OV - exec - Loop 28

	Loop Id: 28	Module: exec	Source: cg.cpp:105-113	Coverage: 0.16%

0x41232c CMP	W10, W8

0x412330 ADD	W10, W10, #1

0x412334 ADD	W12, W12, #1

0x412338 ADD	W6, W6, W11

0x41233c B.EQ	412550

0x412340 SBFM	X6, X6, #0, #31

0x412344 CMP	X17, X4

0x412348 B.CS	4123a8

0x41234c ORR	X19, XZR, X9

0x412350 ADD	X25, X19, X6

0x412354 SUB	X16, X9, X11

0x412358 ADD	X7, X15, X25,LSL #3

0x41235c ADD	X22, X18, X25,LSL #3

0x412360 ADD	X24, X1, X25,LSL #3

0x412364 ADD	X25, X2, X25,LSL #3

0x412368 ADD	X26, X16, X19

  (27) 0x41236c LDR	D2, [X20]

  (27) 0x412370 LDR	D3, [X7], #8

  (27) 0x412374 LDR	D4, [X22]

  (27) 0x412378 ADDS	X26, X26, #1

  (27) 0x41237c FMADD	D2, D3, D2, D4

  (27) 0x412380 STR	D2, [X22], #8

  (27) 0x412384 LDR	D2, [X20]

  (27) 0x412388 LDR	D3, [X24], #8

  (27) 0x41238c LDR	D4, [X25]

  (27) 0x412390 FMSUB	D2, D3, D2, D4

  (27) 0x412394 FMADD	D1, D2, D2, D1

  (27) 0x412398 STR	D2, [X25], #8

  (27) 0x41239c STUR	D1, [X29, #488]

  (27) 0x4123a0 B.CC	41236c

0x4123a4 B	41232c

0x4123a8 ADD	W7, W13, W12

0x4123ac SUB	X27, X2, X9,LSL #3

0x4123b0 SUB	X22, X1, X9,LSL #3

0x4123b4 SUB	X25, X15, X9,LSL #3

0x4123b8 SUB	X30, X18, X9,LSL #3

0x4123bc ADD	X16, X20, #8

0x4123c0 MUL	W7, W11, W7

0x4123c4 SBFM	X7, X7, #0, #31

0x4123c8 ADD	X19, X11, X7

0x4123cc ADD	X7, X9, X7

0x4123d0 ADD	X24, X1, X7,LSL #3

0x4123d4 ADD	X26, X15, X7,LSL #3

0x4123d8 ADD	X27, X27, X19,LSL #3

0x4123dc ADD	X28, X2, X7,LSL #3

0x4123e0 ADD	X7, X18, X7,LSL #3

0x4123e4 ADD	X22, X22, X19,LSL #3

0x4123e8 ADD	X25, X25, X19,LSL #3

0x4123ec ADD	X19, X30, X19,LSL #3

0x4123f0 CMP	X7, X27

0x4123f4 CCMP	X28, X19, #2, #3

0x4123f8 CSINC	W30, WZR, WZR, #2

0x4123fc CMP	X7, X3

0x412400 CCMP	X14, X19, #2, #3

0x412404 CSINC	W30, W30, WZR, #2

0x412408 CMP	X7, X16

0x41240c CCMP	X20, X19, #2, #3

0x412410 CSINC	W30, W30, WZR, #2

0x412414 CMP	X7, X25

0x412418 CCMP	X26, X19, #2, #3

0x41241c CSINC	W30, W30, WZR, #2

0x412420 CMP	X7, X22

0x412424 CCMP	X24, X19, #2, #3

0x412428 CSINC	W7, W30, WZR, #2

0x41242c CMP	X28, X3

0x412430 CCMP	X14, X27, #2, #3

0x412434 CSINC	W7, W7, WZR, #2

0x412438 CMP	X28, X16

0x41243c CCMP	X20, X27, #2, #3

0x412440 CSINC	W7, W7, WZR, #2

0x412444 CMP	X28, X25

0x412448 CCMP	X26, X27, #2, #3

0x41244c CSINC	W19, WZR, WZR, #2

0x412450 CMP	X28, X22

0x412454 CCMP	X24, X27, #2, #3

0x412458 CSINC	W27, WZR, WZR, #2

0x41245c CMP	X14, X25

0x412460 ORR	W19, W19, W27

0x412464 CCMP	X26, X3, #2, #3

0x412468 ORR	W19, W19, W21

0x41246c ORR	W27, W7, W19

0x412470 CSINC	W7, WZR, WZR, #2

0x412474 CMP	X14, X22

0x412478 CCMP	X24, X3, #2, #3

0x41247c CSINC	W19, WZR, WZR, #2

0x412480 TBNZ	W27, #0, 41234c

0x412484 TBNZ	W7, #0, 41234c

0x412488 TBNZ	W19, #0, 41234c

0x41248c LDR	X19, [SP, #40]

0x412490 ADD	X30, X9, X6

0x412494 LDR	D2, [X20]

0x412498 SEL	Z1.D, P0, Z1.D, Z0.D

0x41249c MOVI	V3.2D, #0

0x4124a0 ORR	X7, XZR, XZR

0x4124a4 ADD	X24, X15, X30,LSL #3

0x4124a8 ADD	X22, X18, X30,LSL #3

0x4124ac ADD	X27, X1, X30,LSL #3

0x4124b0 ADD	X25, X19, X30,LSL #3

0x4124b4 LDR	X19, [SP, #32]

0x4124b8 DUP	Z2.D, Z2.D[0]

0x4124bc ADD	X26, X19, X30,LSL #3

0x4124c0 LDP	X16, X19, [SP, #16]

0x4124c4 ADD	X28, X19, X30,LSL #3

0x4124c8 ADD	X19, X2, X30,LSL #3

0x4124cc ADD	X30, X16, X30,LSL #3

0x4124d0 HINT	#0

0x4124d4 HINT	#0

0x4124d8 HINT	#0

0x4124dc HINT	#0

  (29) 0x4124e0 LD1D	{Z4.D}, P1/Z, [X24, X7,LSL #3]

  (29) 0x4124e4 LD1D	{Z5.D}, P1/Z, [X25, X7,LSL #3]

  (29) 0x4124e8 LD1D	{Z6.D}, P1/Z, [X22, X7,LSL #3]

  (29) 0x4124ec FMAD	Z4.D, P1/M, Z2.D, Z6.D

  (29) 0x4124f0 LD1D	{Z7.D}, P1/Z, [X26, X7,LSL #3]

  (29) 0x4124f4 FMAD	Z5.D, P1/M, Z2.D, Z7.D

  (29) 0x4124f8 LD1D	{Z6.D}, P1/Z, [X19, X7,LSL #3]

  (29) 0x4124fc LD1D	{Z7.D}, P1/Z, [X30, X7,LSL #3]

  (29) 0x412500 ST1D	{Z4.D}, P1, [X22, X7,LSL #3]

  (29) 0x412504 ST1D	{Z5.D}, P1, [X26, X7,LSL #3]

  (29) 0x412508 LD1D	{Z4.D}, P1/Z, [X27, X7,LSL #3]

  (29) 0x41250c LD1D	{Z5.D}, P1/Z, [X28, X7,LSL #3]

  (29) 0x412510 FMSB	Z4.D, P1/M, Z2.D, Z6.D

  (29) 0x412514 FMSB	Z5.D, P1/M, Z2.D, Z7.D

  (29) 0x412518 FMLA	Z1.D, P1/M, Z4.D, Z4.D

  (29) 0x41251c FMLA	Z3.D, P1/M, Z5.D, Z5.D

  (29) 0x412520 ST1D	{Z4.D}, P1, [X19, X7,LSL #3]

  (29) 0x412524 ST1D	{Z5.D}, P1, [X30, X7,LSL #3]

  (29) 0x412528 ADD	X7, X7, X0

  (29) 0x41252c CMP	X5, X7

  (29) 0x412530 B.NE	4124e0

0x412534 FADD	Z1.D, Z3.D, Z1.D

0x412538 CMP	X17, X5

0x41253c ADD	X19, X5, X9

0x412540 FADDV	D1, P1, Z1.D

0x412544 STUR	D1, [X29, #488]

0x412548 B.EQ	41232c

0x41254c B	412350

/home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp: 105 - 113

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

105:   #pragma omp parallel for reduction(+ : rrn_temp)

106: #endif

107:   for (int jj = halo_depth; jj < y - halo_depth; ++jj) {

108:     for (int kk = halo_depth; kk < x - halo_depth; ++kk) {

109:       const int index = kk + jj * x;

110:

111:       u[index] += alpha * p[index];

112:       r[index] -= alpha * w[index];

113:       rrn_temp += r[index] * r[index];

Coverage (%)	Name	Source Location	Module
►98.26+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.74+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	run_cg_calc_ur(Chunk*, Setting[...]	cg.cpp:117	exec
○	cg_main_step_driver(Chunk*, Se[...]	cg_driver.cpp:69	exec
○	cg_driver(Chunk*, Settings&, d[...]	cg_driver.cpp:18	exec
○	solve(Chunk*, Settings&, int, [...]	diffuse.cpp:45	exec
○	diffuse(Chunk*, Settings&)	diffuse.cpp:12	exec
○	main	main.cpp:169	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		exec

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Metric	Value
CQA speedup if no scalar integer	8.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.21
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.63
Bottlenecks	P2, P3, P4, P5,
Function	cg_calc_ur(int, int, int, double, double, double, double const, double, double const*) [clone .omp_outlined]
Source	cg.cpp:105-108,cg.cpp:111-113
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	20.00
CQA cycles if no scalar integer	2.50
CQA cycles if FP arith vectorized	20.00
CQA cycles if fully vectorized	4.75
Front-end cycles	12.25
P0 cycles	4.00
P1 cycles	4.00
P2 cycles	20.00
P3 cycles	20.00
P4 cycles	20.00
P5 cycles	20.00
P6 cycles	2.50
P7 cycles	2.50
P8 cycles	1.50
P9 cycles	1.50
P10 cycles	1.83
P11 cycles	1.50
P12 cycles	1.67
P13 cycles	0.00
P14 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	102.00
Nb uops	98.00
Nb loads	NA
Nb stores	1.00
Nb stack references	3.00
FLOP/cycle	0.40
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	0.00
Bytes prefetched	0.00
Bytes loaded	0.00
Bytes stored	0.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	4.44
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	5.26
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	4.35
Vector-efficiency ratio all	27.50
Vector-efficiency ratio load	31.25
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	27.63
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	27.45

Metric	Value
CQA speedup if no scalar integer	8.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.21
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.63
Bottlenecks	P2, P3, P4, P5,
Function	cg_calc_ur(int, int, int, double, double, double, double const, double, double const*) [clone .omp_outlined]
Source	cg.cpp:105-108,cg.cpp:111-113
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	20.00
CQA cycles if no scalar integer	2.50
CQA cycles if FP arith vectorized	20.00
CQA cycles if fully vectorized	4.75
Front-end cycles	12.25
P0 cycles	4.00
P1 cycles	4.00
P2 cycles	20.00
P3 cycles	20.00
P4 cycles	20.00
P5 cycles	20.00
P6 cycles	2.50
P7 cycles	2.50
P8 cycles	1.50
P9 cycles	1.50
P10 cycles	1.83
P11 cycles	1.50
P12 cycles	1.67
P13 cycles	0.00
P14 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	102.00
Nb uops	98.00
Nb loads	NA
Nb stores	1.00
Nb stack references	3.00
FLOP/cycle	0.40
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	0.00
Bytes prefetched	0.00
Bytes loaded	0.00
Bytes stored	0.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	4.44
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	5.26
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	4.35
Vector-efficiency ratio all	27.50
Vector-efficiency ratio load	31.25
Vector-efficiency ratio store	25.00
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	27.63
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	27.45

Path /

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

Function	cg_calc_ur(int, int, int, double, double, double, double const, double, double const*) [clone .omp_outlined]
Source file and lines	cg.cpp:105-113
Module	exec

The loop is defined in /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:105-113.

Analyzed code is defined in /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:105-108,111-113.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=6
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 6 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 20.00 to 2.50 cycles (8.00x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 27% 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 20.00 to 4.75 cycles (4.21x speedup).

Details

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

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
5% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply instructions are used in vector version.
4% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

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

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 does not load or store any data.

General properties

nb instructions	102
nb uops	98
loop length	408
used w registers	12
used x registers	25
used b registers	0
used h registers	0
used s registers	1
used d registers	2
used q registers	0
used v registers	1
used z registers	4
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.25 cycles
front end	12.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	4.00	4.00	20.00	20.00	20.00	20.00	2.50	2.50	1.00	1.00	1.83	1.50	1.67	0.00	0.00
cycles	4.00	4.00	20.00	20.00	20.00	20.00	2.50	2.50	1.50	1.50	1.83	1.50	1.67	0.00	0.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	12.25
Dispatch	20.00
Overall L1	20.00

Vectorization ratios

INT

all	2%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	4%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
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	4%
load	0%
store	0%
mul	0%
add-sub	5%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	4%

Vector efficiency ratios

INT

all	25%
load	31%
store	25%
mul	12%
add-sub	23%
fma	NA (no fma vectorizable/vectorized instructions)
other	27%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
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	27%
load	31%
store	25%
mul	12%
add-sub	27%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 20.00 cycles.

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 412340

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
CMP W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD W10, W10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W12, W12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W6, W6, W11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
B.EQ 412550 <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x370>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X6, X6, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
CMP X17, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 4123a8 <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x1c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X19, XZR, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X19, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X16, X9, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X7, X15, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X18, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X1, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X2, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X26, X16, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 41232c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x14c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W7, W13, W12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
SUB X27, X2, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X22, X1, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X25, X15, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X30, X18, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X16, X20, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
MUL W7, W11, W7	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (12.5%)
SBFM X7, X7, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
ADD X19, X11, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X7, X9, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X1, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X26, X15, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X27, X27, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X28, X2, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X7, X18, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X22, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X25, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X19, X30, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X7, X27	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X28, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X14, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X20, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X26, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X24, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W7, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X14, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W7, W7, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X20, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W7, W7, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X26, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W19, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X24, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W27, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X14, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
ORR W19, W19, W27	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CCMP X26, X3, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W19, W19, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ORR W27, W7, W19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CSINC W7, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X14, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X24, X3, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W19, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
TBNZ W27, #0, 41234c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W7, #0, 41234c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W19, #0, 41234c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X19, [SP, #40]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X30, X9, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR D2, [X20]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
SEL Z1.D, P0, Z1.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
MOVI V3.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ORR X7, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X15, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X18, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X27, X1, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X19, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X19, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
DUP Z2.D, Z2.D[0]	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
ADD X26, X19, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X16, X19, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
ADD X28, X19, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X19, X2, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X30, X16, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
FADD Z1.D, Z3.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP X17, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
ADD X19, X5, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
FADDV D1, P1, Z1.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
STUR D1, [X29, #488]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
B.EQ 41232c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x14c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 412350 <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x170>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	cg_calc_ur(int, int, int, double, double, double, double const, double, double const*) [clone .omp_outlined]
Source file and lines	cg.cpp:105-113
Module	exec

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. Rerun with max-paths=6
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 20.00 to 2.50 cycles (8.00x speedup).

Workaround

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

Vectorization

Details

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

0% of VPU loads are used in vector version.
0% of VPU stores are used in vector version.
5% of VPU addition or subtraction instructions are used in vector version.
0% of VPU multiply instructions are used in vector version.
4% of VPU instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

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

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 does not load or store any data.

General properties

nb instructions	102
nb uops	98
loop length	408
used w registers	12
used x registers	25
used b registers	0
used h registers	0
used s registers	1
used d registers	2
used q registers	0
used v registers	1
used z registers	4
nb stack references	3

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.25 cycles
front end	12.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	4.00	4.00	20.00	20.00	20.00	20.00	2.50	2.50	1.00	1.00	1.83	1.50	1.67	0.00	0.00
cycles	4.00	4.00	20.00	20.00	20.00	20.00	2.50	2.50	1.50	1.50	1.83	1.50	1.67	0.00	0.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

Cycles summary

Front-end	12.25
Dispatch	20.00
Overall L1	20.00

Vectorization ratios

INT

all	2%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	4%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
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	4%
load	0%
store	0%
mul	0%
add-sub	5%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	4%

Vector efficiency ratios

INT

all	25%
load	31%
store	25%
mul	12%
add-sub	23%
fma	NA (no fma vectorizable/vectorized instructions)
other	27%

all	100%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	100%
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	27%
load	31%
store	25%
mul	12%
add-sub	27%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	27%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 20.00 cycles.

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 412340

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
CMP W10, W8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (12.5%)
ADD W10, W10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W12, W12, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W6, W6, W11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
B.EQ 412550 <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x370>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SBFM X6, X6, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
CMP X17, X4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.CS 4123a8 <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x1c8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR X19, XZR, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X19, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X16, X9, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X7, X15, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X18, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X1, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X2, X25,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X26, X16, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
B 41232c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x14c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W7, W13, W12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
SUB X27, X2, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X22, X1, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X25, X15, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X30, X18, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X16, X20, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
MUL W7, W11, W7	1	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	0	0	2	0.50	scal (12.5%)
SBFM X7, X7, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (100.0%)
ADD X19, X11, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X7, X9, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X1, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X26, X15, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X27, X27, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X28, X2, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X7, X18, X7,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X22, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X25, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X19, X30, X19,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CMP X7, X27	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X28, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X14, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X20, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X26, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W30, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X7, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X24, X19, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W7, W30, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X14, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W7, W7, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X20, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W7, W7, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X26, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W19, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X28, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X24, X27, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W27, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X14, X25	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
ORR W19, W19, W27	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CCMP X26, X3, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W19, W19, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
ORR W27, W7, W19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CSINC W7, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
CMP X14, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
CCMP X24, X3, #2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
CSINC W19, WZR, WZR, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (12.5%)
TBNZ W27, #0, 41234c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W7, #0, 41234c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
TBNZ W19, #0, 41234c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x16c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X19, [SP, #40]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X30, X9, X6	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR D2, [X20]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (25.0%)
SEL Z1.D, P0, Z1.D, Z0.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
MOVI V3.2D, #0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	scal (25.0%)
ORR X7, XZR, XZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X24, X15, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X22, X18, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X27, X1, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X25, X19, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X19, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
DUP Z2.D, Z2.D[0]	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
ADD X26, X19, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
LDP X16, X19, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
ADD X28, X19, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X19, X2, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X30, X16, X30,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
HINT #0																			N/A
FADD Z1.D, Z3.D, Z1.D	1	0	0	0	0	0	0	0.50	0.50	0	0	0	0	0	0	0	2	0.50	vect (100.0%)
CMP X17, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
ADD X19, X5, X9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	scal (25.0%)
FADDV D1, P1, Z1.D	1	0	0	0	0	0	0	0.75	0.75	0.25	0.25	0	0	0	0	0	9	2	vect (100.0%)
STUR D1, [X29, #488]	1	0	0	0	0	0	0	0.50	0.50	0	0	0.50	0.50	0	0	0	2	0.50	scal (25.0%)
B.EQ 41232c <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x14c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 412350 <_Z10cg_calc_uriiidPdS_PKdS_S1_.omp_outlined+0x170>	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

Code clean check

Workaround

Vectorization

Details

Workaround

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

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

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code