OV - exec - Function .omp_outlined.#0x4a8df0

	Function: .omp_outlined.#0x4a8df0	Module: exec	Source: vector.c:268-271	Coverage: 0.14%

/home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/vector.c: 268 - 271

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

268: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE

269: #endif

270:    for (i = 0; i < size; i++)

271:       vector_data[i] = value;

0x4a8df0 SUB	SP, SP, #96

0x4a8df4 STP	X29, X30, [SP, #48]

0x4a8df8 STP	X22, X21, [SP, #64]

0x4a8dfc STP	X20, X19, [SP, #80]

0x4a8e00 ADD	X29, SP, #48

0x4a8e04 LDR	X8, [X2]

0x4a8e08 SUBS	X22, X8, #1

0x4a8e0c B.LT	4a8f88

0x4a8e10 LDR	W20, [X0]

0x4a8e14 LDR	X21, [X3]

0x4a8e18 ORR	X19, XZR, X4

0x4a8e1c MOVZ	W8, #1

0x4a8e20 ADRP	X0,

0x4a8e24 ADD	X0, X0, #1968

0x4a8e28 STP	X22, XZR, [X29, #1008]

0x4a8e2c STR	WZR, [SP, #20]

0x4a8e30 ADD	X3, SP, #20

0x4a8e34 SUB	X4, X29, #8

0x4a8e38 SUB	X5, X29, #16

0x4a8e3c ADD	X6, SP, #24

0x4a8e40 STR	X8, [SP, #24]

0x4a8e44 STR	X8, [SP]

0x4a8e48 MOVZ	W2, #34

0x4a8e4c MOVZ	W7, #1

0x4a8e50 ORR	W1, WZR, W20

0x4a8e54 BL	40f550

0x4a8e58 LDP	X8, X9, [X29, #1008]

0x4a8e5c CMP	X8, X22

0x4a8e60 CSEL	X8, X8, X22, #11

0x4a8e64 CMP	X9, X8

0x4a8e68 B.GT	4a8f78

0x4a8e6c SUB	X10, X8, X9

0x4a8e70 MOVZ	W11, #12

0x4a8e74 ADD	X12, X10, #1

0x4a8e78 CNTW	X10, ALL

0x4a8e7c CMP	X10, #12

0x4a8e80 CSEL	X11, X10, X11, #8

0x4a8e84 CMP	X12, X11

0x4a8e88 B.CC	4a8efc

0x4a8e8c ADD	X11, X21, X9,LSL #3

0x4a8e90 ADD	X13, X21, X8,LSL #3

0x4a8e94 ADD	X14, X19, #8

0x4a8e98 ADD	X13, X13, #8

0x4a8e9c CMP	X11, X14

0x4a8ea0 CCMP	X13, X19, #0, #3

0x4a8ea4 B.HI	4a8efc

0x4a8ea8 UDIV	X13, X12, X10

0x4a8eac PTRUE	P0.D, ALL

0x4a8eb0 UBFM	X15, X9, #61, #60

0x4a8eb4 ORR	X11, XZR, XZR

0x4a8eb8 LD1RD	{Z0.D}, P0/Z, [X19]

0x4a8ebc MADD	X13, X13, X10, XZR

0x4a8ec0 ADD	X14, X9, X13

0x4a8ec4 ADD	X9, X21, X15

0x4a8ec8 ADDVL	X15, X15, #1

0x4a8ecc SUB	X12, X12, X13

0x4a8ed0 ADD	X15, X21, X15

0x4a8ed4 HINT	#0

0x4a8ed8 HINT	#0

0x4a8edc HINT	#0

(23) 0x4a8ee0 ST1D	{Z0.D}, P0, [X9, X11,LSL #3]

(23) 0x4a8ee4 ST1D	{Z0.D}, P0, [X15, X11,LSL #3]

(23) 0x4a8ee8 ADD	X11, X11, X10

(23) 0x4a8eec CMP	X13, X11

(23) 0x4a8ef0 B.NE	4a8ee0

0x4a8ef4 ORR	X9, XZR, X14

0x4a8ef8 CBZ	X12, 4a8f78

0x4a8efc SUB	W10, W8, W9

0x4a8f00 ADD	W11, W10, #1

0x4a8f04 SUB	X10, X8, X9

0x4a8f08 ANDS	X11, X11, #4160

0x4a8f0c B.EQ	4a8f34

0x4a8f10 HINT	#0

0x4a8f14 HINT	#0

0x4a8f18 HINT	#0

0x4a8f1c HINT	#0

(22) 0x4a8f20 LDR	D0, [X19]

(22) 0x4a8f24 SUBS	X11, X11, #1

(22) 0x4a8f28 STR	D0, [X21, X9,LSL #3]

(22) 0x4a8f2c ADD	X9, X9, #1

(22) 0x4a8f30 B.NE	4a8f20

0x4a8f34 CMP	X10, #3

0x4a8f38 B.CC	4a8f78

0x4a8f3c ADD	X10, X21, X9,LSL #3

0x4a8f40 SUB	X8, X8, X9

0x4a8f44 ADD	X10, X10, #16

0x4a8f48 ADD	X8, X8, #1

(21) 0x4a8f4c LDR	D0, [X19]

(21) 0x4a8f50 SUBS	X8, X8, #4

(21) 0x4a8f54 STUR	D0, [X10, #496]

(21) 0x4a8f58 LDR	D0, [X19]

(21) 0x4a8f5c STUR	D0, [X10, #504]

(21) 0x4a8f60 LDR	D0, [X19]

(21) 0x4a8f64 STR	D0, [X10]

(21) 0x4a8f68 LDR	D0, [X19]

(21) 0x4a8f6c STR	D0, [X10, #8]

(21) 0x4a8f70 ADD	X10, X10, #32

(21) 0x4a8f74 B.NE	4a8f4c

0x4a8f78 ORR	W1, WZR, W20

0x4a8f7c ADRP	X0,

0x4a8f80 ADD	X0, X0, #1992

0x4a8f84 BL	40f410

0x4a8f88 LDP	X20, X19, [SP, #80]

0x4a8f8c LDP	X22, X21, [SP, #64]

0x4a8f90 LDP	X29, X30, [SP, #48]

0x4a8f94 ADD	SP, SP, #96

0x4a8f98 RET

0x4a8f9c HINT	#0

Coverage (%)	Name	Source Location	Module

Path /

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

Source file and lines	vector.c:268-271
Module	exec

The function is defined in /home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/vector.c:268-271.

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 20.00 to 1.00 cycles (20.00x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 24% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 20.00 to 10.00 cycles (2.00x speedup).

Details

All VPU 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): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

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 20.00 to 1.00 cycles (20.00x speedup).

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 92 bytes. The binary function is storing 84 bytes.

General properties

nb instructions	87
loop length	348
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

9.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	5.00	5.00	14.00	14.00	14.00	14.00	0.00	0.00	0.00	0.00	5.00	5.00	5.00	3.50	3.50
cycles	5.00	5.00	14.00	14.00	14.00	14.00	0.00	0.00	0.00	0.00	5.00	5.00	5.00	3.50	3.50

Execution ports to units layout:

P0:
P1:
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

5.00-20.00

Cycles summary

Front-end	9.88
Overall L1	14.00-20.00

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 20.00 cycles. At this rate:

4% of peak load performance is reached (4.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.20 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 4a8df0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
SUB SP, SP, #96	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X29, X30, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #48	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X8, [X2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SUBS X22, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LT 4a8f88 <.omp_outlined.+0x198>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W20, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X21, [X3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
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
MOVZ W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADRP X0, <4efe20>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X0, X0, #1968	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X22, XZR, [X29, #1008]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR WZR, [SP, #20]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X3, SP, #20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X4, X29, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X5, X29, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X6, SP, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR X8, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR X8, [SP]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ W2, #34	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W1, WZR, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 40f550 <@plt_start@+0x160>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDP X8, X9, [X29, #1008]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
CMP X8, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
CSEL X8, X8, X22, #11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.GT 4a8f78 <.omp_outlined.+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SUB X10, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W11, #12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X12, X10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CNTW X10, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
CMP X10, #12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
CSEL X11, X10, X11, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X12, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.CC 4a8efc <.omp_outlined.+0x10c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X11, X21, 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
ADD X13, X21, 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
ADD X14, X19, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X13, X13, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X11, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
CCMP X13, X19, #0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
B.HI 4a8efc <.omp_outlined.+0x10c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UDIV X13, X12, X10	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UBFM X15, X9, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X11, 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
LD1RD {Z0.D}, P0/Z, [X19]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	6	0.50
MADD X13, X13, X10, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADD X14, 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
ADD X9, X21, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADDVL X15, X15, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
SUB X12, X12, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X15, X21, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
HINT #0
HINT #0
HINT #0
ORR X9, XZR, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CBZ X12, 4a8f78 <.omp_outlined.+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SUB W10, W8, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD W11, 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
SUB X10, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ANDS X11, X11, #4160	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.EQ 4a8f34 <.omp_outlined.+0x144>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
HINT #0
HINT #0
CMP X10, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.CC 4a8f78 <.omp_outlined.+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X10, X21, 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
SUB X8, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X10, X10, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W1, WZR, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADRP X0, <4eff7c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X0, X0, #1992	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 40f410 <@plt_start@+0x20>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X29, X30, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
ADD SP, SP, #96	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0

Source file and lines	vector.c:268-271
Module	exec

The function is defined in /home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/vector.c:268-271.

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)

Vectorization

Details

All VPU 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): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

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 20.00 to 1.00 cycles (20.00x speedup).

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 92 bytes. The binary function is storing 84 bytes.

General properties

nb instructions	87
loop length	348
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

9.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	5.00	5.00	14.00	14.00	14.00	14.00	0.00	0.00	0.00	0.00	5.00	5.00	5.00	3.50	3.50
cycles	5.00	5.00	14.00	14.00	14.00	14.00	0.00	0.00	0.00	0.00	5.00	5.00	5.00	3.50	3.50

Execution ports to units layout:

P0:
P1:
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

5.00-20.00

Cycles summary

Front-end	9.88
Overall L1	14.00-20.00

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 20.00 cycles. At this rate:

4% of peak load performance is reached (4.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (4.20 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 4a8df0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
SUB SP, SP, #96	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X29, X30, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X29, SP, #48	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X8, [X2]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SUBS X22, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LT 4a8f88 <.omp_outlined.+0x198>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR W20, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X21, [X3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
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
MOVZ W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADRP X0, <4efe20>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X0, X0, #1968	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STP X22, XZR, [X29, #1008]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR WZR, [SP, #20]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
ADD X3, SP, #20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X4, X29, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
SUB X5, X29, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X6, SP, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
STR X8, [SP, #24]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
STR X8, [SP]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50
MOVZ W2, #34	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W1, WZR, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 40f550 <@plt_start@+0x160>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDP X8, X9, [X29, #1008]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
CMP X8, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
CSEL X8, X8, X22, #11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.GT 4a8f78 <.omp_outlined.+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SUB X10, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ W11, #12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X12, X10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CNTW X10, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
CMP X10, #12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
CSEL X11, X10, X11, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X12, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.CC 4a8efc <.omp_outlined.+0x10c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X11, X21, 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
ADD X13, X21, 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
ADD X14, X19, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X13, X13, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X11, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
CCMP X13, X19, #0, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
B.HI 4a8efc <.omp_outlined.+0x10c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UDIV X13, X12, X10	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20
PTRUE P0.D, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
UBFM X15, X9, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR X11, 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
LD1RD {Z0.D}, P0/Z, [X19]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	6	0.50
MADD X13, X13, X10, XZR	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
ADD X14, 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
ADD X9, X21, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADDVL X15, X15, #1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1
SUB X12, X12, X13	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X15, X21, X15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
HINT #0
HINT #0
HINT #0
ORR X9, XZR, X14	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CBZ X12, 4a8f78 <.omp_outlined.+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SUB W10, W8, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD W11, 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
SUB X10, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ANDS X11, X11, #4160	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.EQ 4a8f34 <.omp_outlined.+0x144>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
HINT #0
HINT #0
CMP X10, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.CC 4a8f78 <.omp_outlined.+0x188>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD X10, X21, 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
SUB X8, X8, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X10, X10, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ORR W1, WZR, W20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADRP X0, <4eff7c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X0, X0, #1992	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
BL 40f410 <@plt_start@+0x20>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X29, X30, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
ADD SP, SP, #96	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0

Name	Coverage (%)	Time (s)
▼.omp_outlined.#0x4a8df0–	0.14	0.05
○Loop 23 - vector.c:268-268 - exec	0.14	0.04
○Loop 22 - vector.c:270-271 - exec	0	0
○Loop 21 - vector.c:270-271 - exec	0	0

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code