OV - exec - Function std::enable_if<camp::concepts::all_of<camp::concepts::metalib::negate_t<RAJA::internal::loop_data_has_reducers<camp::type::cv::rem_s<camp::type::ref::rem_s<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}>&>::type>::type> > >::value, void>::type 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: std::enable_if<camp::concepts::all_of<camp::concepts::metalib::negate_t<RAJA::internal::lo ...	Module: exec	Source: Collapse.hpp:129-129 [...]	Coverage (incl. loops): 0.15% \| (excl. loops): 0.00%

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp: 187 - 187

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

187:     return sum<IdxLin>((RangeInts == stride_one_dim

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp: 142 - 142

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

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

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp: 46 - 60

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

46: class ReduceOMP

[...]

60: #pragma omp critical(ompReduceCritical)

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 129 - 129

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

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

/home/eoseret/qaas/qaas_runs/178-172-5489/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/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 369 - 369

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

369:     return Ret {lhs} + rhs;

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/detail/reduce.hpp: 78 - 327

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

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

[...]

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

318:         identity {other.identity},

319:         my_data {identity}

[...]

327:     if (parent && my_data != identity)

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/internal/LoopData.hpp: 152 - 152

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

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

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 232 - 291

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

232:     return val - rhs.val;

[...]

291:     return value_type(val + rhs);

0x478360 STP	X29, X30, [SP, #912]!

0x478364 ADD	X29, SP, #0

0x478368 STP	X19, X20, [SP, #16]

0x47836c STP	X25, X26, [SP, #64]

0x478370 LDP	X19, X25, [X0, #8]

0x478374 STP	X21, X22, [SP, #32]

0x478378 LDR	X22, [X25, #56]

0x47837c STP	X23, X24, [SP, #48]

0x478380 STP	D8, D9, [SP, #96]

0x478384 LDR	X23, [X25]

0x478388 CMP	X22, #0

0x47838c LDP	X21, X20, [X25, #32]

0x478390 LDR	X24, [X25, #16]

0x478394 LDR	D9, [X25, #64]

0x478398 STR	X27, [SP, #80]

0x47839c LDR	X27, [X0]

0x4783a0 ADD	X0, X25, #56

0x4783a4 CSEL	X22, X22, X0, #1

0x4783a8 CMP	X27, #0

0x4783ac B.LE	47849c

0x4783b0 CMP	X19, #0

0x4783b4 B.LE	47849c

0x4783b8 BL	410520

0x4783bc MUL	X27, X27, X19

0x4783c0 SBFM	X26, X0, #0, #31

0x4783c4 BL	410420

0x4783c8 SBFM	X4, X0, #0, #31

0x4783cc UDIV	X8, X27, X26

0x4783d0 MSUB	X0, X8, X26, X27

0x4783d4 CMP	X4, X0

0x4783d8 B.CC	478508

0x4783dc MADD	X4, X8, X4, X0

0x4783e0 FMOV	D8, D9

0x4783e4 ADD	X0, X8, X4

0x4783e8 CMP	X4, X0

0x4783ec B.CS	4784a0

0x4783f0 UDIV	X10, X4, X19

0x4783f4 LDR	X5, [X25, #224]

0x4783f8 SUBS	X20, X20, X21

0x4783fc LDP	X12, X11, [X25, #152]

0x478400 SUB	X8, X8, #1

0x478404 MOVZ	X7, #0

0x478408 CNTD	X6, ALL

0x47840c CSEL	X2, X20, XZR, #5

0x478410 PTRUE	P1.B, ALL

0x478414 WHILELO	P2.D, XZR, X2

0x478418 LDR	X13, [X25, #80]

0x47841c ADD	X5, X5, X21,LSL #3

0x478420 LDR	X14, [X25, #120]

0x478424 MSUB	X4, X10, X19, X4

(2137) 0x478428 CMP	X20, #0

(2137) 0x47842c B.LE	478480

(2137) 0x478430 ADD	X3, X10, X23

(2137) 0x478434 ADD	X1, X4, X24

(2137) 0x478438 ORR	P0.B, P2/Z, P2.B, P2.B

(2137) 0x47843c ADD	X9, X13, X3,LSL #3

(2137) 0x478440 MOVZ	X0, #0

(2137) 0x478444 LD1RD	{Z2.D}, P1/Z, [X9]

(2137) 0x478448 MUL	X3, X3, X12

(2137) 0x47844c MADD	X1, X1, X11, X3

(2137) 0x478450 ADD	X1, X1, X21

(2137) 0x478454 ADD	X1, X14, X1,LSL #3

(2137) 0x478458 HINT	#0

(2137) 0x47845c HINT	#0

  (2138) 0x478460 LD1D	{Z1.D}, P0/Z, [X1, X0,LSL #3]

  (2138) 0x478464 LD1D	{Z0.D}, P0/Z, [X5, X0,LSL #3]

  (2138) 0x478468 FMUL	Z1.D, Z2.D, Z1.D

  (2138) 0x47846c ADD	X0, X0, X6

  (2138) 0x478470 FMUL	Z0.D, Z0.D, Z1.D

  (2138) 0x478474 FADDA	D8, P0, D8, Z0.D

  (2138) 0x478478 WHILELO	P0.D, X0, X2

  (2138) 0x47847c B.NE	478460

(2137) 0x478480 CMP	X8, X7

(2137) 0x478484 B.EQ	4784a0

(2137) 0x478488 ADD	X4, X4, #1

(2137) 0x47848c CMP	X19, X4

(2137) 0x478490 B.LE	4784f8

(2137) 0x478494 ADD	X7, X7, #1

(2137) 0x478498 B	478428

0x47849c FMOV	D8, D9

0x4784a0 ADRP	X19,

0x4784a4 LDR	X19, [X19, #3368]

0x4784a8 ORR	X0, XZR, X19

0x4784ac BL	410240

0x4784b0 LDR	D0, [X22, #16]

0x4784b4 ORR	X0, XZR, X19

0x4784b8 FADD	D0, D0, D8

0x4784bc STR	D0, [X22, #16]

0x4784c0 BL	4100e0

0x4784c4 FCMP	D9, D9

0x4784c8 B.EQ	4784d8

0x4784cc LDR	D0, [X22, #16]

0x4784d0 FADD	D0, D0, D9

0x4784d4 STR	D0, [X22, #16]

0x4784d8 LDP	X19, X20, [SP, #16]

0x4784dc LDP	X21, X22, [SP, #32]

0x4784e0 LDP	X23, X24, [SP, #48]

0x4784e4 LDP	X25, X26, [SP, #64]

0x4784e8 LDR	X27, [SP, #80]

0x4784ec LDP	D8, D9, [SP, #96]

0x4784f0 LDP	X29, X30, [SP], #112

0x4784f4 RET

(2137) 0x4784f8 ADD	X10, X10, #1

(2137) 0x4784fc MOVZ	X4, #0

(2137) 0x478500 ADD	X7, X7, #1

(2137) 0x478504 B	478428

0x478508 ADD	X8, X8, #1

0x47850c MOVZ	X0, #0

0x478510 B	4783dc

0x478514 HINT	#0

0x478518 HINT	#0

0x47851c HINT	#0

Coverage (%)	Name	Source Location	Module
►98.40+	omp_fulfill_event		libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.60+	GOMP_parallel		libgomp.so.1.0.0
○	void PopulationSdom::operator([...]	tuple.hpp:223	exec
○	Kripke::Kernel::population(Kri[...]	ArchLayout.h:193	exec
○	Kripke::SteadyStateSolver(Krip[...]	SteadyStateSolver.cpp:108	exec
○	main	kripke.cpp:512	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	iostream:74	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 /

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 gcc_0

Source file and lines	Collapse.hpp:129-129
Module	exec

The function is defined in:

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp:187
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp:142
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:46,60
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:129
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp:56-58
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp:369
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/detail/reduce.hpp:78,317-319,327
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/internal/LoopData.hpp:152
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:232,291

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 40.00 to 20.00 cycles (2.00x speedup).

Workaround

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

Vectorization

Your function is not vectorized. Only 35% of vector register length is used (average across all VPU instructions). By fully vectorizing your function, you can lower the cost of an iteration from 40.00 to 30.00 cycles (1.33x speedup).

Details

4% of VPU instructions are used in vector version (process two or more data elements in vector registers):

6% of VPU loads are used in vector version.
11% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
0% of VPU divide and square root instructions are used in vector version.
0% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 40.00 to 10.17 cycles (3.93x speedup).

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: 4 occurrences►
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:46
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:46
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60

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 does not load or store any data.

General properties

nb instructions	79
nb uops	76
loop length	316
used w registers	0
used x registers	24
used b registers	0
used h registers	0
used s registers	1
used d registers	3
used q registers	0
used v registers	0
used z registers	0
nb stack references	14

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	9.50 cycles
front end	9.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	5.50	5.50	8.75	8.75	8.75	8.75	2.00	2.00	2.00	2.00	10.17	9.83	10.00	3.00	3.00
cycles	5.50	5.50	8.75	8.75	8.75	8.75	2.00	2.00	2.00	2.00	10.17	9.83	10.00	3.00	3.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

10.00-40.00

Cycles summary

Front-end	9.50
Dispatch	10.17
DIV/SQRT	10.00-40.00
Overall L1	10.17-40.00

Vectorization ratios

INT

all	4%
load	6%
store	11%
mul	0%
add-sub	0%
fma	0%
other	0%

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

INT+FP

all	4%
load	6%
store	11%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	0%

Vector efficiency ratios

INT

all	36%
load	33%
store	41%
mul	25%
add-sub	25%
fma	25%
other	43%

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

INT+FP

all	35%
load	33%
store	41%
mul	25%
add-sub	25%
fma	25%
div/sqrt	25%
other	41%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 40.00 cycles.

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 478360

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #912]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDP X19, X25, [X0, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDR X22, [X25, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (50.0%)
LDR X23, [X25]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CMP X22, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
LDP X21, X20, [X25, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDR X24, [X25, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR D9, [X25, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
STR X27, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X27, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X0, X25, #56	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CSEL X22, X22, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X27, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LE 47849c <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X19, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LE 47849c <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
BL 410520 <@plt_start@+0x500>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MUL X27, X27, X19	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (25.0%)
SBFM X26, X0, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
BL 410420 <@plt_start@+0x400>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X4, X0, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
UDIV X8, X27, X26	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20	N/A
MSUB X0, X8, X26, X27	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
CMP X4, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CC 478508 <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x1a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MADD X4, X8, X4, X0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
FMOV D8, D9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ADD X0, X8, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X4, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 4784a0 <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x140>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UDIV X10, X4, X19	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20	scal (25.0%)
LDR X5, [X25, #224]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SUBS X20, X20, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
LDP X12, X11, [X25, #152]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
SUB X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X7, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CNTD X6, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CSEL X2, X20, XZR, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
PTRUE P1.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
WHILELO P2.D, XZR, X2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	2	N/A
LDR X13, [X25, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X5, X5, X21,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X14, [X25, #120]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
MSUB X4, X10, X19, X4	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
FMOV D8, D9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ADRP X19, <4df4a0>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X19, [X19, #3368]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
BL 410240 <@plt_start@+0x220>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D0, [X22, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
FADD D0, D0, D8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
STR D0, [X22, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
BL 4100e0 <@plt_start@+0xc0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
FCMP D9, D9	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
B.EQ 4784d8 <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x178>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D0, [X22, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
FADD D0, D0, D9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
STR D0, [X22, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X27, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (50.0%)
LDP X29, X30, [SP], #112	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X0, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 4783dc <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x7c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run gcc_0

Source file and lines	Collapse.hpp:129-129
Module	exec

The function is defined in:

/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp:187
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp:142
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:46,60
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:129
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp:56-58
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp:369
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/detail/reduce.hpp:78,317-319,327
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/internal/LoopData.hpp:152
/home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:232,291

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

4% of VPU instructions are used in vector version (process two or more data elements in vector registers):

6% of VPU loads are used in vector version.
11% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply instructions are used in vector version.
0% of VPU fused multiply-add instructions are used in vector version.
0% of VPU divide and square root instructions are used in vector version.
0% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 40.00 to 10.17 cycles (3.93x speedup).

CALL instructions

Detected function call instructions.

Details

unknown: 4 occurrences►
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:46
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:46
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60
- /home/eoseret/qaas/qaas_runs/178-172-5489/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/reduce.hpp:60

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 does not load or store any data.

General properties

nb instructions	79
nb uops	76
loop length	316
used w registers	0
used x registers	24
used b registers	0
used h registers	0
used s registers	1
used d registers	3
used q registers	0
used v registers	0
used z registers	0
nb stack references	14

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	9.50 cycles
front end	9.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	5.50	5.50	8.75	8.75	8.75	8.75	2.00	2.00	2.00	2.00	10.17	9.83	10.00	3.00	3.00
cycles	5.50	5.50	8.75	8.75	8.75	8.75	2.00	2.00	2.00	2.00	10.17	9.83	10.00	3.00	3.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P7 (128 bits): VPU, ALU, FP store data
P8 (128 bits): VPU, ALU, DIV/SQRT
P9 (128 bits): ALU, VPU
P10 (256 bits): store address, load
P11 (256 bits): store address, load
P12 (256 bits): load
P13 (64 bits): store data
P14 (64 bits): store data

Cycles executing div or sqrt instructions

10.00-40.00

Cycles summary

Front-end	9.50
Dispatch	10.17
DIV/SQRT	10.00-40.00
Overall L1	10.17-40.00

Vectorization ratios

INT

all	4%
load	6%
store	11%
mul	0%
add-sub	0%
fma	0%
other	0%

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

INT+FP

all	4%
load	6%
store	11%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	0%

Vector efficiency ratios

INT

all	36%
load	33%
store	41%
mul	25%
add-sub	25%
fma	25%
other	43%

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

INT+FP

all	35%
load	33%
store	41%
mul	25%
add-sub	25%
fma	25%
div/sqrt	25%
other	41%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 40.00 cycles.

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 478360

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #912]!	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDP X19, X25, [X0, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
LDR X22, [X25, #56]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	vect (50.0%)
LDR X23, [X25]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CMP X22, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
LDP X21, X20, [X25, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDR X24, [X25, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR D9, [X25, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
STR X27, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X27, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X0, X25, #56	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CSEL X22, X22, X0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X27, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LE 47849c <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X19, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LE 47849c <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
BL 410520 <@plt_start@+0x500>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MUL X27, X27, X19	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (25.0%)
SBFM X26, X0, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
BL 410420 <@plt_start@+0x400>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X4, X0, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
UDIV X8, X27, X26	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20	N/A
MSUB X0, X8, X26, X27	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	N/A
CMP X4, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CC 478508 <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x1a8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MADD X4, X8, X4, X0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
FMOV D8, D9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ADD X0, X8, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP X4, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 4784a0 <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x140>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UDIV X10, X4, X19	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-20	5-20	scal (25.0%)
LDR X5, [X25, #224]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SUBS X20, X20, X21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
LDP X12, X11, [X25, #152]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
SUB X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X7, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CNTD X6, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CSEL X2, X20, XZR, #5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
PTRUE P1.B, ALL	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (100.0%)
WHILELO P2.D, XZR, X2	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	3	2	N/A
LDR X13, [X25, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X5, X5, X21,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X14, [X25, #120]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
MSUB X4, X10, X19, X4	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
FMOV D8, D9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ADRP X19, <4df4a0>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LDR X19, [X19, #3368]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
BL 410240 <@plt_start@+0x220>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D0, [X22, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
FADD D0, D0, D8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
STR D0, [X22, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
BL 4100e0 <@plt_start@+0xc0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
FCMP D9, D9	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
B.EQ 4784d8 <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x178>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR D0, [X22, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
FADD D0, D0, D9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
STR D0, [X22, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDR X27, [SP, #80]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDP D8, D9, [SP, #96]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	vect (50.0%)
LDP X29, X30, [SP], #112	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X8, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ X0, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
B 4783dc <_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_EEEEENSt9enable_ifIXsrNS5_8concepts6all_ofIJNS1X_7metalib8negate_tINS0_22loop_data_has_reducersINS5_4type2cv5rem_sINS22_3ref5rem_sIS1F_E4typeEE4typeEEEEEEEE5valueEvE4typeEOS1F_._omp_fn.0+0x7c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A

Name	Coverage (%)	Time (s)
▼std::enable_if–	0.15	0.17
▼Loop 2137 - For.hpp:142-142 - exec–	0.00	0.00
○Loop 2138 - For.hpp:142-142 - exec	0.15	0.17

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Expensive FP math instructions/calls

CALL instructions

Details

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

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

Expensive FP math instructions/calls

CALL instructions

Details

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code