OV - exec - Function revert_kernel(int, int, int, int, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&) [clone .omp

	Function: revert_kernel(int, int, int, int, clover::Buffer2D<double>&, clover::Buffer2D<double>&, cl ...	Module: exec	Source: revert.cpp:34-38 [...]	Coverage (incl. loops): 2.51% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 69 - 69

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

69:   T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; }

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp: 34 - 38

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

34: #pragma omp parallel for simd collapse(2)

35:   for (int j = (y_min + 1); j < (y_max + 2); j++) {

36:     for (int i = (x_min + 1); i < (x_max + 2); i++) {

37:       density1(i, j) = density0(i, j);

38:       energy1(i, j) = energy0(i, j);

0x247450 PUSH	%RBP

0x247451 MOV	%RSP,%RBP

0x247454 PUSH	%R15

0x247456 PUSH	%R14

0x247458 PUSH	%R13

0x24745a PUSH	%R12

0x24745c PUSH	%RBX

0x24745d SUB	$0x68,%RSP

0x247461 MOV	(%RDX),%EBX

0x247463 MOV	(%RCX),%EAX

0x247465 INC	%EBX

0x247467 ADD	$0x2,%EAX

0x24746a SUB	%EBX,%EAX

0x24746c JLE	2476b6

0x247472 MOV	(%R8),%EDX

0x247475 MOV	(%R9),%R13D

0x247478 INC	%EDX

0x24747a ADD	$0x2,%R13D

0x24747e CMP	%EDX,%R13D

0x247481 JLE	2476b6

0x247487 SUB	%EDX,%R13D

0x24748a MOV	%RAX,%R14

0x24748d IMUL	%R13,%R14

0x247491 DEC	%R14

0x247494 MOVQ	$0,-0x68(%RBP)

0x24749c MOV	%R14,-0x40(%RBP)

0x2474a0 MOVQ	$0x1,-0x90(%RBP)

0x2474ab MOVL	$0,-0x48(%RBP)

0x2474b2 MOV	(%RDI),%ESI

0x2474b4 SUB	$0x8,%RSP

0x2474b8 LEA	-0x90(%RBP),%RAX

0x2474bf LEA	0x1794a(%RIP),%RDI

0x2474c6 LEA	-0x48(%RBP),%RCX

0x2474ca LEA	-0x68(%RBP),%R8

0x2474ce MOV	%EDX,-0x30(%RBP)

0x2474d1 LEA	-0x40(%RBP),%R9

0x2474d5 MOV	%ESI,-0x44(%RBP)

0x2474d8 MOV	$0x22,%EDX

0x2474dd PUSH	$0x1

0x2474df PUSH	$0x1

0x2474e1 PUSH	%RAX

0x2474e2 CALL	25ccf0 <@plt_start@+0x530>

0x2474e7 MOV	-0x30(%RBP),%R9D

0x2474eb MOV	%R14,%R8

0x2474ee ADD	$0x20,%RSP

0x2474f2 MOV	-0x40(%RBP),%RAX

0x2474f6 CMP	%R14,%RAX

0x2474f9 CMOVL	%RAX,%R8

0x2474fd MOV	%R8,-0x40(%RBP)

0x247501 MOV	-0x68(%RBP),%RSI

0x247505 CMP	%R8,%RSI

0x247508 JG	2476a7

0x24750e MOV	0x28(%RBP),%RAX

0x247512 MOV	0x20(%RBP),%RCX

0x247516 MOV	0x18(%RBP),%RDX

0x24751a MOV	0x10(%RBP),%RDI

0x24751e MOV	(%RDX),%R10

0x247521 MOV	%R10,-0x38(%RBP)

0x247525 MOV	0x10(%RDX),%RDX

0x247529 MOV	%RDX,-0x60(%RBP)

0x24752d MOV	(%RDI),%R14

0x247530 MOV	0x10(%RDI),%RDX

0x247534 MOV	%RDX,-0x58(%RBP)

0x247538 MOV	(%RAX),%R15

0x24753b MOV	0x10(%RAX),%RAX

0x24753f MOV	%RAX,-0x50(%RBP)

0x247543 MOV	(%RCX),%R10

0x247546 MOV	0x10(%RCX),%R12

0x24754a MOV	%R8,%RAX

0x24754d SUB	%RSI,%RAX

0x247550 INC	%RAX

0x247553 CMP	$0x2,%RAX

0x247557 JAE	247565

0x247559 MOV	%RSI,%RCX

0x24755c MOV	-0x38(%RBP),%RDI

0x247560 JMP	247738

0x247565 MOV	%R8,-0x80(%RBP)

0x247569 MOV	%EBX,-0x2c(%RBP)

0x24756c MOV	%RAX,-0x78(%RBP)

0x247570 MOV	%RAX,%R9

0x247573 AND	$-0x2,%R9

0x247577 LEA	(%RSI,%R9,1),%RCX

0x24757b MOV	%R9,-0x70(%RBP)

0x24757f MOV	%R14,-0x88(%RBP)

0x247586 JMP	247644

0x24758b NOPL	(%RAX,%RAX,1)

(285) 0x247590 CQTO

(285) 0x247592 IDIV	%R13

(285) 0x247595 ADD	%EBX,%EDI

(285) 0x247597 ADD	%EBX,%EAX

(285) 0x247599 MOV	-0x30(%RBP),%EBX

(285) 0x24759c ADD	%EBX,%R8D

(285) 0x24759f ADD	%EBX,%EDX

(285) 0x2475a1 MOVSXD	%R8D,%R8

(285) 0x2475a4 MOVSXD	%EDX,%RDX

(285) 0x2475a7 MOVSXD	%EDI,%RDI

(285) 0x2475aa CLTQ

(285) 0x2475ac MOV	-0x38(%RBP),%R11

(285) 0x2475b0 MOV	%R11,%RBX

(285) 0x2475b3 IMUL	%RDI,%RBX

(285) 0x2475b7 ADD	%R8,%RBX

(285) 0x2475ba MOV	-0x60(%RBP),%R14

(285) 0x2475be MOVSD	(%R14,%RBX,8),%XMM0

(285) 0x2475c4 IMUL	%RAX,%R11

(285) 0x2475c8 ADD	%RDX,%R11

(285) 0x2475cb MOVSD	(%R14,%R11,8),%XMM1

(285) 0x2475d1 MOV	-0x88(%RBP),%R14

(285) 0x2475d8 MOV	%R14,%RBX

(285) 0x2475db IMUL	%RDI,%RBX

(285) 0x2475df ADD	%R8,%RBX

(285) 0x2475e2 MOV	-0x58(%RBP),%R11

(285) 0x2475e6 MOVSD	%XMM0,(%R11,%RBX,8)

(285) 0x2475ec MOV	%R14,%RBX

(285) 0x2475ef IMUL	%RAX,%RBX

(285) 0x2475f3 ADD	%RDX,%RBX

(285) 0x2475f6 MOVSD	%XMM1,(%R11,%RBX,8)

(285) 0x2475fc MOV	%R15,%RBX

(285) 0x2475ff IMUL	%RDI,%RBX

(285) 0x247603 ADD	%R8,%RBX

(285) 0x247606 MOV	-0x50(%RBP),%R11

(285) 0x24760a MOVSD	(%R11,%RBX,8),%XMM0

(285) 0x247610 MOV	%R15,%RBX

(285) 0x247613 IMUL	%RAX,%RBX

(285) 0x247617 ADD	%RDX,%RBX

(285) 0x24761a MOVSD	(%R11,%RBX,8),%XMM1

(285) 0x247620 IMUL	%R10,%RDI

(285) 0x247624 ADD	%R8,%RDI

(285) 0x247627 IMUL	%R10,%RAX

(285) 0x24762b ADD	%RDX,%RAX

(285) 0x24762e MOVSD	%XMM0,(%R12,%RDI,8)

(285) 0x247634 MOVSD	%XMM1,(%R12,%RAX,8)

(285) 0x24763a ADD	$0x2,%RSI

(285) 0x24763e ADD	$-0x2,%R9

(285) 0x247642 JE	24768a

(285) 0x247644 MOV	%RSI,%RAX

(285) 0x247647 SHR	$0x20,%RAX

(285) 0x24764b JE	247660

(285) 0x24764d MOV	%RSI,%RAX

(285) 0x247650 CQTO

(285) 0x247652 IDIV	%R13

(285) 0x247655 MOV	%RDX,%R8

(285) 0x247658 MOV	%RAX,%RDI

(285) 0x24765b JMP	24766c

0x24765d NOPL	(%RAX)

(285) 0x247660 MOV	%ESI,%EAX

(285) 0x247662 XOR	%EDX,%EDX

(285) 0x247664 DIV	%R13D

(285) 0x247667 MOV	%EDX,%R8D

(285) 0x24766a MOV	%EAX,%EDI

(285) 0x24766c MOV	-0x2c(%RBP),%EBX

(285) 0x24766f LEA	0x1(%RSI),%RAX

(285) 0x247673 MOV	%RAX,%RDX

(285) 0x247676 SHR	$0x20,%RDX

(285) 0x24767a JNE	247590

(285) 0x247680 XOR	%EDX,%EDX

(285) 0x247682 DIV	%R13D

(285) 0x247685 JMP	247595

0x24768a MOV	-0x70(%RBP),%RAX

0x24768e CMP	%RAX,-0x78(%RBP)

0x247692 MOV	-0x2c(%RBP),%EBX

0x247695 MOV	-0x80(%RBP),%R8

0x247699 MOV	-0x30(%RBP),%R9D

0x24769d MOV	-0x38(%RBP),%RDI

0x2476a1 JNE	247738

0x2476a7 LEA	0x1777a(%RIP),%RDI

0x2476ae MOV	-0x44(%RBP),%ESI

0x2476b1 CALL	25cd00 <@plt_start@+0x540>

0x2476b6 ADD	$0x68,%RSP

0x2476ba POP	%RBX

0x2476bb POP	%R12

0x2476bd POP	%R13

0x2476bf POP	%R14

0x2476c1 POP	%R15

0x2476c3 POP	%RBP

0x2476c4 RET

0x2476c5 NOPW	%CS:(%RAX,%RAX,1)

(284) 0x2476d0 MOV	%RCX,%RAX

(284) 0x2476d3 CQTO

(284) 0x2476d5 IDIV	%R13

(284) 0x2476d8 ADD	%EBX,%EAX

(284) 0x2476da ADD	%R9D,%EDX

(284) 0x2476dd MOVSXD	%EDX,%RDX

(284) 0x2476e0 CLTQ

(284) 0x2476e2 MOV	%RDI,%RSI

(284) 0x2476e5 IMUL	%RAX,%RSI

(284) 0x2476e9 ADD	%RDX,%RSI

(284) 0x2476ec MOV	-0x60(%RBP),%R11

(284) 0x2476f0 MOVSD	(%R11,%RSI,8),%XMM0

(284) 0x2476f6 MOV	%R14,%RSI

(284) 0x2476f9 IMUL	%RAX,%RSI

(284) 0x2476fd ADD	%RDX,%RSI

(284) 0x247700 MOV	-0x58(%RBP),%R11

(284) 0x247704 MOVSD	%XMM0,(%R11,%RSI,8)

(284) 0x24770a MOV	%R15,%RSI

(284) 0x24770d IMUL	%RAX,%RSI

(284) 0x247711 ADD	%RDX,%RSI

(284) 0x247714 MOV	-0x50(%RBP),%R11

(284) 0x247718 MOVSD	(%R11,%RSI,8),%XMM0

(284) 0x24771e IMUL	%R10,%RAX

(284) 0x247722 ADD	%RDX,%RAX

(284) 0x247725 MOVSD	%XMM0,(%R12,%RAX,8)

(284) 0x24772b CMP	%R8,%RCX

(284) 0x24772e LEA	0x1(%RCX),%RCX

(284) 0x247732 JGE	2476a7

(284) 0x247738 MOV	%RCX,%RAX

(284) 0x24773b SHR	$0x20,%RAX

(284) 0x24773f JNE	2476d0

(284) 0x247741 MOV	%ECX,%EAX

(284) 0x247743 XOR	%EDX,%EDX

(284) 0x247745 DIV	%R13D

(284) 0x247748 JMP	2476d8

0x24774a NOPW	(%RAX,%RAX,1)

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	revert.cpp:34-38
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:34-38

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 10% 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 13.25 to 0.99 cycles (13.38x 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): 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: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:34
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:34

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.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:35

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 188 bytes. The binary function is storing 112 bytes.

General properties

nb instructions	107
nb uops	106
loop length	399
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	19

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.25 cycles
front end	13.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	13.25
Dispatch	11.50
Overall L1	13.25

Vectorization ratios

all	0%
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	0%

Vector efficiency ratios

all	10%
load	10%
store	10%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 13.25 cycles. At this rate:

5% of peak load performance is reached (14.19 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.45 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 13.25 to 11.50 cycles (1.15x speedup).

ASM code

In the binary file, the address of the function is: 247450

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	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	0.17	N/A
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 %RBX	1	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	1	0.17	N/A
MOV (%RDX),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JLE 2476b6 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x2,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %EDX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 2476b6 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %EDX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
IMUL %R13,%R14	1	0.33	0.33	0.33	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	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	4	0.50	scal (6.3%)
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	4	0.50	scal (6.3%)
MOVL $0,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	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	1	0.25	N/A
LEA 0x1794a(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x48(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	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	1	0.25	N/A
MOV %EDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
LEA -0x40(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x44(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	1	0.17	N/A
PUSH $0x1	1	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	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R14,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	1	0.17	scal (12.5%)
CMOVL %RAX,%R8	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R8,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x68(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R8,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 2476a7 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x257>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x28(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R10,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RDI),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RAX),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RCX),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%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 247565 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x115>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 247738 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R9,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R9,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 247644 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x1f4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX,%RAX,1)	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	0.09	N/A
MOV -0x70(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x78(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0x2c(%RBP),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV -0x80(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 247738 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x1777a(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x44(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x68,%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 %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
POP %RBP	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
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	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	revert.cpp:34-38
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:34-38

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): 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: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:34
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:34

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.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/revert.cpp:35

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 188 bytes. The binary function is storing 112 bytes.

General properties

nb instructions	107
nb uops	106
loop length	399
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	19

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.25 cycles
front end	13.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	13.25
Dispatch	11.50
Overall L1	13.25

Vectorization ratios

all	0%
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	0%

Vector efficiency ratios

all	10%
load	10%
store	10%
mul	12%
add-sub	7%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 13.25 cycles. At this rate:

5% of peak load performance is reached (14.19 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.45 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: 247450

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	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	0.17	N/A
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 %RBX	1	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	1	0.17	N/A
MOV (%RDX),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JLE 2476b6 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x2,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %EDX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 2476b6 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %EDX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
IMUL %R13,%R14	1	0.33	0.33	0.33	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	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	4	0.50	scal (6.3%)
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	4	0.50	scal (6.3%)
MOVL $0,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	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	1	0.25	N/A
LEA 0x1794a(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x48(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	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	1	0.25	N/A
MOV %EDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
LEA -0x40(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x44(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	1	0.17	N/A
PUSH $0x1	1	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	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R14,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	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	1	0.17	scal (12.5%)
CMOVL %RAX,%R8	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R8,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x68(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R8,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 2476a7 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x257>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x28(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R10,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RDI),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RAX),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RCX),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R8,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%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 247565 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x115>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 247738 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R9,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R9,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 247644 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x1f4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX,%RAX,1)	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	0.09	N/A
MOV -0x70(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x78(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0x2c(%RBP),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV -0x80(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 247738 <_Z13revert_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x1777a(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x44(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x68,%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 %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
POP %RBP	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
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼revert_kernel(int, int, int, int, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [clone .omp_outlined]–	2.51	0.98
○Loop 285 - revert.cpp:35-38 - exec	2.51	0.98
○Loop 284 - revert.cpp:35-38 - exec	0.00	0.00

Report Configuration

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

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

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