OV - exec - Function void RAJA::internal::StatementExecutor<RAJA::statement::Collapse<RAJA::omp_parallel_collapse_exec, camp::int_seq<long, 0l, 1l>, RAJA::statement::For<2l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > >, RAJA::internal::LoopTypes<camp::list<void, void, void>, camp::list<void, void, void> > >::exec<RAJA::internal::LoopData<camp::tuple<RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Direction, long, Kripke::Direction*>, long>, RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Group, long, Kripke::Group*>, long>, RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Zone, long, Kripke::Zone*>, long> >, camp::tuple<>, camp::resources::v1::Host, PopulationSdom::operator()<Kripke::ArchLayoutT<Kripke::ArchT_OpenMP, Kripke::LayoutT_DGZ> >(Kripke::ArchLayoutT<Kripke::ArchT_OpenMP, Kripke::LayoutT_DGZ>, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field<double, Kripke::Direction, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Direction>&, Kripke::Core::Field<double, Kripke::Zone>&, double*) const::{lambda(Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&>(RAJA::internal::LoopData<camp::tuple<RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Direction, long, Kripke::Direction*>, long>, RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Group, long, Kripke::Group*>, long>, RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Zone, long, Kripke::Zone*>, long> >, camp::tuple<>, camp::resources::v1::Host, PopulationSdom::operator()<Kripke::ArchLayoutT<Kripke::ArchT_OpenMP, Kripke::LayoutT_DGZ> >(Kripke::ArchLayoutT<Kripke::ArchT_OpenMP, Kripke::LayoutT_DGZ>, Kripke::SdomId, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field<double, Kripke::Direction, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Direction>&, Kripke::Core::Field<double, Kripke::Zone>&, double*) const::{lambda(Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&) [clone .omp

	Function: void RAJA::internal::StatementExecutor<RAJA::statement::Collapse<RAJA::omp_parallel_collap ...	Module: exec	Source: Collapse.hpp:74-77 [...]	Coverage (incl. loops): 0.30% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/detail/reduce.hpp: 76 - 293

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

76:     val = operator_type::operator()(val, v);

[...]

283:       : parent{other.parent ? other.parent : &other},

284:         identity{other.identity},

[...]

293:     if (parent && my_data != identity) {

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp: 137 - 137

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

137:     for (decltype(distance_it) i = 0; i < distance_it; ++i) {

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 269 - 269

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

269:     return value_type(val + rhs);

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp: 59 - 60

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

59: #pragma omp critical(ompReduceCritical)

60:       Reduce()(Base::parent->local(), Base::my_data);

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 74 - 77

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

74: #pragma omp parallel for private(i0, i1) firstprivate(privatizer) \

75:     RAJA_COLLAPSE(2)

76:     for (i0 = 0; i0 < l0; ++i0) {

77:       for (i1 = 0; i1 < l1; ++i1) {

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 334 - 334

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

334:     return Ret{lhs} + rhs;

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp: 56 - 58

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

56:         KRIPKE_LAMBDA (Direction d, Group g, Zone z) {

57:

58:           part_red += w(d) * psi(d,g,z) * volume(z);

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/internal/LoopData.hpp: 146 - 146

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

146:   constexpr LoopData(LoopData const &) = default;

0x26ccd0 PUSH	%RBP

0x26ccd1 MOV	%RSP,%RBP

0x26ccd4 PUSH	%R15

0x26ccd6 PUSH	%R14

0x26ccd8 PUSH	%R13

0x26ccda PUSH	%R12

0x26ccdc PUSH	%RBX

0x26ccdd SUB	$0x68,%RSP

0x26cce1 MOV	(%RDX),%R14

0x26cce4 TEST	%R14,%R14

0x26cce7 JLE	26cf9a

0x26cced MOV	(%RCX),%R15

0x26ccf0 TEST	%R15,%R15

0x26ccf3 JLE	26cf9a

0x26ccf9 IMUL	%R15,%R14

0x26ccfd DEC	%R14

0x26cd00 MOVQ	$0,-0x68(%RBP)

0x26cd08 MOV	%R14,-0x38(%RBP)

0x26cd0c MOVQ	$0x1,-0x90(%RBP)

0x26cd17 MOVL	$0,-0x40(%RBP)

0x26cd1e MOV	(%R8),%RAX

0x26cd21 MOV	%RAX,-0x30(%RBP)

0x26cd25 MOV	0x10(%R8),%RAX

0x26cd29 MOV	%RAX,-0x60(%RBP)

0x26cd2d MOV	0x20(%R8),%R12

0x26cd31 LEA	0x38(%R8),%RCX

0x26cd35 MOV	0x38(%R8),%RAX

0x26cd39 TEST	%RAX,%RAX

0x26cd3c CMOVNE	%RAX,%RCX

0x26cd40 MOV	%RCX,-0x70(%RBP)

0x26cd44 MOV	0x28(%R8),%R13

0x26cd48 MOVSD	0x40(%R8),%XMM0

0x26cd4e MOVSD	%XMM0,-0x48(%RBP)

0x26cd53 MOV	0x50(%R8),%RAX

0x26cd57 MOV	%RAX,-0x88(%RBP)

0x26cd5e MOV	0x78(%R8),%RAX

0x26cd62 MOV	%RAX,-0x58(%RBP)

0x26cd66 MOV	0x98(%R8),%RAX

0x26cd6d MOV	%RAX,-0x80(%RBP)

0x26cd71 MOV	0xa0(%R8),%RBX

0x26cd78 MOV	0xe0(%R8),%RAX

0x26cd7f MOV	%RAX,-0x50(%RBP)

0x26cd83 MOV	(%RDI),%ESI

0x26cd85 SUB	$0x8,%RSP

0x26cd89 LEA	-0x90(%RBP),%RAX

0x26cd90 LEA	0x41b01(%RIP),%RDI

0x26cd97 LEA	-0x40(%RBP),%RCX

0x26cd9b LEA	-0x68(%RBP),%R8

0x26cd9f LEA	-0x38(%RBP),%R9

0x26cda3 MOV	%ESI,-0x3c(%RBP)

0x26cda6 MOV	$0x22,%EDX

0x26cdab PUSH	$0x1

0x26cdad PUSH	$0x1

0x26cdaf PUSH	%RAX

0x26cdb0 CALL	2ac630 <@plt_start@+0x420>

0x26cdb5 MOVSD	-0x48(%RBP),%XMM0

0x26cdba ADD	$0x20,%RSP

0x26cdbe MOV	-0x38(%RBP),%RAX

0x26cdc2 CMP	%R14,%RAX

0x26cdc5 CMOVL	%RAX,%R14

0x26cdc9 MOV	%R14,-0x38(%RBP)

0x26cdcd MOV	-0x68(%RBP),%RCX

0x26cdd1 MOVAPD	%XMM0,%XMM2

0x26cdd5 CMP	%R14,%RCX

0x26cdd8 JG	26cf30

0x26cdde SUB	%R12,%R13

0x26cde1 XOR	%ESI,%ESI

0x26cde3 MOVAPD	%XMM0,%XMM2

0x26cde7 TEST	%R13,%R13

0x26cdea CMOVG	%R13,%RSI

0x26cdee JLE	26cf30

0x26cdf4 LEA	-0x1(%RSI),%RDI

0x26cdf8 MOV	%ESI,%R8D

0x26cdfb AND	$0x1,%R8D

0x26cdff AND	$-0x2,%RSI

0x26ce03 MOV	-0x50(%RBP),%RAX

0x26ce07 LEA	(%RAX,%R12,8),%R9

0x26ce0b ADD	$0x8,%R9

0x26ce0f MOV	-0x58(%RBP),%RAX

0x26ce13 ADD	$0x8,%RAX

0x26ce17 MOV	%RAX,-0x78(%RBP)

0x26ce1b MOV	-0x60(%RBP),%RAX

0x26ce1f LEA	(%RAX,%RCX,1),%R11

0x26ce23 MOVAPD	%XMM0,%XMM2

0x26ce27 JMP	26ce43

0x26ce29 NOPL	(%RAX)

(1089) 0x26ce30 LEA	0x1(%RCX),%RAX

(1089) 0x26ce34 INC	%R11

(1089) 0x26ce37 CMP	%R14,%RCX

(1089) 0x26ce3a MOV	%RAX,%RCX

(1089) 0x26ce3d JGE	26cf30

(1089) 0x26ce43 MOV	%RCX,%RAX

(1089) 0x26ce46 OR	%R15,%RAX

(1089) 0x26ce49 SHR	$0x20,%RAX

(1089) 0x26ce4d JE	26ce60

(1089) 0x26ce4f MOV	%RCX,%RAX

(1089) 0x26ce52 CQTO

(1089) 0x26ce54 IDIV	%R15

(1089) 0x26ce57 JMP	26ce67

0x26ce59 NOPL	(%RAX)

(1089) 0x26ce60 MOV	%ECX,%EAX

(1089) 0x26ce62 XOR	%EDX,%EDX

(1089) 0x26ce64 DIV	%R15D

(1089) 0x26ce67 MOV	%RAX,%RDX

(1089) 0x26ce6a IMUL	%R15,%RDX

(1089) 0x26ce6e ADD	-0x30(%RBP),%RAX

(1089) 0x26ce72 MOV	%RAX,%R10

(1089) 0x26ce75 IMUL	-0x80(%RBP),%R10

(1089) 0x26ce7a MOV	-0x88(%RBP),%R13

(1089) 0x26ce81 MOVSD	(%R13,%RAX,8),%XMM0

(1089) 0x26ce88 TEST	%RDI,%RDI

(1089) 0x26ce8b JNE	26cea0

(1089) 0x26ce8d XOR	%EAX,%EAX

(1089) 0x26ce8f JMP	26cef4

0x26ce91 NOPW	%CS:(%RAX,%RAX,1)

(1089) 0x26cea0 MOV	%R11,%R13

(1089) 0x26cea3 SUB	%RDX,%R13

(1089) 0x26cea6 IMUL	%RBX,%R13

(1089) 0x26ceaa ADD	%R12,%R13

(1089) 0x26cead ADD	%R10,%R13

(1089) 0x26ceb0 MOV	-0x78(%RBP),%RAX

(1089) 0x26ceb4 LEA	(%RAX,%R13,8),%R13

(1089) 0x26ceb8 XOR	%EAX,%EAX

(1089) 0x26ceba NOPW	(%RAX,%RAX,1)

  (1088) 0x26cec0 MOVSD	-0x8(%R13,%RAX,8),%XMM1

  (1088) 0x26cec7 MULSD	%XMM0,%XMM1

  (1088) 0x26cecb MULSD	-0x8(%R9,%RAX,8),%XMM1

  (1088) 0x26ced2 ADDSD	%XMM2,%XMM1

  (1088) 0x26ced6 MOVSD	(%R13,%RAX,8),%XMM2

  (1088) 0x26cedd MULSD	%XMM0,%XMM2

  (1088) 0x26cee1 MULSD	(%R9,%RAX,8),%XMM2

  (1088) 0x26cee7 ADDSD	%XMM1,%XMM2

  (1088) 0x26ceeb ADD	$0x2,%RAX

  (1088) 0x26ceef CMP	%RAX,%RSI

  (1088) 0x26cef2 JNE	26cec0

(1089) 0x26cef4 TEST	%R8,%R8

(1089) 0x26cef7 JE	26ce30

(1089) 0x26cefd MOV	-0x60(%RBP),%R13

(1089) 0x26cf01 ADD	%RCX,%R13

(1089) 0x26cf04 SUB	%RDX,%R13

(1089) 0x26cf07 IMUL	%RBX,%R13

(1089) 0x26cf0b ADD	%R10,%R13

(1089) 0x26cf0e ADD	%R12,%RAX

(1089) 0x26cf11 ADD	%RAX,%R13

(1089) 0x26cf14 MOV	-0x58(%RBP),%RDX

(1089) 0x26cf18 MULSD	(%RDX,%R13,8),%XMM0

(1089) 0x26cf1e MOV	-0x50(%RBP),%RDX

(1089) 0x26cf22 MULSD	(%RDX,%RAX,8),%XMM0

(1089) 0x26cf27 ADDSD	%XMM0,%XMM2

(1089) 0x26cf2b JMP	26ce30

0x26cf30 MOVSD	%XMM2,-0x30(%RBP)

0x26cf35 LEA	0x41974(%RIP),%RDI

0x26cf3c MOV	-0x3c(%RBP),%ESI

0x26cf3f CALL	2ac640 <@plt_start@+0x430>

0x26cf44 LEA	0x41995(%RIP),%RBX

0x26cf4b MOV	%RBX,%RDI

0x26cf4e CALL	2ac650 <@plt_start@+0x440>

0x26cf53 MOV	%EAX,%R14D

0x26cf56 LEA	0x432bb(%RIP),%R15

0x26cf5d MOV	%RBX,%RDI

0x26cf60 MOV	%EAX,%ESI

0x26cf62 MOV	%R15,%RDX

0x26cf65 CALL	2ac660 <@plt_start@+0x450>

0x26cf6a MOV	-0x70(%RBP),%R12

0x26cf6e MOVSD	-0x30(%RBP),%XMM0

0x26cf73 ADDSD	0x10(%R12),%XMM0

0x26cf7a MOVSD	%XMM0,0x10(%R12)

0x26cf81 MOV	%RBX,%RDI

0x26cf84 MOV	%R14D,%ESI

0x26cf87 MOV	%R15,%RDX

0x26cf8a CALL	2ac670 <@plt_start@+0x460>

0x26cf8f MOVSD	-0x48(%RBP),%XMM0

0x26cf94 UCOMISD	%XMM0,%XMM0

0x26cf98 JP	26cfa9

0x26cf9a ADD	$0x68,%RSP

0x26cf9e POP	%RBX

0x26cf9f POP	%R12

0x26cfa1 POP	%R13

0x26cfa3 POP	%R14

0x26cfa5 POP	%R15

0x26cfa7 POP	%RBP

0x26cfa8 RET

0x26cfa9 ADDSD	0x10(%R12),%XMM0

0x26cfb0 MOVSD	%XMM0,0x10(%R12)

0x26cfb7 JMP	26cf9a

0x26cfb9 NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module

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 /

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

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	Collapse.hpp:74-77
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/detail/reduce.hpp:76,283-284,293
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp:137
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:269
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:59-60
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74-77
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp:334
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp:56-58
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/internal/LoopData.hpp:146

Warnings:
Ignoring paths for analysis

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 16.00 to 3.00 cycles (5.33x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is probably not vectorized. Only 12% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 16.00 to 1.28 cycles (12.48x speedup).

Details

Store and arithmetical 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 function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function 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

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

unknown: 5 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:75
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:75
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:59
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

CMOVG: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:76
CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:76
UCOMISD: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60

Type of elements and instruction set

3 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 2 FP arithmetical operations:

2: addition or subtraction

The binary function is loading 200 bytes (25 double precision FP elements). The binary function is storing 136 bytes (17 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	124
nb uops	128
loop length	518
used x86 registers	15
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	14

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.00 cycles
front end	16.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.00	8.00	8.00	8.00	8.00	8.00	12.25	12.25	12.25	12.25	0.00	0.00	1.50	1.50	2.50	2.50
cycles	8.00	8.00	8.00	8.00	8.00	8.00	12.25	12.25	12.25	12.25	0.00	0.00	1.50	1.50	2.50	2.50

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	16.00
Dispatch	12.25
Overall L1	16.00

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	21%
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	75%

INT+FP

all	6%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

Vector efficiency ratios

INT

all	11%
load	12%
store	10%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	15%
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	21%

INT+FP

all	12%
load	12%
store	11%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 16.00 cycles. At this rate:

4% of peak load performance is reached (12.50 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.50 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 16.00 to 12.25 cycles (1.31x speedup).

ASM code

In the binary file, the address of the function is: 26ccd0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x68,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV (%RDX),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
TEST %R14,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JLE 26cf9a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2ca>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV (%RCX),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
TEST %R15,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JLE 26cf9a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2ca>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
IMUL %R15,%R14	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOV %R14,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOVQ $0x1,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOVL $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOV (%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x10(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x20(%R8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA 0x38(%R8),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV 0x38(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVNE %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x28(%R8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOVSD 0x40(%R8),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
MOVSD %XMM0,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV 0x50(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x78(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x98(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0xa0(%R8),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV 0xe0(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x90(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x41b01(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x68(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x3c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 2ac630 <@plt_start@+0x420>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOVSD -0x48(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
CMP %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%R14	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %R14,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x68(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOVAPD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMP %R14,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JG 26cf30 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x260>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
SUB %R12,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOVAPD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R13,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %R13,%RSI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
JLE 26cf30 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x260>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%RSI),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %ESI,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x1,%R8D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x2,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RAX,%R12,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD $0x8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x58(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
ADD $0x8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RAX,%RCX,1),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVAPD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 26ce43 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x173>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	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	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOVSD %XMM2,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
LEA 0x41974(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x3c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
CALL 2ac640 <@plt_start@+0x430>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
LEA 0x41995(%RIP),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2ac650 <@plt_start@+0x440>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
LEA 0x432bb(%RIP),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2ac660 <@plt_start@+0x450>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOVSD -0x30(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
ADDSD 0x10(%R12),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2ac670 <@plt_start@+0x460>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOVSD -0x48(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JP 26cfa9 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD $0x68,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50	N/A
ADDSD 0x10(%R12),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
JMP 26cf9a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2ca>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	Collapse.hpp:74-77
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/detail/reduce.hpp:76,283-284,293
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp:137
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:269
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:59-60
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74-77
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp:334
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp:56-58
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/internal/LoopData.hpp:146

Warnings:
Ignoring paths for analysis

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 16.00 to 3.00 cycles (5.33x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function 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

CALL instructions

Detected function call instructions.

Details

unknown: 5 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:75
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:75
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:59
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

CMOVG: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:76
CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:76
UCOMISD: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60

Type of elements and instruction set

3 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

The binary function is composed of 2 FP arithmetical operations:

2: addition or subtraction

The binary function is loading 200 bytes (25 double precision FP elements). The binary function is storing 136 bytes (17 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	124
nb uops	128
loop length	518
used x86 registers	15
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	14

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	16.00 cycles
front end	16.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.00	8.00	8.00	8.00	8.00	8.00	12.25	12.25	12.25	12.25	0.00	0.00	1.50	1.50	2.50	2.50
cycles	8.00	8.00	8.00	8.00	8.00	8.00	12.25	12.25	12.25	12.25	0.00	0.00	1.50	1.50	2.50	2.50

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	16.00
Dispatch	12.25
Overall L1	16.00

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	21%
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	75%

INT+FP

all	6%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

Vector efficiency ratios

INT

all	11%
load	12%
store	10%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	15%
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	21%

INT+FP

all	12%
load	12%
store	11%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 16.00 cycles. At this rate:

4% of peak load performance is reached (12.50 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.50 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 26ccd0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x68,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV (%RDX),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
TEST %R14,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JLE 26cf9a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2ca>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV (%RCX),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
TEST %R15,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JLE 26cf9a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2ca>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
IMUL %R15,%R14	1	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOV %R14,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOVQ $0x1,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOVL $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOV (%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x10(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x20(%R8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA 0x38(%R8),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV 0x38(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVNE %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x28(%R8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOVSD 0x40(%R8),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
MOVSD %XMM0,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV 0x50(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x78(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x98(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV 0xa0(%R8),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	scal (12.5%)
MOV 0xe0(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x90(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x41b01(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x68(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x38(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x3c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 2ac630 <@plt_start@+0x420>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOVSD -0x48(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
CMP %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%R14	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
MOV %R14,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x68(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOVAPD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CMP %R14,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JG 26cf30 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x260>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
SUB %R12,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOVAPD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
TEST %R13,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
CMOVG %R13,%RSI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.33	N/A
JLE 26cf30 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x260>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%RSI),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %ESI,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x1,%R8D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x2,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RAX,%R12,8),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD $0x8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x58(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
ADD $0x8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	4	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
LEA (%RAX,%RCX,1),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVAPD %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 26ce43 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x173>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	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	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOVSD %XMM2,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
LEA 0x41974(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV -0x3c(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
CALL 2ac640 <@plt_start@+0x430>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
LEA 0x41995(%RIP),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2ac650 <@plt_start@+0x440>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
LEA 0x432bb(%RIP),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2ac660 <@plt_start@+0x450>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOV -0x70(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	3	0.25	N/A
MOVSD -0x30(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
ADDSD 0x10(%R12),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2ac670 <@plt_start@+0x460>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0.50	N/A
MOVSD -0x48(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	1	0.50	scal (12.5%)
UCOMISD %XMM0,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
JP 26cfa9 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD $0x68,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	1	0.50	N/A
ADDSD 0x10(%R12),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM0,0x10(%R12)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	1	0.50	scal (12.5%)
JMP 26cf9a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy10sequential8seq_execEJNS2_6LambdaILl0EJEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvEEESI_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSS_EElEENSO_INSQ_INSR_5GroupElPSW_EElEENSO_INSQ_INSR_4ZoneElPS10_EElEEEEENSN_IJEEENS5_9resources2v14HostEJZNK14PopulationSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1K_S1K_RNS1H_5FieldIdJSS_SW_S10_EEERNS1L_IdJSS_EEERNS1L_IdJS10_EEEPdEUlSS_SW_S10_E_EEEEEvOS1F_.omp_outlined+0x2ca>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼void RAJA::internal::StatementExecutor, RAJA::statement::For<2l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > >, RAJA::internal::LoopTypes–	0.30	0.05
▼Loop 1089 - Operators.hpp:334-334 - exec–	0.00	0.00
○Loop 1088 - For.hpp:137-137 - exec	0.30	0.05

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

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

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code