OV - exec - Loop 992

0x49aea4 STR	D0, [X13, X20,LSL #3]

0x49aea8 ORR	X20, XZR, X17

0x49aeac CMP	X17, X19

0x49aeb0 B.EQ	49b83c

0x49aeb4 LDR	D0, [X8, X20,LSL #3]

0x49aeb8 ADD	X17, X20, #1

0x49aebc ORR	X18, XZR, X16

0x49aec0 LDR	X16, [X9, X17,LSL #3]

0x49aec4 CMP	X16, X18

0x49aec8 B.LE	49aea4

0x49aecc SUB	W0, W16, W18

0x49aed0 ANDS	X1, X0, #4160

0x49aed4 B.EQ	49af10

0x49aed8 ORR	X0, XZR, X18

0x49aedc HINT	#0

  (994) 0x49aee0 LDR	X2, [X12, X0,LSL #3]

  (994) 0x49aee4 LDR	D1, [X10, X0,LSL #3]

  (994) 0x49aee8 ADD	X0, X0, #1

  (994) 0x49aeec SUBS	X1, X1, #1

  (994) 0x49aef0 LDR	D2, [X11, X2,LSL #3]

  (994) 0x49aef4 FMADD	D0, D1, D2, D0

  (994) 0x49aef8 B.NE	49aee0

0x49aefc ORN	X18, XZR, X18

0x49af00 ADD	X18, X16, X18

0x49af04 CMP	X18, #3

0x49af08 B.CC	49aea4

0x49af0c B	49af24

0x49af10 ORR	X0, XZR, X18

0x49af14 ORN	X18, XZR, X18

0x49af18 ADD	X18, X16, X18

0x49af1c CMP	X18, #3

0x49af20 B.CC	49aea4

0x49af24 UBFM	X1, X0, #61, #60

0x49af28 SUB	X18, X16, X0

0x49af2c ADD	X0, X14, X1

0x49af30 ADD	X1, X15, X1

0x49af34 HINT	#0

0x49af38 HINT	#0

0x49af3c HINT	#0

  (993) 0x49af40 LDP	X2, X3, [X1, #1008]

  (993) 0x49af44 LDP	D2, D3, [X0, #1008]

  (993) 0x49af48 SUBS	X18, X18, #4

  (993) 0x49af4c LDR	D1, [X11, X2,LSL #3]

  (993) 0x49af50 FMADD	D0, D2, D1, D0

  (993) 0x49af54 LDR	D1, [X11, X3,LSL #3]

  (993) 0x49af58 FMADD	D0, D3, D1, D0

  (993) 0x49af5c LDP	X2, X3, [X1], #32

  (993) 0x49af60 LDR	D2, [X11, X2,LSL #3]

  (993) 0x49af64 LDP	D1, D3, [X0], #32

  (993) 0x49af68 FMADD	D0, D1, D2, D0

  (993) 0x49af6c LDR	D1, [X11, X3,LSL #3]

  (993) 0x49af70 FMADD	D0, D3, D1, D0

  (993) 0x49af74 B.NE	49af40

0x49af78 B	49aea4

/home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 334 - 341

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

334:             for (i = iBegin; i < iEnd; i++)

335:             {

336:                tempx = b_data[i];

337:                for (jj = A_i[i]; jj < A_i[i+1]; jj++)

338:                {

339:                   tempx += A_data[jj] * x_data[A_j[jj]];

340:                }

341:                y_data[i] = tempx;

Coverage (%)	Name	Source Location	Module

Path /

Metric	Value
CQA speedup if no scalar integer	5.70
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.31
Bottlenecks	P2, P3, P4, P5,
Function	.omp_outlined..18#0x49a9a0
Source	csr_matvec.c:334-337,csr_matvec.c:341-341
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.75
CQA cycles if no scalar integer	0.83
CQA cycles if FP arith vectorized	4.75
CQA cycles if fully vectorized	1.00
Front-end cycles	3.63
DIV/SQRT cycles	3.50
P0 cycles	3.50
P1 cycles	4.75
P2 cycles	4.75
P3 cycles	4.75
P4 cycles	4.75
P5 cycles	0.50
P6 cycles	0.50
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	1.17
P10 cycles	0.83
P11 cycles	1.00
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	33.00
Nb uops	29.00
Nb loads	NA
Nb stores	1.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
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	5.05
Bytes prefetched	0.00
Bytes loaded	16.00
Bytes stored	8.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	24.22
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	22.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	25.00

Metric	Value
CQA speedup if no scalar integer	5.70
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.75
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.31
Bottlenecks	P2, P3, P4, P5,
Function	.omp_outlined..18#0x49a9a0
Source	csr_matvec.c:334-337,csr_matvec.c:341-341
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.75
CQA cycles if no scalar integer	0.83
CQA cycles if FP arith vectorized	4.75
CQA cycles if fully vectorized	1.00
Front-end cycles	3.63
DIV/SQRT cycles	3.50
P0 cycles	3.50
P1 cycles	4.75
P2 cycles	4.75
P3 cycles	4.75
P4 cycles	4.75
P5 cycles	0.50
P6 cycles	0.50
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	1.17
P10 cycles	0.83
P11 cycles	1.00
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	33.00
Nb uops	29.00
Nb loads	NA
Nb stores	1.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
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	5.05
Bytes prefetched	0.00
Bytes loaded	16.00
Bytes stored	8.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	24.22
Vector-efficiency ratio load	25.00
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	22.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	25.00

Path /

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

Function	.omp_outlined..18#0x49a9a0
Source file and lines	csr_matvec.c:334-341
Module	exec

The loop is defined in /home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:334-341.

Analyzed code is defined in /home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:334-337,341.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=5
RecMII not computed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 5 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 4.75 to 0.83 cycles (5.70x 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 24% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 4.75 to 1.00 cycles (4.75x 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 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 does not contain any FP arithmetical operations. The binary loop is loading 16 bytes. The binary loop is storing 8 bytes.

General properties

nb instructions	33
loop length	132
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	3.50	3.50	4.75	4.75	4.75	4.75	0.50	0.50	0.00	0.00	1.17	0.83	1.00	0.00	0.00
cycles	3.50	3.50	4.75	4.75	4.75	4.75	0.50	0.50	0.00	0.00	1.17	0.83	1.00	0.00	0.00

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

NA

Cycles summary

Front-end	3.63
Overall L1	4.75

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.75 cycles. At this rate:

3% of peak load performance is reached (3.37 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (1.68 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 49aeb4

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STR D0, [X13, X20,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
ORR X20, 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
CMP X17, X19	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 49b83c <.omp_outlined..18+0xe9c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR D0, [X8, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
ADD X17, X20, #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 X18, 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
LDR X16, [X9, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X16, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LE 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SUB W0, W16, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ANDS X1, X0, #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 49af10 <.omp_outlined..18+0x570>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, 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
HINT #0
ORN X18, 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
ADD X18, X16, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X18, #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 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
B 49af24 <.omp_outlined..18+0x584>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, 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
ORN X18, 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
ADD X18, X16, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X18, #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 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X1, X0, #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
SUB X18, X16, X0	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, X14, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X1, X15, X1	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
B 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	.omp_outlined..18#0x49a9a0
Source file and lines	csr_matvec.c:334-341
Module	exec

The loop is defined in /home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:334-341.

Analyzed code is defined in /home/hbollore/qaas-runs/171-233-5044/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c:334-337,341.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=5
RecMII not computed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 5 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 4.75 to 0.83 cycles (5.70x 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 24% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 4.75 to 1.00 cycles (4.75x 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 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 does not contain any FP arithmetical operations. The binary loop is loading 16 bytes. The binary loop is storing 8 bytes.

General properties

nb instructions	33
loop length	132
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	3.50	3.50	4.75	4.75	4.75	4.75	0.50	0.50	0.00	0.00	1.17	0.83	1.00	0.00	0.00
cycles	3.50	3.50	4.75	4.75	4.75	4.75	0.50	0.50	0.00	0.00	1.17	0.83	1.00	0.00	0.00

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

NA

Cycles summary

Front-end	3.63
Overall L1	4.75

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.75 cycles. At this rate:

3% of peak load performance is reached (3.37 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (1.68 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 49aeb4

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
STR D0, [X13, X20,LSL #3]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50
ORR X20, 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
CMP X17, X19	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 49b83c <.omp_outlined..18+0xe9c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR D0, [X8, X20,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33
ADD X17, X20, #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 X18, 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
LDR X16, [X9, X17,LSL #3]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X16, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.LE 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
SUB W0, W16, W18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ANDS X1, X0, #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 49af10 <.omp_outlined..18+0x570>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, 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
HINT #0
ORN X18, 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
ADD X18, X16, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X18, #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 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
B 49af24 <.omp_outlined..18+0x584>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, 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
ORN X18, 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
ADD X18, X16, X18	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
CMP X18, #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 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
UBFM X1, X0, #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
SUB X18, X16, X0	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, X14, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X1, X15, X1	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
B 49aea4 <.omp_outlined..18+0x504>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code