OV - exec - Loop 1034

	Loop Id: 1034	Module: exec	Source: par_multi_interp.c:550-571 [...]	Coverage: 0.03%

0x26f710 MOV	(%RAX,%R15,8),%RDI

0x26f714 LEA	0x1(%R10),%R14

0x26f718 MOV	%R14,-0x30(%RBP)

0x26f71c MOV	%RDI,(%RAX,%R10,8)

0x26f720 MOV	%R11,(%RAX,%R15,8)

0x26f724 INC	%R15

0x26f727 MOV	-0x38(%RBP),%RDI

0x26f72b MOV	%RDI,(%RSI,%R11,8)

0x26f72f MOV	-0x30(%RBP),%RDI

0x26f733 LEA	-0x1(%RDI),%R10

0x26f737 MOV	%R10,-0x30(%RBP)

0x26f73b CMP	%R15,%RDI

0x26f73e JLE	26f7b0

0x26f740 MOV	(%RAX,%R10,8),%R11

0x26f744 MOV	(%RCX,%R11,8),%R14

0x26f748 MOV	0x8(%RCX,%R11,8),%R13

0x26f74d CMP	%R13,%R14

0x26f750 JGE	26f772

0x26f752 MOV	-0x38(%RBP),%R12

0x26f756 DEC	%R12

0x26f759 NOPL	(%RAX)

  (1036) 0x26f760 MOV	(%RDX,%R14,8),%RDI

  (1036) 0x26f764 CMP	%R12,(%RSI,%RDI,8)

  (1036) 0x26f768 JE	26f710

  (1036) 0x26f76a INC	%R14

  (1036) 0x26f76d CMP	%R14,%R13

  (1036) 0x26f770 JNE	26f760

0x26f772 MOV	-0x48(%RBP),%RDI

0x26f776 MOV	(%RDI,%R11,8),%R14

0x26f77a MOV	0x8(%RDI,%R11,8),%R13

0x26f77f CMP	%R13,%R14

0x26f782 JGE	26f72f

0x26f784 MOV	-0x38(%RBP),%R12

0x26f788 DEC	%R12

0x26f78b NOPL	(%RAX,%RAX,1)

  (1035) 0x26f790 MOV	(%R8,%R14,8),%RDI

  (1035) 0x26f794 CMP	%R12,(%R9,%RDI,8)

  (1035) 0x26f798 JE	26f710

  (1035) 0x26f79e INC	%R14

  (1035) 0x26f7a1 CMP	%R14,%R13

  (1035) 0x26f7a4 JNE	26f790

0x26f7a6 JMP	26f72f

/home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 550 - 571

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

550:       for (i = pass_array_size-1; i > cnt-1; i--)

551:       {

552:          i1 = pass_array[i];

553:          no_break = 1;

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

555:          {

556:             j1 = S_diag_j[j];

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

[...]

568:             for (j=S_offd_i[i1]; j < S_offd_i[i1+1]; j++)

569:             {

570:                j1 = S_offd_j[j];

571:                if (assigned_offd[j1] == pass-1)

Coverage (%)	Name	Source Location	Module
►99.74+	hypre_BoomerAMGSetup	par_amg_setup.c:737	exec
○	hypre_PCGSetup	pcg.c:234	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	8.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.14
Bottlenecks	P6, P7, P8, P9,
Function	hypre_BoomerAMGBuildMultipass
Source	par_multi_interp.c:550-554,par_multi_interp.c:568-568
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.00
CQA cycles if no scalar integer	4.00
CQA cycles if FP arith vectorized	4.00
CQA cycles if fully vectorized	0.50
Front-end cycles	3.50
P0 cycles	2.00
P1 cycles	2.00
P2 cycles	2.00
P3 cycles	2.00
P4 cycles	2.00
P5 cycles	2.00
P6 cycles	4.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	4.00
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	30.00
Nb uops	28.00
Nb loads	11.00
Nb stores	5.00
Nb stack references	3.00
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	88.00
Bytes stored	40.00
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	12.50
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	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	8.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.14
Bottlenecks	P6, P7, P8, P9,
Function	hypre_BoomerAMGBuildMultipass
Source	par_multi_interp.c:550-554,par_multi_interp.c:568-568
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.00
CQA cycles if no scalar integer	4.00
CQA cycles if FP arith vectorized	4.00
CQA cycles if fully vectorized	0.50
Front-end cycles	3.50
P0 cycles	2.00
P1 cycles	2.00
P2 cycles	2.00
P3 cycles	2.00
P4 cycles	2.00
P5 cycles	2.00
P6 cycles	4.00
P7 cycles	4.00
P8 cycles	4.00
P9 cycles	4.00
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	30.00
Nb uops	28.00
Nb loads	11.00
Nb stores	5.00
Nb stack references	3.00
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	88.00
Bytes stored	40.00
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	12.50
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	12.50

Path /

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

Function	hypre_BoomerAMGBuildMultipass
Source file and lines	par_multi_interp.c:550-571
Module	exec

The loop is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:550-557,568-571.

Analyzed code is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:550-554,568.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=7
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 7 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. 8 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 4.00 to 0.50 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

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)

By removing all these bottlenecks, you can lower the cost of an iteration from 4.00 to 3.50 cycles (1.14x speedup).

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 88 bytes. The binary loop is storing 40 bytes.

General properties

nb instructions	30
nb uops	28
loop length	112
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.50 cycles
front end	3.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	2.00	2.00	2.00	2.00	2.00	2.00	4.00	4.00	4.00	4.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	2.00	2.00	2.00	2.00	2.00	2.00	4.00	4.00	4.00	4.00	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	3.50
Dispatch	4.00
Overall L1	4.00

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	12%
load	12%
store	12%
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	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.00 cycles. At this rate:

8% of peak load performance is reached (22.00 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (10.00 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: 26f740

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV (%RAX,%R15,8),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA 0x1(%R10),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R14,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,(%RAX,%R10,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,(%RAX,%R15,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
INC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,(%RSI,%R11,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA -0x1(%RDI),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %R15,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 26f7b0 <hypre_BoomerAMGBuildMultipass+0xf00>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%RAX,%R10,8),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RCX,%R11,8),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RCX,%R11,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP %R13,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JGE 26f772 <hypre_BoomerAMGBuildMultipass+0xec2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x38(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
DEC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x48(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDI,%R11,8),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RDI,%R11,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP %R13,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JGE 26f72f <hypre_BoomerAMGBuildMultipass+0xe7f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x38(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
DEC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
JMP 26f72f <hypre_BoomerAMGBuildMultipass+0xe7f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A

Function	hypre_BoomerAMGBuildMultipass
Source file and lines	par_multi_interp.c:550-571
Module	exec

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=7
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

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 4.00 to 0.50 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

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)

By removing all these bottlenecks, you can lower the cost of an iteration from 4.00 to 3.50 cycles (1.14x speedup).

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 88 bytes. The binary loop is storing 40 bytes.

General properties

nb instructions	30
nb uops	28
loop length	112
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.50 cycles
front end	3.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	2.00	2.00	2.00	2.00	2.00	2.00	4.00	4.00	4.00	4.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	2.00	2.00	2.00	2.00	2.00	2.00	4.00	4.00	4.00	4.00	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	3.50
Dispatch	4.00
Overall L1	4.00

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	12%
load	12%
store	12%
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	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.00 cycles. At this rate:

8% of peak load performance is reached (22.00 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (10.00 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: 26f740

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV (%RAX,%R15,8),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA 0x1(%R10),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R14,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,(%RAX,%R10,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,(%RAX,%R15,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
INC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,(%RSI,%R11,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x30(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA -0x1(%RDI),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %R15,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 26f7b0 <hypre_BoomerAMGBuildMultipass+0xf00>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%RAX,%R10,8),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RCX,%R11,8),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RCX,%R11,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP %R13,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JGE 26f772 <hypre_BoomerAMGBuildMultipass+0xec2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x38(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
DEC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x48(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDI,%R11,8),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RDI,%R11,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
CMP %R13,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JGE 26f72f <hypre_BoomerAMGBuildMultipass+0xe7f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x38(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
DEC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
JMP 26f72f <hypre_BoomerAMGBuildMultipass+0xe7f>	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

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