OV - exec - Function setTemperature._omp

	Function: setTemperature._omp_fn.0	Module: exec	Source: initAtoms.c:151-162	Coverage (incl. loops): 0.02% \| (excl. loops): 0.00%

/home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/initAtoms.c: 151 - 162

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

151:    #pragma omp parallel for

152:    for (int iBox=0; iBox<s->boxes->nLocalBoxes; ++iBox)

153:    {

154:       for (int iOff=MAXATOMS*iBox, ii=0; ii<s->boxes->nAtoms[iBox]; ++ii, ++iOff)

155:       {

156:          int iType = s->atoms->iSpecies[iOff];

157:          real_t mass = s->species[iType].mass;

158:          real_t sigma = sqrt(kB_eV * temperature/mass);

159:          uint64_t seed = mkSeed(s->atoms->gid[iOff], 123);

160:          s->atoms->p[iOff][0] = mass * sigma * gasdev(&seed);

161:          s->atoms->p[iOff][1] = mass * sigma * gasdev(&seed);

162:          s->atoms->p[iOff][2] = mass * sigma * gasdev(&seed);

0x408a80 STP	X29, X30, [SP, #912]!

0x408a84 ADD	X29, SP, #0

0x408a88 STP	X19, X20, [SP, #16]

0x408a8c ORR	X20, XZR, X0

0x408a90 STP	X21, X22, [SP, #32]

0x408a94 STP	X23, X24, [SP, #48]

0x408a98 LDR	X21, [X0]

0x408a9c BL	402640

0x408aa0 ORR	W19, WZR, W0

0x408aa4 BL	402660

0x408aa8 ORR	W22, WZR, W0

0x408aac LDR	X24, [X21, #24]

0x408ab0 LDR	W23, [X24, #12]

0x408ab4 SDIV	W2, W23, W19

0x408ab8 MSUB	W1, W2, W19, W23

0x408abc CMP	W0, W1

0x408ac0 B.LT	408bf4

(93) 0x408ac4 MADD	W3, W2, W22, W1

(93) 0x408ac8 ADD	W0, W2, W3

(93) 0x408acc CMP	W3, W0

(93) 0x408ad0 B.GE	408be0

(93) 0x408ad4 ADRP	X4,

(93) 0x408ad8 STP	D13, D14, [SP, #80]

(93) 0x408adc ORR	W5, WZR, W2

(93) 0x408ae0 ADD	X6, X5, W3,SXTW

(93) 0x408ae4 LDR	D14, [X20, #8]

(93) 0x408ae8 UBFM	X23, X6, #62, #61

(93) 0x408aec UBFM	W22, W3, #26, #25

(93) 0x408af0 LDR	D31, [X4, #968]

(93) 0x408af4 LDR	X5, [X24, #120]

(93) 0x408af8 STR	X25, [SP, #64]

(93) 0x408afc SBFM	X25, X3, #62, #31

(93) 0x408b00 STR	D15, [SP, #72]

(93) 0x408b04 FMUL	D14, D14, D31

  (94) 0x408b08 LDR	W7, [X5, X25]

  (94) 0x408b0c CMP	W7, #0

  (94) 0x408b10 B.LE	408bc4

  (94) 0x408b14 LDR	X0, [X21, #32]

  (94) 0x408b18 MOVZ	W24, #0

  (94) 0x408b1c SBFM	X19, X22, #62, #31

    (95) 0x408b20 LDP	X8, X9, [X0, #8]

    (95) 0x408b24 ADD	X11, X19, X19,LSL #1

    (95) 0x408b28 MOVZ	W1, #123

    (95) 0x408b2c ADD	W24, W24, #1

    (95) 0x408b30 UBFM	X20, X11, #63, #62

    (95) 0x408b34 LDR	X12, [X21, #40]

    (95) 0x408b38 LDRSW	X10, [X9, X19]

    (95) 0x408b3c LDR	W0, [X8, X19]

    (95) 0x408b40 ADD	X19, X19, #4

    (95) 0x408b44 ADD	X13, X12, X10,LSL #4

    (95) 0x408b48 LDR	D15, [X13, #8]

    (95) 0x408b4c FDIV	D13, D14, D15

    (95) 0x408b50 FSQRT	D13, D13

    (95) 0x408b54 BL	40d508

    (95) 0x408b58 FMUL	D15, D15, D13

    (95) 0x408b5c ORR	X14, XZR, X0

    (95) 0x408b60 ADD	X0, SP, #104

    (95) 0x408b64 STR	X14, [SP, #104]

    (95) 0x408b68 BL	40d400

    (95) 0x408b6c LDR	X15, [X21, #32]

    (95) 0x408b70 FMUL	D0, D15, D0

    (95) 0x408b74 ADD	X0, SP, #104

    (95) 0x408b78 LDR	X18, [X15, #32]

    (95) 0x408b7c STR	D0, [X18, X20]

    (95) 0x408b80 BL	40d400

    (95) 0x408b84 LDR	X2, [X21, #32]

    (95) 0x408b88 FMUL	D1, D15, D0

    (95) 0x408b8c ADD	X0, SP, #104

    (95) 0x408b90 LDR	X1, [X2, #32]

    (95) 0x408b94 ADD	X3, X1, X20

    (95) 0x408b98 STR	D1, [X3, #8]

    (95) 0x408b9c BL	40d400

    (95) 0x408ba0 LDP	X4, X0, [X21, #24]

    (95) 0x408ba4 FMUL	D2, D15, D0

    (95) 0x408ba8 LDR	X5, [X4, #120]

    (95) 0x408bac LDR	X7, [X0, #32]

    (95) 0x408bb0 LDR	W6, [X5, X25]

    (95) 0x408bb4 ADD	X8, X7, X20

    (95) 0x408bb8 STR	D2, [X8, #16]

    (95) 0x408bbc CMP	W6, W24

    (95) 0x408bc0 B.GT	408b20

  (94) 0x408bc4 ADD	X25, X25, #4

  (94) 0x408bc8 ADD	W22, W22, #64

  (94) 0x408bcc CMP	X25, X23

  (94) 0x408bd0 B.NE	408b08

(93) 0x408bd4 LDR	D15, [SP, #72]

(93) 0x408bd8 LDP	D13, D14, [SP, #80]

(93) 0x408bdc LDR	X25, [SP, #64]

(93) 0x408be0 LDP	X19, X20, [SP, #16]

(93) 0x408be4 LDP	X21, X22, [SP, #32]

(93) 0x408be8 LDP	X23, X24, [SP, #48]

(93) 0x408bec LDP	X29, X30, [SP], #112

(93) 0x408bf0 RET

(93) 0x408bf4 ADD	W2, W2, #1

(93) 0x408bf8 MOVZ	W1, #0

(93) 0x408bfc B	408ac4

Coverage (%)	Name	Source Location	Module
►100.00+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►54.55+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec
►45.45+	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
►73.68+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►26.32+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►84.21+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►15.79+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►88.89+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►11.11+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►94.12+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►5.88+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►92.59+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►7.41+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►91.67+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►8.33+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►92.86+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►7.14+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	exec

Coverage (%)	Name	Source Location	Module
►100.00+	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
►100.00+	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
►94.12+	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6
►5.88+	GOMP_parallel	libgomp.h:980	libgomp.so.1.0.0
○	setTemperature	initAtoms.c:167	exec
○	main	CoMD.c:200	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	CoMD.c:266	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 1x1

Source file and lines	initAtoms.c:151-162
Module	exec

The function is defined in /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/initAtoms.c:151-162.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 60% of vector register length is used (average across all VPU instructions). By vectorizing your function, you can lower the cost of an iteration from 12.50 to 3.12 cycles (4.00x 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 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 20 bytes. The binary function is storing 64 bytes.

General properties

nb instructions	17
loop length	68
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	1.50	1.50	1.67	1.50	1.67	1.67	2.00	1.50	0.00	0.00	0.00	0.00	2.33	2.33	2.33	2.00	2.00
cycles	1.50	1.50	1.67	1.50	1.67	1.67	2.00	1.50	0.00	0.00	0.00	0.00	2.33	2.33	2.33	2.00	2.00

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	2.13
Overall L1	5.00-12.50

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	0%
other	0%

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:

1% of peak load performance is reached (1.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (5.12 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 408a80

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #912]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	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	1	0.17	scal (50.0%)
STP X19, X20, [SP, #16]	1	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	1	0.17	scal (50.0%)
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
LDR X21, [X0]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 402640 <@plt_start@+0x100>	1	0.50	0.50	0.50	0.50	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	1	0.17	scal (25.0%)
BL 402660 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W22, WZR, W0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
LDR X24, [X21, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR W23, [X24, #12]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SDIV W2, W23, W19	1	0	0	0	0	0	0	1	0	0	0	0	0	0	5-12	5-12.50	scal (25.0%)
MSUB W1, W2, W19, W23	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	N/A
CMP W0, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	N/A
B.LT 408bf4 <setTemperature._omp_fn.0+0x174>	1	0.50	0.50	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 1x1

Source file and lines	initAtoms.c:151-162
Module	exec

The function is defined in /home/hbollore/qaas/qaas-runs/174-108-7908/intel/CoMD/build/CoMD/CoMD/src-openmp/initAtoms.c:151-162.

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 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 20 bytes. The binary function is storing 64 bytes.

General properties

nb instructions	17
loop length	68
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

2.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	1.50	1.50	1.67	1.50	1.67	1.67	2.00	1.50	0.00	0.00	0.00	0.00	2.33	2.33	2.33	2.00	2.00
cycles	1.50	1.50	1.67	1.50	1.67	1.67	2.00	1.50	0.00	0.00	0.00	0.00	2.33	2.33	2.33	2.00	2.00

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	2.13
Overall L1	5.00-12.50

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	0%
other	0%

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:

1% of peak load performance is reached (1.60 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (5.12 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the function is: 408a80

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P12	P13	P14	P15	P16	Latency	Recip. throughput	Vectorization
STP X29, X30, [SP, #912]!	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	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	1	0.17	scal (50.0%)
STP X19, X20, [SP, #16]	1	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	1	0.17	scal (50.0%)
STP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
STP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0.50	0.50	0	0.50	0.50	1	0.50	scal (100.0%)
LDR X21, [X0]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
BL 402640 <@plt_start@+0x100>	1	0.50	0.50	0.50	0.50	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	1	0.17	scal (25.0%)
BL 402660 <@plt_start@+0x120>	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	1	0.50	N/A
ORR W22, WZR, W0	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
LDR X24, [X21, #24]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	N/A
LDR W23, [X24, #12]	1	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33	scal (25.0%)
SDIV W2, W23, W19	1	0	0	0	0	0	0	1	0	0	0	0	0	0	5-12	5-12.50	scal (25.0%)
MSUB W1, W2, W19, W23	1	0	0	0	0	0	0	1	0	0	0	0	0	0	2	1	N/A
CMP W0, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	N/A
B.LT 408bf4 <setTemperature._omp_fn.0+0x174>	1	0.50	0.50	0	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	0.86	0	0.98	0	0.96	0	0.97	0	1	0	0.64	0.01	1.4	0	1.19	0	1.08	0	1.21	0	0.92	0	3.77	0	2.09	0	3.64	0

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	0.094999991357327	0.017701910808682
1x2	2	0.86	1.72	2	0.059999991208315	0.020561704412103
1x4	4	0.98	3.94	4	0.029999995604157	0.017724050208926
1x8	8	0.96	7.67	8	0.01999999769032	0.01768034696579
1x16	11	0.97	15.58	16	0.010000000707805	0.016645403578877
1x24	15	1	23.95	24	0.00999999884516	0.01555738132447
1x32	19	0.64	20.58	32	0.00999999884516	0.024517150595784
1x40	10	1.4	55.96	40	0.00999999884516	0.010829344391823
1x48	14	1.19	57.13	48	0.0049999998882413	0.012541314586997
1x56	15	1.08	60.66	56	0.0050000003539026	0.013352090492845
1x64	13	1.21	77.57	64	0.0049999998882413	0.01147781778127
1x72	17	0.92	66.24	72	0.00499999942258	0.014886029064655
1x80	4	3.77	301.29	80	0.00499999942258	0.0034899131860584
1x88	7	2.09	184.14	88	0.00499999942258	0.006076707970351
1x96	4	3.64	349.45	96	0.0049999998882413	0.0034631418529898

Name	Coverage (%)	Time (s)
▼setTemperature._omp_fn.0–	0.02	0.09
▼Loop 93 - initAtoms.c:151-162 - exec–	0.00	0.00
▼Loop 94 - initAtoms.c:154-162 - exec–	0.00	0.00
○Loop 95 - initAtoms.c:154-162 - exec	0.02	0.09

Report Configuration

Vectorization

Details

Workaround

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

Workaround

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

▶Scalability Runs Description

▼Columns Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency