OV - exec - Function main._omp

	Function: main._omp_fn.6	Module: exec	Source: stream.c:342-344	Coverage (incl. loops): 27.69% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c: 342 - 344

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

342: #pragma omp parallel for

343: 	for (j=0; j<STREAM_ARRAY_SIZE; j++)

344: 	    c[j] = a[j]+b[j];

0x402510 PUSH	%RBP

0x402511 MOV	$0x401060,%RAX

0x40251b MOV	%RSP,%RBP

0x40251e PUSH	%R14

0x402520 PUSH	%R13

0x402522 PUSH	%R12

0x402524 PUSH	%RBX

0x402525 MOV	$0x401030,%R12

0x40252f AND	$-0x40,%RSP

0x402533 CALL	%RAX

0x402535 MOVSXD	%EAX,%RBX

0x402538 CALL	%R12

0x40253b MOVSXD	%EAX,%RCX

0x40253e MOV	$0x33450000,%EAX

0x402543 CQTO

0x402545 IDIV	%RBX

0x402548 CMP	%RDX,%RCX

0x40254b JL	402830

0x402551 IMUL	%RAX,%RCX

0x402555 ADD	%RCX,%RDX

0x402558 LEA	(%RAX,%RDX,1),%R10

0x40255c CMP	%R10,%RDX

0x40255f JGE	40280f

0x402565 LEA	-0x1(%RAX),%RSI

0x402569 MOV	%RDX,%RBX

0x40256c CMP	$0x6,%RSI

0x402570 JBE	402840

0x402576 MOV	%RAX,%R11

0x402579 LEA	(,%RDX,8),%RSI

0x402581 MOV	$0x334907100,%R12

0x40258b MOV	$0x19a687100,%R13

0x402595 SHR	$0x3,%R11

0x402599 SAL	$0x6,%R11

0x40259d LEA	-0x40(%R11),%R9

0x4025a1 MOV	$0x407100,%R14

0x4025ab LEA	(%R12,%RSI,1),%RDI

0x4025af LEA	(%R13,%RSI,1),%R8

0x4025b4 SHR	$0x6,%R9

0x4025b8 INC	%R9

0x4025bb ADD	%R14,%RSI

0x4025be XOR	%ECX,%ECX

0x4025c0 AND	$0x7,%R9D

0x4025c4 JE	4026ac

0x4025ca CMP	$0x1,%R9

0x4025ce JE	40268a

0x4025d4 CMP	$0x2,%R9

0x4025d8 JE	402671

0x4025de CMP	$0x3,%R9

0x4025e2 JE	402658

0x4025e4 CMP	$0x4,%R9

0x4025e8 JE	40263f

0x4025ea CMP	$0x5,%R9

0x4025ee JE	402626

0x4025f0 CMP	$0x6,%R9

0x4025f4 JE	40260d

0x4025f6 VMOVUPD	(%R8),%ZMM0

0x4025fc VADDPD	(%RDI),%ZMM0,%ZMM1

0x402602 MOV	$0x40,%ECX

0x402607 VMOVUPD	%ZMM1,(%RSI)

0x40260d VMOVUPD	(%R8,%RCX,1),%ZMM2

0x402614 VADDPD	(%RDI,%RCX,1),%ZMM2,%ZMM3

0x40261b VMOVUPD	%ZMM3,(%RSI,%RCX,1)

0x402622 ADD	$0x40,%RCX

0x402626 VMOVUPD	(%R8,%RCX,1),%ZMM4

0x40262d VADDPD	(%RDI,%RCX,1),%ZMM4,%ZMM5

0x402634 VMOVUPD	%ZMM5,(%RSI,%RCX,1)

0x40263b ADD	$0x40,%RCX

0x40263f VMOVUPD	(%R8,%RCX,1),%ZMM6

0x402646 VADDPD	(%RDI,%RCX,1),%ZMM6,%ZMM7

0x40264d VMOVUPD	%ZMM7,(%RSI,%RCX,1)

0x402654 ADD	$0x40,%RCX

0x402658 VMOVUPD	(%R8,%RCX,1),%ZMM8

0x40265f VADDPD	(%RDI,%RCX,1),%ZMM8,%ZMM9

0x402666 VMOVUPD	%ZMM9,(%RSI,%RCX,1)

0x40266d ADD	$0x40,%RCX

0x402671 VMOVUPD	(%R8,%RCX,1),%ZMM10

0x402678 VADDPD	(%RDI,%RCX,1),%ZMM10,%ZMM11

0x40267f VMOVUPD	%ZMM11,(%RSI,%RCX,1)

0x402686 ADD	$0x40,%RCX

0x40268a VMOVUPD	(%R8,%RCX,1),%ZMM12

0x402691 VADDPD	(%RDI,%RCX,1),%ZMM12,%ZMM13

0x402698 VMOVUPD	%ZMM13,(%RSI,%RCX,1)

0x40269f ADD	$0x40,%RCX

0x4026a3 CMP	%R11,%RCX

0x4026a6 JE	402779

(3) 0x4026ac VMOVUPD	(%R8,%RCX,1),%ZMM14

(3) 0x4026b3 VADDPD	(%RDI,%RCX,1),%ZMM14,%ZMM15

(3) 0x4026ba VMOVUPD	%ZMM15,(%RSI,%RCX,1)

(3) 0x4026c1 VMOVUPD	0x40(%R8,%RCX,1),%ZMM0

(3) 0x4026c9 VADDPD	0x40(%RDI,%RCX,1),%ZMM0,%ZMM1

(3) 0x4026d1 VMOVUPD	%ZMM1,0x40(%RSI,%RCX,1)

(3) 0x4026d9 VMOVUPD	0x80(%R8,%RCX,1),%ZMM2

(3) 0x4026e1 VADDPD	0x80(%RDI,%RCX,1),%ZMM2,%ZMM3

(3) 0x4026e9 VMOVUPD	%ZMM3,0x80(%RSI,%RCX,1)

(3) 0x4026f1 VMOVUPD	0xc0(%R8,%RCX,1),%ZMM4

(3) 0x4026f9 VADDPD	0xc0(%RDI,%RCX,1),%ZMM4,%ZMM5

(3) 0x402701 VMOVUPD	%ZMM5,0xc0(%RSI,%RCX,1)

(3) 0x402709 VMOVUPD	0x100(%R8,%RCX,1),%ZMM6

(3) 0x402711 VADDPD	0x100(%RDI,%RCX,1),%ZMM6,%ZMM7

(3) 0x402719 VMOVUPD	%ZMM7,0x100(%RSI,%RCX,1)

(3) 0x402721 VMOVUPD	0x140(%R8,%RCX,1),%ZMM8

(3) 0x402729 VADDPD	0x140(%RDI,%RCX,1),%ZMM8,%ZMM9

(3) 0x402731 VMOVUPD	%ZMM9,0x140(%RSI,%RCX,1)

(3) 0x402739 VMOVUPD	0x180(%R8,%RCX,1),%ZMM10

(3) 0x402741 VADDPD	0x180(%RDI,%RCX,1),%ZMM10,%ZMM11

(3) 0x402749 VMOVUPD	%ZMM11,0x180(%RSI,%RCX,1)

(3) 0x402751 VMOVUPD	0x1c0(%R8,%RCX,1),%ZMM12

(3) 0x402759 VADDPD	0x1c0(%RDI,%RCX,1),%ZMM12,%ZMM13

(3) 0x402761 VMOVUPD	%ZMM13,0x1c0(%RSI,%RCX,1)

(3) 0x402769 ADD	$0x200,%RCX

(3) 0x402770 CMP	%R11,%RCX

(3) 0x402773 JNE	4026ac

0x402779 MOV	%RAX,%RDI

0x40277c AND	$-0x8,%RDI

0x402780 ADD	%RDI,%RDX

0x402783 CMP	%RDI,%RAX

0x402786 JE	402820

0x40278c SUB	%RDI,%RAX

0x40278f LEA	-0x1(%RAX),%RSI

0x402793 CMP	$0x2,%RSI

0x402797 JBE	4027c1

0x402799 ADD	%RBX,%RDI

0x40279c MOV	%RAX,%RBX

0x40279f SAL	$0x3,%RDI

0x4027a3 VMOVUPD	(%R13,%RDI,1),%YMM14

0x4027aa VADDPD	(%R12,%RDI,1),%YMM14,%YMM15

0x4027b0 AND	$-0x4,%RBX

0x4027b4 ADD	%RBX,%RDX

0x4027b7 VMOVUPD	%YMM15,(%R14,%RDI,1)

0x4027bd TEST	$0x3,%AL

0x4027bf JE	402820

0x4027c1 LEA	0x1(%RDX),%RAX

0x4027c5 VMOVSD	(%R12,%RDX,8),%XMM0

0x4027cb VADDSD	(%R13,%RDX,8),%XMM0,%XMM1

0x4027d2 VMOVSD	%XMM1,(%R14,%RDX,8)

0x4027d8 CMP	%RAX,%R10

0x4027db JLE	402820

0x4027dd ADD	$0x2,%RDX

0x4027e1 VMOVSD	(%R13,%RAX,8),%XMM2

0x4027e8 VADDSD	(%R12,%RAX,8),%XMM2,%XMM3

0x4027ee VMOVSD	%XMM3,(%R14,%RAX,8)

0x4027f4 CMP	%RDX,%R10

0x4027f7 JLE	402820

0x4027f9 VMOVSD	(%R12,%RDX,8),%XMM4

0x4027ff VADDSD	(%R13,%RDX,8),%XMM4,%XMM5

0x402806 VMOVSD	%XMM5,(%R14,%RDX,8)

0x40280c VZEROUPPER

0x40280f LEA	-0x20(%RBP),%RSP

0x402813 POP	%RBX

0x402814 POP	%R12

0x402816 POP	%R13

0x402818 POP	%R14

0x40281a POP	%RBP

0x40281b RET

0x40281c NOPL	(%RAX)

0x402820 VZEROUPPER

0x402823 LEA	-0x20(%RBP),%RSP

0x402827 POP	%RBX

0x402828 POP	%R12

0x40282a POP	%R13

0x40282c POP	%R14

0x40282e POP	%RBP

0x40282f RET

0x402830 INC	%RAX

0x402833 XOR	%EDX,%EDX

0x402835 JMP	402551

0x40283a NOPW	(%RAX,%RAX,1)

0x402840 XOR	%EDI,%EDI

0x402842 MOV	$0x334907100,%R12

0x40284c MOV	$0x19a687100,%R13

0x402856 MOV	$0x407100,%R14

0x402860 JMP	40278c

0x402865 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
○98.94	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○1.06	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0

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	stream.c:342-344
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342-344.

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 25.33 to 15.67 cycles (1.62x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 45% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 25.33 to 20.25 cycles (1.25x speedup).

Details

44% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

72% of SSE/AVX loads are used in vector version.
72% of SSE/AVX stores are used in vector version.
66% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
8% of SSE/AVX 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)

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►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342

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.

IDIV: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342
VMOVUPD: 7 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344

Vector unaligned load/store instructions

Detected 2 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

3 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 1 AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (four at a time). 7 AVX-512 instructions are processing arithmetic or math operations on double precision FP elements in vector mode (eight at a time).

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

The binary function is composed of 63 FP arithmetical operations:

63: addition or subtraction

The binary function is loading 1008 bytes (126 double precision FP elements). The binary function is storing 504 bytes (63 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.04 FP operations per loaded or stored byte.

General properties

nb instructions	146
nb uops	152
loop length	659
used x86 registers	15
used mmx registers	0
used xmm registers	6
used ymm registers	2
used zmm registers	14
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	25.33 cycles
front end	25.33 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	18.25	18.25	18.25	18.25	12.00	11.67	11.67	11.67	0.00	0.00	5.50	5.50	9.00	9.00
cycles	18.25	18.25	18.25	18.25	12.00	16.33	16.33	16.33	0.00	0.00	9.00	9.00	9.00	9.00

Execution ports to units layout:

ALU0/BRU0: ALU, BRU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1: BRU
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

7.00-12.00

Cycles summary

Front-end	25.33
Dispatch	18.25
DIV/SQRT	7.00-12.00
Overall L1	25.33

Vectorization ratios

INT

all	7%
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)
other	8%

all	72%
load	72%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	72%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	44%
load	72%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	66%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	8%

Vector efficiency ratios

INT

all	12%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	71%
load	71%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	71%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	45%
load	71%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	66%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 25.33 cycles. At this rate:

41% of peak load performance is reached (39.79 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
31% of peak store performance is reached (19.89 out of 64.00 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 25.33 to 18.25 cycles (1.39x speedup).

ASM code

In the binary file, the address of the function is: 402510

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV $0x401060,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV $0x401030,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
AND $-0x40,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CALL %RAX	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	2	N/A
MOVSXD %EAX,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (6.3%)
CALL %R12	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	2	N/A
MOVSXD %EAX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x33450000,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CQTO																		scal (12.5%)
IDIV %RBX	2	2	0	0	0	0	0	0	0	0	0	0	0	0	0	9-19	7-12	scal (12.5%)
CMP %RDX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 402830 <main._omp_fn.6+0x320>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
IMUL %RAX,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RCX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%RDX,1),%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %R10,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 40280f <main._omp_fn.6+0x2ff>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%RAX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP $0x6,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JBE 402840 <main._omp_fn.6+0x330>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RAX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (,%RDX,8),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x334907100,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x19a687100,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
SHR $0x3,%R11	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SAL $0x6,%R11	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LEA -0x40(%R11),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x407100,%R14	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%R12,%RSI,1),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R13,%RSI,1),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SHR $0x6,%R9	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	scal (12.5%)
INC %R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD %R14,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
AND $0x7,%R9D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (6.3%)
JE 4026ac <main._omp_fn.6+0x19c>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x1,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 40268a <main._omp_fn.6+0x17a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x2,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402671 <main._omp_fn.6+0x161>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x3,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402658 <main._omp_fn.6+0x148>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 40263f <main._omp_fn.6+0x12f>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x5,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402626 <main._omp_fn.6+0x116>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x6,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 40260d <main._omp_fn.6+0xfd>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVUPD (%R8),%ZMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI),%ZMM0,%ZMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
MOV $0x40,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD %ZMM1,(%RSI)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
VMOVUPD (%R8,%RCX,1),%ZMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM2,%ZMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM3,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM4,%ZMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM5,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM6	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM6,%ZMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM7,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM8	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM8,%ZMM9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM9,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM10,%ZMM11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM11,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM12,%ZMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM13,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %R11,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402779 <main._omp_fn.6+0x269>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x8,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %RDI,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %RDI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
SUB %RDI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x1(%RAX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP $0x2,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JBE 4027c1 <main._omp_fn.6+0x2b1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD %RBX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAL $0x3,%RDI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
VMOVUPD (%R13,%RDI,1),%YMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.50	vect (50.0%)
VADDPD (%R12,%RDI,1),%YMM14,%YMM15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	vect (50.0%)
AND $-0x4,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD %RBX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD %YMM15,(%R14,%RDI,1)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	4	1	vect (50.0%)
TEST $0x3,%AL	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA 0x1(%RDX),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD (%R12,%RDX,8),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R13,%RDX,8),%XMM0,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM1,(%R14,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1	scal (12.5%)
CMP %RAX,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JLE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD $0x2,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD (%R13,%RAX,8),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R12,%RAX,8),%XMM2,%XMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM3,(%R14,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1	scal (12.5%)
CMP %RDX,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JLE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD (%R12,%RDX,8),%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R13,%RDX,8),%XMM4,%XMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM5,(%R14,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1	scal (12.5%)
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x20(%RBP),%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x20(%RBP),%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INC %RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 402551 <main._omp_fn.6+0x41>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV $0x334907100,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x19a687100,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x407100,%R14	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
JMP 40278c <main._omp_fn.6+0x27c>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

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	stream.c:342-344
Module	exec

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

44% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

72% of SSE/AVX loads are used in vector version.
72% of SSE/AVX stores are used in vector version.
66% of SSE/AVX addition or subtraction instructions are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
8% of SSE/AVX 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)

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►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342

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.

IDIV: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342
VMOVUPD: 7 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344

Vector unaligned load/store instructions

Detected 2 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:344

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz16.benchmarkcenter.megware.com/177-374-0958/stream/build/stream/src/stream.c:342

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

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

The binary function is composed of 63 FP arithmetical operations:

63: addition or subtraction

The binary function is loading 1008 bytes (126 double precision FP elements). The binary function is storing 504 bytes (63 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.04 FP operations per loaded or stored byte.

General properties

nb instructions	146
nb uops	152
loop length	659
used x86 registers	15
used mmx registers	0
used xmm registers	6
used ymm registers	2
used zmm registers	14
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	25.33 cycles
front end	25.33 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	18.25	18.25	18.25	18.25	12.00	11.67	11.67	11.67	0.00	0.00	5.50	5.50	9.00	9.00
cycles	18.25	18.25	18.25	18.25	12.00	16.33	16.33	16.33	0.00	0.00	9.00	9.00	9.00	9.00

Execution ports to units layout:

ALU0/BRU0: ALU, BRU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1: BRU
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

7.00-12.00

Cycles summary

Front-end	25.33
Dispatch	18.25
DIV/SQRT	7.00-12.00
Overall L1	25.33

Vectorization ratios

INT

all	7%
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)
other	8%

all	72%
load	72%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	72%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	44%
load	72%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	66%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	8%

Vector efficiency ratios

INT

all	12%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	71%
load	71%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	71%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

INT+FP

all	45%
load	71%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	66%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 25.33 cycles. At this rate:

41% of peak load performance is reached (39.79 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
31% of peak store performance is reached (19.89 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 402510

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV $0x401060,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV $0x401030,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
AND $-0x40,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CALL %RAX	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	2	N/A
MOVSXD %EAX,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (6.3%)
CALL %R12	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	2	N/A
MOVSXD %EAX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x33450000,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CQTO																		scal (12.5%)
IDIV %RBX	2	2	0	0	0	0	0	0	0	0	0	0	0	0	0	9-19	7-12	scal (12.5%)
CMP %RDX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 402830 <main._omp_fn.6+0x320>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
IMUL %RAX,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RCX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%RAX,%RDX,1),%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %R10,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 40280f <main._omp_fn.6+0x2ff>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%RAX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP $0x6,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JBE 402840 <main._omp_fn.6+0x330>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RAX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (,%RDX,8),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x334907100,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x19a687100,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
SHR $0x3,%R11	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SAL $0x6,%R11	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LEA -0x40(%R11),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV $0x407100,%R14	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA (%R12,%RSI,1),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA (%R13,%RSI,1),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SHR $0x6,%R9	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	scal (12.5%)
INC %R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD %R14,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
AND $0x7,%R9D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (6.3%)
JE 4026ac <main._omp_fn.6+0x19c>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x1,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 40268a <main._omp_fn.6+0x17a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x2,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402671 <main._omp_fn.6+0x161>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x3,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402658 <main._omp_fn.6+0x148>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 40263f <main._omp_fn.6+0x12f>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x5,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402626 <main._omp_fn.6+0x116>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x6,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 40260d <main._omp_fn.6+0xfd>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVUPD (%R8),%ZMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI),%ZMM0,%ZMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
MOV $0x40,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD %ZMM1,(%RSI)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
VMOVUPD (%R8,%RCX,1),%ZMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM2,%ZMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM3,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM4,%ZMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM5,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM6	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM6,%ZMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM7,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM8	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM8,%ZMM9	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM9,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM10	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM10,%ZMM11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM11,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD (%R8,%RCX,1),%ZMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	1	vect (100.0%)
VADDPD (%RDI,%RCX,1),%ZMM12,%ZMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	1	vect (100.0%)
VMOVUPD %ZMM13,(%RSI,%RCX,1)	2	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	1	5	2	vect (100.0%)
ADD $0x40,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %R11,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402779 <main._omp_fn.6+0x269>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x8,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
ADD %RDI,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %RDI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
SUB %RDI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x1(%RAX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP $0x2,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JBE 4027c1 <main._omp_fn.6+0x2b1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD %RBX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SAL $0x3,%RDI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
VMOVUPD (%R13,%RDI,1),%YMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.50	vect (50.0%)
VADDPD (%R12,%RDI,1),%YMM14,%YMM15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	vect (50.0%)
AND $-0x4,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD %RBX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVUPD %YMM15,(%R14,%RDI,1)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	4	1	vect (50.0%)
TEST $0x3,%AL	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
LEA 0x1(%RDX),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD (%R12,%RDX,8),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R13,%RDX,8),%XMM0,%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM1,(%R14,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1	scal (12.5%)
CMP %RAX,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JLE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD $0x2,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD (%R13,%RAX,8),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R12,%RAX,8),%XMM2,%XMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM3,(%R14,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1	scal (12.5%)
CMP %RDX,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
JLE 402820 <main._omp_fn.6+0x310>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
VMOVSD (%R12,%RDX,8),%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD (%R13,%RDX,8),%XMM4,%XMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50	scal (12.5%)
VMOVSD %XMM5,(%R14,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1	scal (12.5%)
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x20(%RBP),%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
LEA -0x20(%RBP),%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INC %RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
JMP 402551 <main._omp_fn.6+0x41>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV $0x334907100,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x19a687100,%R13	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV $0x407100,%R14	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
JMP 40278c <main._omp_fn.6+0x27c>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼main._omp_fn.6–	27.69	7.48
○Loop 3 - stream.c:344-344 - exec	27.69	7.29

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code