OV - exec - Loop 1819

	Loop Id: 1819	Module: exec	Source: :0-0	Coverage: 0.01%

0x4733b0 MOV	0x50(%RSP),%RAX

0x4733b5 MOV	0x40(%RSP),%RDI

0x4733ba MOV	0x80(%RSP),%R10

0x4733c2 MOV	0x48(%RSP),%R9

0x4733c7 LEA	(%RAX,%RBP,1),%R8

0x4733cb MOV	0x58(%RSP),%RAX

0x4733d0 MOV	0x10(%RSP),%RDX

0x4733d5 IMUL	%RDI,%R10

0x4733d9 MOV	0x30(%RSP),%R12

0x4733de MOV	0x78(%RSP),%R13

0x4733e3 IMUL	%R8,%RAX

0x4733e7 ADD	%RAX,%R10

0x4733ea MOV	0x90(%RSP),%RAX

0x4733f2 ADD	%RDI,%RAX

0x4733f5 MOV	0x60(%RSP),%RDI

0x4733fa LEA	(%RDI,%RAX,8),%RSI

0x4733fe MOV	0x70(%RSP),%RAX

0x473403 IMUL	%RAX,%R8

0x473407 MOV	0x68(%RSP),%RAX

0x47340c ADD	%RAX,%R8

0x47340f LEA	(%R8,%R9,1),%RAX

0x473413 ADD	%R10,%R9

0x473416 LEA	(%RDX,%RAX,8),%RDX

0x47341a MOV	0xa0(%RSP),%RAX

0x473422 SAL	$0x3,%R9

0x473426 ADD	%R12,%RAX

0x473429 MOV	0x88(%RSP),%R12

0x473431 LEA	(%RDI,%RAX,8),%RDI

0x473435 LEA	(%R13,%R9,1),%RAX

0x47343a MOV	%RAX,0x20(%RSP)

0x47343f MOV	0x18(%RSP),%RAX

0x473444 ADD	%R12,%R9

0x473447 LEA	(%R13,%R9,1),%R12

0x47344c XOR	%R9D,%R9D

0x47344f ADD	%RAX,%R10

0x473452 MOV	0x20(%RSP),%RAX

0x473457 LEA	(%R13,%R10,8),%R13

  (1818) 0x47345c CMP	$0x2,%R11

  (1818) 0x473460 JLE	473569

  (1818) 0x473466 MOV	%RBP,0x20(%RSP)

    (1821) 0x47346b LEA	-0x8(%RDI),%R10

    (1821) 0x47346f CMP	%R12,%R10

    (1821) 0x473472 SETAE	%BPL

    (1821) 0x473476 CMP	%RDI,%RAX

    (1821) 0x473479 SETAE	%R10B

    (1821) 0x47347d OR	%BPL,%R10B

    (1821) 0x473480 JE	473564

    (1821) 0x473486 LEA	0x8(%RDX),%R10

    (1821) 0x47348a CMP	%R10,%RAX

    (1821) 0x47348d JE	473564

    (1821) 0x473493 MOVSD	(%RSI),%XMM1

    (1821) 0x473497 XOR	%R10D,%R10D

    (1821) 0x47349a UNPCKLPD	%XMM1,%XMM1

    (1821) 0x47349e NOPW	%CS:(%RAX,%RAX,1)

    (1821) 0x4734a9 NOPW	%CS:(%RAX,%RAX,1)

    (1821) 0x4734b4 NOPW	%CS:(%RAX,%RAX,1)

    (1821) 0x4734bf NOP

      (1820) 0x4734c0 MOVUPD	(%RDX,%R10,1),%XMM0

      (1820) 0x4734c6 MOVUPD	(%RAX,%R10,1),%XMM2

      (1820) 0x4734cc MULPD	%XMM1,%XMM0

      (1820) 0x4734d0 ADDPD	%XMM2,%XMM0

      (1820) 0x4734d4 MOVUPS	%XMM0,(%RAX,%R10,1)

      (1820) 0x4734d9 ADD	$0x10,%R10

      (1820) 0x4734dd CMP	%R10,%RCX

      (1820) 0x4734e0 JNE	4734c0

    (1821) 0x4734e2 CMPQ	$0,0x8(%RSP)

    (1821) 0x4734e8 JE	47350e

    (1821) 0x4734ea MOV	0x18(%RSP),%R10

    (1821) 0x4734ef MOV	0x10(%RSP),%RBP

    (1821) 0x4734f4 ADD	%R8,%R10

    (1821) 0x4734f7 MOVSD	(%RBP,%R10,8),%XMM0

    (1821) 0x4734fe MULSD	(%RSI),%XMM0

    (1821) 0x473502 ADDSD	(%R13),%XMM0

    (1821) 0x473508 MOVSD	%XMM0,(%R13)

    (1821) 0x47350e ADD	$0x1,%R9

    (1821) 0x473512 ADD	%RBX,%RSI

    (1821) 0x473515 ADD	%R14,%R8

    (1821) 0x473518 ADD	%R15,%RDX

    (1821) 0x47351b ADD	%RBX,%RDI

    (1821) 0x47351e CMP	%R9,(%RSP)

    (1821) 0x473522 JG	47346b

0x473528 MOV	0x20(%RSP),%RBP

0x47352d MOV	0x98(%RSP),%RSI

0x473535 CMP	%RSI,0x28(%RSP)

0x47353a JE	473552

0x47353c ADD	$0x1,%RBP

0x473540 CMP	%RBP,0x38(%RSP)

0x473545 JLE	4735c1

0x473547 ADDQ	$0x1,0x28(%RSP)

0x47354d JMP	4733b0

  (1818) 0x473564 MOV	0x20(%RSP),%RBP

  (1818) 0x473569 XOR	%R10D,%R10D

  (1818) 0x47356c NOPW	%CS:(%RAX,%RAX,1)

  (1818) 0x473577 NOPW	(%RAX,%RAX,1)

    (1817) 0x473580 MOVSD	(%RDX,%R10,8),%XMM0

    (1817) 0x473586 MULSD	(%RSI),%XMM0

    (1817) 0x47358a ADDSD	(%RAX,%R10,8),%XMM0

    (1817) 0x473590 MOVSD	%XMM0,(%RAX,%R10,8)

    (1817) 0x473596 ADD	$0x1,%R10

    (1817) 0x47359a CMP	%R10,%R11

    (1817) 0x47359d JG	473580

  (1818) 0x47359f MOV	(%RSP),%R10

  (1818) 0x4735a3 ADD	$0x1,%R9

  (1818) 0x4735a7 ADD	%RBX,%RSI

  (1818) 0x4735aa ADD	%R14,%R8

  (1818) 0x4735ad ADD	%R15,%RDX

  (1818) 0x4735b0 ADD	%RBX,%RDI

  (1818) 0x4735b3 CMP	%R10,%R9

  (1818) 0x4735b6 JL	47345c

0x4735bc JMP	47352d

0x4735c1 ADDQ	$0x1,0x30(%RSP)

0x4735c7 MOV	0xa8(%RSP),%RSI

0x4735cf XOR	%EBP,%EBP

0x4735d1 MOV	0x30(%RSP),%RAX

0x4735d6 ADD	%RSI,%RAX

0x4735d9 MOV	%RAX,0x40(%RSP)

0x4735de JMP	473547

  ***  This Panel is Intentionally Left Blank.  ***

It is due to a lack of debug symbols in the given object
(loop or function).

Coverage (%)	Name	Source Location	Module
►100.00+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		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	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	1.04
Bottlenecks	micro-operation queue,
Function	void RAJA::internal::StatementExecutor, RAJA::statement::For<1l, RAJA::policy::sequential::seq_exec, RAJA::statement::For<3l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > > >, RAJA::internal::LoopTypes, camp::list > >::exec, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&>(RAJA::internal::LoopData, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&) [clone ._omp_fn.0]
Source
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	6.75
CQA cycles if no scalar integer	6.75
CQA cycles if FP arith vectorized	6.75
CQA cycles if fully vectorized	0.84
Front-end cycles	6.75
P0 cycles	5.00
P1 cycles	5.00
P2 cycles	5.00
P3 cycles	5.00
P4 cycles	5.00
P5 cycles	5.00
P6 cycles	6.50
P7 cycles	6.50
P8 cycles	6.50
P9 cycles	6.50
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	54.00
Nb uops	54.00
Nb loads	24.00
Nb stores	4.00
Nb stack references	20.00
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	33.19
Bytes prefetched	0.00
Bytes loaded	192.00
Bytes stored	32.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	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	1.04
Bottlenecks	micro-operation queue,
Function	void RAJA::internal::StatementExecutor, RAJA::statement::For<1l, RAJA::policy::sequential::seq_exec, RAJA::statement::For<3l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > > >, RAJA::internal::LoopTypes, camp::list > >::exec, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&>(RAJA::internal::LoopData, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&) [clone ._omp_fn.0]
Source
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	6.75
CQA cycles if no scalar integer	6.75
CQA cycles if FP arith vectorized	6.75
CQA cycles if fully vectorized	0.84
Front-end cycles	6.75
P0 cycles	5.00
P1 cycles	5.00
P2 cycles	5.00
P3 cycles	5.00
P4 cycles	5.00
P5 cycles	5.00
P6 cycles	6.50
P7 cycles	6.50
P8 cycles	6.50
P9 cycles	6.50
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	54.00
Nb uops	54.00
Nb loads	24.00
Nb stores	4.00
Nb stack references	20.00
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	33.19
Bytes prefetched	0.00
Bytes loaded	192.00
Bytes stored	32.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	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	void RAJA::internal::StatementExecutor, RAJA::statement::For<1l, RAJA::policy::sequential::seq_exec, RAJA::statement::For<3l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > > >, RAJA::internal::LoopTypes, camp::list > >::exec, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&>(RAJA::internal::LoopData, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&) [clone ._omp_fn.0]
Source file and lines
Module	exec

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=10
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 10 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

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 6.75 to 0.84 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
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA)

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 192 bytes. The binary loop is storing 32 bytes.

General properties

nb instructions	54
nb uops	54
loop length	253
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	20

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	6.75 cycles
front end	6.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.00	5.00	5.00	5.00	5.00	5.00	6.50	6.50	6.50	6.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	5.00	5.00	5.00	5.00	5.00	5.00	6.50	6.50	6.50	6.50	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	6.75
Dispatch	6.50
Overall L1	6.75

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 6.75 cycles. At this rate:

11% of peak load performance is reached (28.44 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.74 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).

ASM code

In the binary file, the address of the loop is: 4733b0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV 0x50(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x40(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x80(%RSP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x48(%RSP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%RAX,%RBP,1),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x58(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RSP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RDI,%R10	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV 0x30(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x78(%RSP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %R8,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
ADD %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x90(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x60(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%RDI,%RAX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RAX,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV 0x68(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %RAX,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R8,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD %R10,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RDX,%RAX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0xa0(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SAL $0x3,%R9	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
ADD %R12,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x88(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
LEA (%RDI,%RAX,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA (%R13,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,0x20(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x18(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %R12,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R13,%R9,1),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
ADD %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x20(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%R13,%R10,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x20(%RSP),%RBP	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x98(%RSP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RSI,0x28(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD $0x1,%RBP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP %RBP,0x38(%RSP)	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 4735c1 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x3c1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADDQ $0x1,0x28(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
JMP 4733b0 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x1b0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
JMP 47352d <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x32d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
ADDQ $0x1,0x30(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOV 0xa8(%RSP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
XOR %EBP,%EBP	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV 0x30(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,0x40(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 473547 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x347>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A

Function	void RAJA::internal::StatementExecutor, RAJA::statement::For<1l, RAJA::policy::sequential::seq_exec, RAJA::statement::For<3l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > > >, RAJA::internal::LoopTypes, camp::list > >::exec, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&>(RAJA::internal::LoopData, long>, RAJA::Span, long>, RAJA::Span, long>, RAJA::Span, long> >, camp::tuple<>, camp::resources::v1::Host, LTimesSdom::operator() >(Kripke::ArchLayoutT, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field&, Kripke::Core::Field&, Kripke::Core::Field&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&) [clone ._omp_fn.0]
Source file and lines
Module	exec

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=10
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

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 6.75 to 0.84 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
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA)

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 192 bytes. The binary loop is storing 32 bytes.

General properties

nb instructions	54
nb uops	54
loop length	253
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	20

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	6.75 cycles
front end	6.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.00	5.00	5.00	5.00	5.00	5.00	6.50	6.50	6.50	6.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	5.00	5.00	5.00	5.00	5.00	5.00	6.50	6.50	6.50	6.50	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	6.75
Dispatch	6.50
Overall L1	6.75

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 6.75 cycles. At this rate:

11% of peak load performance is reached (28.44 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.74 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).

ASM code

In the binary file, the address of the loop is: 4733b0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV 0x50(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x40(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x80(%RSP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x48(%RSP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%RAX,%RBP,1),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x58(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RSP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RDI,%R10	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV 0x30(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x78(%RSP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %R8,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
ADD %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x90(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x60(%RSP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%RDI,%RAX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x70(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RAX,%R8	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV 0x68(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %RAX,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R8,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD %R10,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RDX,%RAX,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0xa0(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SAL $0x3,%R9	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
ADD %R12,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x88(%RSP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
LEA (%RDI,%RAX,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA (%R13,%R9,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,0x20(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x18(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %R12,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R13,%R9,1),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
ADD %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x20(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (%R13,%R10,8),%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x20(%RSP),%RBP	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x98(%RSP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RSI,0x28(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
JE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADD $0x1,%RBP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP %RBP,0x38(%RSP)	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 4735c1 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x3c1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
ADDQ $0x1,0x28(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
JMP 4733b0 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x1b0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
JMP 47352d <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x32d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
ADDQ $0x1,0x30(%RSP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.50	scal (12.5%)
MOV 0xa8(%RSP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
XOR %EBP,%EBP	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV 0x30(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,0x40(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 473547 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x347>	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

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code