OV - exec - Loop 13

	Loop Id: 13	Module: exec	Source: stream.c:296-296	Coverage: 0.20%

0x4019d8 LDR	D17, [X16]    [3]

0x4019dc ORR	X15, XZR, X16

0x4019e0 FADD	D7, D17, D17

0x4019e4 STR	D7, [X15], #8    [1]

0x4019e8 LDR	D18, [X16, #8]    [3]

0x4019ec FADD	D16, D18, D18

0x4019f0 STR	D16, [X16, #8]    [3]

0x4019f4 LDR	D19, [X15, #8]    [1]

0x4019f8 FADD	D20, D19, D19

0x4019fc STR	D20, [X15, #8]    [1]

0x401a00 LDR	D29, [X16, #56]    [3]

0x401a04 LDP	D24, D21, [X16, #24]    [3]

0x401a08 LDP	D22, D23, [X16, #40]    [3]

0x401a0c ADD	X16, X16, #64

0x401a10 FADD	D2, D29, D29

0x401a14 FADD	D31, D24, D24

0x401a18 FADD	D0, D21, D21

0x401a1c FADD	D30, D22, D22

0x401a20 FADD	D1, D23, D23

0x401a24 STUR	D2, [X16, #504]    [2]

0x401a28 STP	D31, D0, [X16, #984]    [2]

0x401a2c STP	D30, D1, [X16, #1000]    [2]

0x401a30 CMP	X9, X16

0x401a34 B.NE	4019d8

/home/eoseret/Tools/QaaS/qaas_runs/175-492-1446/intel/stream/build/stream/src/stream.c: 296 - 296

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

296: 		a[j] = 2.0E0 * a[j];

Coverage (%)	Name	Source Location	Module
►98.92+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.08+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	main	stream.c:444	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stream.c:290	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 /

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.20
CQA speedup if fully vectorized	1.50
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.14
Bottlenecks	P12, P13, P14,
Function	main._omp_fn.3
Source	stream.c:296-296
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.00
CQA cycles if no scalar integer	4.00
CQA cycles if FP arith vectorized	3.33
CQA cycles if fully vectorized	2.67
Front-end cycles	3.00
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	0.75
P3 cycles	0.75
P4 cycles	0.67
P5 cycles	0.67
P6 cycles	0.58
P7 cycles	0.58
P8 cycles	3.50
P9 cycles	3.50
P10 cycles	3.50
P11 cycles	3.50
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	4.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	24.00
Nb uops	24.00
Nb loads	NA
Nb stores	6.00
Nb stack references	0.00
FLOP/cycle	2.00
Nb FLOP add-sub	8.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	32.00
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
Stride 0	0.00
Stride 1	1.00
Stride n	0.00
Stride unknown	1.00
Stride indirect	0.00
Vectorization ratio all	20.00
Vectorization ratio load	33.33
Vectorization ratio store	33.33
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	60.00
Vector-efficiency ratio load	66.67
Vector-efficiency ratio store	66.67
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	50.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.20
CQA speedup if fully vectorized	1.50
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.14
Bottlenecks	P12, P13, P14,
Function	main._omp_fn.3
Source	stream.c:296-296
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.00
CQA cycles if no scalar integer	4.00
CQA cycles if FP arith vectorized	3.33
CQA cycles if fully vectorized	2.67
Front-end cycles	3.00
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	0.75
P3 cycles	0.75
P4 cycles	0.67
P5 cycles	0.67
P6 cycles	0.58
P7 cycles	0.58
P8 cycles	3.50
P9 cycles	3.50
P10 cycles	3.50
P11 cycles	3.50
P12 cycles	4.00
P13 cycles	4.00
P14 cycles	4.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	24.00
Nb uops	24.00
Nb loads	NA
Nb stores	6.00
Nb stack references	0.00
FLOP/cycle	2.00
Nb FLOP add-sub	8.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	32.00
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
Stride 0	0.00
Stride 1	1.00
Stride n	0.00
Stride unknown	1.00
Stride indirect	0.00
Vectorization ratio all	20.00
Vectorization ratio load	33.33
Vectorization ratio store	33.33
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	60.00
Vector-efficiency ratio load	66.67
Vector-efficiency ratio store	66.67
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	50.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Path /

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

Function	main._omp_fn.3
Source file and lines	stream.c:296-296
Module	exec

The loop is defined in /home/eoseret/Tools/QaaS/qaas_runs/175-492-1446/intel/stream/build/stream/src/stream.c:296.

The related source loop is not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Vectorization

Your loop is poorly vectorized. Only 60% of vector register length is used (average across all VPU instructions). By fully vectorizing your loop, you can lower the cost of an iteration from 4.00 to 2.67 cycles (1.50x speedup).

Details

20% of VPU instructions are used in vector version (process two or more data elements in vector registers):

33% of VPU loads are used in vector version.
33% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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)

No data for this section

Slow data structures access

Detected data structures (typically arrays) that cannot be efficiently read/written

Details

Constant unknown stride: 1 occurrence(s)

Non-unit stride (uncontiguous) accesses are not efficiently using data caches

Workaround

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

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

The binary loop is composed of 8 FP arithmetical operations:

8: addition or subtraction

The binary loop is loading 64 bytes. The binary loop is storing 64 bytes.

Arithmetic intensity

Arithmetic intensity is 0.06 FP operations per loaded or stored byte.

General properties

nb instructions	24
nb uops	24
loop length	96
used w registers	0
used x registers	4
used b registers	0
used h registers	0
used s registers	0
used d registers	16
used q registers	0
used v registers	0
used z registers	0
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.00 cycles
front end	3.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	0.50	0.50	0.75	0.75	0.67	0.67	0.58	0.58	3.50	3.50	3.50	3.50	4.00	4.00	4.00	0.00	0.00
cycles	0.50	0.50	0.75	0.75	0.67	0.67	0.58	0.58	3.50	3.50	3.50	3.50	4.00	4.00	4.00	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	1.00

Cycles summary

Front-end	3.00
Dispatch	4.00
Data deps.	1.00
Overall L1	4.00

Vectorization ratios

INT

all	33%
load	33%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

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

INT+FP

all	20%
load	33%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

Vector efficiency ratios

INT

all	66%
load	66%
store	66%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

all	50%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
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	60%
load	66%
store	66%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.00 cycles. At this rate:

16% of peak load performance is reached (16.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
33% of peak store performance is reached (16.00 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 4019d8

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDR D17, [X16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ORR X15, XZR, X16	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FADD D7, D17, D17	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STR D7, [X15], #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR D18, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FADD D16, D18, D18	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STR D16, [X16, #8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR D19, [X15, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FADD D20, D19, D19	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STR D20, [X15, #8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR D29, [X16, #56]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
LDP D24, D21, [X16, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP D22, D23, [X16, #40]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
ADD X16, X16, #64	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FADD D2, D29, D29	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D31, D24, D24	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D0, D21, D21	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D30, D22, D22	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D1, D23, D23	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STUR D2, [X16, #504]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
STP D31, D0, [X16, #984]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
STP D30, D1, [X16, #1000]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
CMP X9, X16	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 4019d8 <main._omp_fn.3+0xf8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	main._omp_fn.3
Source file and lines	stream.c:296-296
Module	exec

The loop is defined in /home/eoseret/Tools/QaaS/qaas_runs/175-492-1446/intel/stream/build/stream/src/stream.c:296.

The related source loop is not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Vectorization

Details

20% of VPU instructions are used in vector version (process two or more data elements in vector registers):

33% of VPU loads are used in vector version.
33% of VPU stores are used in vector version.
0% of VPU addition or subtraction instructions are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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)

No data for this section

Slow data structures access

Detected data structures (typically arrays) that cannot be efficiently read/written

Details

Constant unknown stride: 1 occurrence(s)

Non-unit stride (uncontiguous) accesses are not efficiently using data caches

Workaround

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

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

The binary loop is composed of 8 FP arithmetical operations:

8: addition or subtraction

The binary loop is loading 64 bytes. The binary loop is storing 64 bytes.

Arithmetic intensity

Arithmetic intensity is 0.06 FP operations per loaded or stored byte.

General properties

nb instructions	24
nb uops	24
loop length	96
used w registers	0
used x registers	4
used b registers	0
used h registers	0
used s registers	0
used d registers	16
used q registers	0
used v registers	0
used z registers	0
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	3.00 cycles
front end	3.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	0.50	0.50	0.75	0.75	0.67	0.67	0.58	0.58	3.50	3.50	3.50	3.50	4.00	4.00	4.00	0.00	0.00
cycles	0.50	0.50	0.75	0.75	0.67	0.67	0.58	0.58	3.50	3.50	3.50	3.50	4.00	4.00	4.00	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	1.00

Cycles summary

Front-end	3.00
Dispatch	4.00
Data deps.	1.00
Overall L1	4.00

Vectorization ratios

INT

all	33%
load	33%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

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

INT+FP

all	20%
load	33%
store	33%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

Vector efficiency ratios

INT

all	66%
load	66%
store	66%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

all	50%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
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	60%
load	66%
store	66%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	50%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	NA (no other vectorizable/vectorized instructions)

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.00 cycles. At this rate:

16% of peak load performance is reached (16.00 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
33% of peak store performance is reached (16.00 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 4019d8

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDR D17, [X16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ORR X15, XZR, X16	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FADD D7, D17, D17	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STR D7, [X15], #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR D18, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FADD D16, D18, D18	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STR D16, [X16, #8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR D19, [X15, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FADD D20, D19, D19	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STR D20, [X15, #8]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
LDR D29, [X16, #56]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
LDP D24, D21, [X16, #24]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
LDP D22, D23, [X16, #40]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	vect (100.0%)
ADD X16, X16, #64	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	1	0.17	N/A
FADD D2, D29, D29	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D31, D24, D24	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D0, D21, D21	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D30, D22, D22	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
FADD D1, D23, D23	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	2	0.25	scal (50.0%)
STUR D2, [X16, #504]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	scal (50.0%)
STP D31, D0, [X16, #984]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
STP D30, D1, [X16, #1000]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	2	0.50	vect (100.0%)
CMP X9, X16	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	1	0.33	N/A
B.NE 4019d8 <main._omp_fn.3+0xf8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Vectorization

Details

Workaround

Slow data structures access

Details

Workaround

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

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

Vectorization

Details

Workaround

Slow data structures access

Details

Workaround

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

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