.D, Z18.D

  (25) 0x411ef0 FMLA	Z5.D, P1/M, Z31.D, Z19.D

  (25) 0x411ef4 FNMLS	Z4.D, P1/M, Z22.D, Z20.D

  (25) 0x411ef8 FNMLS	Z5.D, P1/M, Z23.D, Z21.D

  (25) 0x411efc FMLA	Z2.D, P1/M, Z6.D, Z4.D

  (25) 0x411f00 FMLA	Z3.D, P1/M, Z7.D, Z5.D

  (25) 0x411f04 ST1D	{Z4.D}, P1, [X22, X3,LSL #3]

  (25) 0x411f08 ST1D	{Z5.D}, P1, [X8, X3,LSL #3]

  (25) 0x411f0c ADD	X3, X3, X2

  (25) 0x411f10 CMP	X7, X3

  (25) 0x411f14 B.NE	411e4c

0x411f18 FADD	Z2.D, Z3.D, Z2.D

0x411f1c LDUR	X21, [X29, #392]

0x411f20 LDR	X22, [SP, #144]

0x411f24 LDUR	X23, [X29, #456]

0x411f28 ADD	X3, X7, X4

0x411f2c CMP	X21, X7

0x411f30 FADDV	D2, P1, Z2.D

0x411f34 STUR	D2, [X29, #480]

0x411f38 B.EQ	411c20

0x411f3c B	411f54

0x411f40 LDUR	W10, [X29, #452]

0x411f44 ORR	X3, XZR, X4

0x411f48 LDUR	X21, [X29, #392]

0x411f4c LDR	X22, [SP, #144]

0x411f50 LDUR	X23, [X29, #456]

0x411f54 ADD	X9, X3, X23

0x411f58 LDP	X2, X8, [X29, #936]

0x411f5c ADD	X1, X16, X3

0x411f60 ORR	X13, XZR, XZR

0x411f64 ADD	X11, X9, X5

0x411f68 ADD	X14, X18, X11,LSL #3

0x411f6c ADD	X0, X17, X11,LSL #3

0x411f70 ADD	X11, X19, X3,LSL #3

0x411f74 ADD	X3, X18, X11

0x411f78 ADD	X19, X17, X11

0x411f7c LDUR	X11, [X29, #464]

0x411f80 ADD	X8, X9, X8

0x411f84 ADD	X6, X2, X9,LSL #3

0x411f88 ADD	X8, X17, X8,LSL #3

0x411f8c ADD	X20, X11, X9,LSL #3

0x411f90 HINT	#0

0x411f94 HINT	#0

0x411f98 HINT	#0

0x411f9c HINT	#0

  (23) 0x411fa0 ADD	X9, X6, X13

  (23) 0x411fa4 LDR	D5, [X14, X13]

  (23) 0x411fa8 LDR	D19, [X0, X13]

  (23) 0x411fac LDR	D6, [X3, X13]

  (23) 0x411fb0 ADDS	X1, X1, #1

  (23) 0x411fb4 LDR	D20, [X8, X13]

  (23) 0x411fb8 LDP	D4, D3, [X9, #1016]

  (23) 0x411fbc ADD	X9, X19, X13

  (23) 0x411fc0 FADD	D7, D3, D0

  (23) 0x411fc4 LDUR	D18, [X9, #504]

  (23) 0x411fc8 FADD	D16, D4, D5

  (23) 0x411fcc FADD	D7, D7, D16

  (23) 0x411fd0 LDP	D17, D16, [X9]

  (23) 0x411fd4 FMUL	D3, D16, D3

  (23) 0x411fd8 FMADD	D3, D18, D4, D3

  (23) 0x411fdc FADD	D7, D7, D6

  (23) 0x411fe0 FMADD	D3, D19, D5, D3

  (23) 0x411fe4 FMADD	D3, D20, D6, D3

  (23) 0x411fe8 FNMSUB	D3, D17, D7, D3

  (23) 0x411fec STR	D3, [X20, X13]

  (23) 0x411ff0 ADD	X13, X13, #8

  (23) 0x411ff4 LDR	D4, [X9]

  (23) 0x411ff8 FMADD	D2, D4, D3, D2

  (23) 0x411ffc STUR	D2, [X29, #480]

  (23) 0x412000 B.CC	411fa0

0x412004 B	411c20

0x412008 ORR	X3, XZR, X4

0x41200c B	412034

0x412010 LDUR	W15, [X29, #400]

0x412014 ORR	X4, XZR, X19

0x412018 ORR	X3, XZR, X19

0x41201c ORR	X5, XZR, X2

0x412020 ORR	X18, XZR, X17

0x412024 B	412030

0x412028 ORR	X4, XZR, X19

0x41202c ORR	X3, XZR, X19

0x412030 ORR	X17, XZR, X16

0x412034 LDUR	X16, [X29, #376]

0x412038 LDUR	W10, [X29, #452]

0x41203c LDUR	X21, [X29, #392]

0x412040 LDR	X22, [SP, #144]

0x412044 LDUR	X23, [X29, #456]

0x412048 LDUR	X19, [X29, #440]

0x41204c B	411f54

/home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp: 85 - 90

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

85:   for (int jj = halo_depth; jj < y - halo_depth; ++jj) {

86:     for (int kk = halo_depth; kk < x - halo_depth; ++kk) {

87:       const int index = kk + jj * x;

88:       const double smvp = tealeaf_SMVP(p);

89:       w[index] = smvp;

90:       pw_temp += w[index] * p[index];

Coverage (%)	Name	Source Location	Module
►98.36+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.64+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	run_cg_calc_w(Chunk*, Settings[...]	cg.cpp:94	exec
○	cg_main_step_driver(Chunk*, Se[...]	cg_driver.cpp:57	exec
○	cg_driver(Chunk*, Settings&, d[...]	cg_driver.cpp:18	exec
○	solve(Chunk*, Settings&, int, [...]	diffuse.cpp:45	exec
○	diffuse(Chunk*, Settings&)	diffuse.cpp:12	exec
○	main	main.cpp:169	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		exec

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 /

Metric	Value
CQA speedup if no scalar integer	5.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.73
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.28
Bottlenecks	P2, P3, P4, P5,
Function	cg_calc_w(int, int, int, double, double const, double, double const, double const*) [clone .omp_outlined]
Source	cg.cpp:85-86,cg.cpp:90-90
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	30.00
CQA cycles if no scalar integer	6.00
CQA cycles if FP arith vectorized	30.00
CQA cycles if fully vectorized	11.00
Front-end cycles	23.50
P0 cycles	11.00
P1 cycles	11.00
P2 cycles	30.00
P3 cycles	30.00
P4 cycles	30.00
P5 cycles	30.00
P6 cycles	2.00
P7 cycles	2.00
P8 cycles	1.50
P9 cycles	1.50
P10 cycles	14.00
P11 cycles	14.00
P12 cycles	14.00
P13 cycles	1.50
P14 cycles	1.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	192.00
Nb uops	188.00
Nb loads	NA
Nb stores	4.00
Nb stack references	13.00
FLOP/cycle	0.27
Nb FLOP add-sub	8.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	0.70
Bytes prefetched	0.00
Bytes loaded	18.00
Bytes stored	3.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	2.11
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	4.44
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	1.49
Vector-efficiency ratio all	26.76
Vector-efficiency ratio load	23.00
Vector-efficiency ratio store	21.88
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	27.22
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	28.36

Metric	Value
CQA speedup if no scalar integer	5.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.73
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.28
Bottlenecks	P2, P3, P4, P5,
Function	cg_calc_w(int, int, int, double, double const, double, double const, double const*) [clone .omp_outlined]
Source	cg.cpp:85-86,cg.cpp:90-90
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	30.00
CQA cycles if no scalar integer	6.00
CQA cycles if FP arith vectorized	30.00
CQA cycles if fully vectorized	11.00
Front-end cycles	23.50
P0 cycles	11.00
P1 cycles	11.00
P2 cycles	30.00
P3 cycles	30.00
P4 cycles	30.00
P5 cycles	30.00
P6 cycles	2.00
P7 cycles	2.00
P8 cycles	1.50
P9 cycles	1.50
P10 cycles	14.00
P11 cycles	14.00
P12 cycles	14.00
P13 cycles	1.50
P14 cycles	1.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	192.00
Nb uops	188.00
Nb loads	NA
Nb stores	4.00
Nb stack references	13.00
FLOP/cycle	0.27
Nb FLOP add-sub	8.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	0.70
Bytes prefetched	0.00
Bytes loaded	18.00
Bytes stored	3.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	2.11
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	4.44
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	1.49
Vector-efficiency ratio all	26.76
Vector-efficiency ratio load	23.00
Vector-efficiency ratio store	21.88
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	27.22
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	28.36

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	cg_calc_w(int, int, int, double, double const, double, double const, double const*) [clone .omp_outlined]
Source file and lines	cg.cpp:85-90
Module	exec

The loop is defined in /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:85-90.

Analyzed code is defined in /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:85-86,90.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

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 30.00 to 6.00 cycles (5.00x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 26% of vector register length is used (average across all VPU instructions). By fully vectorizing your loop, you can lower the cost of an iteration from 30.00 to 11.00 cycles (2.73x speedup).

Details

2% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
4% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply instructions are used in vector version.
1% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

No data for this section

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

The binary loop is composed of 8 FP arithmetical operations:

8: addition or subtraction

The binary loop is loading 18 bytes. The binary loop is storing 3 bytes.

Arithmetic intensity

Arithmetic intensity is 0.38 FP operations per loaded or stored byte.

General properties

nb instructions	192
nb uops	188
loop length	768
used w registers	17
used x registers	29
used b registers	0
used h registers	0
used s registers	1
used d registers	1
used q registers	0
used v registers	1
used z registers	3
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	23.50 cycles
front end	23.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	11.00	11.00	30.00	30.00	30.00	30.00	2.00	2.00	1.00	1.00	14.00	14.00	14.00	1.50	1.50
cycles	11.00	11.00	30.00	30.00	30.00	30.00	2.00	2.00	1.50	1.50	14.00	14.00	14.00	1.50	1.50

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	23.50
Dispatch	30.00
Overall L1	30.00

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	1%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	2%
load	0%
store	0%
mul	0%
add-sub	4%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	1%

Vector efficiency ratios

INT

all	25%
load	23%
store	21%
mul	12%
add-sub	23%
fma	NA (no fma vectorizable/vectorized instructions)
other	28%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	26%
load	23%
store	21%
mul	12%
add-sub	27%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	28%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 30.00 cycles. At this rate:

0% of peak load performance is reached (0.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.10 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 411c20

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
CMP W10, W15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD W10, W10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W12, W12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W8, W23, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
B.EQ 412050 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x620>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X23, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
SBFM X19, X8, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
CMP X21, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 411c4c <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x21c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X3, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 411f54 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x524>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W8, [X29, #404]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
STUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (12.5%)
LDP X10, X9, [SP, #88]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ORR X2, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD W8, W8, W12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
MUL W8, W5, W8	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (12.5%)
STUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STUR X19, [X29, #440]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X19, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SBFM X13, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
SBFM X8, X8, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
ADD X0, X4, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X14, X5, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X9, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X9, [SP, #104]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X24, X10, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X4, X18, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X23, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X9, [X29, #408]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X1, X9, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X10, X9, [SP, #112]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD X13, X16, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X16, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X30, X17, X13,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X15, X18, X1,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X27, X17, X1,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X17, XZR, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X18, X29, #32	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X10, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X21, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X9, X8, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDUR X10, [X29, #384]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X6, X8, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X8, [X29, #416]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X20, X9, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X5, X8, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X8, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X8, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDUR X8, [X29, #464]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X11, X8, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X11, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X5, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W8, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X4, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W13, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X15, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W14, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X30, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W0, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X27, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W1, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X25, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W3, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X5, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W6, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X4, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W20, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X18, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X15, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W21, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X30, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W22, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X27, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W23, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X25, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W24, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X11, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B.CC 412010 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x5e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W15, [X29, #400]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR X5, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X18, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
TBNZ W8, #0, 412028 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x5f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X4, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X17, XZR, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
TBNZ W13, #0, 412008 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x5d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X16, [X29, #376]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X19, [X29, #440]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
TBNZ W14, #0, 411f40 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x510>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
TBNZ W0, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W1, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W3, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W6, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W20, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W21, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W22, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W23, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W24, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X8, X9, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDUR X2, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SEL Z2.D, P0, Z2.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
MOVI V3.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ORR X3, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X30, X9, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X8, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X9, X11, [X29, #920]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD X8, X4, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X20, X11, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X11, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X9, X9, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X25, X17, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X21, X18, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X23, X11, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X14, X11, [SP, #40]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD X27, X11, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X14, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X9, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X0, X14, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X1, X9, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X16, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTW X2, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ADD X14, X17, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X6, X11, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X9, [X29, #464]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X22, X9, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X9, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X9, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
FADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
LDUR X21, [X29, #392]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X3, X7, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X21, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FADDV D2, P1, Z2.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
STUR D2, [X29, #480]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
B.EQ 411c20 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x1f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 411f54 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x524>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR X3, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X21, [X29, #392]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X3, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDP X2, X8, [X29, #936]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
ADD X1, X16, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X13, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X9, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X14, X18, X11,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X17, X11,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X19, X3,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X3, X18, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X19, X17, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X11, [X29, #464]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X6, X2, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X17, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X20, X11, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
B 411c20 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x1f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X3, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 412034 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x604>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W15, [X29, #400]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR X4, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X3, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X5, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X18, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 412030 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x600>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X4, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X3, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X17, XZR, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X16, [X29, #376]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
LDUR X21, [X29, #392]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X19, [X29, #440]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
B 411f54 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x524>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	cg_calc_w(int, int, int, double, double const, double, double const, double const*) [clone .omp_outlined]
Source file and lines	cg.cpp:85-90
Module	exec

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

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 30.00 to 6.00 cycles (5.00x speedup).

Workaround

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

Vectorization

Details

2% of VPU instructions are used in vector version (process two or more data elements in vector registers):

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
4% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply instructions are used in vector version.
1% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

No data for this section

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

The binary loop is composed of 8 FP arithmetical operations:

8: addition or subtraction

The binary loop is loading 18 bytes. The binary loop is storing 3 bytes.

Arithmetic intensity

Arithmetic intensity is 0.38 FP operations per loaded or stored byte.

General properties

nb instructions	192
nb uops	188
loop length	768
used w registers	17
used x registers	29
used b registers	0
used h registers	0
used s registers	1
used d registers	1
used q registers	0
used v registers	1
used z registers	3
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	23.50 cycles
front end	23.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	11.00	11.00	30.00	30.00	30.00	30.00	2.00	2.00	1.00	1.00	14.00	14.00	14.00	1.50	1.50
cycles	11.00	11.00	30.00	30.00	30.00	30.00	2.00	2.00	1.50	1.50	14.00	14.00	14.00	1.50	1.50

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	23.50
Dispatch	30.00
Overall L1	30.00

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	1%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	2%
load	0%
store	0%
mul	0%
add-sub	4%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	1%

Vector efficiency ratios

INT

all	25%
load	23%
store	21%
mul	12%
add-sub	23%
fma	NA (no fma vectorizable/vectorized instructions)
other	28%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	26%
load	23%
store	21%
mul	12%
add-sub	27%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	28%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 30.00 cycles. At this rate:

0% of peak load performance is reached (0.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
0% of peak store performance is reached (0.10 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 411c20

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
CMP W10, W15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD W10, W10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W12, W12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W8, W23, W5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
B.EQ 412050 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x620>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X23, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
SBFM X19, X8, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
CMP X21, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 411c4c <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x21c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X3, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 411f54 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x524>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W8, [X29, #404]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
STUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (12.5%)
LDP X10, X9, [SP, #88]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ORR X2, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD W8, W8, W12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
MUL W8, W5, W8	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (12.5%)
STUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STUR X19, [X29, #440]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X19, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SBFM X13, X8, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
SBFM X8, X8, #61, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
ADD X0, X4, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X14, X5, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X9, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X9, [SP, #104]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X24, X10, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X4, X18, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X23, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X9, [X29, #408]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X1, X9, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X10, X9, [SP, #112]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD X13, X16, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X16, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X30, X17, X13,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X15, X18, X1,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X27, X17, X1,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X17, XZR, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X18, X29, #32	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X10, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X21, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X9, X8, [SP, #128]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDUR X10, [X29, #384]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X6, X8, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X8, [X29, #416]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X20, X9, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X5, X8, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X8, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X8, X14,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDUR X8, [X29, #464]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X11, X8, X0,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X11, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X5, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W8, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X4, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W13, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X15, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W14, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X30, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W0, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X27, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W1, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X11, X24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X25, X9, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W3, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X5, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W6, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X4, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W20, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X18, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X15, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W21, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X30, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W22, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X27, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W23, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X25, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W24, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X18, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X11, X10, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B.CC 412010 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x5e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W15, [X29, #400]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR X5, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X18, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
TBNZ W8, #0, 412028 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x5f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X4, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X17, XZR, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
TBNZ W13, #0, 412008 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x5d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X16, [X29, #376]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X19, [X29, #440]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
TBNZ W14, #0, 411f40 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x510>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
TBNZ W0, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W1, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W3, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W6, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W20, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W21, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W22, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W23, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W24, #0, 411f44 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x514>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X8, X9, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDUR X2, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SEL Z2.D, P0, Z2.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
MOVI V3.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ORR X3, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X30, X9, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X8, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X9, X11, [X29, #920]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD X8, X4, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X20, X11, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X11, [SP, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X9, X9, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X25, X17, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X21, X18, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X23, X11, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X14, X11, [SP, #40]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADD X27, X11, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X14, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X9, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X0, X14, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X1, X9, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X16, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CNTW X2, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ADD X14, X17, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X6, X11, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X9, [X29, #464]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X22, X9, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X9, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X9, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
FADD Z2.D, Z3.D, Z2.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
LDUR X21, [X29, #392]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X3, X7, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X21, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
FADDV D2, P1, Z2.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
STUR D2, [X29, #480]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
B.EQ 411c20 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x1f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 411f54 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x524>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR X3, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X21, [X29, #392]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X3, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDP X2, X8, [X29, #936]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
ADD X1, X16, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X13, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X9, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X14, X18, X11,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X17, X11,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X19, X3,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD X3, X18, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X19, X17, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X11, [X29, #464]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X6, X2, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X17, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X20, X11, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
B 411c20 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x1f0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X3, XZR, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 412034 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x604>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR W15, [X29, #400]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR X4, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X3, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X5, XZR, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X18, XZR, X17	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 412030 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x600>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X4, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X3, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X17, XZR, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X16, [X29, #376]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR W10, [X29, #452]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
LDUR X21, [X29, #392]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR X22, [SP, #144]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X23, [X29, #456]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDUR X19, [X29, #440]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
B 411f54 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x524>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

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

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

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

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