OV - exec - Loop 296

	Loop Id: 296	Module: exec	Source: par_coarsen.c:2528-2540	Coverage: 0.07%

0x43d200 MOVQ	$0,(%R13,%R9,8)    [1]

0x43d209 ADD	$0x20,%R8

0x43d20d DEC	%RDI

0x43d210 JE	43d29d

0x43d216 MOV	-0x18(%R8),%R9    [3]

0x43d21a CMPQ	$0,(%R14,%R9,8)    [2]

0x43d21f JE	43d260

0x43d221 MOVQ	$0,(%R13,%R9,8)    [1]

0x43d22a MOV	-0x10(%R8),%R9    [3]

0x43d22e CMPQ	$0,(%R14,%R9,8)    [2]

0x43d233 JE	43d26e

0x43d235 MOVQ	$0,(%R13,%R9,8)    [1]

0x43d23e MOV	-0x8(%R8),%R9    [3]

0x43d242 CMPQ	$0,(%R14,%R9,8)    [2]

0x43d247 JE	43d27c

0x43d249 MOVQ	$0,(%R13,%R9,8)    [1]

0x43d252 MOV	(%R8),%R9    [3]

0x43d255 CMPQ	$0,(%R14,%R9,8)    [2]

0x43d25a JNE	43d200

0x43d25c JMP	43d28d

0x43d260 INC	%RDX

0x43d263 MOV	-0x10(%R8),%R9    [3]

0x43d267 CMPQ	$0,(%R14,%R9,8)    [2]

0x43d26c JNE	43d235

0x43d26e INC	%RDX

0x43d271 MOV	-0x8(%R8),%R9    [3]

0x43d275 CMPQ	$0,(%R14,%R9,8)    [2]

0x43d27a JNE	43d249

0x43d27c INC	%RDX

0x43d27f MOV	(%R8),%R9    [3]

0x43d282 CMPQ	$0,(%R14,%R9,8)    [2]

0x43d287 JNE	43d200

0x43d28d INC	%RDX

0x43d290 ADD	$0x20,%R8

0x43d294 DEC	%RDI

0x43d297 JNE	43d216

/home/eoseret/qaas_runs_ZEN5/173-989-6379/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
►95.98+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.75+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	hypre_BoomerAMGCoarsenPMIS	par_coarsen.c:2516	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		exec
►1.05+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.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	11.52
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.03
Bottlenecks	P6, P7, P8, P9,
Function	hypre_BoomerAMGCoarsenPMIS.extracted
Source	par_coarsen.c:2528-2540
Source loop unroll info	unrolled by 7
Source loop unroll confidence level	max
Unroll/vectorization loop type	main
Unroll factor	7
CQA cycles	4.50
CQA cycles if no scalar integer	4.50
CQA cycles if FP arith vectorized	4.50
CQA cycles if fully vectorized	0.39
Front-end cycles	4.38
P0 cycles	4.00
P1 cycles	4.00
P2 cycles	4.00
P3 cycles	4.00
P4 cycles	4.00
P5 cycles	4.00
P6 cycles	4.50
P7 cycles	4.50
P8 cycles	4.50
P9 cycles	4.50
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
P15 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	36.00
Nb uops	35.00
Nb loads	14.00
Nb stores	4.00
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	32.00
Bytes prefetched	0.00
Bytes loaded	112.00
Bytes stored	32.00
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	10.83
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	6.25
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	11.52
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.03
Bottlenecks	P6, P7, P8, P9,
Function	hypre_BoomerAMGCoarsenPMIS.extracted
Source	par_coarsen.c:2528-2540
Source loop unroll info	unrolled by 7
Source loop unroll confidence level	max
Unroll/vectorization loop type	main
Unroll factor	7
CQA cycles	4.50
CQA cycles if no scalar integer	4.50
CQA cycles if FP arith vectorized	4.50
CQA cycles if fully vectorized	0.39
Front-end cycles	4.38
P0 cycles	4.00
P1 cycles	4.00
P2 cycles	4.00
P3 cycles	4.00
P4 cycles	4.00
P5 cycles	4.00
P6 cycles	4.50
P7 cycles	4.50
P8 cycles	4.50
P9 cycles	4.50
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
P15 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	36.00
Nb uops	35.00
Nb loads	14.00
Nb stores	4.00
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	32.00
Bytes prefetched	0.00
Bytes loaded	112.00
Bytes stored	32.00
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	10.83
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	6.25
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	12.50

Path /

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

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

The loop is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c:2528-2540.

It is main loop of related source loop which is unrolled by 7 (including vectorization).
Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=16
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 16 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 10% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your loop, you can lower the cost of an iteration from 4.50 to 0.39 cycles (11.52x speedup).

Details

All SSE/AVX 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)

Execution units bottlenecks

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

Workaround

Read less array elements
Write less array elements
Provide more information to your compiler:
- hardcode the bounds of the corresponding 'for' loop
- use the 'restrict' C99 keyword

No data for this section

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This loop is probably writing/copying data or processing integer elements.

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 112 bytes. The binary loop is storing 32 bytes.

General properties

nb instructions	36
nb uops	35
loop length	155
used x86 registers	6
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	4.38 cycles
front end	4.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.00	4.00	4.00	4.00	4.00	4.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	4.00	4.00	4.00	4.00	4.00	4.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	4.38
Dispatch	4.50
Overall L1	4.50

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%

Vector efficiency ratios

all	10%
load	12%
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.50 cycles. At this rate:

9% of peak load performance is reached (24.89 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.11 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 43d216

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
ADD $0x20,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
DEC %RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JE 43d29d <hypre_BoomerAMGCoarsenPMIS.extracted+0x12d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x18(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 43d260 <hypre_BoomerAMGCoarsenPMIS.extracted+0xf0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV -0x10(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 43d26e <hypre_BoomerAMGCoarsenPMIS.extracted+0xfe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV -0x8(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 43d27c <hypre_BoomerAMGCoarsenPMIS.extracted+0x10c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d200 <hypre_BoomerAMGCoarsenPMIS.extracted+0x90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
JMP 43d28d <hypre_BoomerAMGCoarsenPMIS.extracted+0x11d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x10(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d235 <hypre_BoomerAMGCoarsenPMIS.extracted+0xc5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x8(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d249 <hypre_BoomerAMGCoarsenPMIS.extracted+0xd9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d200 <hypre_BoomerAMGCoarsenPMIS.extracted+0x90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
ADD $0x20,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
DEC %RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JNE 43d216 <hypre_BoomerAMGCoarsenPMIS.extracted+0xa6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A

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

Ignoring paths for analysis
Too many paths. Rerun with max-paths=16
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 SSE/AVX 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)

Execution units bottlenecks

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

Workaround

Read less array elements
Write less array elements
Provide more information to your compiler:
- hardcode the bounds of the corresponding 'for' loop
- use the 'restrict' C99 keyword

No data for this section

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This loop is probably writing/copying data or processing integer elements.

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 112 bytes. The binary loop is storing 32 bytes.

General properties

nb instructions	36
nb uops	35
loop length	155
used x86 registers	6
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	4.38 cycles
front end	4.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	4.00	4.00	4.00	4.00	4.00	4.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	4.00	4.00	4.00	4.00	4.00	4.00	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	4.38
Dispatch	4.50
Overall L1	4.50

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%

Vector efficiency ratios

all	10%
load	12%
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.50 cycles. At this rate:

9% of peak load performance is reached (24.89 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.11 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 43d216

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
ADD $0x20,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
DEC %RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JE 43d29d <hypre_BoomerAMGCoarsenPMIS.extracted+0x12d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x18(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 43d260 <hypre_BoomerAMGCoarsenPMIS.extracted+0xf0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV -0x10(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 43d26e <hypre_BoomerAMGCoarsenPMIS.extracted+0xfe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV -0x8(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 43d27c <hypre_BoomerAMGCoarsenPMIS.extracted+0x10c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%R13,%R9,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d200 <hypre_BoomerAMGCoarsenPMIS.extracted+0x90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
JMP 43d28d <hypre_BoomerAMGCoarsenPMIS.extracted+0x11d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x10(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d235 <hypre_BoomerAMGCoarsenPMIS.extracted+0xc5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x8(%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d249 <hypre_BoomerAMGCoarsenPMIS.extracted+0xd9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV (%R8),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R14,%R9,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JNE 43d200 <hypre_BoomerAMGCoarsenPMIS.extracted+0x90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
ADD $0x20,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
DEC %RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JNE 43d216 <hypre_BoomerAMGCoarsenPMIS.extracted+0xa6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code