OV - K-Means scalability acfl-O3 100000000 - Function k_means(int, point_t*, point_t*, int*, int, int) [clone .omp

	Function: k_means(int, point_t, point_t, int*, int, int) [clone .omp_outlined.3]	Module: kmeans-acfl-O3	Source: main.cpp:138-143	Coverage (incl. loops): 0.01% \| (excl. loops): 0.00%

/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 138 - 143

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

138:         #pragma omp parallel for reduction(+:sum_x[:k], sum_y[:k], count[:k])

139:         for (int i = 0; i < n; ++i) {

140:             int cid = assignment[i];

141:             count[cid] += 1;

142:             sum_x[cid] += points[i].x;

143:             sum_y[cid] += points[i].y;

0x1f54 STP	X29, X30, [SP, #928]!

0x1f58 STP	X28, X27, [SP, #16]

0x1f5c STP	X26, X25, [SP, #32]

0x1f60 STP	X24, X23, [SP, #48]

0x1f64 STP	X22, X21, [SP, #64]

0x1f68 STP	X20, X19, [SP, #80]

0x1f6c ADD	X29, SP, #0

0x1f70 SUB	SP, SP, #160

0x1f74 LDR	W8, [X2]

0x1f78 SUBS	W28, W8, #1

0x1f7c B.LT	2410

0x1f80 LDR	X20, [X29, #120]

0x1f84 ADD	X8, SP, #0

0x1f88 MOVZ	W9, #1

0x1f8c STUR	X8, [X29, #416]

0x1f90 ORR	X23, XZR, X7

0x1f94 ORR	X19, XZR, X5

0x1f98 LDRSW	X8, [X20]

0x1f9c STP	WZR, W9, [X29, #488]

0x1fa0 ADD	X9, SP, #0

0x1fa4 ORR	X25, XZR, X3

0x1fa8 ORR	X21, XZR, X0

0x1fac STP	W28, WZR, [X29, #496]

0x1fb0 UBFM	X8, X8, #61, #60

0x1fb4 SUB	X22, X8, #8

0x1fb8 ADD	X8, X8, #15

0x1fbc SBFM	X10, X22, #3, #63

0x1fc0 AND	X8, X8, #7932

0x1fc4 SUB	X24, X9, X8

0x1fc8 ADD	X10, X10, #1

0x1fcc ADD	SP, X24, #0

0x1fd0 ANDS	X8, X10, #7936

0x1fd4 STUR	X10, [X29, #424]

0x1fd8 STUR	X8, [X29, #392]

0x1fdc B.EQ	1ff0

0x1fe0 ADD	X2, X22, #8

0x1fe4 ORR	X0, XZR, X24

0x1fe8 ORR	W1, WZR, WZR

0x1fec BL	13d0

0x1ff0 LDRSW	X20, [X20]

0x1ff4 STUR	X22, [X29, #368]

0x1ff8 UBFM	X8, X20, #61, #60

0x1ffc SUB	X26, X8, #8

0x2000 ADD	X8, X8, #15

0x2004 SBFM	X9, X26, #3, #63

0x2008 AND	X8, X8, #7932

0x200c ADD	X10, X9, #1

0x2010 ADD	X9, SP, #0

0x2014 SUB	X22, X9, X8

0x2018 ADD	SP, X22, #0

0x201c ANDS	X8, X10, #7936

0x2020 STUR	X10, [X29, #432]

0x2024 STUR	X8, [X29, #400]

0x2028 B.EQ	203c

0x202c ADD	X2, X26, #8

0x2030 ORR	X0, XZR, X22

0x2034 ORR	W1, WZR, WZR

0x2038 BL	13d0

0x203c UBFM	X8, X20, #62, #61

0x2040 STUR	X26, [X29, #376]

0x2044 SUB	X27, X8, #4

0x2048 ADD	X8, X8, #15

0x204c SBFM	X9, X27, #2, #63

0x2050 AND	X8, X8, #7932

0x2054 STUR	X9, [X29, #360]

0x2058 ADD	X10, X9, #1

0x205c ADD	X9, SP, #0

0x2060 SUB	X20, X9, X8

0x2064 ADD	SP, X20, #0

0x2068 ORR	X26, XZR, X10

0x206c ANDS	X8, X10, #8000

0x2070 STUR	X8, [X29, #408]

0x2074 B.EQ	2088

0x2078 ADD	X2, X27, #4

0x207c ORR	X0, XZR, X20

0x2080 ORR	W1, WZR, WZR

0x2084 BL	13d0

0x2088 STUR	X27, [X29, #384]

0x208c LDR	X27, [X29, #112]

0x2090 LDR	W21, [X21]

0x2094 MOVZ	W8, #1

0x2098 ADRP	X0,

0x209c ADD	X0, X0, #3312

0x20a0 SUB	X3, X29, #24

0x20a4 SUB	X4, X29, #12

0x20a8 SUB	X5, X29, #16

0x20ac SUB	X6, X29, #20

0x20b0 ORR	W1, WZR, W21

0x20b4 MOVZ	W2, #34

0x20b8 MOVZ	W7, #1

0x20bc STR	W8, [SP, #496]!

0x20c0 BL	1450

0x20c4 ADD	SP, SP, #16

0x20c8 LDP	W8, W9, [X29, #496]

0x20cc SBFM	X9, X9, #0, #31

0x20d0 CMP	W8, W28

0x20d4 CSEL	W10, W8, W28, #11

0x20d8 CMP	W9, W10

0x20dc B.GT	2138

0x20e0 LDR	X8, [X29, #96]

0x20e4 LDR	X11, [X25]

0x20e8 SUB	W10, W10, W9

0x20ec ADD	W10, W10, #1

0x20f0 LDR	X8, [X8]

0x20f4 ADD	X12, X8, X9,LSL #4

0x20f8 ADD	X8, X11, X9,LSL #2

0x20fc ADD	X9, X12, #8

(25) 0x2100 LDRSW	X11, [X8], #4

(25) 0x2104 LDUR	D0, [X9, #504]

(25) 0x2108 SUBS	W10, W10, #1

(25) 0x210c LDR	D1, [X24, X11,LSL #3]

(25) 0x2110 LDR	W12, [X20, X11,LSL #2]

(25) 0x2114 FADD	D0, D0, D1

(25) 0x2118 LDR	D1, [X22, X11,LSL #3]

(25) 0x211c ADD	W12, W12, #1

(25) 0x2120 STR	W12, [X20, X11,LSL #2]

(25) 0x2124 STR	D0, [X24, X11,LSL #3]

(25) 0x2128 LDR	D0, [X9], #16

(25) 0x212c FADD	D0, D0, D1

(25) 0x2130 STR	D0, [X22, X11,LSL #3]

(25) 0x2134 B.NE	2100

0x2138 ADRP	X0,

0x213c ADD	X0, X0, #3336

0x2140 ORR	W1, WZR, W21

0x2144 BL	12e0

0x2148 LDP	X9, X8, [X29, #936]

0x214c ADRP	X6,

0x2150 STP	X20, X26, [X29, #984]

0x2154 ADRP	X0,

0x2158 ADD	X0, X0, #3360

0x215c ADRP	X5,

0x2160 ADD	X5, X5, #3376

0x2164 SUB	X4, X29, #72

0x2168 STP	X24, X9, [X29, #952]

0x216c ORR	W1, WZR, W21

0x2170 MOVZ	W2, #3

0x2174 STP	X22, X8, [X29, #968]

0x2178 MOVZ	W3, #48

0x217c LDR	X6, [X6, #4016]

0x2180 BL	1330

0x2184 CMP	W0, #2

0x2188 B.EQ	2350

0x218c LDUR	X25, [X29, #416]

0x2190 CMP	W0, #1

0x2194 B.NE	240c

0x2198 LDP	X9, X15, [X29, #880]

0x219c LDUR	X8, [X29, #392]

0x21a0 CBZ	X8, 2224

0x21a4 CMP	X9, #24

0x21a8 ORR	X8, XZR, X23

0x21ac B.CC	2204

0x21b0 UBFM	X8, X9, #3, #63

0x21b4 ADD	X12, X23, #16

0x21b8 ADD	X13, X24, #16

0x21bc ADD	X9, X8, #1

0x21c0 AND	X10, X9, #7934

0x21c4 UBFM	X8, X10, #61, #60

0x21c8 ORR	X14, XZR, X10

0x21cc ADD	X11, X24, X8

0x21d0 ADD	X8, X23, X8

(24) 0x21d4 LDP	Q0, Q3, [X13, #2032]

(24) 0x21d8 SUBS	X14, X14, #4

(24) 0x21dc LDP	Q1, Q2, [X12, #2032]

(24) 0x21e0 ADD	X13, X13, #32

(24) 0x21e4 FADD	V0.2D, V1.2D, V0.2D

(24) 0x21e8 FADD	V1.2D, V2.2D, V3.2D

(24) 0x21ec STP	Q0, Q1, [X12, #2032]

(24) 0x21f0 ADD	X12, X12, #32

(24) 0x21f4 B.NE	21d4

0x21f8 CMP	X9, X10

0x21fc ORR	X24, XZR, X11

0x2200 B.EQ	2224

0x2204 LDUR	X9, [X29, #424]

0x2208 ADD	X9, X23, X9,LSL #3

(23) 0x220c LDR	D0, [X8]

(23) 0x2210 LDR	D1, [X24], #8

(23) 0x2214 FADD	D0, D0, D1

(23) 0x2218 STR	D0, [X8], #8

(23) 0x221c CMP	X8, X9

(23) 0x2220 B.NE	220c

0x2224 LDUR	X8, [X29, #400]

0x2228 CBZ	X8, 22ac

0x222c CMP	X15, #24

0x2230 ORR	X8, XZR, X27

0x2234 B.CC	228c

0x2238 UBFM	X8, X15, #3, #63

0x223c ADD	X12, X27, #16

0x2240 ADD	X13, X22, #16

0x2244 ADD	X9, X8, #1

0x2248 AND	X10, X9, #7934

0x224c UBFM	X8, X10, #61, #60

0x2250 ORR	X14, XZR, X10

0x2254 ADD	X11, X22, X8

0x2258 ADD	X8, X27, X8

(22) 0x225c LDP	Q0, Q3, [X13, #2032]

(22) 0x2260 SUBS	X14, X14, #4

(22) 0x2264 LDP	Q1, Q2, [X12, #2032]

(22) 0x2268 ADD	X13, X13, #32

(22) 0x226c FADD	V0.2D, V1.2D, V0.2D

(22) 0x2270 FADD	V1.2D, V2.2D, V3.2D

(22) 0x2274 STP	Q0, Q1, [X12, #2032]

(22) 0x2278 ADD	X12, X12, #32

(22) 0x227c B.NE	225c

0x2280 CMP	X9, X10

0x2284 ORR	X22, XZR, X11

0x2288 B.EQ	22ac

0x228c LDUR	X9, [X29, #432]

0x2290 ADD	X9, X27, X9,LSL #3

(21) 0x2294 LDR	D0, [X8]

(21) 0x2298 LDR	D1, [X22], #8

(21) 0x229c FADD	D0, D0, D1

(21) 0x22a0 STR	D0, [X8], #8

(21) 0x22a4 CMP	X8, X9

(21) 0x22a8 B.NE	2294

0x22ac LDUR	X8, [X29, #408]

0x22b0 LDUR	X9, [X29, #384]

0x22b4 CBZ	X8, 2334

0x22b8 CMP	X9, #28

0x22bc ORR	X8, XZR, X19

0x22c0 B.CC	2318

0x22c4 UBFM	X8, X9, #2, #63

0x22c8 ADD	X12, X19, #16

0x22cc ADD	X13, X20, #16

0x22d0 ADD	X9, X8, #1

0x22d4 AND	X10, X9, #7933

0x22d8 UBFM	X8, X10, #62, #61

0x22dc ORR	X14, XZR, X10

0x22e0 ADD	X11, X20, X8

0x22e4 ADD	X8, X19, X8

(20) 0x22e8 LDP	Q0, Q3, [X13, #2032]

(20) 0x22ec SUBS	X14, X14, #8

(20) 0x22f0 LDP	Q1, Q2, [X12, #2032]

(20) 0x22f4 ADD	X13, X13, #32

(20) 0x22f8 ADD	V0.4S, V0.4S, V1.4S

(20) 0x22fc ADD	V1.4S, V3.4S, V2.4S

(20) 0x2300 STP	Q0, Q1, [X12, #2032]

(20) 0x2304 ADD	X12, X12, #32

(20) 0x2308 B.NE	22e8

0x230c CMP	X9, X10

0x2310 ORR	X20, XZR, X11

0x2314 B.EQ	2334

0x2318 ADD	X9, X19, X26,LSL #2

(19) 0x231c LDR	W10, [X8]

(19) 0x2320 LDR	W11, [X20], #4

(19) 0x2324 ADD	W10, W11, W10

(19) 0x2328 STR	W10, [X8], #4

(19) 0x232c CMP	X8, X9

(19) 0x2330 B.NE	231c

0x2334 ADRP	X2,

0x2338 ADRP	X0,

0x233c ADD	X0, X0, #3360

0x2340 LDR	X2, [X2, #4016]

0x2344 ORR	W1, WZR, W21

0x2348 BL	1360

0x234c B	240c

0x2350 LDUR	X25, [X29, #416]

0x2354 LDUR	X8, [X29, #392]

0x2358 CBZ	X8, 239c

0x235c LDUR	X8, [X29, #424]

0x2360 ADD	X8, X23, X8,LSL #3

(18) 0x2364 LDR	D0, [X24]

(18) 0x2368 LDR	D1, [X23]

  (17) 0x236c FADD	D2, D1, D0

  (17) 0x2370 FMOV	X9, D1

  (17) 0x2374 ORR	X11, XZR, X9

  (17) 0x2378 FMOV	X10, D2

  (17) 0x237c CAS	X11, X10, [X23]

  (17) 0x2380 FMOV	D1, X11

  (17) 0x2384 CMP	X11, X9

  (17) 0x2388 B.NE	236c

(18) 0x238c ADD	X23, X23, #8

(18) 0x2390 ADD	X24, X24, #8

(18) 0x2394 CMP	X23, X8

(18) 0x2398 B.NE	2364

0x239c LDUR	X8, [X29, #400]

0x23a0 CBZ	X8, 23e4

0x23a4 LDUR	X8, [X29, #432]

0x23a8 ADD	X8, X27, X8,LSL #3

(16) 0x23ac LDR	D0, [X22]

(16) 0x23b0 LDR	D1, [X27]

  (15) 0x23b4 FADD	D2, D1, D0

  (15) 0x23b8 FMOV	X9, D1

  (15) 0x23bc ORR	X11, XZR, X9

  (15) 0x23c0 FMOV	X10, D2

  (15) 0x23c4 CAS	X11, X10, [X27]

  (15) 0x23c8 FMOV	D1, X11

  (15) 0x23cc CMP	X11, X9

  (15) 0x23d0 B.NE	23b4

(16) 0x23d4 ADD	X27, X27, #8

(16) 0x23d8 ADD	X22, X22, #8

(16) 0x23dc CMP	X27, X8

(16) 0x23e0 B.NE	23ac

0x23e4 LDUR	X8, [X29, #408]

0x23e8 CBZ	X8, 240c

0x23ec LDUR	X8, [X29, #360]

0x23f0 UBFM	X8, X8, #62, #61

0x23f4 ADD	X8, X8, #4

(14) 0x23f8 LDR	W9, [X20], #4

(14) 0x23fc SUBS	X8, X8, #4

(14) 0x2400 LDADD	W9, W9, [X19]

(14) 0x2404 ADD	X19, X19, #4

(14) 0x2408 B.NE	23f8

0x240c ADD	SP, X25, #0

0x2410 ADD	SP, X29, #0

0x2414 LDP	X20, X19, [SP, #80]

0x2418 LDP	X22, X21, [SP, #64]

0x241c LDP	X24, X23, [SP, #48]

0x2420 LDP	X26, X25, [SP, #32]

0x2424 LDP	X28, X27, [SP, #16]

0x2428 LDP	X29, X30, [SP], #96

0x242c RET

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

Coverage (%)	Name	Source Location	Module
○100.00	__kmp_invoke_microtask		libomp.so

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 run_1_thread

Source file and lines	main.cpp:138-143
Module	kmeans-acfl-O3

The function is defined in /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138-143.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 28% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 35.75 to 20.72 cycles (1.73x speedup).

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 35.75 to 3.50 cycles (10.21x speedup).

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

unknown: 7 occurrences►
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:139
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:139
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:139
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 320 bytes. The binary function is storing 244 bytes.

General properties

nb instructions	219
nb uops	219
loop length	876
used w registers	11
used x registers	28
used b registers	0
used h registers	0
used s registers	1
used d registers	0
used q registers	0
used v registers	0
used z registers	0
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	27.38 cycles
front end	27.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	14.00	14.00	35.75	35.75	35.75	35.75	0.00	0.00	0.00	0.00	18.67	18.67	18.67	11.00	11.00
cycles	14.00	14.00	35.75	35.75	35.75	35.75	0.00	0.00	0.00	0.00	18.67	18.67	18.67	11.00	11.00

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	27.38
Dispatch	35.75
Overall L1	35.75

Vectorization ratios

all	0%
load	0%
store	0%
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	0%

Vector efficiency ratios

all	28%
load	34%
store	34%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	24%
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 call to the function takes 35.75 cycles. At this rate:

9% of peak load performance is reached (8.95 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
14% of peak store performance is reached (6.83 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 function is: 1f54

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #928]!	1	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X28, X27, [SP, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X26, X25, [SP, #32]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X24, X23, [SP, #48]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB SP, SP, #160	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDR W8, [X2]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
SUBS W28, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.LT 2410 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X20, [X29, #120]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
MOVZ W9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
STUR X8, [X29, #416]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X23, XZR, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X19, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDRSW X8, [X20]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP WZR, W9, [X29, #488]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ADD X9, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X25, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X21, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STP W28, WZR, [X29, #496]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
UBFM X8, X8, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB X22, X8, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X8, #15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SBFM X10, X22, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
AND X8, X8, #7932	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB X24, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X10, X10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD SP, X24, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ANDS X8, X10, #7936	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	N/A
STUR X10, [X29, #424]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STUR X8, [X29, #392]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.EQ 1ff0 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x9c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X2, X22, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X0, XZR, X24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, WZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 13d0 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
LDRSW X20, [X20]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STUR X22, [X29, #368]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
UBFM X8, X20, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB X26, X8, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X8, #15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SBFM X9, X26, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
AND X8, X8, #7932	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X10, X9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X22, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD SP, X22, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ANDS X8, X10, #7936	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	N/A
STUR X10, [X29, #432]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STUR X8, [X29, #400]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.EQ 203c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0xe8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X2, X26, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, WZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 13d0 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X20, #62, #61	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STUR X26, [X29, #376]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
SUB X27, X8, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X8, #15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SBFM X9, X27, #2, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
AND X8, X8, #7932	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STUR X9, [X29, #360]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ADD X10, X9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X20, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD SP, X20, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X26, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ANDS X8, X10, #8000	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	N/A
STUR X8, [X29, #408]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.EQ 2088 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x134>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X2, X27, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X0, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, WZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 13d0 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
STUR X27, [X29, #384]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X27, [X29, #112]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR W21, [X21]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MOVZ W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADRP X0, <1f098>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3312	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X3, X29, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X4, X29, #12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X5, X29, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X6, X29, #20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
MOVZ W2, #34	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
MOVZ W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
STR W8, [SP, #496]!	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (12.5%)
BL 1450 <@plt_start@+0x1a0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
ADD SP, SP, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDP W8, W9, [X29, #496]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
SBFM X9, X9, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
CMP W8, W28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
CSEL W10, W8, W28, #11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
CMP W9, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.GT 2138 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x1e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X29, #96]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X25]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SUB W10, W10, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W10, W10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
LDR X8, [X8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X12, X8, X9,LSL #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X11, X9,LSL #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X9, X12, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADRP X0, <1f138>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3336	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 12e0 <@plt_start@+0x30>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
LDP X9, X8, [X29, #936]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADRP X6, <1f14c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STP X20, X26, [X29, #984]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADRP X0, <1f154>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3360	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADRP X5, <20000115c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X5, X5, #3376	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X4, X29, #72	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
STP X24, X9, [X29, #952]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
MOVZ W2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STP X22, X8, [X29, #968]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
MOVZ W3, #48	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
LDR X6, [X6, #4016]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 1330 <@plt_start@+0x80>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
CMP W0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 2350 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X25, [X29, #416]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP W0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.NE 240c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X9, X15, [X29, #880]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDUR X8, [X29, #392]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 2224 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X9, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X8, XZR, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.CC 2204 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x2b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X9, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X12, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X24, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
AND X10, X9, #7934	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X8, X10, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X14, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X24, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X23, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
CMP X9, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X24, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
B.EQ 2224 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X9, [X29, #424]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X23, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X8, [X29, #400]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 22ac <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X15, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X8, XZR, X27	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.CC 228c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X15, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X12, X27, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X22, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
AND X10, X9, #7934	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X8, X10, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X14, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X22, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X27, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
CMP X9, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X22, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
B.EQ 22ac <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X9, [X29, #432]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X27, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X8, [X29, #408]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDUR X9, [X29, #384]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CBZ X8, 2334 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X9, #28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X8, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.CC 2318 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X9, #2, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X12, X19, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X20, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
AND X10, X9, #7933	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X8, X10, #62, #61	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X14, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X20, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X19, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
CMP X9, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X20, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.EQ 2334 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X9, X19, X26,LSL #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADRP X2, <1f334>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADRP X0, <1f338>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3360	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X2, [X2, #4016]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 1360 <@plt_start@+0xb0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
B 240c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X25, [X29, #416]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDUR X8, [X29, #392]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 239c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x448>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X8, [X29, #424]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X23, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDUR X8, [X29, #400]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 23e4 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x490>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X8, [X29, #432]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X27, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDUR X8, [X29, #408]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 240c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X8, [X29, #360]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
UBFM X8, X8, #62, #61	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X8, X8, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD SP, X25, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD SP, X29, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X24, X23, [SP, #48]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X26, X25, [SP, #32]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X28, X27, [SP, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X29, X30, [SP], #96	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run run_1_thread

Source file and lines	main.cpp:138-143
Module	kmeans-acfl-O3

The function is defined in /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138-143.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 35.75 to 3.50 cycles (10.21x speedup).

CALL instructions

Detected function call instructions.

Details

unknown: 7 occurrences►
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:139
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:139
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:139
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138
- /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp:138

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 320 bytes. The binary function is storing 244 bytes.

General properties

nb instructions	219
nb uops	219
loop length	876
used w registers	11
used x registers	28
used b registers	0
used h registers	0
used s registers	1
used d registers	0
used q registers	0
used v registers	0
used z registers	0
nb stack references	13

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	27.38 cycles
front end	27.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	14.00	14.00	35.75	35.75	35.75	35.75	0.00	0.00	0.00	0.00	18.67	18.67	18.67	11.00	11.00
cycles	14.00	14.00	35.75	35.75	35.75	35.75	0.00	0.00	0.00	0.00	18.67	18.67	18.67	11.00	11.00

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	27.38
Dispatch	35.75
Overall L1	35.75

Vectorization ratios

all	0%
load	0%
store	0%
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	0%

Vector efficiency ratios

all	28%
load	34%
store	34%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	24%
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 call to the function takes 35.75 cycles. At this rate:

9% of peak load performance is reached (8.95 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
14% of peak store performance is reached (6.83 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 function is: 1f54

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #928]!	1	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X28, X27, [SP, #16]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X26, X25, [SP, #32]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X24, X23, [SP, #48]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
STP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADD X29, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB SP, SP, #160	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDR W8, [X2]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
SUBS W28, W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.LT 2410 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4bc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X20, [X29, #120]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
MOVZ W9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
STUR X8, [X29, #416]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ORR X23, XZR, X7	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X19, XZR, X5	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDRSW X8, [X20]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STP WZR, W9, [X29, #488]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ADD X9, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR X25, XZR, X3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X21, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STP W28, WZR, [X29, #496]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
UBFM X8, X8, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB X22, X8, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X8, #15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SBFM X10, X22, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
AND X8, X8, #7932	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB X24, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X10, X10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD SP, X24, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ANDS X8, X10, #7936	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	N/A
STUR X10, [X29, #424]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STUR X8, [X29, #392]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.EQ 1ff0 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x9c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X2, X22, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X0, XZR, X24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, WZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 13d0 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
LDRSW X20, [X20]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
STUR X22, [X29, #368]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
UBFM X8, X20, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SUB X26, X8, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X8, #15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SBFM X9, X26, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
AND X8, X8, #7932	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X10, X9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X22, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD SP, X22, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ANDS X8, X10, #7936	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	N/A
STUR X10, [X29, #432]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
STUR X8, [X29, #400]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.EQ 203c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0xe8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X2, X26, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X0, XZR, X22	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, WZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 13d0 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X20, #62, #61	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STUR X26, [X29, #376]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
SUB X27, X8, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X8, #15	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
SBFM X9, X27, #2, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
AND X8, X8, #7932	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STUR X9, [X29, #360]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
ADD X10, X9, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, SP, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X20, X9, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD SP, X20, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X26, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ANDS X8, X10, #8000	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	N/A
STUR X8, [X29, #408]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
B.EQ 2088 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x134>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X2, X27, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X0, XZR, X20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, WZR	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 13d0 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
STUR X27, [X29, #384]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR X27, [X29, #112]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
LDR W21, [X21]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
MOVZ W8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADRP X0, <1f098>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3312	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X3, X29, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X4, X29, #12	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X5, X29, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X6, X29, #20	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
MOVZ W2, #34	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
MOVZ W7, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
STR W8, [SP, #496]!	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (12.5%)
BL 1450 <@plt_start@+0x1a0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
ADD SP, SP, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDP W8, W9, [X29, #496]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
SBFM X9, X9, #0, #31	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (100.0%)
CMP W8, W28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
CSEL W10, W8, W28, #11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
CMP W9, W10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.GT 2138 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x1e4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR X8, [X29, #96]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR X11, [X25]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SUB W10, W10, W9	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
ADD W10, W10, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
LDR X8, [X8]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X12, X8, X9,LSL #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X11, X9,LSL #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X9, X12, #8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADRP X0, <1f138>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3336	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 12e0 <@plt_start@+0x30>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
LDP X9, X8, [X29, #936]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
ADRP X6, <1f14c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STP X20, X26, [X29, #984]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ADRP X0, <1f154>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3360	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADRP X5, <20000115c>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X5, X5, #3376	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
SUB X4, X29, #72	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
STP X24, X9, [X29, #952]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
MOVZ W2, #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
STP X22, X8, [X29, #968]	1	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
MOVZ W3, #48	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
LDR X6, [X6, #4016]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 1330 <@plt_start@+0x80>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
CMP W0, #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.EQ 2350 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3fc>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X25, [X29, #416]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CMP W0, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (12.5%)
B.NE 240c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDP X9, X15, [X29, #880]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDUR X8, [X29, #392]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 2224 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X9, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X8, XZR, X23	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.CC 2204 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x2b0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X9, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X12, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X24, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
AND X10, X9, #7934	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X8, X10, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X14, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X24, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X23, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
CMP X9, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X24, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
B.EQ 2224 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x2d0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X9, [X29, #424]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X23, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X8, [X29, #400]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 22ac <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X15, #24	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X8, XZR, X27	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.CC 228c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X15, #3, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X12, X27, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X22, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
AND X10, X9, #7934	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X8, X10, #61, #60	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X14, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X22, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X27, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
CMP X9, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X22, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
B.EQ 22ac <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x358>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X9, [X29, #432]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD X9, X27, X9,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDUR X8, [X29, #408]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDUR X9, [X29, #384]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
CBZ X8, 2334 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP X9, #28	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X8, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.CC 2318 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3c4>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
UBFM X8, X9, #2, #63	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X12, X19, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X13, X20, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X9, X8, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
AND X10, X9, #7933	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
UBFM X8, X10, #62, #61	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ORR X14, XZR, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X11, X20, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X8, X19, X8	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
CMP X9, X10	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
ORR X20, XZR, X11	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
B.EQ 2334 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x3e0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD X9, X19, X26,LSL #2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADRP X2, <1f334>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADRP X0, <1f338>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
ADD X0, X0, #3360	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (25.0%)
LDR X2, [X2, #4016]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ORR W1, WZR, W21	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	scal (12.5%)
BL 1360 <@plt_start@+0xb0>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	1	0.50	N/A
B 240c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X25, [X29, #416]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDUR X8, [X29, #392]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 239c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x448>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X8, [X29, #424]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X23, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDUR X8, [X29, #400]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 23e4 <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x490>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X8, [X29, #432]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
ADD X8, X27, X8,LSL #3	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDUR X8, [X29, #408]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
CBZ X8, 240c <_Z7k_meansiP7point_tS0_Piii.omp_outlined.3+0x4b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDUR X8, [X29, #360]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
UBFM X8, X8, #62, #61	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD X8, X8, #4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD SP, X25, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
ADD SP, X29, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	1	0.25	N/A
LDP X20, X19, [SP, #80]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X22, X21, [SP, #64]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X24, X23, [SP, #48]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X26, X25, [SP, #32]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X28, X27, [SP, #16]	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
LDP X29, X30, [SP], #96	1	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A

▶Scalability Runs Description

Run run_1_thread	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_NUM_THREADS: 1OMP_PLACES: cores
Run run_2_threads	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PLACES: coresOMP_PROC_BIND: closeOMP_NUM_THREADS: 2
Run run_4_threads	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PLACES: coresOMP_PROC_BIND: closeOMP_NUM_THREADS: 4
Run run_8_threads	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PLACES: coresOMP_PROC_BIND: closeOMP_NUM_THREADS: 8
Run run_16_threads	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PLACES: coresOMP_PROC_BIND: closeOMP_NUM_THREADS: 16
Run run_32_threads	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 32
Run run_64_threads	Number processes: 1Number nodes: 1Run Command: <executable> kmeans/input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: closeOMP_PLACES: coresOMP_NUM_THREADS: 64

(run_1_thread) Efficiency	(run_1_thread) Potential Speed-Up (%)	(run_2_threads) Efficiency	(run_2_threads) Potential Speed-Up (%)	(run_4_threads) Efficiency	(run_4_threads) Potential Speed-Up (%)	(run_8_threads) Efficiency	(run_8_threads) Potential Speed-Up (%)	(run_16_threads) Efficiency	(run_16_threads) Potential Speed-Up (%)	(run_32_threads) Efficiency	(run_32_threads) Potential Speed-Up (%)	(run_64_threads) Efficiency	(run_64_threads) Potential Speed-Up (%)
1	0	0.33	0.02	0.14	0.07	0.07	0.14	0.02	0.58	0	2.22	0	6.42

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
run_1_thread	1	1	1	1	0.014999998733401	0.011545123532414
run_2_threads	2	0.33	0.66	2	0.025000000372529	0.034394461661577
run_4_threads	4	0.14	0.54	4	0.044999994337559	0.08256708085537
run_8_threads	8	0.07	0.57	8	0.049999997019768	0.1558672785759
run_16_threads	16	0.02	0.29	16	0.10499998927116	0.59189110994339
run_32_threads	31	0	0.14	32	0.18499997258186	2.2254490852356
run_64_threads	64	0	0.08	64	0.20500001311302	6.4298806190491

Name	Coverage (%)	Time (s)
▼k_means(int, point_t, point_t, int*, int, int) [clone .omp_outlined.3]–	0.01	0.01
○Loop 25 - main.cpp:139-143 - kmeans-acfl-O3	0.01	0.01
○Loop 22 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
○Loop 14 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
○Loop 24 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
▼Loop 18 - main.cpp:138-138 - kmeans-acfl-O3–	0.00	0.00
○Loop 17 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
▼Loop 16 - main.cpp:138-138 - kmeans-acfl-O3–	0.00	0.00
○Loop 15 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
○Loop 23 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
○Loop 21 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
○Loop 20 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00
○Loop 19 - main.cpp:138-138 - kmeans-acfl-O3	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Expensive FP math instructions/calls

CALL instructions

Details

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Expensive FP math instructions/calls

CALL instructions

Details

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

▶Scalability Runs Description

▼Columns Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency