OV - exec - Loop 127

0x40ad04 ORR	X9, XZR, X2

0x40ad08 STR	Q31, [X0, #32]    [8]

0x40ad0c ADD	X14, X0, #48

0x40ad10 STP	Q31, Q31, [X0]    [8]

0x40ad14 STR	Q31, [X9], #16    [2]

0x40ad18 ADD	X13, X0, #96

0x40ad1c ADD	X12, X0, #144

0x40ad20 STR	Q31, [X0, #48]    [8]

0x40ad24 ADD	X11, X0, #192

0x40ad28 ADD	X10, X0, #240

0x40ad2c STP	Q31, Q31, [X14, #16]    [9]

0x40ad30 STR	Q31, [X2, #16]    [12]

0x40ad34 ADD	X7, X0, #288

0x40ad38 ADD	X15, X0, #336

0x40ad3c STR	Q31, [X0, #96]    [8]

0x40ad40 ADD	X2, X2, #128

0x40ad44 ADD	X0, X0, #384

0x40ad48 STP	Q31, Q31, [X13, #16]    [6]

0x40ad4c STR	Q31, [X9, #16]    [2]

0x40ad50 STUR	Q31, [X0, #272]    [7]

0x40ad54 STP	Q31, Q31, [X12, #16]    [5]

0x40ad58 STUR	Q31, [X2, #432]    [11]

0x40ad5c STUR	Q31, [X0, #320]    [7]

0x40ad60 STP	Q31, Q31, [X11, #16]    [4]

0x40ad64 STUR	Q31, [X2, #448]    [11]

0x40ad68 STUR	Q31, [X0, #368]    [7]

0x40ad6c STP	Q31, Q31, [X10, #16]    [3]

0x40ad70 STUR	Q31, [X2, #464]    [11]

0x40ad74 STUR	Q31, [X0, #416]    [7]

0x40ad78 STP	Q31, Q31, [X7, #16]    [1]

0x40ad7c STUR	Q31, [X2, #480]    [11]

0x40ad80 STUR	Q31, [X0, #464]    [7]

0x40ad84 STP	Q31, Q31, [X15, #16]    [10]

0x40ad88 STUR	Q31, [X2, #496]    [11]

0x40ad8c CMP	X20, X2

0x40ad90 B.NE	40ad04

/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/ljForce.c: 161 - 161

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

161:       s->atoms->U[ii] = 0.;

/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/mytype.h: 22 - 24

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

22:    a[0] = 0.0;

23:    a[1] = 0.0;

24:    a[2] = 0.0;

Coverage (%)	Name	Source Location	Module
►98.95+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec
►1.05+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	main	CoMD.c:211	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►51.27+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►48.22+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►72.20+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►27.44+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►88.25+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►11.43+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►93.47+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►6.53+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►94.75+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►5.10+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►96.90+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►3.10+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►97.88+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►2.12+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►98.46+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.54+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►98.30+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.64+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►98.02+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.98+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►99.01+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

Coverage (%)	Name	Source Location	Module
►98.93+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.07+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►98.90+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►1.10+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	ljForce	ljForce.c:157	exec
○	timestep	timestep.c:51	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►98.98+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

min	med	avg	max

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

min	med	avg	max

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

Path /

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	2.67
Bottlenecks	P8, P9, P12, P13,
Function	ljForce._omp_fn.0
Source	ljForce.c:161-161,mytype.h:22-24
Source loop unroll info	unrolled by 2
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	2
CQA cycles	12.00
CQA cycles if no scalar integer	12.00
CQA cycles if FP arith vectorized	12.00
CQA cycles if fully vectorized	12.00
Front-end cycles	4.50
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	2.08
P3 cycles	2.08
P4 cycles	2.00
P5 cycles	2.00
P6 cycles	1.92
P7 cycles	1.92
P8 cycles	12.00
P9 cycles	12.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	12.00
P13 cycles	12.00
P14 cycles	0.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	36.00
Nb uops	36.00
Nb loads	NA
Nb stores	24.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	42.67
Bytes prefetched	0.00
Bytes loaded	0.00
Bytes stored	512.00
Stride 0	0.00
Stride 1	0.00
Stride n	4.00
Stride unknown	8.00
Stride indirect	0.00
Vectorization ratio all	100.00
Vectorization ratio load	NA
Vectorization ratio store	100.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	100.00
Vector-efficiency ratio load	NA
Vector-efficiency ratio store	100.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	1.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	2.67
Bottlenecks	P8, P9, P12, P13,
Function	ljForce._omp_fn.0
Source	ljForce.c:161-161,mytype.h:22-24
Source loop unroll info	unrolled by 2
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	2
CQA cycles	12.00
CQA cycles if no scalar integer	12.00
CQA cycles if FP arith vectorized	12.00
CQA cycles if fully vectorized	12.00
Front-end cycles	4.50
P0 cycles	0.50
P1 cycles	0.50
P2 cycles	2.08
P3 cycles	2.08
P4 cycles	2.00
P5 cycles	2.00
P6 cycles	1.92
P7 cycles	1.92
P8 cycles	12.00
P9 cycles	12.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	12.00
P13 cycles	12.00
P14 cycles	0.00
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	36.00
Nb uops	36.00
Nb loads	NA
Nb stores	24.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	42.67
Bytes prefetched	0.00
Bytes loaded	0.00
Bytes stored	512.00
Stride 0	0.00
Stride 1	0.00
Stride n	4.00
Stride unknown	8.00
Stride indirect	0.00
Vectorization ratio all	100.00
Vectorization ratio load	NA
Vectorization ratio store	100.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	100.00
Vector-efficiency ratio load	NA
Vector-efficiency ratio store	100.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	NA
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Path /

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

Function	ljForce._omp_fn.0
Source file and lines	ljForce.c:161-161
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/ljForce.c:161
/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/mytype.h:22-24

The related source loop is unrolled by 2 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is fully vectorized, using full register length.

Details

All VPU instructions are used in vector version (process two or more data elements in vector registers).

No data for this section

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

The binary loop does not contain any FP arithmetical operations. The binary loop is storing 512 bytes.

General properties

nb instructions	36
loop length	144
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

4.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	0.50	0.50	2.08	2.08	2.00	2.00	1.92	1.92	12.00	12.00	0.00	0.00	12.00	12.00	0.00	0.00	0.00
cycles	0.50	0.50	2.08	2.08	2.00	2.00	1.92	1.92	12.00	12.00	0.00	0.00	12.00	12.00	0.00	0.00	0.00

Execution ports to units layout:

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

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

Cycles summary

Front-end	4.50
Data deps.	1.00
Overall L1	12.00

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 12.00 cycles. At this rate:

88% of peak store performance is reached (42.67 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 40ad04

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	Latency	Recip. throughput	Vectorization
ORR X9, XZR, X2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STR Q31, [X0, #32]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X14, X0, #48	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STP Q31, Q31, [X0]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STR Q31, [X9], #16	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X13, X0, #96	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X12, X0, #144	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STR Q31, [X0, #48]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X11, X0, #192	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X10, X0, #240	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STP Q31, Q31, [X14, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STR Q31, [X2, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X7, X0, #288	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X15, X0, #336	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STR Q31, [X0, #96]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X2, X2, #128	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X0, X0, #384	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STP Q31, Q31, [X13, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STR Q31, [X9, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #272]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X12, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #432]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #320]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X11, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #448]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #368]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X10, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #464]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #416]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X7, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #480]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #464]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X15, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #496]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
CMP X20, X2	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	N/A
B.NE 40ad04 <ljForce._omp_fn.0+0x164>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	ljForce._omp_fn.0
Source file and lines	ljForce.c:161-161
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/ljForce.c:161
/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/mytype.h:22-24

The related source loop is unrolled by 2 (including vectorization).

gain
potential
hint
expert

Vectorization

Your loop is fully vectorized, using full register length.

Details

All VPU instructions are used in vector version (process two or more data elements in vector registers).

No data for this section

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

The binary loop does not contain any FP arithmetical operations. The binary loop is storing 512 bytes.

General properties

nb instructions	36
loop length	144
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

4.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	0.50	0.50	2.08	2.08	2.00	2.00	1.92	1.92	12.00	12.00	0.00	0.00	12.00	12.00	0.00	0.00	0.00
cycles	0.50	0.50	2.08	2.08	2.00	2.00	1.92	1.92	12.00	12.00	0.00	0.00	12.00	12.00	0.00	0.00	0.00

Execution ports to units layout:

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

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

Cycles summary

Front-end	4.50
Data deps.	1.00
Overall L1	12.00

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 12.00 cycles. At this rate:

88% of peak store performance is reached (42.67 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 40ad04

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	Latency	Recip. throughput	Vectorization
ORR X9, XZR, X2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STR Q31, [X0, #32]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X14, X0, #48	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STP Q31, Q31, [X0]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STR Q31, [X9], #16	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X13, X0, #96	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X12, X0, #144	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STR Q31, [X0, #48]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X11, X0, #192	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X10, X0, #240	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STP Q31, Q31, [X14, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STR Q31, [X2, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X7, X0, #288	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X15, X0, #336	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STR Q31, [X0, #96]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
ADD X2, X2, #128	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD X0, X0, #384	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
STP Q31, Q31, [X13, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STR Q31, [X9, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #272]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X12, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #432]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #320]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X11, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #448]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #368]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X10, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #464]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #416]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X7, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #480]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STUR Q31, [X0, #464]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
STP Q31, Q31, [X15, #16]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	1	vect (100.0%)
STUR Q31, [X2, #496]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	2	0.50	vect (100.0%)
CMP X20, X2	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	1	0.33	N/A
B.NE 40ad04 <ljForce._omp_fn.0+0x164>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

▶Scalability Runs Description

Run 1x1	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_NUM_THREADS: 1OMP_PLACES: threads
Run 1x2	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 2OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x4	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 4OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x8	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 8OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x16	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 16OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x24	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 24OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x32	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 32OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x40	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 40OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x48	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 48OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x56	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 56OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x64	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 64OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x72	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 72OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x80	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 80OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x88	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 88OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads
Run 1x96	Number processes: 1Number nodes: 1Run Command: <executable> -x 100 -y 100 -z 100MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=96 --rank-by fill --report-bindings Dataset: Run Directory: /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/run/oneview_runs/multicore/gcc_1/oneview_run_1741097920OMP_NUM_THREADS: 96OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

(1x1) Efficiency	(1x1) Potential Speed-Up (%)	(1x2) Efficiency	(1x2) Potential Speed-Up (%)	(1x4) Efficiency	(1x4) Potential Speed-Up (%)	(1x8) Efficiency	(1x8) Potential Speed-Up (%)	(1x16) Efficiency	(1x16) Potential Speed-Up (%)	(1x24) Efficiency	(1x24) Potential Speed-Up (%)	(1x32) Efficiency	(1x32) Potential Speed-Up (%)	(1x40) Efficiency	(1x40) Potential Speed-Up (%)	(1x48) Efficiency	(1x48) Potential Speed-Up (%)	(1x56) Efficiency	(1x56) Potential Speed-Up (%)	(1x64) Efficiency	(1x64) Potential Speed-Up (%)	(1x72) Efficiency	(1x72) Potential Speed-Up (%)	(1x80) Efficiency	(1x80) Potential Speed-Up (%)	(1x88) Efficiency	(1x88) Potential Speed-Up (%)	(1x96) Efficiency	(1x96) Potential Speed-Up (%)
1	0	0.96	0.01	0.68	0.08	0.58	0.12	0.35	0.3	0.26	0.45	0.19	0.69	0.16	0.78	0.13	1.01	0.11	1.21	0.09	1.33	0.09	1.46	0.07	1.66	0.06	1.85	0.06	1.92

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
1x1	1	1	1	1	0.95499980449677	0.17795078456402
1x2	2	0.96	1.93	2	0.50499993562698	0.1841206997633
1x4	4	0.68	2.71	4	0.41999992728233	0.25839799642563
1x8	8	0.58	4.65	8	0.23000001907349	0.2931215763092
1x16	16	0.35	5.58	16	0.22000002861023	0.46699604392052
1x24	24	0.26	6.14	24	0.17499998211861	0.61039841175079
1x32	32	0.19	5.98	32	0.19499994814396	0.84901988506317
1x40	40	0.16	6.51	40	0.17000000178814	0.93583583831787
1x48	48	0.13	6.18	48	0.17999997735023	1.1645505428314
1x56	56	0.11	5.99	56	0.2049999833107	1.360132932663
1x64	64	0.09	6.07	64	0.18999996781349	1.4735751152039
1x72	72	0.09	6.22	72	0.21999996900558	1.5936808586121
1x80	80	0.07	5.89	80	0.20000000298023	1.7938152551651
1x88	88	0.06	5.7	88	0.25999996066093	1.9749299287796
1x96	96	0.06	5.95	96	0.23999997973442	2.0458512306213

Report Configuration

Vectorization

Details

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Vectorization

Details

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

▶Scalability Runs Description

▼Columns Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency