OV - exec - Function cg_calc_p(int, int, int, double, double*, double const*) [clone ._omp

	Function: cg_calc_p(int, int, int, double, double, double const) [clone ._omp_fn.0]	Module: exec	Source: cg.cpp:125-131	Coverage (incl. loops): 20.75% \| (excl. loops): 0.01%

/home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp: 125 - 131

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

125:   #pragma omp parallel for

126: #endif

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

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

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

130:

131:       p[index] = beta * p[index] + r[index];

0x411884 STP	X29, X30, [SP, #976]!

0x411888 ADD	X29, SP, #0

0x41188c STP	X19, X20, [SP, #16]

0x411890 ORR	X20, XZR, X0

0x411894 STR	X21, [SP, #32]

0x411898 LDR	W21, [X0, #32]

0x41189c BL	410320

0x4118a0 ORR	W19, WZR, W0

0x4118a4 BL	4102b0

0x4118a8 LDR	W1, [X20, #28]

0x4118ac ORR	W4, WZR, W0

0x4118b0 SUB	W0, W1, W21,LSL #1

0x4118b4 SDIV	W2, W0, W19

0x4118b8 MSUB	W1, W2, W19, W0

0x4118bc CMP	W4, W1

0x4118c0 B.LT	411a04

0x4118c4 MADD	W4, W2, W4, W1

0x4118c8 ADD	W2, W2, W4

0x4118cc CMP	W4, W2

0x4118d0 B.GE	4119b4

0x4118d4 LDR	W12, [X20, #24]

0x4118d8 ADD	W4, W21, W4

0x4118dc ADD	W7, W21, W2

0x4118e0 LDP	X5, X8, [X20, #8]

0x4118e4 SUB	W11, W12, W21

0x4118e8 LDR	D31, [X20]

0x4118ec CMP	W21, W11

0x4118f0 B.GE	4119b4

0x4118f4 MUL	W9, W12, W4

0x4118f8 SBFM	X0, X21, #0, #31

0x4118fc SUB	W11, W11, W21

0x411900 ADD	X6, X0, #1

0x411904 UBFM	X14, X11, #61, #31

0x411908 DUP	V30.2D, V31.D[0]

0x41190c UBFM	W3, W11, #1, #31

0x411910 AND	W13, W11, #0xfffffffe

0x411914 SBFM	X1, X9, #0, #31

0x411918 MOVN	X15, #7

0x41191c ADD	X6, X6, X1

0x411920 ADD	X0, X0, X1

0x411924 SUB	X14, X14, X8

0x411928 ADD	X6, X8, X6,LSL #3

0x41192c SUB	W16, W11, #1

0x411930 ADD	X1, X5, X0,LSL #3

0x411934 ADD	X14, X14, X15

0x411938 UBFM	X3, X3, #60, #59

0x41193c ADD	W13, W13, W21

0x411940 AND	W11, W11, #0x1

0x411944 SUB	X15, X15, X8

0x411948 SBFM	X10, X12, #61, #31

(29) 0x41194c CMP	W16, #1

(29) 0x411950 B.LS	4119c4

  (31) 0x411954 CMP	X1, X6

  (31) 0x411958 B.EQ	4119c4

  (31) 0x41195c MOVZ	X0, #0

  (31) 0x411960 SUB	X2, X6, #8

    (30) 0x411964 LDR	Q3, [X1, X0]

    (30) 0x411968 LDR	Q2, [X2, X0]

    (30) 0x41196c FMLA	V2.2D, V3.2D, V30.2D

    (30) 0x411970 STR	Q2, [X1, X0]

    (30) 0x411974 ADD	X0, X0, #16

    (30) 0x411978 CMP	X0, X3

    (30) 0x41197c B.NE	411964

  (31) 0x411980 CBZ	W11, 41199c

  (31) 0x411984 ADD	W0, W13, W9

  (31) 0x411988 SBFM	X0, X0, #61, #31

  (31) 0x41198c LDR	D1, [X5, X0]

  (31) 0x411990 LDR	D0, [X8, X0]

  (31) 0x411994 FMADD	D0, D31, D1, D0

  (31) 0x411998 STR	D0, [X5, X0]

  (31) 0x41199c ADD	W4, W4, #1

  (31) 0x4119a0 ADD	W9, W9, W12

  (31) 0x4119a4 ADD	X6, X6, X10

  (31) 0x4119a8 ADD	X1, X1, X10

  (31) 0x4119ac CMP	W7, W4

  (31) 0x4119b0 B.GT	411954

0x4119b4 LDR	X21, [SP, #32]

0x4119b8 LDP	X19, X20, [SP, #16]

0x4119bc LDP	X29, X30, [SP], #48

0x4119c0 RET

(29) 0x4119c4 ADD	X0, X15, X6

(29) 0x4119c8 ADD	X2, X14, X6

  (28) 0x4119cc LDR	D29, [X5, X0]

  (28) 0x4119d0 LDR	D28, [X8, X0]

  (28) 0x4119d4 FMADD	D28, D31, D29, D28

  (28) 0x4119d8 STR	D28, [X5, X0]

  (28) 0x4119dc ADD	X0, X0, #8

  (28) 0x4119e0 CMP	X0, X2

  (28) 0x4119e4 B.NE	4119cc

(29) 0x4119e8 ADD	W4, W4, #1

(29) 0x4119ec ADD	W9, W9, W12

(29) 0x4119f0 ADD	X6, X6, X10

(29) 0x4119f4 ADD	X1, X1, X10

(29) 0x4119f8 CMP	W7, W4

(29) 0x4119fc B.GT	41194c

0x411a00 B	4119b4

0x411a04 ADD	W2, W2, #1

0x411a08 MOVZ	W1, #0

0x411a0c B	4118c4

Coverage (%)	Name	Source Location	Module
►98.43+	omp_fulfill_event		libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.57+	GOMP_parallel		libgomp.so.1.0.0
○	run_cg_calc_p(Chunk*, Settings[...]	cg.cpp:125	exec
○	cg_main_step_driver(Chunk*, Se[...]	cg_driver.cpp:83	exec
○	cg_driver(Chunk*, Settings&, d[...]	cg_driver.cpp:18	exec
○	solve(Chunk*, Settings&, int, [...]	diffuse.cpp:51	exec
○	diffuse(Chunk*, Settings&)	diffuse.cpp:12	exec
○	main	main.cpp:179	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	new_allocator.h:104	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 /

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 0.01% of application time for run gcc_0

Source file and lines	cg.cpp:125-131
Module	exec

The function is defined in /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:125-131.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is probably not vectorized. Only 25% of vector register length is used (average across all VPU instructions).

Details

Store and arithmetical VPU instructions are used in scalar version (process only one data element in vector registers).

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 12.50 to 10.00 cycles (1.25x 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: 2 occurrences►
- /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:125
- /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:125

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 9 bytes.

General properties

nb instructions	58
nb uops	58
loop length	232
used w registers	14
used x registers	18
used b registers	0
used h registers	0
used s registers	1
used d registers	1
used q registers	0
used v registers	2
used z registers	0
nb stack references	6

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	7.25 cycles
front end	7.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	4.00	4.00	10.25	10.25	10.25	10.25	0.25	0.25	0.25	0.25	3.83	3.50	3.67	1.50	1.50
cycles	4.00	4.00	10.25	10.25	10.25	10.25	0.25	0.25	0.25	0.25	3.83	3.50	3.67	1.50	1.50

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

5.00-12.50

Cycles summary

Front-end	7.25
Dispatch	10.25
DIV/SQRT	5.00-12.50
Overall L1	10.25-12.50

Vectorization ratios

all	2%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	6%

Vector efficiency ratios

all	25%
load	26%
store	41%
mul	12%
add-sub	19%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	29%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 12.50 cycles. At this rate:

0% of peak load performance is reached (0.72 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 411884

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #976]!	1	0	0	0.25	0.25	0.25	0.25	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	0	0	0	0	1	0.25	scal (25.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ORR X20, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR W21, [X0, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
BL 410320 <@plt_start@+0x300>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W19, WZR, W0	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%)
BL 4102b0 <@plt_start@+0x290>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W1, [X20, #28]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR W4, WZR, W0	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 W0, W1, W21,LSL #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SDIV W2, W0, W19	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-12	5-12.50	N/A
MSUB W1, W2, W19, W0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
CMP W4, W1	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%)
B.LT 411a04 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x180>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MADD W4, W2, W4, W1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
ADD W2, W2, W4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP W4, W2	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%)
B.GE 4119b4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x130>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W12, [X20, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ADD W4, W21, W4	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 W7, W21, W2	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%)
LDP X5, X8, [X20, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
SUB W11, W12, 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%)
LDR D31, [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%)
CMP W21, W11	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%)
B.GE 4119b4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x130>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MUL W9, W12, W4	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 X0, X21, #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	N/A
SUB W11, W11, 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%)
ADD X6, X0, #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 (25.0%)
UBFM X14, X11, #61, #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 (25.0%)
DUP V30.2D, V31.D[0]	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
UBFM W3, W11, #1, #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 (12.5%)
AND W13, W11, #0xfffffffe	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%)
SBFM X1, X9, #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%)
MOVN X15, #7	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 X6, X6, X1	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 X0, X0, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB X14, X14, X8	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 X6, X8, X6,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 W16, W11, #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 X1, X5, X0,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 X14, X14, X15	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%)
UBFM X3, X3, #60, #59	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 W13, W13, 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%)
AND W11, W11, #0x1	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 X15, X15, X8	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%)
SBFM X10, X12, #61, #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%)
LDR X21, [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%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X29, X30, [SP], #48	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 4119b4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x130>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ W1, #0	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 4118c4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x40>	1	0.50	0.50	0	0	0	0	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 0.01% of application time for run gcc_0

Source file and lines	cg.cpp:125-131
Module	exec

The function is defined in /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:125-131.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is probably not vectorized. Only 25% of vector register length is used (average across all VPU instructions).

Details

Store and arithmetical VPU instructions are used in scalar version (process only one data element in vector registers).

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 12.50 to 10.00 cycles (1.25x speedup).

CALL instructions

Detected function call instructions.

Details

unknown: 2 occurrences►
- /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:125
- /home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp:125

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 9 bytes.

General properties

nb instructions	58
nb uops	58
loop length	232
used w registers	14
used x registers	18
used b registers	0
used h registers	0
used s registers	1
used d registers	1
used q registers	0
used v registers	2
used z registers	0
nb stack references	6

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	7.25 cycles
front end	7.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	4.00	4.00	10.25	10.25	10.25	10.25	0.25	0.25	0.25	0.25	3.83	3.50	3.67	1.50	1.50
cycles	4.00	4.00	10.25	10.25	10.25	10.25	0.25	0.25	0.25	0.25	3.83	3.50	3.67	1.50	1.50

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

5.00-12.50

Cycles summary

Front-end	7.25
Dispatch	10.25
DIV/SQRT	5.00-12.50
Overall L1	10.25-12.50

Vectorization ratios

all	2%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	6%

Vector efficiency ratios

all	25%
load	26%
store	41%
mul	12%
add-sub	19%
fma	12%
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	29%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 12.50 cycles. At this rate:

0% of peak load performance is reached (0.72 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 411884

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #976]!	1	0	0	0.25	0.25	0.25	0.25	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	0	0	0	0	1	0.25	scal (25.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (50.0%)
ORR X20, XZR, X0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
STR X21, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (25.0%)
LDR W21, [X0, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
BL 410320 <@plt_start@+0x300>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W19, WZR, W0	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%)
BL 4102b0 <@plt_start@+0x290>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W1, [X20, #28]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ORR W4, WZR, W0	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 W0, W1, W21,LSL #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SDIV W2, W0, W19	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	5-12	5-12.50	N/A
MSUB W1, W2, W19, W0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
CMP W4, W1	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%)
B.LT 411a04 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x180>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MADD W4, W2, W4, W1	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (12.5%)
ADD W2, W2, W4	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP W4, W2	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%)
B.GE 4119b4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x130>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
LDR W12, [X20, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (12.5%)
ADD W4, W21, W4	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 W7, W21, W2	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%)
LDP X5, X8, [X20, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
SUB W11, W12, 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%)
LDR D31, [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%)
CMP W21, W11	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%)
B.GE 4119b4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x130>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MUL W9, W12, W4	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 X0, X21, #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	N/A
SUB W11, W11, 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%)
ADD X6, X0, #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 (25.0%)
UBFM X14, X11, #61, #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 (25.0%)
DUP V30.2D, V31.D[0]	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (50.0%)
UBFM W3, W11, #1, #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 (12.5%)
AND W13, W11, #0xfffffffe	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%)
SBFM X1, X9, #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%)
MOVN X15, #7	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 X6, X6, X1	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 X0, X0, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SUB X14, X14, X8	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 X6, X8, X6,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 W16, W11, #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 X1, X5, X0,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 X14, X14, X15	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%)
UBFM X3, X3, #60, #59	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 W13, W13, 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%)
AND W11, W11, #0x1	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 X15, X15, X8	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%)
SBFM X10, X12, #61, #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%)
LDR X21, [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%)
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	N/A
LDP X29, X30, [SP], #48	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1	scal (50.0%)
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
B 4119b4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x130>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ADD W2, W2, #1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOVZ W1, #0	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 4118c4 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x40>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Name	Coverage (%)	Time (s)
▼cg_calc_p(int, int, int, double, double, double const) [clone ._omp_fn.0]–	20.75	55.35
▼Loop 29 - cg.cpp:125-131 - exec–	0.00	0.00
▼Loop 31 - cg.cpp:127-131 - exec–	0.00	0.03
○Loop 30 - cg.cpp:128-131 - exec	20.75	55.29
○Loop 28 - cg.cpp:128-131 - exec	0.00	0.00

Report Configuration

Vectorization

Details

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

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