OV - exec - Loop 112

	Loop Id: 112	Module: exec	Source: par_coarsen.c:2528-2540	Coverage: 0.07%

0x4304ea MOV	(%RAX),%RDX    [1]

0x4304ed CMPQ	$0,(%R12,%RDX,8)    [2]

0x4304f2 LEA	(,%RDX,8),%R9

0x4304fa JNE	430c70

0x430500 INC	%RSI

0x430503 MOV	$0x1,%EDI

0x430508 LEA	0x8(%RAX),%RDX

0x43050c MOV	0x8(%RAX),%RAX    [1]

0x430510 CMPQ	$0,(%R12,%RAX,8)    [2]

0x430515 LEA	(,%RAX,8),%R9

0x43051d JE	430d60

0x430523 MOVQ	$0,(%RCX,%R9,1)    [3]

0x43052b MOV	0x8(%RDX),%RAX    [4]

0x43052f CMPQ	$0,(%R12,%RAX,8)    [2]

0x430534 LEA	(,%RAX,8),%R9

0x43053c JE	430d50

0x430542 MOVQ	$0,(%RCX,%R9,1)    [3]

0x43054a MOV	0x10(%RDX),%RAX    [4]

0x43054e CMPQ	$0,(%R12,%RAX,8)    [2]

0x430553 LEA	(,%RAX,8),%R9

0x43055b JE	430da0

0x430561 MOVQ	$0,(%RCX,%R9,1)    [3]

0x430569 MOV	0x18(%RDX),%RAX    [4]

0x43056d CMPQ	$0,(%R12,%RAX,8)    [2]

0x430572 LEA	(,%RAX,8),%R9

0x43057a JE	430d90

0x430580 MOVQ	$0,(%RCX,%R9,1)    [3]

0x430588 MOV	0x20(%RDX),%RAX    [4]

0x43058c CMPQ	$0,(%R12,%RAX,8)    [2]

0x430591 LEA	(,%RAX,8),%R9

0x430599 JE	430d80

0x43059f MOVQ	$0,(%RCX,%R9,1)    [3]

0x4305a7 MOV	0x28(%RDX),%RAX    [4]

0x4305ab CMPQ	$0,(%R12,%RAX,8)    [2]

0x4305b0 LEA	(,%RAX,8),%R9

0x4305b8 JE	430d70

0x4305be MOVQ	$0,(%RCX,%R9,1)    [3]

0x4305c6 MOV	0x30(%RDX),%RAX    [4]

0x4305ca CMPQ	$0,(%R12,%RAX,8)    [2]

0x4305cf LEA	(,%RAX,8),%R9

0x4305d7 JE	430d40

0x4305dd MOVQ	$0,(%RCX,%R9,1)    [3]

0x4305e5 LEA	0x38(%RDX),%RAX

0x4305e9 CMP	%R11,%RAX

0x4305ec JNE	4304ea

0x430c70 MOVQ	$0,(%RCX,%R9,1)    [3]

0x430c78 JMP	430508

0x430d40 INC	%RSI

0x430d43 MOV	$0x1,%EDI

0x430d48 JMP	4305e5

0x430d50 INC	%RSI

0x430d53 MOV	$0x1,%EDI

0x430d58 JMP	43054a

0x430d60 INC	%RSI

0x430d63 MOV	$0x1,%EDI

0x430d68 JMP	43052b

0x430d70 INC	%RSI

0x430d73 MOV	$0x1,%EDI

0x430d78 JMP	4305c6

0x430d80 INC	%RSI

0x430d83 MOV	$0x1,%EDI

0x430d88 JMP	4305a7

0x430d90 INC	%RSI

0x430d93 MOV	$0x1,%EDI

0x430d98 JMP	430588

0x430da0 INC	%RSI

0x430da3 MOV	$0x1,%EDI

0x430da8 JMP	430569

/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
►97.04+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.63+	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
○	hypre_BoomerAMGCoarsenPMIS	par_coarsen.c:2585	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	13.64
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.02
Bottlenecks	P0, P1, P2, P3, P4, P5,
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	8.67
CQA cycles if no scalar integer	8.67
CQA cycles if FP arith vectorized	8.67
CQA cycles if fully vectorized	0.64
Front-end cycles	8.50
P0 cycles	8.67
P1 cycles	8.67
P2 cycles	8.67
P3 cycles	8.67
P4 cycles	8.67
P5 cycles	8.67
P6 cycles	6.00
P7 cycles	6.00
P8 cycles	6.00
P9 cycles	6.00
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	68.00
Nb uops	68.00
Nb loads	16.00
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	22.15
Bytes prefetched	0.00
Bytes loaded	128.00
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	8.50
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	6.25
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	9.56

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	13.64
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.02
Bottlenecks	P0, P1, P2, P3, P4, P5,
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	8.67
CQA cycles if no scalar integer	8.67
CQA cycles if FP arith vectorized	8.67
CQA cycles if fully vectorized	0.64
Front-end cycles	8.50
P0 cycles	8.67
P1 cycles	8.67
P2 cycles	8.67
P3 cycles	8.67
P4 cycles	8.67
P5 cycles	8.67
P6 cycles	6.00
P7 cycles	6.00
P8 cycles	6.00
P9 cycles	6.00
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	68.00
Nb uops	68.00
Nb loads	16.00
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	22.15
Bytes prefetched	0.00
Bytes loaded	128.00
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	8.50
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	6.25
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	9.56

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/eoseret/qaas_runs_ZEN5/173-989-6379/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 8% 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 8.67 to 0.64 cycles (13.64x 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
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

Found no such bottlenecks but see expert reports for more complex bottlenecks.

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 128 bytes. The binary loop is storing 64 bytes.

Unroll opportunity

Loop is potentially data access bound.

Workaround

Unroll your loop if trip count is significantly higher than target unroll factor and if some data references are common to consecutive iterations. This can be done manually. Or by recompiling with -funroll-loops and/or -floop-unroll-and-jam. Or with the unroll (resp. unroll_and_jam) directive on top of the inner (resp. surrounding) loop. You can enforce an unroll factor: #pragma GCC unroll N

General properties

nb instructions	68
nb uops	68
loop length	368
used x86 registers	8
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	8.50 cycles
front end	8.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.67	8.67	8.67	8.67	8.67	8.67	6.00	6.00	6.00	6.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	8.67	8.67	8.67	8.67	8.67	8.67	6.00	6.00	6.00	6.00	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	8.50
Dispatch	8.67
Overall L1	8.67

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%

Vector efficiency ratios

all	8%
load	12%
store	6%
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	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 8.67 cycles. At this rate:

5% of peak load performance is reached (14.77 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.38 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: 4304ea

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV (%RAX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RDX,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%)
LEA (,%RDX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JNE 430c70 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x980>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
LEA 0x8(%RAX),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d60 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa70>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x8(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d50 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa60>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x10(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430da0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xab0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x18(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d90 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xaa0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x20(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d80 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x28(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d70 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa80>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x30(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d40 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa50>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
LEA 0x38(%RDX),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CMP %R11,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JNE 4304ea <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1fa>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
JMP 430508 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x218>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 4305e5 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x2f5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 43054a <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x25a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 43052b <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x23b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 4305c6 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x2d6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 4305a7 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x2b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 430588 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x298>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 430569 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x279>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	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 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
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

Found no such bottlenecks but see expert reports for more complex bottlenecks.

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 128 bytes. The binary loop is storing 64 bytes.

Unroll opportunity

Loop is potentially data access bound.

Workaround

General properties

nb instructions	68
nb uops	68
loop length	368
used x86 registers	8
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	8.50 cycles
front end	8.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.67	8.67	8.67	8.67	8.67	8.67	6.00	6.00	6.00	6.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	8.67	8.67	8.67	8.67	8.67	8.67	6.00	6.00	6.00	6.00	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	8.50
Dispatch	8.67
Overall L1	8.67

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%

Vector efficiency ratios

all	8%
load	12%
store	6%
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	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 8.67 cycles. At this rate:

5% of peak load performance is reached (14.77 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.38 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: 4304ea

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV (%RAX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RDX,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%)
LEA (,%RDX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JNE 430c70 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x980>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
LEA 0x8(%RAX),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d60 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa70>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x8(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d50 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa60>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x10(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430da0 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xab0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x18(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d90 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xaa0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x20(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d80 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa90>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x28(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d70 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa80>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV 0x30(%RDX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMPQ $0,(%R12,%RAX,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%)
LEA (,%RAX,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
JE 430d40 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0xa50>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
LEA 0x38(%RDX),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CMP %R11,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JNE 4304ea <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x1fa>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOVQ $0,(%RCX,%R9,1)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
JMP 430508 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x218>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 4305e5 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x2f5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 43054a <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x25a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 43052b <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x23b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 4305c6 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x2d6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 4305a7 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x2b7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 430588 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x298>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
INC %RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x1,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JMP 430569 <hypre_BoomerAMGCoarsenPMIS._omp_fn.8+0x279>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

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

Unroll opportunity

Workaround

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

Type of elements and instruction set

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

Unroll opportunity

Workaround

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code