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): 16.48% \| (excl. loops): 0.00%

/home/hbollore/qaas/qaas-runs/174-118-5752/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];

0x402f04 STP	X29, X30, [SP, #992]!

0x402f08 ADD	X29, SP, #0

0x402f0c STP	X19, X20, [SP, #16]

0x402f10 ORR	X20, XZR, X0

0x402f14 BL	401910

0x402f18 ORR	W19, WZR, W0

0x402f1c BL	4018a0

0x402f20 ORR	W4, WZR, W0

0x402f24 LDP	W0, W10, [X20, #28]

0x402f28 SUB	W0, W0, W10,LSL #1

0x402f2c SDIV	W2, W0, W19

0x402f30 MSUB	W1, W2, W19, W0

0x402f34 CMP	W4, W1

0x402f38 B.LT	40307c

0x402f3c MADD	W4, W2, W4, W1

0x402f40 ADD	W2, W2, W4

0x402f44 CMP	W4, W2

0x402f48 B.GE	403030

0x402f4c LDR	W12, [X20, #24]

0x402f50 ADD	W4, W10, W4

0x402f54 ADD	W7, W10, W2

0x402f58 LDP	X5, X8, [X20, #8]

0x402f5c SUB	W11, W12, W10

0x402f60 LDR	D31, [X20]

0x402f64 CMP	W10, W11

0x402f68 B.GE	403030

0x402f6c MADD	W9, W12, W4, WZR

0x402f70 SBFM	X0, X10, #0, #31

0x402f74 SUB	W11, W11, W10

0x402f78 DUP	V30.2D, V31.D[0]

0x402f7c ADD	X6, X0, #1

0x402f80 UBFM	X14, X11, #61, #31

0x402f84 UBFM	W3, W11, #1, #31

0x402f88 AND	W13, W11, #1951

0x402f8c SBFM	X1, X9, #0, #31

0x402f90 MOVN	X15, #7

0x402f94 ADD	X6, X6, X1

0x402f98 ADD	X0, X0, X1

0x402f9c SUB	X14, X14, X8

0x402fa0 ADD	X6, X8, X6,LSL #3

0x402fa4 ADD	W13, W13, W10

0x402fa8 ADD	X1, X5, X0,LSL #3

0x402fac ADD	X14, X14, X15

0x402fb0 SUB	W16, W11, #1

0x402fb4 UBFM	X3, X3, #60, #59

0x402fb8 AND	W11, W11, #0

0x402fbc SUB	X15, X15, X8

0x402fc0 SBFM	X10, X12, #61, #31

  (42) 0x402fc4 CMP	W16, #1

  (42) 0x402fc8 B.LS	40303c

    (44) 0x402fcc CMP	X1, X6

    (44) 0x402fd0 B.EQ	40303c

    (44) 0x402fd4 MOVZ	X0, #0

    (44) 0x402fd8 SUB	X2, X6, #8

    (44) 0x402fdc HINT	#0

      (43) 0x402fe0 LDR	Q3, [X1, X0]

      (43) 0x402fe4 LDR	Q2, [X2, X0]

      (43) 0x402fe8 FMLA	V2.2D, V3.2D, V30.2D

      (43) 0x402fec STR	Q2, [X1, X0]

      (43) 0x402ff0 ADD	X0, X0, #16

      (43) 0x402ff4 CMP	X0, X3

      (43) 0x402ff8 B.NE	402fe0

    (44) 0x402ffc CBZ	W11, 403018

    (44) 0x403000 ADD	W0, W13, W9

    (44) 0x403004 SBFM	X0, X0, #61, #31

    (44) 0x403008 LDR	D1, [X5, X0]

    (44) 0x40300c LDR	D0, [X8, X0]

    (44) 0x403010 FMADD	D0, D31, D1, D0

    (44) 0x403014 STR	D0, [X5, X0]

    (44) 0x403018 ADD	W4, W4, #1

    (44) 0x40301c ADD	W9, W9, W12

    (44) 0x403020 ADD	X6, X6, X10

    (44) 0x403024 ADD	X1, X1, X10

    (44) 0x403028 CMP	W7, W4

    (44) 0x40302c B.GT	402fcc

(45) 0x403030 LDP	X19, X20, [SP, #16]

(45) 0x403034 LDP	X29, X30, [SP], #32

(45) 0x403038 RET

  (42) 0x40303c ADD	X0, X15, X6

  (42) 0x403040 ADD	X2, X14, X6

    (41) 0x403044 LDR	D29, [X5, X0]

    (41) 0x403048 LDR	D28, [X8, X0]

    (41) 0x40304c FMADD	D28, D31, D29, D28

    (41) 0x403050 STR	D28, [X5, X0]

    (41) 0x403054 ADD	X0, X0, #8

    (41) 0x403058 CMP	X0, X2

    (41) 0x40305c B.NE	403044

  (42) 0x403060 ADD	W4, W4, #1

  (42) 0x403064 ADD	W9, W9, W12

  (42) 0x403068 ADD	X6, X6, X10

  (42) 0x40306c ADD	X1, X1, X10

  (42) 0x403070 CMP	W7, W4

  (42) 0x403074 B.GT	402fc4

(45) 0x403078 B	403030

0x40307c ADD	W2, W2, #1

0x403080 MOVZ	W1, #0

0x403084 B	402f3c

Coverage (%)	Name	Source Location	Module
►98.95+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.05+	GOMP_parallel	libgomp.h:980	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 0.00% of application time for run gcc_0

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

The function is defined in /home/hbollore/qaas/qaas-runs/174-118-5752/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 46% 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 1.00 cycles (12.50x speedup).

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 36 bytes. The binary function is storing 32 bytes.

General properties

nb instructions	51
loop length	204
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

6.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	3.00	3.00	6.92	6.75	6.83	6.83	6.83	6.83	0.25	0.25	0.25	0.25	2.00	2.00	2.00	1.00	1.00
cycles	3.00	3.00	6.92	6.75	6.83	6.83	6.83	6.83	0.25	0.25	0.25	0.25	2.00	2.00	2.00	1.00	1.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

5.00-12.50

Cycles summary

Front-end	6.38
Overall L1	6.92-12.50

Vectorization ratios

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

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:

3% of peak load performance is reached (2.88 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (2.56 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 402f04

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #992]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ADD X29, SP, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X20, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BL 401910 <@plt_start@+0x300>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W19, WZR, W0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
BL 4018a0 <@plt_start@+0x290>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W4, WZR, W0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDP W0, W10, [X20, #28]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
SUB W0, W0, W10,LSL #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SDIV W2, W0, W19	1	0	0	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	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CMP W4, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LT 40307c <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x178>	1	0.50	0.50	0	0	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	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ADD W2, W2, W4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP W4, W2	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.GE 403030 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x12c>	1	0.50	0.50	0	0	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	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD W4, W10, W4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
ADD W7, W10, W2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDP X5, X8, [X20, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	scal (100.0%)
SUB W11, W12, W10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDR D31, [X20]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
CMP W10, W11	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.GE 403030 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x12c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MADD W9, W12, W4, WZR	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SBFM X0, X10, #0, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (100.0%)
SUB W11, W11, W10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
DUP V30.2D, V31.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (100.0%)
ADD X6, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
UBFM X14, X11, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
UBFM W3, W11, #1, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
AND W13, W11, #1951	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SBFM X1, X9, #0, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (100.0%)
MOVN X15, #7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X6, X6, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X0, X0, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
SUB X14, X14, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X6, X8, X6,LSL #3	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD W13, W13, W10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
ADD X1, X5, X0,LSL #3	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X14, X14, X15	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
SUB W16, W11, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X3, X3, #60, #59	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
AND W11, W11, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SUB X15, X15, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
SBFM X10, X12, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (100.0%)
ADD W2, W2, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVZ W1, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
B 402f3c <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x38>	1	0.50	0.50	0	0	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 0.00% of application time for run gcc_0

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

The function is defined in /home/hbollore/qaas/qaas-runs/174-118-5752/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 46% 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 1.00 cycles (12.50x speedup).

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 36 bytes. The binary function is storing 32 bytes.

General properties

nb instructions	51
loop length	204
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

6.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	3.00	3.00	6.92	6.75	6.83	6.83	6.83	6.83	0.25	0.25	0.25	0.25	2.00	2.00	2.00	1.00	1.00
cycles	3.00	3.00	6.92	6.75	6.83	6.83	6.83	6.83	0.25	0.25	0.25	0.25	2.00	2.00	2.00	1.00	1.00

Execution ports to units layout:

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

Cycles executing div or sqrt instructions

5.00-12.50

Cycles summary

Front-end	6.38
Overall L1	6.92-12.50

Vectorization ratios

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

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:

3% of peak load performance is reached (2.88 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
5% of peak store performance is reached (2.56 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 402f04

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #992]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ADD X29, SP, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
STP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
ORR X20, XZR, X0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
BL 401910 <@plt_start@+0x300>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W19, WZR, W0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
BL 4018a0 <@plt_start@+0x290>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W4, WZR, W0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDP W0, W10, [X20, #28]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (50.0%)
SUB W0, W0, W10,LSL #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SDIV W2, W0, W19	1	0	0	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	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
CMP W4, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.LT 40307c <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x178>	1	0.50	0.50	0	0	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	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
ADD W2, W2, W4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP W4, W2	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.GE 403030 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x12c>	1	0.50	0.50	0	0	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	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
ADD W4, W10, W4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
ADD W7, W10, W2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDP X5, X8, [X20, #8]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.50	scal (100.0%)
SUB W11, W12, W10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
LDR D31, [X20]	1	0	0	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	6	0.33	scal (50.0%)
CMP W10, W11	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33	scal (25.0%)
B.GE 403030 <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x12c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MADD W9, W12, W4, WZR	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	2	1	scal (25.0%)
SBFM X0, X10, #0, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (100.0%)
SUB W11, W11, W10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
DUP V30.2D, V31.D[0]	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	2	0.25	vect (100.0%)
ADD X6, X0, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
UBFM X14, X11, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
UBFM W3, W11, #1, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
AND W13, W11, #1951	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SBFM X1, X9, #0, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (100.0%)
MOVN X15, #7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X6, X6, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X0, X0, X1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
SUB X14, X14, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X6, X8, X6,LSL #3	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD W13, W13, W10	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
ADD X1, X5, X0,LSL #3	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
ADD X14, X14, X15	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
SUB W16, W11, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
UBFM X3, X3, #60, #59	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
AND W11, W11, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
SUB X15, X15, X8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (50.0%)
SBFM X10, X12, #61, #31	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (100.0%)
ADD W2, W2, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVZ W1, #0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	1	0.17	scal (25.0%)
B 402f3c <_Z9cg_calc_piiidPdPKd._omp_fn.0+0x38>	1	0.50	0.50	0	0	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]–	16.48	26.50
▼Loop 45 - cg.cpp:125-131 - exec–	0.00	0.01
▼Loop 42 - cg.cpp:125-131 - exec–	0.00	0.00
▼Loop 44 - cg.cpp:127-131 - exec–	0.00	0.01
○Loop 43 - cg.cpp:128-131 - exec	16.47	26.20
○Loop 41 - cg.cpp:128-131 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Vectorization

Details

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code