OV - exec - Loop 1843

	Loop Id: 1843	Module: exec	Source: par_strength.c:492-513	Coverage: 0.07%

0x5084e0 ADD	%R10,(%RSI)

0x5084e3 VMOVQ	%XMM2,%RCX

0x5084e8 ADD	(%RDI),%RCX

0x5084eb MOV	%RCX,(%RDI)

0x5084ee MOV	-0x8(%R8),%RAX

0x5084f2 MOV	(%R8),%R15

0x5084f5 MOV	(%RSI),%R14

0x5084f8 CMP	%R15,%RAX

0x5084fb JGE	508522

0x5084fd NOPL	(%RAX)

  (1845) 0x508500 MOV	(%RBX,%RAX,8),%RDX

  (1845) 0x508504 TEST	%RDX,%RDX

  (1845) 0x508507 JS	508b70

  (1845) 0x50850d MOV	%RDX,(%R9,%R14,8)

  (1845) 0x508511 MOV	(%R8),%R15

  (1845) 0x508514 INC	%RAX

  (1845) 0x508517 INC	%R14

  (1845) 0x50851a CMP	%R15,%RAX

  (1845) 0x50851d JL	508500

0x50851f MOV	(%RDI),%RCX

0x508522 MOV	-0x8(%R11),%RAX

0x508526 MOV	(%R11),%R14

0x508529 CMP	%R14,%RAX

0x50852c JGE	508560

0x50852e NOPW	%CS:(%RAX,%RAX,1)

0x508539 NOPL	(%RAX)

  (1844) 0x508540 MOV	(%R12,%RAX,8),%RDX

  (1844) 0x508544 TEST	%RDX,%RDX

  (1844) 0x508547 JS	508b50

  (1844) 0x50854d MOV	%RDX,(%R13,%RCX,8)

  (1844) 0x508552 MOV	(%R11),%R14

  (1844) 0x508555 INC	%RAX

  (1844) 0x508558 INC	%RCX

  (1844) 0x50855b CMP	%RAX,%R14

  (1844) 0x50855e JG	508540

0x508560 ADD	$0x8,%RSI

0x508564 ADD	$0x8,%RDI

0x508568 ADD	$0x8,%R8

0x50856c ADD	$0x8,%R11

0x508570 CMP	%RSI,0x78(%RSP)

0x508575 JNE	5084e0

  (1844) 0x508b50 INC	%RAX

  (1844) 0x508b53 CMP	%R14,%RAX

  (1844) 0x508b56 JL	508540

0x508b5c JMP	508560

  (1845) 0x508b70 INC	%RAX

  (1845) 0x508b73 CMP	%R15,%RAX

  (1845) 0x508b76 JL	508500

0x508b7c JMP	50851f

/home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 492 - 513

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

492:    for (i = start; i < stop; i++)

493:    {

494:       S_diag_i[i] += jS_diag;

495:       S_offd_i[i] += jS_offd;

496:

497:       jS = S_diag_i[i];

498:       for (jA = A_diag_i[i]; jA < A_diag_i[i+1]; jA++)

499:       {

500:          if (S_temp_diag_j[jA] > -1)

501:          {

502:             S_diag_j[jS]    = S_temp_diag_j[jA];

503:             jS++;

504:          }

505:       }

506:

507:       jS = S_offd_i[i];

508:       for (jA = A_offd_i[i]; jA < A_offd_i[i+1]; jA++)

509:       {

510:          if (S_temp_offd_j[jA] > -1)

511:          {

512:             S_offd_j[jS]    = S_temp_offd_j[jA];

513:             jS++;

Coverage (%)	Name	Source Location	Module
►94.81+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►3.46+	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
○	hypre_BoomerAMGCreateS	par_strength.c:246	exec
○	hypre_BoomerAMGSetup	par_amg_setup.c:581	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
►1.73+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		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	2.75
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	8.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	hypre_BoomerAMGCreateS._omp_fn.1
Source	par_strength.c:492-498,par_strength.c:507-508
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	2.75
CQA cycles if no scalar integer	1.00
CQA cycles if FP arith vectorized	2.75
CQA cycles if fully vectorized	0.34
Front-end cycles	2.75
P0 cycles	2.33
P1 cycles	2.33
P2 cycles	2.33
P3 cycles	2.33
P4 cycles	2.33
P5 cycles	2.33
P6 cycles	2.50
P7 cycles	2.50
P8 cycles	2.50
P9 cycles	2.50
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.50
P15 cycles	0.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	25.00
Nb uops	22.00
Nb loads	9.00
Nb stores	2.00
Nb stack references	1.00
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	72.00
Bytes stored	16.00
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	12.50
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	2.75
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	8.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	micro-operation queue,
Function	hypre_BoomerAMGCreateS._omp_fn.1
Source	par_strength.c:492-498,par_strength.c:507-508
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	2.75
CQA cycles if no scalar integer	1.00
CQA cycles if FP arith vectorized	2.75
CQA cycles if fully vectorized	0.34
Front-end cycles	2.75
P0 cycles	2.33
P1 cycles	2.33
P2 cycles	2.33
P3 cycles	2.33
P4 cycles	2.33
P5 cycles	2.33
P6 cycles	2.50
P7 cycles	2.50
P8 cycles	2.50
P9 cycles	2.50
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.50
P15 cycles	0.50
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	25.00
Nb uops	22.00
Nb loads	9.00
Nb stores	2.00
Nb stack references	1.00
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	72.00
Bytes stored	16.00
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	12.50
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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_BoomerAMGCreateS._omp_fn.1
Source file and lines	par_strength.c:492-513
Module	exec

The loop is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c:492-513.

Analyzed code is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c:492-498,507-508.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=9
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 9 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 2.75 to 1.00 cycles (2.75x 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. 8 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 2.75 to 0.34 cycles (8.00x 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 72 bytes. The binary loop is storing 16 bytes.

General properties

nb instructions	25
nb uops	22
loop length	102
used x86 registers	10
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	2.75 cycles
front end	2.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	2.33	2.33	2.33	2.33	2.33	2.33	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	0.50	0.50
cycles	2.33	2.33	2.33	2.33	2.33	2.33	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	0.50	0.50

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	2.75
Dispatch	2.50
Overall L1	2.75

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	12%
load	12%
store	12%
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 2.75 cycles. At this rate:

10% of peak load performance is reached (26.18 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.82 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 2.75 to 2.50 cycles (1.10x speedup).

ASM code

In the binary file, the address of the loop is: 5084e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P14	P15	Latency	Recip. throughput	Vectorization
ADD %R10,(%RSI)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVQ %XMM2,%RCX	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
ADD (%RDI),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV %RCX,(%RDI)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
MOV -0x8(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV (%R8),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
MOV (%RSI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
CMP %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 508522 <hypre_BoomerAMGCreateS._omp_fn.1+0x8e2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV (%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
MOV -0x8(%R11),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV (%R11),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
CMP %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 508560 <hypre_BoomerAMGCreateS._omp_fn.1+0x920>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x8,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x8,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x8,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x8,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RSI,0x78(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
JNE 5084e0 <hypre_BoomerAMGCreateS._omp_fn.1+0x8a0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
JMP 508560 <hypre_BoomerAMGCreateS._omp_fn.1+0x920>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
JMP 50851f <hypre_BoomerAMGCreateS._omp_fn.1+0x8df>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A

Function	hypre_BoomerAMGCreateS._omp_fn.1
Source file and lines	par_strength.c:492-513
Module	exec

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=9
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

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 2.75 to 1.00 cycles (2.75x 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. 8 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 2.75 to 0.34 cycles (8.00x 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 72 bytes. The binary loop is storing 16 bytes.

General properties

nb instructions	25
nb uops	22
loop length	102
used x86 registers	10
used mmx registers	0
used xmm registers	1
used ymm registers	0
used zmm registers	0
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	2.75 cycles
front end	2.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	2.33	2.33	2.33	2.33	2.33	2.33	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	0.50	0.50
cycles	2.33	2.33	2.33	2.33	2.33	2.33	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	0.50	0.50

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	2.75
Dispatch	2.50
Overall L1	2.75

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	12%
load	12%
store	12%
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 2.75 cycles. At this rate:

10% of peak load performance is reached (26.18 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.82 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 5084e0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P14	P15	Latency	Recip. throughput	Vectorization
ADD %R10,(%RSI)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.50	scal (12.5%)
VMOVQ %XMM2,%RCX	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
ADD (%RDI),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOV %RCX,(%RDI)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	4	0.50	scal (12.5%)
MOV -0x8(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV (%R8),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
MOV (%RSI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
CMP %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 508522 <hypre_BoomerAMGCreateS._omp_fn.1+0x8e2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV (%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
MOV -0x8(%R11),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	N/A
MOV (%R11),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	3	0.25	scal (12.5%)
CMP %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 508560 <hypre_BoomerAMGCreateS._omp_fn.1+0x920>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x8,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x8,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x8,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
ADD $0x8,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	1	0.17	N/A
CMP %RSI,0x78(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	1	0.25	N/A
JNE 5084e0 <hypre_BoomerAMGCreateS._omp_fn.1+0x8a0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50-1	N/A
JMP 508560 <hypre_BoomerAMGCreateS._omp_fn.1+0x920>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A
JMP 50851f <hypre_BoomerAMGCreateS._omp_fn.1+0x8df>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	1	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

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

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

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