OV - exec - Loop 938

	Loop Id: 938	Module: exec	Source: par_multi_interp.c:646-661	Coverage: 0.01%

0x2680c0 MOV	-0x30(%RBP),%RCX

0x2680c4 MOV	-0x60(%RBP),%RAX

0x2680c8 INC	%RCX

0x2680cb MOV	%RCX,-0x30(%RBP)

0x2680cf CMP	%RCX,0x10(%RAX)

0x2680d3 JLE	2681a3

0x2680d9 MOV	-0x80(%RBP),%RAX

0x2680dd MOV	-0x40(%RBP),%RDX

0x2680e1 MOV	(%RAX,%RCX,8),%R12

0x2680e5 MOV	-0xb0(%RBP),%RCX

0x2680ec MOV	%R10,(%RDX,%R12,8)

0x2680f0 MOV	%R8,(%RCX,%R12,8)

0x2680f4 MOV	(%RDI,%R12,8),%R13

0x2680f8 MOV	0x8(%RDI,%R12,8),%RSI

0x2680fd CMP	%RSI,%R13

0x268100 JGE	268150

0x268102 MOV	-0x178(%RBP),%RCX

0x268109 MOV	-0x98(%RBP),%RDX

0x268110 JMP	268128

  (940) 0x268120 INC	%R13

  (940) 0x268123 CMP	%RSI,%R13

  (940) 0x268126 JGE	268150

  (940) 0x268128 MOV	(%R9,%R13,8),%RAX

  (940) 0x26812c CMPQ	$0x1,(%R11,%RAX,8)

  (940) 0x268131 JNE	268120

  (940) 0x268133 MOV	(%RCX,%RAX,8),%RAX

  (940) 0x268137 MOV	0x8(%RDX),%RSI

  (940) 0x26813b MOV	%RAX,(%RSI,%R10,8)

  (940) 0x26813f INC	%R10

  (940) 0x268142 MOV	0x8(%RDI,%R12,8),%RSI

  (940) 0x268147 JMP	268120

0x268150 MOV	(%RBX,%R12,8),%R13

0x268154 MOV	0x8(%RBX,%R12,8),%RSI

0x268159 CMP	%RSI,%R13

0x26815c JGE	2680c0

0x268162 MOV	-0x210(%RBP),%RCX

0x268169 MOV	-0x70(%RBP),%RDX

0x26816d JMP	26817c

  (939) 0x268170 INC	%R13

  (939) 0x268173 CMP	%RSI,%R13

  (939) 0x268176 JGE	2680c0

  (939) 0x26817c MOV	(%R14,%R13,8),%RAX

  (939) 0x268180 CMPQ	$0x1,(%R15,%RAX,8)

  (939) 0x268185 JNE	268170

  (939) 0x268187 MOV	(%RCX,%RAX,8),%RAX

  (939) 0x26818b MOV	0x8(%RDX),%RSI

  (939) 0x26818f MOV	%RAX,(%RSI,%R8,8)

  (939) 0x268193 INC	%R8

  (939) 0x268196 MOV	0x8(%RBX,%R12,8),%RSI

  (939) 0x26819b JMP	268170

/home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 646 - 661

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

646:    for (i=pass_pointer[1]; i < pass_pointer[2]; i++)

647:    {

648:       i1 = pass_array[i];

649:       P_diag_start[i1] = cnt_nz;

650:       P_offd_start[i1] = cnt_nz_offd;

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

652:       {

653:          j1 = S_diag_j[j];

654:          if (CF_marker[j1] == 1)

655:          {   P_diag_pass[1][cnt_nz++] = fine_to_coarse[j1]; }

656:       }

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

658:       {

659:          j1 = S_offd_j[j];

660:          if (CF_marker_offd[j1] == 1)

661:          {   P_offd_pass[1][cnt_nz_offd++] = map_S_to_new[j1]; }

Coverage (%)	Name	Source Location	Module
►100.00+	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	1.38
Bottlenecks	P6, P7, P8, P9,
Function	hypre_BoomerAMGBuildMultipass
Source	par_multi_interp.c:646-651,par_multi_interp.c:657-657
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
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	0.56
Front-end cycles	3.25
P0 cycles	1.33
P1 cycles	1.33
P2 cycles	1.33
P3 cycles	1.67
P4 cycles	1.67
P5 cycles	1.67
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	26.00
Nb uops	26.00
Nb loads	15.00
Nb stores	3.00
Nb stack references	9.00
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	120.00
Bytes stored	24.00
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	1.38
Bottlenecks	P6, P7, P8, P9,
Function	hypre_BoomerAMGBuildMultipass
Source	par_multi_interp.c:646-651,par_multi_interp.c:657-657
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
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	0.56
Front-end cycles	3.25
P0 cycles	1.33
P1 cycles	1.33
P2 cycles	1.33
P3 cycles	1.67
P4 cycles	1.67
P5 cycles	1.67
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	26.00
Nb uops	26.00
Nb loads	15.00
Nb stores	3.00
Nb stack references	9.00
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	120.00
Bytes stored	24.00
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:646-661
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:646-661.

Analyzed code is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c:646-651,657.

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

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 4.50 to 0.56 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:
- 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)

By removing all these bottlenecks, you can lower the cost of an iteration from 4.50 to 3.25 cycles (1.38x 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 120 bytes. The binary loop is storing 24 bytes.

General properties

nb instructions	26
nb uops	26
loop length	113
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	9

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.25 cycles
front end	3.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.33	1.33	1.33	1.67	1.67	1.67	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.33	1.33	1.33	1.67	1.67	1.67	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	3.25
Dispatch	4.50
Overall L1	4.50

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 4.50 cycles. At this rate:

10% of peak load performance is reached (26.67 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.33 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: 2680d9

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %RCX,0x10(%RAX)	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%)
JLE 2681a3 <hypre_BoomerAMGBuildMultipass+0x1273>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x80(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x40(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RAX,%RCX,8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0xb0(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R10,(%RDX,%R12,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R8,(%RCX,%R12,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI,%R12,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%RDI,%R12,8),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RSI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JGE 268150 <hypre_BoomerAMGBuildMultipass+0x1220>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x178(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x98(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 268128 <hypre_BoomerAMGBuildMultipass+0x11f8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV (%RBX,%R12,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%RBX,%R12,8),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RSI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JGE 2680c0 <hypre_BoomerAMGBuildMultipass+0x1190>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x210(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x70(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 26817c <hypre_BoomerAMGBuildMultipass+0x124c>	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:646-661
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

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 4.50 to 0.56 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:
- 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)

By removing all these bottlenecks, you can lower the cost of an iteration from 4.50 to 3.25 cycles (1.38x 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 120 bytes. The binary loop is storing 24 bytes.

General properties

nb instructions	26
nb uops	26
loop length	113
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	9

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.25 cycles
front end	3.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	1.33	1.33	1.33	1.67	1.67	1.67	4.50	4.50	4.50	4.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	1.33	1.33	1.33	1.67	1.67	1.67	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	3.25
Dispatch	4.50
Overall L1	4.50

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 4.50 cycles. At this rate:

10% of peak load performance is reached (26.67 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (5.33 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: 2680d9

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %RCX,0x10(%RAX)	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%)
JLE 2681a3 <hypre_BoomerAMGBuildMultipass+0x1273>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x80(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x40(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RAX,%RCX,8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0xb0(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R10,(%RDX,%R12,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R8,(%RCX,%R12,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI,%R12,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%RDI,%R12,8),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RSI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JGE 268150 <hypre_BoomerAMGBuildMultipass+0x1220>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x178(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x98(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 268128 <hypre_BoomerAMGBuildMultipass+0x11f8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV (%RBX,%R12,8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%RBX,%R12,8),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RSI,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JGE 2680c0 <hypre_BoomerAMGBuildMultipass+0x1190>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV -0x210(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x70(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 26817c <hypre_BoomerAMGBuildMultipass+0x124c>	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