OV - exec - Loop 170

0x427db0 ADD	X3, X3, #8

0x427db4 CMP	X16, X3

0x427db8 B.EQ	427e94

0x427dbc LDR	X12, [X3]

0x427dc0 UBFM	X17, X12, #61, #60

0x427dc4 LDR	D30, [X2, X17]

0x427dc8 FCMPE	D30, D31

0x427dcc B.LS	427db0

0x427dd0 ADD	X18, X17, #8

0x427dd4 LDR	X20, [X14, X17]

0x427dd8 ADD	X30, X14, X18

0x427ddc LDR	X21, [X14, X18]

0x427de0 CMP	X20, X21

0x427de4 B.LT	427e04

0x427de8 B	427e34

  (172) 0x427dec B.GE	427df8

  (172) 0x427df0 STR	XZR, [X11, X17]

  (172) 0x427df4 LDR	X21, [X30]

  (172) 0x427df8 ADD	X20, X20, #1

  (172) 0x427dfc CMP	X20, X21

  (172) 0x427e00 B.GE	427e34

  (172) 0x427e04 LDR	X19, [X9, X20,LSL #3]

  (172) 0x427e08 UBFM	X0, X19, #61, #60

  (172) 0x427e0c LDR	D0, [X2, X0]

  (172) 0x427e10 FCMPE	D0, D31

  (172) 0x427e14 B.LS	427df8

  (172) 0x427e18 FCMPE	D30, D0

  (172) 0x427e1c B.LS	427dec

  (172) 0x427e20 STR	XZR, [X11, X0]

  (172) 0x427e24 ADD	X20, X20, #1

  (172) 0x427e28 LDR	X21, [X30]

  (172) 0x427e2c CMP	X20, X21

  (172) 0x427e30 B.LT	427e04

0x427e34 LDR	X6, [X13, X17]

0x427e38 ADD	X10, X13, X18

0x427e3c LDR	X5, [X13, X18]

0x427e40 CMP	X6, X5

0x427e44 B.LT	427e6c

0x427e48 B	427db0

  (171) 0x427e4c B.GE	427e60

  (171) 0x427e50 STR	XZR, [X11, X17]

  (171) 0x427e54 LDR	X5, [X10]

  (171) 0x427e58 HINT	#0

  (171) 0x427e5c HINT	#0

  (171) 0x427e60 ADD	X6, X6, #1

  (171) 0x427e64 CMP	X6, X5

  (171) 0x427e68 B.GE	427db0

  (171) 0x427e6c LDR	X1, [X8, X6,LSL #3]

  (171) 0x427e70 ADD	X4, X7, X1

  (171) 0x427e74 LDR	D29, [X2, X4,LSL #3]

  (171) 0x427e78 FCMPE	D29, D31

  (171) 0x427e7c B.LS	427e60

  (171) 0x427e80 FCMPE	D30, D29

  (171) 0x427e84 B.LS	427e4c

  (171) 0x427e88 STR	XZR, [X15, X1,LSL #3]

  (171) 0x427e8c LDR	X5, [X10]

  (171) 0x427e90 B	427e60

/home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c: 2354 - 2381

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

2354: #pragma omp parallel for private(ig, i, jS, j, jj) HYPRE_SMP_SCHEDULE

2355: #endif

2356:         for (ig = 0; ig < graph_size; ig++)

2357:         {

2358:            i = graph_array[ig];

2359:            if (measure_array[i] > 1)

2360:            {

2361:               for (jS = S_diag_i[i]; jS < S_diag_i[i+1]; jS++)

2362:               {

2363:                  j = S_diag_j[jS];

2364:                  if (measure_array[j] > 1)

2365:                  {

2366:                     if (measure_array[i] > measure_array[j])

2367:                        CF_marker[j] = 0;

2368:                     else if (measure_array[j] > measure_array[i])

2369:                        CF_marker[i] = 0;

2370:                  }

2371:               } /* for each local neighbor j of i */

2372:               for (jS = S_offd_i[i]; jS < S_offd_i[i+1]; jS++)

2373:               {

2374:                  jj = S_offd_j[jS];

2375:                  j = num_variables+jj;

2376:                  if (measure_array[j] > 1)

2377:                  {

2378:                     if (measure_array[i] > measure_array[j])

2379:                        CF_marker_offd[jj] = 0;

2380:                     else if (measure_array[j] > measure_array[i])

2381:                        CF_marker[i] = 0;

Coverage (%)	Name	Source Location	Module
►100.00+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

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	3.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.14
Bottlenecks	P0, P1,
Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.6
Source	par_coarsen.c:2354-2354,par_coarsen.c:2359-2361,par_coarsen.c:2372-2372
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	3.00
CQA cycles if no scalar integer	1.00
CQA cycles if FP arith vectorized	3.00
CQA cycles if fully vectorized	1.50
Front-end cycles	2.63
P0 cycles	3.00
P1 cycles	3.00
P2 cycles	1.42
P3 cycles	1.42
P4 cycles	1.33
P5 cycles	1.33
P6 cycles	1.25
P7 cycles	1.25
P8 cycles	1.00
P9 cycles	0.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	2.00
P13 cycles	2.00
P14 cycles	2.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	21.00
Nb uops	21.00
Nb loads	NA
Nb stores	0.00
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	16.00
Bytes prefetched	0.00
Bytes loaded	48.00
Bytes stored	0.00
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	NA
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	50.00
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	50.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	50.00

Metric	Value
CQA speedup if no scalar integer	3.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.14
Bottlenecks	P0, P1,
Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.6
Source	par_coarsen.c:2354-2354,par_coarsen.c:2359-2361,par_coarsen.c:2372-2372
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	3.00
CQA cycles if no scalar integer	1.00
CQA cycles if FP arith vectorized	3.00
CQA cycles if fully vectorized	1.50
Front-end cycles	2.63
P0 cycles	3.00
P1 cycles	3.00
P2 cycles	1.42
P3 cycles	1.42
P4 cycles	1.33
P5 cycles	1.33
P6 cycles	1.25
P7 cycles	1.25
P8 cycles	1.00
P9 cycles	0.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	2.00
P13 cycles	2.00
P14 cycles	2.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	21.00
Nb uops	21.00
Nb loads	NA
Nb stores	0.00
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	16.00
Bytes prefetched	0.00
Bytes loaded	48.00
Bytes stored	0.00
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	NA
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	50.00
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	50.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	50.00

Path /

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

Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.6
Source file and lines	par_coarsen.c:2354-2381
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:2354-2381.

Analyzed code is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2354,2359-2361,2372.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=26
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 26 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 3.00 to 1.00 cycles (3.00x 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. 2 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 3.00 to 1.50 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 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 48 bytes.

General properties

nb instructions	21
loop length	84
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	3.00	3.00	1.42	1.42	1.33	1.33	1.25	1.25	1.00	0.00	0.00	0.00	2.00	2.00	2.00	0.00	0.00
cycles	3.00	3.00	1.42	1.42	1.33	1.33	1.25	1.25	1.00	0.00	0.00	0.00	2.00	2.00	2.00	0.00	0.00

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

NA

Cycles summary

Front-end	2.63
Overall L1	3.00

Vectorization ratios

INT

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

FP

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
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%

INT+FP

all	0%
load	0%
store	NA (no store vectorizable/vectorized instructions)
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 3.00 cycles. At this rate:

16% of peak load performance is reached (16.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 427dbc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P12	P13	P14	Latency	Recip. throughput	Vectorization
ADD X3, X3, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP X16, X3	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	scal (50.0%)
B.EQ 427e94 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x154>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X12, [X3]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (50.0%)
UBFM X17, X12, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LDR D30, [X2, X17]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FCMPE D30, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	2	1	scal (50.0%)
B.LS 427db0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x70>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X18, X17, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LDR X20, [X14, X17]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (50.0%)
ADD X30, X14, X18	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (50.0%)
LDR X21, [X14, X18]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (50.0%)
CMP X20, X21	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	scal (50.0%)
B.LT 427e04 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0xc4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 427e34 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0xf4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X6, [X13, X17]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X10, X13, X18	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (50.0%)
LDR X5, [X13, X18]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP X6, X5	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	N/A
B.LT 427e6c <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x12c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 427db0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x70>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	hypre_BoomerAMGCoarsenPMIS._omp_fn.6
Source file and lines	par_coarsen.c:2354-2381
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:2354-2381.

Analyzed code is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2354,2359-2361,2372.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=26
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 26 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 3.00 to 1.00 cycles (3.00x 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. 2 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 3.00 to 1.50 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 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 48 bytes.

General properties

nb instructions	21
loop length	84
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	3.00	3.00	1.42	1.42	1.33	1.33	1.25	1.25	1.00	0.00	0.00	0.00	2.00	2.00	2.00	0.00	0.00
cycles	3.00	3.00	1.42	1.42	1.33	1.33	1.25	1.25	1.00	0.00	0.00	0.00	2.00	2.00	2.00	0.00	0.00

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

NA

Cycles summary

Front-end	2.63
Overall L1	3.00

Vectorization ratios

INT

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

FP

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
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%

INT+FP

all	0%
load	0%
store	NA (no store vectorizable/vectorized instructions)
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 3.00 cycles. At this rate:

16% of peak load performance is reached (16.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 427dbc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P12	P13	P14	Latency	Recip. throughput	Vectorization
ADD X3, X3, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP X16, X3	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	scal (50.0%)
B.EQ 427e94 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x154>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X12, [X3]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (50.0%)
UBFM X17, X12, #61, #60	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LDR D30, [X2, X17]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FCMPE D30, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	2	1	scal (50.0%)
B.LS 427db0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x70>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X18, X17, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LDR X20, [X14, X17]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (50.0%)
ADD X30, X14, X18	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (50.0%)
LDR X21, [X14, X18]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	scal (50.0%)
CMP X20, X21	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	scal (50.0%)
B.LT 427e04 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0xc4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 427e34 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0xf4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X6, [X13, X17]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X10, X13, X18	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (50.0%)
LDR X5, [X13, X18]	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP X6, X5	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	N/A
B.LT 427e6c <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x12c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 427db0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.6+0x70>	1	0.50	0.50	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

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