OV - exec - Function getBoxFromTuple

	Function: getBoxFromTuple	Module: exec	Source: linkCells.c:204-249	Coverage (incl. loops): 0.01% \| (excl. loops): 0.01%

/home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c: 204 - 249

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

204: {

205:    int iBox = 0;

206:    const int* gridSize = boxes->gridSize; // alias

207:

208:    // Halo in Z+

209:    if (iz == gridSize[2])

210:    {

211:       iBox = boxes->nLocalBoxes + 2*gridSize[2]*gridSize[1] + 2*gridSize[2]*(gridSize[0]+2) +

212:          (gridSize[0]+2)*(gridSize[1]+2) + (gridSize[0]+2)*(iy+1) + (ix+1);

213:    }

214:    // Halo in Z-

215:    else if (iz == -1)

216:    {

217:       iBox = boxes->nLocalBoxes + 2*gridSize[2]*gridSize[1] + 2*gridSize[2]*(gridSize[0]+2) +

218:          (gridSize[0]+2)*(iy+1) + (ix+1);

219:    }

220:    // Halo in Y+

221:    else if (iy == gridSize[1])

222:    {

223:       iBox = boxes->nLocalBoxes + 2*gridSize[2]*gridSize[1] + gridSize[2]*(gridSize[0]+2) +

224:          (gridSize[0]+2)*iz + (ix+1);

225:    }

226:    // Halo in Y-

227:    else if (iy == -1)

228:    {

229:       iBox = boxes->nLocalBoxes + 2*gridSize[2]*gridSize[1] + iz*(gridSize[0]+2) + (ix+1);

230:    }

231:    // Halo in X+

232:    else if (ix == gridSize[0])

233:    {

234:       iBox = boxes->nLocalBoxes + gridSize[1]*gridSize[2] + iz*gridSize[1] + iy;

235:    }

236:    // Halo in X-

237:    else if (ix == -1)

238:    {

239:       iBox = boxes->nLocalBoxes + iz*gridSize[1] + iy;

240:    }

241:    // local link celll.

242:    else

243:    {

244:       iBox = ix + gridSize[0]*iy + gridSize[0]*gridSize[1]*iz;

245:    }

246:    assert(iBox >= 0);

247:    assert(iBox < boxes->nTotalBoxes);

248:

249:    return iBox;

0x40a410 PUSH	%RBP

0x40a411 MOV	%RSP,%RBP

0x40a414 MOV	0x8(%RDI),%EAX

0x40a417 MOV	(%RDI),%R8D

0x40a41a MOV	0x4(%RDI),%R9D

0x40a41e CMP	%ECX,%EAX

0x40a420 JNE	40a44a

0x40a422 MOV	0xc(%RDI),%EAX

0x40a425 LEA	(%RCX,%RCX,1),%R10D

0x40a429 IMUL	%R9D,%R10D

0x40a42d ADD	$0x2,%R8D

0x40a431 ADD	%R9D,%EDX

0x40a434 LEA	0x3(%RDX,%RCX,2),%ECX

0x40a438 IMUL	%R8D,%ECX

0x40a43c ADD	%R10D,%ESI

0x40a43f ADD	%ECX,%ESI

0x40a441 LEA	0x1(%RAX,%RSI,1),%EAX

0x40a445 JMP	40a4e1

0x40a44a CMP	$-0x1,%ECX

0x40a44d JE	40a471

0x40a44f CMP	%EDX,%R9D

0x40a452 JNE	40a493

0x40a454 MOV	0xc(%RDI),%R9D

0x40a458 IMUL	%EAX,%EDX

0x40a45b ADD	$0x2,%R8D

0x40a45f ADD	%EAX,%ECX

0x40a461 IMUL	%R8D,%ECX

0x40a465 LEA	(%RSI,%RDX,2),%EAX

0x40a468 ADD	%ECX,%EAX

0x40a46a LEA	0x1(%R9,%RAX,1),%EAX

0x40a46f JMP	40a4e1

0x40a471 MOV	0xc(%RDI),%ECX

0x40a474 LEA	(%RAX,%RAX,1),%R10D

0x40a478 IMUL	%R9D,%R10D

0x40a47c ADD	$0x2,%R8D

0x40a480 LEA	0x1(%RDX,%RAX,2),%EAX

0x40a484 IMUL	%R8D,%EAX

0x40a488 ADD	%R10D,%ESI

0x40a48b ADD	%EAX,%ESI

0x40a48d LEA	0x1(%RCX,%RSI,1),%EAX

0x40a491 JMP	40a4e1

0x40a493 CMP	$-0x1,%EDX

0x40a496 JE	40a4aa

0x40a498 CMP	%ESI,%R8D

0x40a49b JNE	40a4c5

0x40a49d ADD	%ECX,%EAX

0x40a49f IMUL	%R9D,%EAX

0x40a4a3 ADD	%EDX,%EAX

0x40a4a5 ADD	0xc(%RDI),%EAX

0x40a4a8 JMP	40a4e1

0x40a4aa MOV	0xc(%RDI),%EDX

0x40a4ad IMUL	%R9D,%EAX

0x40a4b1 ADD	$0x2,%R8D

0x40a4b5 IMUL	%ECX,%R8D

0x40a4b9 LEA	(%RSI,%RAX,2),%EAX

0x40a4bc ADD	%R8D,%EAX

0x40a4bf LEA	0x1(%RDX,%RAX,1),%EAX

0x40a4c3 JMP	40a4e1

0x40a4c5 IMUL	%ECX,%R9D

0x40a4c9 ADD	%EDX,%R9D

0x40a4cc CMP	$-0x1,%ESI

0x40a4cf JE	40a4da

0x40a4d1 IMUL	%R8D,%R9D

0x40a4d5 ADD	%ESI,%R9D

0x40a4d8 JMP	40a4de

0x40a4da ADD	0xc(%RDI),%R9D

0x40a4de MOV	%R9D,%EAX

0x40a4e1 TEST	%EAX,%EAX

0x40a4e3 JS	40a4ec

0x40a4e5 CMP	0x14(%RDI),%EAX

0x40a4e8 JGE	40a505

0x40a4ea POP	%RBP

0x40a4eb RET

0x40a4ec MOV	$0x41f914,%EDI

0x40a4f1 MOV	$0x41f83e,%ESI

0x40a4f6 MOV	$0x41f91e,%ECX

0x40a4fb MOV	$0xf6,%EDX

0x40a500 CALL	4030b0 <__assert_fail@plt>

0x40a505 MOV	$0x41f94d,%EDI

0x40a50a MOV	$0x41f83e,%ESI

0x40a50f MOV	$0x41f91e,%ECX

0x40a514 MOV	$0xf7,%EDX

0x40a519 CALL	4030b0 <__assert_fail@plt>

0x40a51e XCHG	%AX,%AX

Coverage (%)	Name	Source Location	Module
►11.77+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►8.82+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►8.82+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►5.89+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►5.88+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	unloadAtomsBuffer	haloExchange.c:416	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	createFccLattice	initAtoms.c:100	exec
○	main	CoMD.c:199	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	createFccLattice	initAtoms.c:100	exec
○	main	CoMD.c:199	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	createFccLattice	initAtoms.c:100	exec
○	main	CoMD.c:199	exec
○	__libc_start_call_main		libc.so.6
►2.94+	putAtomInBox	linkCells.c:179	exec
○	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	haloExchange.c:302	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec
○	__libc_start_call_main		libc.so.6
►2.94+	unloadAtomsBuffer	haloExchange.c:414	exec
○	haloExchange	memUtils.h:28	exec
○	timestep	timestep.c:150	exec
○	main	CoMD.c:125	exec

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 orig_0

Source file and lines	linkCells.c:204-249
Module	exec

The function is defined in /home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c:204-249.

Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=21

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This function has 21 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside function: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the function)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 6% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 24.60 to 1.54 cycles (16.00x speedup).

Details

All SSE/AVX 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)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

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.

__assert_fail@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c:246
- /home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c:247

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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 40 bytes.

General properties

nb instructions	84
nb uops	86
loop length	272
used x86 registers	10
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.33 cycles
front end	14.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	11.70	17.00	4.00	4.00	1.50	11.80	11.70	1.50	1.50	1.50	11.80	4.00
cycles	11.70	24.60	4.00	4.00	1.50	11.80	11.70	1.50	1.50	1.50	11.80	4.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.33
Dispatch	24.60
Overall L1	24.60

Vectorization ratios

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

Vector efficiency ratios

all	6%
load	6%
store	NA (no store vectorizable/vectorized instructions)
mul	6%
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	7%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.60 cycles. At this rate:

0% of peak load performance is reached (1.63 out of 192.00 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: 40a410

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x8(%RDI),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOV 0x4(%RDI),%R9D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %ECX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40a44a <getBoxFromTuple+0x3a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0xc(%RDI),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RCX,%RCX,1),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
IMUL %R9D,%R10D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD %R9D,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x3(%RDX,%RCX,2),%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %R8D,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R10D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %ECX,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RAX,%RSI,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
CMP $-0x1,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 40a471 <getBoxFromTuple+0x61>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP %EDX,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40a493 <getBoxFromTuple+0x83>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0xc(%RDI),%R9D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %EAX,%EDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD %EAX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL %R8D,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA (%RSI,%RDX,2),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %ECX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R9,%RAX,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV 0xc(%RDI),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RAX,%RAX,1),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
IMUL %R9D,%R10D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x1(%RDX,%RAX,2),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %R8D,%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R10D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %EAX,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RCX,%RSI,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
CMP $-0x1,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 40a4aa <getBoxFromTuple+0x9a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP %ESI,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40a4c5 <getBoxFromTuple+0xb5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %ECX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL %R9D,%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD 0xc(%RDI),%EAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV 0xc(%RDI),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R9D,%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
IMUL %ECX,%R8D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
LEA (%RSI,%RAX,2),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %R8D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RDX,%RAX,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
IMUL %ECX,%R9D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %EDX,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $-0x1,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 40a4da <getBoxFromTuple+0xca>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %R8D,%R9D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %ESI,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 40a4de <getBoxFromTuple+0xce>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
ADD 0xc(%RDI),%R9D	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R9D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %EAX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JS 40a4ec <getBoxFromTuple+0xdc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP 0x14(%RDI),%EAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
JGE 40a505 <getBoxFromTuple+0xf5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
MOV $0x41f914,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f83e,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f91e,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xf6,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 4030b0 <__assert_fail@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x41f94d,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f83e,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f91e,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xf7,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 4030b0 <__assert_fail@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run orig_0

Source file and lines	linkCells.c:204-249
Module	exec

The function is defined in /home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c:204-249.

Warnings:

Ignoring paths for analysis
Too many paths. Rerun with max-paths=21

hoisting them (moving them outside the function)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Vectorization

Details

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)

Execution units bottlenecks

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

CALL instructions

Detected function call instructions.

Details

__assert_fail@plt: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c:246
- /home/eoseret/qaas_runs_GNR/173-814-1858/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c:247

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

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 40 bytes.

General properties

nb instructions	84
nb uops	86
loop length	272
used x86 registers	10
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.33 cycles
front end	14.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	11.70	17.00	4.00	4.00	1.50	11.80	11.70	1.50	1.50	1.50	11.80	4.00
cycles	11.70	24.60	4.00	4.00	1.50	11.80	11.70	1.50	1.50	1.50	11.80	4.00

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.33
Dispatch	24.60
Overall L1	24.60

Vectorization ratios

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

Vector efficiency ratios

all	6%
load	6%
store	NA (no store vectorizable/vectorized instructions)
mul	6%
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	7%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 24.60 cycles. At this rate:

0% of peak load performance is reached (1.63 out of 192.00 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: 40a410

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV 0x8(%RDI),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%R8D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOV 0x4(%RDI),%R9D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %ECX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40a44a <getBoxFromTuple+0x3a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0xc(%RDI),%EAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RCX,%RCX,1),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
IMUL %R9D,%R10D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD %R9D,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x3(%RDX,%RCX,2),%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %R8D,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R10D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %ECX,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RAX,%RSI,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
CMP $-0x1,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 40a471 <getBoxFromTuple+0x61>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP %EDX,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40a493 <getBoxFromTuple+0x83>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0xc(%RDI),%R9D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %EAX,%EDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
ADD %EAX,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL %R8D,%ECX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
LEA (%RSI,%RDX,2),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %ECX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%R9,%RAX,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV 0xc(%RDI),%ECX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RAX,%RAX,1),%R10D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
IMUL %R9D,%R10D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
LEA 0x1(%RDX,%RAX,2),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %R8D,%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R10D,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %EAX,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RCX,%RSI,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
CMP $-0x1,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 40a4aa <getBoxFromTuple+0x9a>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP %ESI,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 40a4c5 <getBoxFromTuple+0xb5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %ECX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL %R9D,%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %EDX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD 0xc(%RDI),%EAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
MOV 0xc(%RDI),%EDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R9D,%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD $0x2,%R8D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
IMUL %ECX,%R8D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (6.3%)
LEA (%RSI,%RAX,2),%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %R8D,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA 0x1(%RDX,%RAX,1),%EAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
JMP 40a4e1 <getBoxFromTuple+0xd1>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
IMUL %ECX,%R9D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %EDX,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $-0x1,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 40a4da <getBoxFromTuple+0xca>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %R8D,%R9D	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %ESI,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 40a4de <getBoxFromTuple+0xce>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
ADD 0xc(%RDI),%R9D	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
MOV %R9D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
TEST %EAX,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (6.3%)
JS 40a4ec <getBoxFromTuple+0xdc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP 0x14(%RDI),%EAX	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
JGE 40a505 <getBoxFromTuple+0xf5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
MOV $0x41f914,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f83e,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f91e,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xf6,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 4030b0 <__assert_fail@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV $0x41f94d,%EDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f83e,%ESI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x41f91e,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0xf7,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CALL 4030b0 <__assert_fail@plt>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
○getBoxFromTuple	0.01	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Type of elements and instruction set

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