OV - exec - Function void RAJA::internal::StatementExecutor<RAJA::statement::Collapse<RAJA::omp_parallel_collapse_exec, camp::int_seq<long, 0l, 2l>, RAJA::statement::For<1l, RAJA::policy::sequential::seq_exec, RAJA::statement::For<3l, RAJA::policy::sequential::seq_exec, RAJA::statement::Lambda<0l> > > >, RAJA::internal::LoopTypes<camp::list<void, void, void, void>, camp::list<void, void, void, void> > >::exec<RAJA::internal::LoopData<camp::tuple<RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Moment, long, Kripke::Moment*>, long>, 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, LTimesSdom::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::Set const&, Kripke::Core::Field<double, Kripke::Direction, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Direction>&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&>(RAJA::internal::LoopData<camp::tuple<RAJA::Span<RAJA::Iterators::numeric_iterator<Kripke::Moment, long, Kripke::Moment*>, long>, 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, LTimesSdom::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::Set const&, Kripke::Core::Field<double, Kripke::Direction, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Direction>&) const::{lambda(Kripke::Moment, Kripke::Direction, Kripke::Group, Kripke::Zone)#1}>&) [clone ._omp

	Function: void RAJA::internal::StatementExecutor<RAJA::statement::Collapse<RAJA::omp_parallel_collap ...	Module: exec	Source: :0-0	Coverage (incl. loops): 3.67% \| (excl. loops): 0.00%

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

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

0x473200 PUSH	%R15

0x473202 PUSH	%R14

0x473204 PUSH	%R13

0x473206 PUSH	%R12

0x473208 PUSH	%RBP

0x473209 PUSH	%RBX

0x47320a SUB	$0xb8,%RSP

0x473211 MOV	0x8(%RDI),%R15

0x473215 MOV	(%RDI),%RBP

0x473218 MOV	%R15,0x38(%RSP)

0x47321d TEST	%RBP,%RBP

0x473220 JLE	473552

0x473226 TEST	%R15,%R15

0x473229 JLE	473552

0x47322f MOV	%RDI,%R12

0x473232 CALL	403500 <omp_get_num_threads@plt>

0x473237 MOVSXD	%EAX,%RBX

0x47323a CALL	403440 <omp_get_thread_num@plt>

0x47323f XOR	%EDX,%EDX

0x473241 MOVSXD	%EAX,%RCX

0x473244 MOV	%R15,%RAX

0x473247 IMUL	%RBP,%RAX

0x47324b DIV	%RBX

0x47324e MOV	%RAX,%RSI

0x473251 CMP	%RDX,%RCX

0x473254 JB	4735e3

0x47325a IMUL	%RSI,%RCX

0x47325e LEA	(%RCX,%RDX,1),%RAX

0x473262 LEA	(%RSI,%RAX,1),%RDX

0x473266 CMP	%RDX,%RAX

0x473269 JAE	473552

0x47326f XOR	%EDX,%EDX

0x473271 MOV	0x10(%R12),%RDI

0x473276 DIVQ	0x38(%RSP)

0x47327b MOV	0x10(%RDI),%RCX

0x47327f MOV	0x30(%RDI),%R8

0x473283 MOV	0x38(%RDI),%R11

0x473287 MOV	%R8,0x48(%RSP)

0x47328c SUB	%R8,%R11

0x47328f MOV	%RAX,0x30(%RSP)

0x473294 MOV	0x18(%RDI),%RAX

0x473298 MOV	%RDX,%RBP

0x47329b XOR	%EDX,%EDX

0x47329d SUB	%RCX,%RAX

0x4732a0 TEST	%RAX,%RAX

0x4732a3 CMOVNS	%RAX,%RDX

0x4732a7 MOV	%RDX,(%RSP)

0x4732ab JLE	473552

0x4732b1 TEST	%R11,%R11

0x4732b4 JLE	473552

0x4732ba MOV	0x20(%RDI),%RBX

0x4732be MOV	0xd0(%RDI),%RAX

0x4732c5 MOVQ	$0,0x28(%RSP)

0x4732ce MOV	(%RDI),%RDX

0x4732d1 MOV	0x118(%RDI),%R14

0x4732d8 MOV	%RBX,0x50(%RSP)

0x4732dd MOV	0x48(%RDI),%RBX

0x4732e1 MOV	%RDX,0xa8(%RSP)

0x4732e9 LEA	(,%R14,8),%R15

0x4732f1 MOV	%RBX,0x78(%RSP)

0x4732f6 MOV	0x68(%RDI),%RBX

0x4732fa MOV	%RBX,0x80(%RSP)

0x473302 MOV	0x70(%RDI),%RBX

0x473306 MOV	%RBX,0x58(%RSP)

0x47330b MOV	0xb0(%RDI),%RBX

0x473312 MOV	%RBX,0x60(%RSP)

0x473317 MOV	0xf8(%RDI),%RBX

0x47331e MOV	%RBX,0x10(%RSP)

0x473323 MOV	0x120(%RDI),%RBX

0x47332a MOV	%RAX,%RDI

0x47332d IMUL	%RCX,%RDI

0x473331 MOV	%RBX,0x70(%RSP)

0x473336 IMUL	%R14,%RCX

0x47333a LEA	-0x1(%RSI),%RBX

0x47333e MOV	%RBX,0x98(%RSP)

0x473346 LEA	(,%RAX,8),%RBX

0x47334e MOV	0x30(%RSP),%RAX

0x473353 LEA	(,%R11,8),%RSI

0x47335b MOV	%RDI,0x90(%RSP)

0x473363 ADD	%RDX,%RAX

0x473366 MOV	%RCX,0x68(%RSP)

0x47336b MOV	%R11,%RCX

0x47336e MOV	%RAX,0x40(%RSP)

0x473373 LEA	0x1(%RDX,%RDI,1),%RAX

0x473378 SHR	$0x1,%RCX

0x47337b MOV	%RAX,0xa0(%RSP)

0x473383 MOV	%R11,%RAX

0x473386 SAL	$0x4,%RCX

0x47338a AND	$0x1,%EAX

0x47338d MOV	%RSI,0x88(%RSP)

0x473395 MOV	%RAX,0x8(%RSP)

0x47339a MOV	%R11,%RAX

0x47339d AND	$-0x2,%RAX

0x4733a1 ADD	%R8,%RAX

0x4733a4 MOV	%RAX,0x18(%RSP)

0x4733a9 NOPL	(%RAX)

(1819) 0x4733b0 MOV	0x50(%RSP),%RAX

(1819) 0x4733b5 MOV	0x40(%RSP),%RDI

(1819) 0x4733ba MOV	0x80(%RSP),%R10

(1819) 0x4733c2 MOV	0x48(%RSP),%R9

(1819) 0x4733c7 LEA	(%RAX,%RBP,1),%R8

(1819) 0x4733cb MOV	0x58(%RSP),%RAX

(1819) 0x4733d0 MOV	0x10(%RSP),%RDX

(1819) 0x4733d5 IMUL	%RDI,%R10

(1819) 0x4733d9 MOV	0x30(%RSP),%R12

(1819) 0x4733de MOV	0x78(%RSP),%R13

(1819) 0x4733e3 IMUL	%R8,%RAX

(1819) 0x4733e7 ADD	%RAX,%R10

(1819) 0x4733ea MOV	0x90(%RSP),%RAX

(1819) 0x4733f2 ADD	%RDI,%RAX

(1819) 0x4733f5 MOV	0x60(%RSP),%RDI

(1819) 0x4733fa LEA	(%RDI,%RAX,8),%RSI

(1819) 0x4733fe MOV	0x70(%RSP),%RAX

(1819) 0x473403 IMUL	%RAX,%R8

(1819) 0x473407 MOV	0x68(%RSP),%RAX

(1819) 0x47340c ADD	%RAX,%R8

(1819) 0x47340f LEA	(%R8,%R9,1),%RAX

(1819) 0x473413 ADD	%R10,%R9

(1819) 0x473416 LEA	(%RDX,%RAX,8),%RDX

(1819) 0x47341a MOV	0xa0(%RSP),%RAX

(1819) 0x473422 SAL	$0x3,%R9

(1819) 0x473426 ADD	%R12,%RAX

(1819) 0x473429 MOV	0x88(%RSP),%R12

(1819) 0x473431 LEA	(%RDI,%RAX,8),%RDI

(1819) 0x473435 LEA	(%R13,%R9,1),%RAX

(1819) 0x47343a MOV	%RAX,0x20(%RSP)

(1819) 0x47343f MOV	0x18(%RSP),%RAX

(1819) 0x473444 ADD	%R12,%R9

(1819) 0x473447 LEA	(%R13,%R9,1),%R12

(1819) 0x47344c XOR	%R9D,%R9D

(1819) 0x47344f ADD	%RAX,%R10

(1819) 0x473452 MOV	0x20(%RSP),%RAX

(1819) 0x473457 LEA	(%R13,%R10,8),%R13

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

  (1818) 0x473460 JLE	473569

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

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

    (1821) 0x47346f CMP	%R12,%R10

    (1821) 0x473472 SETAE	%BPL

    (1821) 0x473476 CMP	%RDI,%RAX

    (1821) 0x473479 SETAE	%R10B

    (1821) 0x47347d OR	%BPL,%R10B

    (1821) 0x473480 JE	473564

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

    (1821) 0x47348a CMP	%R10,%RAX

    (1821) 0x47348d JE	473564

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

    (1821) 0x473497 XOR	%R10D,%R10D

    (1821) 0x47349a UNPCKLPD	%XMM1,%XMM1

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

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

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

    (1821) 0x4734bf NOP

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

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

      (1820) 0x4734cc MULPD	%XMM1,%XMM0

      (1820) 0x4734d0 ADDPD	%XMM2,%XMM0

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

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

      (1820) 0x4734dd CMP	%R10,%RCX

      (1820) 0x4734e0 JNE	4734c0

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

    (1821) 0x4734e8 JE	47350e

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

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

    (1821) 0x4734f4 ADD	%R8,%R10

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

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

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

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

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

    (1821) 0x473512 ADD	%RBX,%RSI

    (1821) 0x473515 ADD	%R14,%R8

    (1821) 0x473518 ADD	%R15,%RDX

    (1821) 0x47351b ADD	%RBX,%RDI

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

    (1821) 0x473522 JG	47346b

(1819) 0x473528 MOV	0x20(%RSP),%RBP

(1819) 0x47352d MOV	0x98(%RSP),%RSI

(1819) 0x473535 CMP	%RSI,0x28(%RSP)

(1819) 0x47353a JE	473552

(1819) 0x47353c ADD	$0x1,%RBP

(1819) 0x473540 CMP	%RBP,0x38(%RSP)

(1819) 0x473545 JLE	4735c1

(1819) 0x473547 ADDQ	$0x1,0x28(%RSP)

(1819) 0x47354d JMP	4733b0

0x473552 ADD	$0xb8,%RSP

0x473559 POP	%RBX

0x47355a POP	%RBP

0x47355b POP	%R12

0x47355d POP	%R13

0x47355f POP	%R14

0x473561 POP	%R15

0x473563 RET

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

  (1818) 0x473569 XOR	%R10D,%R10D

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

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

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

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

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

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

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

    (1817) 0x47359a CMP	%R10,%R11

    (1817) 0x47359d JG	473580

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

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

  (1818) 0x4735a7 ADD	%RBX,%RSI

  (1818) 0x4735aa ADD	%R14,%R8

  (1818) 0x4735ad ADD	%R15,%RDX

  (1818) 0x4735b0 ADD	%RBX,%RDI

  (1818) 0x4735b3 CMP	%R10,%R9

  (1818) 0x4735b6 JL	47345c

(1819) 0x4735bc JMP	47352d

(1819) 0x4735c1 ADDQ	$0x1,0x30(%RSP)

(1819) 0x4735c7 MOV	0xa8(%RSP),%RSI

(1819) 0x4735cf XOR	%EBP,%EBP

(1819) 0x4735d1 MOV	0x30(%RSP),%RAX

(1819) 0x4735d6 ADD	%RSI,%RAX

(1819) 0x4735d9 MOV	%RAX,0x40(%RSP)

(1819) 0x4735de JMP	473547

0x4735e3 ADD	$0x1,%RSI

0x4735e7 XOR	%EDX,%EDX

0x4735e9 JMP	47325a

0x4735ee XCHG	%AX,%AX

Coverage (%)	Name	Source Location	Module
►97.07+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.64+	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0
○	void Kripke::DispatchHelper<Kr[...]		exec
○	Kripke::Kernel::LTimes(Kripke:[...]		exec
○	Kripke::SteadyStateSolver(Krip[...]		exec
○	main		exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		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
Module	exec

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is 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 24.00 to 3.00 cycles (8.00x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized 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)

Execution units bottlenecks

Performance is limited by execution of divide and square root operations (the divide/square root unit is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 24.00 to 13.88 cycles (1.73x speedup).

Workaround

Reduce the number of division or square root instructions:

If denominator is constant over iterations, use reciprocal (replace x/y with x*(1/y)). Check precision impact.

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 24.00 to 13.63 cycles (1.76x 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.

omp_get_num_threads@plt: 1 occurrences►
omp_get_thread_num@plt: 1 occurrences►

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.

DIV: 2 occurrences►
LEA: 1 occurrences►

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 152 bytes. The binary function is storing 168 bytes.

General properties

nb instructions	108
nb uops	111
loop length	463
used x86 registers	14
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	21

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.88 cycles
front end	13.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	7.50	7.50	7.50	7.50	7.50	7.50	10.75	10.75	10.75	10.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	7.50	7.50	7.50	7.50	7.50	7.50	10.75	10.75	10.75	10.75	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

14.00-24.00

Cycles summary

Front-end	13.88
Dispatch	10.75
DIV/SQRT	14.00-24.00
Overall L1	14.00-24.00

Vectorization ratios

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

Vector efficiency ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.00 cycles. At this rate:

2% of peak load performance is reached (6.33 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.00 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 473200

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %R15	1	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	1	0.50	N/A
PUSH %R13	1	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	1	0.50	N/A
PUSH %RBP	1	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	1	0.50	N/A
SUB $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x8(%RDI),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RDI),%RBP	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R15,0x38(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
TEST %RBP,%RBP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
TEST %R15,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 403500 <omp_get_num_threads@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOVSXD %EAX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CALL 403440 <omp_get_thread_num@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOVSXD %EAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R15,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RBP,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
DIV %RBX	2	0	0	0	2	0	0	0	0	0	0	10-22	7-12	scal (12.5%)
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JB 4735e3 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x3e3>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
IMUL %RSI,%RCX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RCX,%RDX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA (%RSI,%RAX,1),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CMP %RDX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV 0x10(%R12),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
DIVQ 0x38(%RSP)	2	0	0	0	2	0	0	0.25	0.25	0.25	0.25	10-22	7-12	scal (12.5%)
MOV 0x10(%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x30(%RDI),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x38(%RDI),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,0x48(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
SUB %R8,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,0x30(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x18(%RDI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
SUB %RCX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVNS %RAX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RDX,(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
TEST %R11,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x20(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xd0(%RDI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOVQ $0,0x28(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x118(%RDI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RBX,0x50(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x48(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RDX,0xa8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (,%R14,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x68(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x80(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x70(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x58(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xb0(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x60(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xf8(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x120(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RCX,%RDI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %R14,%RCX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
LEA -0x1(%RSI),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RBX,0x98(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (,%RAX,8),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x30(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (,%R11,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RDI,0x90(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
ADD %RDX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,0x68(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,0x40(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA 0x1(%RDX,%RDI,1),%RAX	2	0	0	0.50	0.50	0	0	0.25	0.25	0.25	0.25	2	0.50	N/A
SHR $0x1,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %RAX,0xa0(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
AND $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RSI,0x88(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,0x18(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R12	1	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	1	0.33	N/A
POP %R14	1	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	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
ADD $0x1,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 47325a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x5a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	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 gcc_0

Source file and lines
Module	exec

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

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)

Execution units bottlenecks

Workaround

Reduce the number of division or square root instructions:

If denominator is constant over iterations, use reciprocal (replace x/y with x*(1/y)). Check precision impact.

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 24.00 to 13.63 cycles (1.76x speedup).

CALL instructions

Detected function call instructions.

Details

omp_get_num_threads@plt: 1 occurrences►
omp_get_thread_num@plt: 1 occurrences►

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.

DIV: 2 occurrences►
LEA: 1 occurrences►

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 152 bytes. The binary function is storing 168 bytes.

General properties

nb instructions	108
nb uops	111
loop length	463
used x86 registers	14
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	21

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.88 cycles
front end	13.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	7.50	7.50	7.50	7.50	7.50	7.50	10.75	10.75	10.75	10.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	7.50	7.50	7.50	7.50	7.50	7.50	10.75	10.75	10.75	10.75	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

14.00-24.00

Cycles summary

Front-end	13.88
Dispatch	10.75
DIV/SQRT	14.00-24.00
Overall L1	14.00-24.00

Vectorization ratios

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

Vector efficiency ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.00 cycles. At this rate:

2% of peak load performance is reached (6.33 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (7.00 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 473200

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %R15	1	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	1	0.50	N/A
PUSH %R13	1	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	1	0.50	N/A
PUSH %RBP	1	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	1	0.50	N/A
SUB $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV 0x8(%RDI),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RDI),%RBP	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R15,0x38(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
TEST %RBP,%RBP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
TEST %R15,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 403500 <omp_get_num_threads@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOVSXD %EAX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CALL 403440 <omp_get_thread_num@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOVSXD %EAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R15,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RBP,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
DIV %RBX	2	0	0	0	2	0	0	0	0	0	0	10-22	7-12	scal (12.5%)
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JB 4735e3 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x3e3>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
IMUL %RSI,%RCX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
LEA (%RCX,%RDX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA (%RSI,%RAX,1),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
CMP %RDX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV 0x10(%R12),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
DIVQ 0x38(%RSP)	2	0	0	0	2	0	0	0.25	0.25	0.25	0.25	10-22	7-12	scal (12.5%)
MOV 0x10(%RDI),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x30(%RDI),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x38(%RDI),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R8,0x48(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
SUB %R8,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,0x30(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x18(%RDI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
SUB %RCX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVNS %RAX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RDX,(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
TEST %R11,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JLE 473552 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x352>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x20(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xd0(%RDI),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOVQ $0,0x28(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x118(%RDI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RBX,0x50(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x48(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RDX,0xa8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (,%R14,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RBX,0x78(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x68(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x80(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x70(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x58(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xb0(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x60(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xf8(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RBX,0x10(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x120(%RDI),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RCX,%RDI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RBX,0x70(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %R14,%RCX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
LEA -0x1(%RSI),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RBX,0x98(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (,%RAX,8),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV 0x30(%RSP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (,%R11,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RDI,0x90(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
ADD %RDX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,0x68(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,0x40(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA 0x1(%RDX,%RDI,1),%RAX	2	0	0	0.50	0.50	0	0	0.25	0.25	0.25	0.25	2	0.50	N/A
SHR $0x1,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %RAX,0xa0(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
AND $0x1,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RSI,0x88(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,0x8(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,0x18(%RSP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R12	1	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	1	0.33	N/A
POP %R14	1	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	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
ADD $0x1,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 47325a <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy10sequential8seq_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEENS0_9LoopTypesINS5_4listIJvvvvEEESJ_EEE4execIRNS0_8LoopDataINS5_5tupleIJNS_4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPST_EElEENSP_INSR_INSS_9DirectionElPSX_EElEENSP_INSR_INSS_5GroupElPS11_EElEENSP_INSR_INSS_4ZoneElPS15_EElEEEEENSO_IJEEENS5_9resources2v14HostEJZNK10LTimesSdomclINSS_11ArchLayoutTINSS_12ArchT_OpenMPENSS_11LayoutT_DGZEEEEEvT_NSS_6SdomIdERKNSS_4Core3SetES1P_S1P_S1P_RNS1M_5FieldIdJSX_S11_S15_EEERNS1Q_IdJST_S11_S15_EEERNS1Q_IdJST_SX_EEEEUlST_SX_S11_S15_E_EEEEEvOS1K_._omp_fn.0+0x5a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
XCHG %AX,%AX	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<1l, RAJA::policy::sequential::seq_exec, RAJA::statement::For<3l, RAJA::policy::sequential::seq_exec, RAJA::...–	3.67	0.40
▼Loop 1819 - - exec–	0.01	0.01
▼Loop 1818 - - exec–	0.00	0.00
▼Loop 1821 - - exec–	0.05	0.01
○Loop 1820 - - exec	3.61	0.37
○Loop 1817 - - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Expensive FP math instructions/calls

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Expensive FP math instructions/calls

CALL instructions

Details

Complex instructions

Details

Type of elements and instruction set

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