OV - exec - Loop 711

0x434908 LDR	X10, [X13, X2,LSL #3]

0x43490c ADD	X3, X3, #1

0x434910 CMP	X3, X10

0x434914 B.GE	4349e0

0x434918 LDR	X10, [X14, X3,LSL #3]

0x43491c LDR	X25, [X21]

0x434920 LDR	X20, [X15, X10,LSL #3]

0x434924 SUB	X25, X25, #1

0x434928 CMP	X20, X25

0x43492c B.NE	434908

0x434930 ADD	X26, X10, #1

0x434934 LDR	X20, [X4, X26,LSL #3]

0x434938 CMP	X20, #1

0x43493c B.LT	434988

0x434940 LDR	X25, [X11, X10,LSL #3]

0x434944 ADD	X30, X20, X25

0x434948 B	434958

  (713) 0x43494c ADD	X25, X25, #1

  (713) 0x434950 CMP	X25, X30

  (713) 0x434954 B.GE	434988

  (713) 0x434958 LDR	X20, [X21]

  (713) 0x43495c LDR	X20, [X5, X20,LSL #3]

  (713) 0x434960 LDR	X28, [X20, X25,LSL #3]

  (713) 0x434964 LDR	X20, [X22, X28,LSL #3]

  (713) 0x434968 CMP	X20, X1

  (713) 0x43496c B.EQ	43494c

  (713) 0x434970 LDR	X20, [X4, X2,LSL #3]

  (713) 0x434974 ADD	X8, X8, #1

  (713) 0x434978 ADD	X20, X20, #1

  (713) 0x43497c STR	X20, [X4, X2,LSL #3]

  (713) 0x434980 STR	X1, [X22, X28,LSL #3]

  (713) 0x434984 B	43494c

0x434988 LDR	X20, [X6, X26,LSL #3]

0x43498c CMP	X20, #1

0x434990 B.LT	434908

0x434994 LDR	X10, [X12, X10,LSL #3]

0x434998 ADD	X25, X20, X10

0x43499c B	4349ac

  (712) 0x4349a0 ADD	X10, X10, #1

  (712) 0x4349a4 CMP	X10, X25

  (712) 0x4349a8 B.GE	434908

  (712) 0x4349ac LDR	X20, [X21]

  (712) 0x4349b0 LDR	X20, [X7, X20,LSL #3]

  (712) 0x4349b4 LDR	X26, [X20, X10,LSL #3]

  (712) 0x4349b8 LDR	X20, [X23, X26,LSL #3]

  (712) 0x4349bc CMP	X20, X1

  (712) 0x4349c0 B.EQ	4349a0

  (712) 0x4349c4 LDR	X20, [X6, X2,LSL #3]

  (712) 0x4349c8 ADD	X9, X9, #1

  (712) 0x4349cc ADD	X20, X20, #1

  (712) 0x4349d0 STR	X20, [X6, X2,LSL #3]

  (712) 0x4349d4 STR	X1, [X23, X26,LSL #3]

  (712) 0x4349d8 B	4349a0

/home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 944 - 970

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

944:              for (j=S_diag_i[i1]; j < S_diag_i[i1+1]; j++)

945:              {

946:                 j1 = S_diag_j[j];

947:                 if (assigned[j1] == pass-1)

948:                 {

949:                    j_start = P_diag_start[j1];

950:                    j_end = j_start+P_diag_i[j1+1];

951:                    for (k=j_start; k < j_end; k++)

952:                    {

953:                       k1 = P_diag_pass[pass-1][k];

954:                       if (P_marker[k1] != i1)

955:                       {

956:                          cnt_nz++;

957:                          P_diag_i[i1+1]++;

958:                          P_marker[k1] = i1;

959:                       }

960:                    }

961:                    j_start = P_offd_start[j1];

962:                    j_end = j_start+P_offd_i[j1+1];

963:                    for (k=j_start; k < j_end; k++)

964:                    {

965:                       k1 = P_offd_pass[pass-1][k];

966:                       if (P_marker_offd[k1] != i1)

967:                       {

968:                          cnt_nz_offd++;

969:                          P_offd_i[i1+1]++;

970:                          P_marker_offd[k1] = i1;

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

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	2.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.04
Bottlenecks	P0, P1,
Function	hypre_BoomerAMGBuildMultipass.omp_outlined.10
Source	par_multi_interp.c:944-947,par_multi_interp.c:950-951,par_multi_interp.c:962-963
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	3.00
CQA cycles if FP arith vectorized	3.00
CQA cycles if fully vectorized	1.50
Front-end cycles	2.88
P0 cycles	3.00
P1 cycles	3.00
P2 cycles	1.50
P3 cycles	1.50
P4 cycles	1.50
P5 cycles	1.50
P6 cycles	1.50
P7 cycles	1.50
P8 cycles	0.00
P9 cycles	0.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	2.67
P13 cycles	2.67
P14 cycles	2.67
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	23.00
Nb uops	23.00
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	21.33
Bytes prefetched	0.00
Bytes loaded	64.00
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	NA
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	NA
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	1.00
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	1.04
Bottlenecks	P0, P1,
Function	hypre_BoomerAMGBuildMultipass.omp_outlined.10
Source	par_multi_interp.c:944-947,par_multi_interp.c:950-951,par_multi_interp.c:962-963
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	3.00
CQA cycles if FP arith vectorized	3.00
CQA cycles if fully vectorized	1.50
Front-end cycles	2.88
P0 cycles	3.00
P1 cycles	3.00
P2 cycles	1.50
P3 cycles	1.50
P4 cycles	1.50
P5 cycles	1.50
P6 cycles	1.50
P7 cycles	1.50
P8 cycles	0.00
P9 cycles	0.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	2.67
P13 cycles	2.67
P14 cycles	2.67
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	23.00
Nb uops	23.00
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	21.33
Bytes prefetched	0.00
Bytes loaded	64.00
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	NA
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	NA
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_BoomerAMGBuildMultipass.omp_outlined.10
Source file and lines	par_multi_interp.c:944-970
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:944-970.

Analyzed code is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:944-947,950-951,962-963.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=10
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 10 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. 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:
- recompile with ffast-math (included in Ofast) 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 64 bytes.

General properties

nb instructions	23
loop length	92
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.88 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	1.50	1.50	1.50	1.50	1.50	1.50	0.00	0.00	0.00	0.00	2.67	2.67	2.67	0.00	0.00
cycles	3.00	3.00	1.50	1.50	1.50	1.50	1.50	1.50	0.00	0.00	0.00	0.00	2.67	2.67	2.67	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	2.88
Overall L1	3.00

Vectorization ratios

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	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:

22% of peak load performance is reached (21.33 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 434918

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDR X10, [X13, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X3, X3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
CMP X3, X10	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.GE 4349e0 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x390>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [X14, X3,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
LDR X25, [X21]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
LDR X20, [X15, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
SUB X25, X25, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
CMP X20, X25	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.NE 434908 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X26, X10, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
LDR X20, [X4, X26,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP X20, #1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.LT 434988 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X25, [X11, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X30, X20, X25	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	scal (50.0%)
B 434958 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X20, [X6, X26,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP X20, #1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.LT 434908 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X25, X20, X10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
B 4349ac <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x35c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	hypre_BoomerAMGBuildMultipass.omp_outlined.10
Source file and lines	par_multi_interp.c:944-970
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:944-970.

Analyzed code is defined in /home/hbollore/qaas/qaas-runs/174-161-6712/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:944-947,950-951,962-963.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=10
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 10 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. 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:
- recompile with ffast-math (included in Ofast) 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 64 bytes.

General properties

nb instructions	23
loop length	92
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.88 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	1.50	1.50	1.50	1.50	1.50	1.50	0.00	0.00	0.00	0.00	2.67	2.67	2.67	0.00	0.00
cycles	3.00	3.00	1.50	1.50	1.50	1.50	1.50	1.50	0.00	0.00	0.00	0.00	2.67	2.67	2.67	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	2.88
Overall L1	3.00

Vectorization ratios

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	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:

22% of peak load performance is reached (21.33 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 434918

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDR X10, [X13, X2,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X3, X3, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
CMP X3, X10	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.GE 4349e0 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x390>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [X14, X3,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
LDR X25, [X21]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
LDR X20, [X15, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
SUB X25, X25, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
CMP X20, X25	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.NE 434908 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X26, X10, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
LDR X20, [X4, X26,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP X20, #1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.LT 434988 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X25, [X11, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X30, X20, X25	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	scal (50.0%)
B 434958 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x308>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X20, [X6, X26,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
CMP X20, #1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	1	0.33	scal (50.0%)
B.LT 434908 <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X10, [X12, X10,LSL #3]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	4	0.33	N/A
ADD X25, X20, X10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	1	0.17	N/A
B 4349ac <hypre_BoomerAMGBuildMultipass.omp_outlined.10+0x35c>	1	0.50	0.50	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