OV - exec - Loop 205

	Loop Id: 205	Module: exec	Source: par_coarsen.c:2528-2540	Coverage: 0.07%

0x428f9c LDR	X15, [X1]    [12]

0x428fa0 UBFM	X16, X15, #61, #60

0x428fa4 LDR	X17, [X20, X16]    [13]

0x428fa8 CBNZ	X17, 429668

0x428fac LDR	X18, [X1, #8]    [12]

0x428fb0 ADD	X0, X0, #1

0x428fb4 MOVZ	W3, #1

0x428fb8 ADD	X1, X1, #8

0x428fbc UBFM	X30, X18, #61, #60

0x428fc0 LDR	X2, [X20, X30]    [13]

0x428fc4 CBZ	X2, 429680

0x428fc8 LDR	X4, [X1, #8]    [1]

0x428fcc STR	XZR, [X27, X30]    [15]

0x428fd0 UBFM	X7, X4, #61, #60

0x428fd4 LDR	X5, [X20, X7]    [13]

0x428fd8 CBZ	X5, 429698

0x428fdc LDR	X8, [X1, #16]    [3]

0x428fe0 STR	XZR, [X27, X7]    [15]

0x428fe4 UBFM	X9, X8, #61, #60

0x428fe8 LDR	X10, [X20, X9]    [13]

0x428fec CBZ	X10, 4296b0

0x428ff0 LDR	X11, [X1, #24]    [5]

0x428ff4 STR	XZR, [X27, X9]    [15]

0x428ff8 UBFM	X12, X11, #61, #60

0x428ffc LDR	X13, [X20, X12]    [13]

0x429000 CBZ	X13, 4296c8

0x429004 LDR	X14, [X1, #32]    [7]

0x429008 STR	XZR, [X27, X12]    [15]

0x42900c UBFM	X15, X14, #61, #60

0x429010 LDR	X16, [X20, X15]    [13]

0x429014 CBZ	X16, 4296e0

0x429018 LDR	X17, [X1, #40]    [9]

0x42901c STR	XZR, [X27, X15]    [15]

0x429020 UBFM	X18, X17, #61, #60

0x429024 LDR	X30, [X20, X18]    [13]

0x429028 CBZ	X30, 4296f8

0x42902c LDR	X2, [X1, #48]    [11]

0x429030 STR	XZR, [X27, X18]    [15]

0x429034 UBFM	X4, X2, #61, #60

0x429038 LDR	X7, [X20, X4]    [13]

0x42903c CBZ	X7, 429710

0x429040 STR	XZR, [X27, X4]    [15]

0x429044 ADD	X1, X1, #56

0x429048 CMP	X1, X6

0x42904c B.NE	428f9c

0x429668 LDR	X18, [X1, #8]    [12]

0x42966c ADD	X1, X1, #8

0x429670 STR	XZR, [X27, X16]    [15]

0x429674 UBFM	X30, X18, #61, #60

0x429678 LDR	X2, [X20, X30]    [13]

0x42967c CBNZ	X2, 428fc8

0x429680 LDR	X4, [X1, #8]    [14]

0x429684 ADD	X0, X0, #1

0x429688 MOVZ	W3, #1

0x42968c UBFM	X7, X4, #61, #60

0x429690 LDR	X5, [X20, X7]    [13]

0x429694 CBNZ	X5, 428fdc

0x429698 LDR	X8, [X1, #16]    [2]

0x42969c ADD	X0, X0, #1

0x4296a0 MOVZ	W3, #1

0x4296a4 UBFM	X9, X8, #61, #60

0x4296a8 LDR	X10, [X20, X9]    [13]

0x4296ac CBNZ	X10, 428ff0

0x4296b0 LDR	X11, [X1, #24]    [4]

0x4296b4 ADD	X0, X0, #1

0x4296b8 MOVZ	W3, #1

0x4296bc UBFM	X12, X11, #61, #60

0x4296c0 LDR	X13, [X20, X12]    [13]

0x4296c4 CBNZ	X13, 429004

0x4296c8 LDR	X14, [X1, #32]    [6]

0x4296cc ADD	X0, X0, #1

0x4296d0 MOVZ	W3, #1

0x4296d4 UBFM	X15, X14, #61, #60

0x4296d8 LDR	X16, [X20, X15]    [13]

0x4296dc CBNZ	X16, 429018

0x4296e0 LDR	X17, [X1, #40]    [8]

0x4296e4 ADD	X0, X0, #1

0x4296e8 MOVZ	W3, #1

0x4296ec UBFM	X18, X17, #61, #60

0x4296f0 LDR	X30, [X20, X18]    [13]

0x4296f4 CBNZ	X30, 42902c

0x4296f8 LDR	X2, [X1, #48]    [10]

0x4296fc ADD	X0, X0, #1

0x429700 MOVZ	W3, #1

0x429704 UBFM	X4, X2, #61, #60

0x429708 LDR	X7, [X20, X4]    [13]

0x42970c CBNZ	X7, 429040

0x429710 ADD	X0, X0, #1

0x429714 MOVZ	W3, #1

0x429718 B	429044

/home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c: 2528 - 2540

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

2528:         for (ig = ig_begin; ig < ig_end; ig++)

2529:         {

2530:            i = graph_array[ig];

2531:

2532:            if (CF_marker[i]!=0) /* C or F point */

2533:            {

2534:               /* the independent set subroutine needs measure 0 for

2535:                  removed nodes */

2536:               measure_array[i] = 0;

2537:            }

2538:            else

2539:            {

2540:               private_graph_size_cnt++;

Coverage (%)	Name	Source Location	Module
►98.88+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.12+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	hypre_BoomerAMGCoarsenPMIS	par_coarsen.c:2587	exec
○	hypre_BoomerAMGSetup	par_amg_setup.c:612	exec
○	hypre_PCGSetup	pcg.c:234	exec
○	main	amg.c:398	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	amg.c:253	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	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.34
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.13
Bottlenecks	P12, P13, P14,
Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.8
Source	par_coarsen.c:2528-2540
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	12.67
CQA cycles if no scalar integer	12.67
CQA cycles if FP arith vectorized	12.67
CQA cycles if fully vectorized	5.42
Front-end cycles	11.25
P0 cycles	8.50
P1 cycles	8.50
P2 cycles	5.92
P3 cycles	5.92
P4 cycles	5.83
P5 cycles	5.83
P6 cycles	5.75
P7 cycles	5.75
P8 cycles	0.00
P9 cycles	0.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	12.67
P13 cycles	12.67
P14 cycles	12.67
P15 cycles	4.00
P16 cycles	4.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
Nb loads	NA
Nb stores	8.00
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	24.00
Bytes prefetched	0.00
Bytes loaded	240.00
Bytes stored	64.00
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	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	44.44
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	27.78

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.34
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.13
Bottlenecks	P12, P13, P14,
Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.8
Source	par_coarsen.c:2528-2540
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	12.67
CQA cycles if no scalar integer	12.67
CQA cycles if FP arith vectorized	12.67
CQA cycles if fully vectorized	5.42
Front-end cycles	11.25
P0 cycles	8.50
P1 cycles	8.50
P2 cycles	5.92
P3 cycles	5.92
P4 cycles	5.83
P5 cycles	5.83
P6 cycles	5.75
P7 cycles	5.75
P8 cycles	0.00
P9 cycles	0.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	12.67
P13 cycles	12.67
P14 cycles	12.67
P15 cycles	4.00
P16 cycles	4.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	90.00
Nb loads	NA
Nb stores	8.00
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	24.00
Bytes prefetched	0.00
Bytes loaded	240.00
Bytes stored	64.00
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	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	44.44
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	27.78

Path /

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

Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.8
Source file and lines	par_coarsen.c:2528-2540
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2528-2540.

The related source loop is not unrolled or unrolled with no peel/tail loop.
Warnings:

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 256 paths individually, rerun with max-paths=256
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed 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 256 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

Vectorization

Your loop is not vectorized. Only 44% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 12.67 to 5.42 cycles (2.34x 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:
- recompile with fassociative-math (included in Ofast or ffast-math) to extend loop vectorization to FP reductions.
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 240 bytes. The binary loop is storing 64 bytes.

General properties

nb instructions	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	8.50	8.50	5.92	5.92	5.83	5.83	5.75	5.75	0.00	0.00	0.00	0.00	12.67	12.67	12.67	4.00	4.00
cycles	8.50	8.50	5.92	5.92	5.83	5.83	5.75	5.75	0.00	0.00	0.00	0.00	12.67	12.67	12.67	4.00	4.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	12.67

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 12.67 cycles. At this rate:

19% of peak load performance is reached (18.95 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (5.05 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 428f9c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
LDR X15, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
UBFM X16, X15, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X17, [X20, X16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X17, 429668 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x844>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X18, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
ADD X1, X1, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
UBFM X30, X18, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X2, [X20, X30]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X2, 429680 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x85c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X4, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR XZR, [X27, X30]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X7, X4, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X5, [X20, X7]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X5, 429698 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x874>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X1, #16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X7]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X9, X8, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X10, [X20, X9]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X10, 4296b0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x88c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [X1, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X9]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X12, X11, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X13, [X20, X12]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X13, 4296c8 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X14, [X1, #32]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X12]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X15, X14, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X16, [X20, X15]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X16, 4296e0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [X1, #40]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X15]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X18, X17, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X30, [X20, X18]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X30, 4296f8 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8d4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X2, [X1, #48]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X18]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X4, X2, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X7, [X20, X4]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X7, 429710 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8ec>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR XZR, [X27, X4]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X1, X1, #56	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
CMP X1, X6	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (50.0%)
B.NE 428f9c <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x178>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X18, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X1, X1, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
STR XZR, [X27, X16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X30, X18, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X2, [X20, X30]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X2, 428fc8 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X4, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X7, X4, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X5, [X20, X7]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X5, 428fdc <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X1, #16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X9, X8, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X10, [X20, X9]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X10, 428ff0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1cc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [X1, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X12, X11, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X13, [X20, X12]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X13, 429004 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X14, [X1, #32]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X15, X14, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X16, [X20, X15]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBNZ X16, 429018 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [X1, #40]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X18, X17, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X30, [X20, X18]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBNZ X30, 42902c <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x208>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X2, [X1, #48]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X4, X2, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X7, [X20, X4]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBNZ X7, 429040 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x21c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
B 429044 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x220>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.8
Source file and lines	par_coarsen.c:2528-2540
Module	exec

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 256 paths individually, rerun with max-paths=256
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

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

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 loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with fassociative-math (included in Ofast or ffast-math) to extend loop vectorization to FP reductions.
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 240 bytes. The binary loop is storing 64 bytes.

General properties

nb instructions	90
loop length	360
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

11.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	8.50	8.50	5.92	5.92	5.83	5.83	5.75	5.75	0.00	0.00	0.00	0.00	12.67	12.67	12.67	4.00	4.00
cycles	8.50	8.50	5.92	5.92	5.83	5.83	5.75	5.75	0.00	0.00	0.00	0.00	12.67	12.67	12.67	4.00	4.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	11.25
Overall L1	12.67

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 12.67 cycles. At this rate:

19% of peak load performance is reached (18.95 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (5.05 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 428f9c

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
LDR X15, [X1]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
UBFM X16, X15, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X17, [X20, X16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X17, 429668 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x844>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X18, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
ADD X1, X1, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
UBFM X30, X18, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X2, [X20, X30]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X2, 429680 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x85c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X4, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STR XZR, [X27, X30]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X7, X4, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X5, [X20, X7]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X5, 429698 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x874>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X1, #16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X7]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X9, X8, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X10, [X20, X9]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X10, 4296b0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x88c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [X1, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X9]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X12, X11, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X13, [X20, X12]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBZ X13, 4296c8 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X14, [X1, #32]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X12]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X15, X14, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X16, [X20, X15]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X16, 4296e0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [X1, #40]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X15]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X18, X17, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X30, [X20, X18]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X30, 4296f8 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8d4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X2, [X1, #48]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
STR XZR, [X27, X18]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X4, X2, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X7, [X20, X4]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X7, 429710 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x8ec>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR XZR, [X27, X4]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X1, X1, #56	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
CMP X1, X6	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (50.0%)
B.NE 428f9c <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x178>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X18, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X1, X1, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
STR XZR, [X27, X16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
UBFM X30, X18, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X2, [X20, X30]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X2, 428fc8 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1a4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X4, [X1, #8]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X7, X4, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X5, [X20, X7]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X5, 428fdc <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X1, #16]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X9, X8, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X10, [X20, X9]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X10, 428ff0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1cc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X11, [X1, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X12, X11, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X13, [X20, X12]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
CBNZ X13, 429004 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X14, [X1, #32]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X15, X14, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X16, [X20, X15]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBNZ X16, 429018 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1f4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X17, [X1, #40]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X18, X17, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X30, [X20, X18]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBNZ X30, 42902c <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x208>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X2, [X1, #48]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X4, X2, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR X7, [X20, X4]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBNZ X7, 429040 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x21c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X0, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
MOVZ W3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
B 429044 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x220>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

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

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