OV - exec - Function void qmcplusplus::DTD_BConds<double, 3u, 40>::computeDistances<qmcplusplus::TinyVector<double, 3u>, qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 64ul> >, qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 64ul> > >(qmcplusplus::TinyVector<double, 3u> const&, qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 64ul> > const&, double*, qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 64ul> >&, int, int, int) const

	Function: void qmcplusplus::DTD_BConds<double, 3u, 40>::computeDistances<qmcplusplus::TinyVector<dou ...	Module: exec	Source: ParticleBConds3DSoa.h:221-257 [...]	Coverage (incl. loops): 1.09% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h: 221 - 257

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

221:   {

222:     const T x0 = pos[0];

223:     const T y0 = pos[1];

224:     const T z0 = pos[2];

[...]

234: #pragma omp simd aligned(temp_r, px, py, pz, dx, dy, dz: QMC_SIMD_ALIGNMENT)

235:     for (int iat = first; iat < last; ++iat)

236:     {

237:       T displ_0 = px[iat] - x0;

238:       T displ_1 = py[iat] - y0;

239:       T displ_2 = pz[iat] - z0;

240:

241:       T ar_0 = displ_0 * g00 + displ_1 * g10 + displ_2 * g20;

242:       T ar_1 = displ_0 * g01 + displ_1 * g11 + displ_2 * g21;

243:       T ar_2 = displ_0 * g02 + displ_1 * g12 + displ_2 * g22;

244:

245:       //put them in the box

246:       ar_0 -= round(ar_0);

247:       ar_1 -= round(ar_1);

248:       ar_2 -= round(ar_2);

249:

250:       //unit2cart

251:       dx[iat] = ar_0 * r00 + ar_1 * r10 + ar_2 * r20;

252:       dy[iat] = ar_0 * r01 + ar_1 * r11 + ar_2 * r21;

253:       dz[iat] = ar_0 * r02 + ar_1 * r12 + ar_2 * r22;

254:

255:       temp_r[iat] = std::sqrt(dx[iat] * dx[iat] + dy[iat] * dy[iat] + dz[iat] * dz[iat]);

256:     }

257:   }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 271 - 273

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

271:   inline T* restrict data(size_t i) { return myData + i * nGhosts; }

272:   ///return the const pointer of the i-th components

273:   inline const T* restrict data(size_t i) const { return myData + i * nGhosts; }

0x48be50 PUSH	%RBP

0x48be51 MOV	%RSP,%RBP

0x48be54 PUSH	%R15

0x48be56 PUSH	%R14

0x48be58 PUSH	%R13

0x48be5a PUSH	%R12

0x48be5c PUSH	%RBX

0x48be5d SUB	$0x288,%RSP

0x48be64 MOV	0x10(%RBP),%R13D

0x48be68 MOV	%R13D,%R10D

0x48be6b SUB	%R9D,%R10D

0x48be6e JLE	48c771

0x48be74 MOV	%RCX,%R15

0x48be77 MOV	%RDI,%R14

0x48be7a MOVUPD	(%RSI),%XMM0

0x48be7e MOVSD	0x10(%RSI),%XMM1

0x48be83 MOV	0x8(%RDX),%RCX

0x48be87 MOV	0x18(%RDX),%RDX

0x48be8b LEA	(%RDX,%RCX,8),%RSI

0x48be8f SAL	$0x4,%RCX

0x48be93 ADD	%RDX,%RCX

0x48be96 MOV	0x8(%R8),%RBX

0x48be9a MOV	0x18(%R8),%RAX

0x48be9e MOV	%RAX,-0xa8(%RBP)

0x48bea5 LEA	(%RAX,%RBX,8),%RDI

0x48bea9 MOV	%RDI,-0xa0(%RBP)

0x48beb0 SAL	$0x4,%RBX

0x48beb4 ADD	%RAX,%RBX

0x48beb7 MOVSD	0x48(%R14),%XMM2

0x48bebd MOVUPD	0x50(%R14),%XMM3

0x48bec3 MOVSD	0x60(%R14),%XMM4

0x48bec9 MOVSD	0x68(%R14),%XMM5

0x48becf MOVSD	0x78(%R14),%XMM9

0x48bed5 MOVSD	0x80(%R14),%XMM11

0x48bede MOVSD	0x70(%R14),%XMM6

0x48bee4 MOVSD	0x88(%R14),%XMM10

0x48beed MOVSD	(%R14),%XMM7

0x48bef2 MOVUPD	0x8(%R14),%XMM8

0x48bef8 MOV	%R10D,%R12D

0x48befb AND	$-0x4,%R12D

0x48beff MOV	%RCX,-0xc0(%RBP)

0x48bf06 MOV	%RDX,-0xb8(%RBP)

0x48bf0d MOV	%RSI,-0xb0(%RBP)

0x48bf14 MOVAPD	%XMM0,-0x170(%RBP)

0x48bf1c MOVAPD	%XMM1,-0x160(%RBP)

0x48bf24 MOVAPD	%XMM2,-0x150(%RBP)

0x48bf2c MOVAPD	%XMM3,-0x140(%RBP)

0x48bf34 MOVAPD	%XMM7,-0x2b0(%RBP)

0x48bf3c MOVAPD	%XMM8,-0x2a0(%RBP)

0x48bf45 JE	48c56a

0x48bf4b MOV	%R10D,-0x74(%RBP)

0x48bf4f LEA	-0x1(%R12),%EAX

0x48bf54 MOV	%EAX,-0x78(%RBP)

0x48bf57 MOVAPD	%XMM0,%XMM12

0x48bf5c UNPCKLPD	%XMM0,%XMM12

0x48bf61 MOVAPD	%XMM12,-0x290(%RBP)

0x48bf6a UNPCKHPD	%XMM0,%XMM0

0x48bf6e MOVAPD	%XMM0,-0x280(%RBP)

0x48bf76 UNPCKLPD	%XMM1,%XMM1

0x48bf7a MOVAPD	%XMM1,-0x270(%RBP)

0x48bf82 UNPCKLPD	%XMM2,%XMM2

0x48bf86 MOVAPD	%XMM2,-0x260(%RBP)

0x48bf8e MOVAPD	%XMM3,%XMM0

0x48bf92 UNPCKLPD	%XMM3,%XMM0

0x48bf96 MOVAPD	%XMM0,-0x250(%RBP)

0x48bf9e UNPCKHPD	%XMM3,%XMM3

0x48bfa2 MOVAPD	%XMM3,-0x240(%RBP)

0x48bfaa MOVAPD	%XMM4,-0x100(%RBP)

0x48bfb2 UNPCKLPD	%XMM4,%XMM4

0x48bfb6 MOVAPD	%XMM4,-0x230(%RBP)

0x48bfbe MOVAPD	%XMM5,-0xf0(%RBP)

0x48bfc6 UNPCKLPD	%XMM5,%XMM5

0x48bfca MOVAPD	%XMM5,-0x220(%RBP)

0x48bfd2 MOVAPD	%XMM6,-0xe0(%RBP)

0x48bfda UNPCKLPD	%XMM6,%XMM6

0x48bfde MOVAPD	%XMM6,-0x210(%RBP)

0x48bfe6 MOVAPD	%XMM9,-0x1a0(%RBP)

0x48bfef UNPCKLPD	%XMM9,%XMM9

0x48bff4 MOVAPD	%XMM9,-0x200(%RBP)

0x48bffd MOVAPD	%XMM11,-0x180(%RBP)

0x48c006 UNPCKLPD	%XMM11,%XMM11

0x48c00b MOVAPD	%XMM11,-0x1f0(%RBP)

0x48c014 MOVAPD	%XMM10,-0x190(%RBP)

0x48c01d UNPCKLPD	%XMM10,%XMM10

0x48c022 MOVAPD	%XMM10,-0x1e0(%RBP)

0x48c02b UNPCKLPD	%XMM7,%XMM7

0x48c02f MOVAPD	%XMM7,-0x1d0(%RBP)

0x48c037 MOVAPD	%XMM8,%XMM0

0x48c03c UNPCKLPD	%XMM8,%XMM0

0x48c041 MOVAPD	%XMM0,-0x1c0(%RBP)

0x48c049 UNPCKHPD	%XMM8,%XMM8

0x48c04e MOVAPD	%XMM8,-0x1b0(%RBP)

0x48c057 MOV	%R15,-0x98(%RBP)

0x48c05e XOR	%R15D,%R15D

0x48c061 MOV	%RBX,-0x128(%RBP)

0x48c068 NOPL	(%RAX,%RAX,1)

(1504) 0x48c070 LEA	(%R9,%R15,1),%EAX

(1504) 0x48c074 MOVSXD	%EAX,%R13

(1504) 0x48c077 MOVUPD	(%RDX,%R13,8),%XMM3

(1504) 0x48c07d MOVUPD	0x10(%RDX,%R13,8),%XMM1

(1504) 0x48c084 MOVAPD	-0x290(%RBP),%XMM0

(1504) 0x48c08c SUBPD	%XMM0,%XMM3

(1504) 0x48c090 SUBPD	%XMM0,%XMM1

(1504) 0x48c094 MOVUPD	(%RSI,%R13,8),%XMM10

(1504) 0x48c09a MOVUPD	0x10(%RSI,%R13,8),%XMM2

(1504) 0x48c0a1 MOVAPD	-0x280(%RBP),%XMM4

(1504) 0x48c0a9 SUBPD	%XMM4,%XMM10

(1504) 0x48c0ae SUBPD	%XMM4,%XMM2

(1504) 0x48c0b2 MOVUPD	(%RCX,%R13,8),%XMM9

(1504) 0x48c0b8 MOVUPD	0x10(%RCX,%R13,8),%XMM8

(1504) 0x48c0bf MOVAPD	-0x270(%RBP),%XMM4

(1504) 0x48c0c7 SUBPD	%XMM4,%XMM8

(1504) 0x48c0cc SUBPD	%XMM4,%XMM9

(1504) 0x48c0d1 MOVAPD	-0x260(%RBP),%XMM5

(1504) 0x48c0d9 MOVAPD	%XMM5,%XMM4

(1504) 0x48c0dd MULPD	%XMM1,%XMM4

(1504) 0x48c0e1 MULPD	%XMM3,%XMM5

(1504) 0x48c0e5 MOVAPD	-0x250(%RBP),%XMM7

(1504) 0x48c0ed MOVAPD	%XMM7,%XMM6

(1504) 0x48c0f1 MULPD	%XMM2,%XMM6

(1504) 0x48c0f5 ADDPD	%XMM4,%XMM6

(1504) 0x48c0f9 MOVAPD	%XMM7,%XMM4

(1504) 0x48c0fd MULPD	%XMM10,%XMM4

(1504) 0x48c102 ADDPD	%XMM5,%XMM4

(1504) 0x48c106 MOVAPD	-0x240(%RBP),%XMM5

(1504) 0x48c10e MOVAPD	%XMM5,%XMM7

(1504) 0x48c112 MULPD	%XMM9,%XMM7

(1504) 0x48c117 ADDPD	%XMM4,%XMM7

(1504) 0x48c11b MOVAPD	%XMM7,%XMM0

(1504) 0x48c11f MOVAPD	%XMM7,-0xd0(%RBP)

(1504) 0x48c127 MULPD	%XMM8,%XMM5

(1504) 0x48c12c ADDPD	%XMM6,%XMM5

(1504) 0x48c130 MOVAPD	%XMM5,-0x60(%RBP)

(1504) 0x48c135 MOVAPD	-0x230(%RBP),%XMM5

(1504) 0x48c13d MOVAPD	%XMM5,%XMM4

(1504) 0x48c141 MULPD	%XMM1,%XMM4

(1504) 0x48c145 MULPD	%XMM3,%XMM5

(1504) 0x48c149 MOVAPD	-0x220(%RBP),%XMM7

(1504) 0x48c151 MOVAPD	%XMM7,%XMM6

(1504) 0x48c155 MULPD	%XMM2,%XMM6

(1504) 0x48c159 ADDPD	%XMM4,%XMM6

(1504) 0x48c15d MOVAPD	%XMM7,%XMM4

(1504) 0x48c161 MULPD	%XMM10,%XMM4

(1504) 0x48c166 ADDPD	%XMM5,%XMM4

(1504) 0x48c16a MOVAPD	-0x210(%RBP),%XMM5

(1504) 0x48c172 MOVAPD	%XMM5,%XMM7

(1504) 0x48c176 MULPD	%XMM9,%XMM7

(1504) 0x48c17b ADDPD	%XMM4,%XMM7

(1504) 0x48c17f MOVAPD	%XMM7,-0x50(%RBP)

(1504) 0x48c184 MULPD	%XMM8,%XMM5

(1504) 0x48c189 ADDPD	%XMM6,%XMM5

(1504) 0x48c18d MOVAPD	%XMM5,-0x70(%RBP)

(1504) 0x48c192 MOVAPD	-0x200(%RBP),%XMM4

(1504) 0x48c19a MULPD	%XMM4,%XMM3

(1504) 0x48c19e MOVAPD	-0x1f0(%RBP),%XMM5

(1504) 0x48c1a6 MULPD	%XMM5,%XMM10

(1504) 0x48c1ab ADDPD	%XMM3,%XMM10

(1504) 0x48c1b0 MULPD	%XMM4,%XMM1

(1504) 0x48c1b4 MULPD	%XMM5,%XMM2

(1504) 0x48c1b8 ADDPD	%XMM1,%XMM2

(1504) 0x48c1bc MOVAPD	-0x1e0(%RBP),%XMM1

(1504) 0x48c1c4 MULPD	%XMM1,%XMM8

(1504) 0x48c1c9 ADDPD	%XMM2,%XMM8

(1504) 0x48c1ce MOVAPD	%XMM8,-0x120(%RBP)

(1504) 0x48c1d7 MULPD	%XMM1,%XMM9

(1504) 0x48c1dc ADDPD	%XMM10,%XMM9

(1504) 0x48c1e1 MOVAPD	%XMM9,-0x110(%RBP)

(1504) 0x48c1ea MOV	%R9,%RBX

(1504) 0x48c1ed CALL	506ad0 <round>

(1504) 0x48c1f2 MOVAPD	%XMM0,-0x40(%RBP)

(1504) 0x48c1f7 MOVAPS	-0xd0(%RBP),%XMM0

(1504) 0x48c1fe MOVHLPS	%XMM0,%XMM0

(1504) 0x48c201 CALL	506ad0 <round>

(1504) 0x48c206 MOVAPS	-0x40(%RBP),%XMM1

(1504) 0x48c20a MOVLHPS	%XMM0,%XMM1

(1504) 0x48c20d MOVAPS	%XMM1,-0x40(%RBP)

(1504) 0x48c211 MOVAPS	-0x60(%RBP),%XMM0

(1504) 0x48c215 CALL	506ad0 <round>

(1504) 0x48c21a MOVAPS	%XMM0,-0x90(%RBP)

(1504) 0x48c221 MOVAPD	-0x60(%RBP),%XMM0

(1504) 0x48c226 UNPCKHPD	%XMM0,%XMM0

(1504) 0x48c22a CALL	506ad0 <round>

(1504) 0x48c22f MOVAPD	-0x90(%RBP),%XMM1

(1504) 0x48c237 UNPCKLPD	%XMM0,%XMM1

(1504) 0x48c23b MOVAPD	-0x60(%RBP),%XMM0

(1504) 0x48c240 SUBPD	%XMM1,%XMM0

(1504) 0x48c244 MOVAPD	%XMM0,-0x60(%RBP)

(1504) 0x48c249 MOVAPD	-0xd0(%RBP),%XMM0

(1504) 0x48c251 SUBPD	-0x40(%RBP),%XMM0

(1504) 0x48c256 MOVAPD	%XMM0,-0xd0(%RBP)

(1504) 0x48c25e MOVAPS	-0x50(%RBP),%XMM0

(1504) 0x48c262 CALL	506ad0 <round>

(1504) 0x48c267 MOVAPS	%XMM0,-0x40(%RBP)

(1504) 0x48c26b MOVAPS	-0x50(%RBP),%XMM0

(1504) 0x48c26f MOVHLPS	%XMM0,%XMM0

(1504) 0x48c272 CALL	506ad0 <round>

(1504) 0x48c277 MOVAPS	-0x40(%RBP),%XMM1

(1504) 0x48c27b MOVLHPS	%XMM0,%XMM1

(1504) 0x48c27e MOVAPS	%XMM1,-0x40(%RBP)

(1504) 0x48c282 MOVAPS	-0x70(%RBP),%XMM0

(1504) 0x48c286 CALL	506ad0 <round>

(1504) 0x48c28b MOVAPS	%XMM0,-0x90(%RBP)

(1504) 0x48c292 MOVAPD	-0x70(%RBP),%XMM0

(1504) 0x48c297 UNPCKHPD	%XMM0,%XMM0

(1504) 0x48c29b CALL	506ad0 <round>

(1504) 0x48c2a0 MOVAPD	-0x90(%RBP),%XMM1

(1504) 0x48c2a8 UNPCKLPD	%XMM0,%XMM1

(1504) 0x48c2ac MOVAPD	-0x70(%RBP),%XMM0

(1504) 0x48c2b1 SUBPD	%XMM1,%XMM0

(1504) 0x48c2b5 MOVAPD	%XMM0,-0x70(%RBP)

(1504) 0x48c2ba MOVAPD	-0x50(%RBP),%XMM0

(1504) 0x48c2bf SUBPD	-0x40(%RBP),%XMM0

(1504) 0x48c2c4 MOVAPD	%XMM0,-0x50(%RBP)

(1504) 0x48c2c9 MOVAPS	-0x120(%RBP),%XMM0

(1504) 0x48c2d0 CALL	506ad0 <round>

(1504) 0x48c2d5 MOVAPS	%XMM0,-0x40(%RBP)

(1504) 0x48c2d9 MOVAPS	-0x120(%RBP),%XMM0

(1504) 0x48c2e0 MOVHLPS	%XMM0,%XMM0

(1504) 0x48c2e3 CALL	506ad0 <round>

(1504) 0x48c2e8 MOVAPS	-0x40(%RBP),%XMM1

(1504) 0x48c2ec MOVLHPS	%XMM0,%XMM1

(1504) 0x48c2ef MOVAPS	%XMM1,-0x40(%RBP)

(1504) 0x48c2f3 MOVAPS	-0x110(%RBP),%XMM0

(1504) 0x48c2fa CALL	506ad0 <round>

(1504) 0x48c2ff MOVAPS	%XMM0,-0x90(%RBP)

(1504) 0x48c306 MOVAPD	-0x110(%RBP),%XMM0

(1504) 0x48c30e UNPCKHPD	%XMM0,%XMM0

(1504) 0x48c312 CALL	506ad0 <round>

(1504) 0x48c317 MOV	%RBX,%R9

(1504) 0x48c31a MOV	-0x128(%RBP),%RBX

(1504) 0x48c321 MOV	-0xa0(%RBP),%RDI

(1504) 0x48c328 MOV	-0xa8(%RBP),%RAX

(1504) 0x48c32f MOV	-0xb0(%RBP),%RSI

(1504) 0x48c336 MOV	-0xb8(%RBP),%RDX

(1504) 0x48c33d MOV	-0xc0(%RBP),%RCX

(1504) 0x48c344 MOVAPD	-0x90(%RBP),%XMM2

(1504) 0x48c34c UNPCKLPD	%XMM0,%XMM2

(1504) 0x48c350 MOVAPD	-0x120(%RBP),%XMM12

(1504) 0x48c359 SUBPD	-0x40(%RBP),%XMM12

(1504) 0x48c35f MOVAPD	-0x1d0(%RBP),%XMM1

(1504) 0x48c367 MOVAPD	%XMM1,%XMM0

(1504) 0x48c36b MOVAPD	-0x110(%RBP),%XMM5

(1504) 0x48c373 SUBPD	%XMM2,%XMM5

(1504) 0x48c377 MOVAPD	-0xd0(%RBP),%XMM7

(1504) 0x48c37f MULPD	%XMM7,%XMM0

(1504) 0x48c383 MOVAPD	-0x1c0(%RBP),%XMM3

(1504) 0x48c38b MOVAPD	%XMM3,%XMM2

(1504) 0x48c38f MOVAPD	-0x60(%RBP),%XMM6

(1504) 0x48c394 MULPD	%XMM6,%XMM1

(1504) 0x48c398 MOVAPD	-0x50(%RBP),%XMM8

(1504) 0x48c39e MULPD	%XMM8,%XMM2

(1504) 0x48c3a3 MOVAPD	-0x70(%RBP),%XMM10

(1504) 0x48c3a9 MULPD	%XMM10,%XMM3

(1504) 0x48c3ae ADDPD	%XMM0,%XMM2

(1504) 0x48c3b2 ADDPD	%XMM1,%XMM3

(1504) 0x48c3b6 MOVAPD	%XMM12,%XMM1

(1504) 0x48c3bb MOVAPD	-0x1b0(%RBP),%XMM4

(1504) 0x48c3c3 MULPD	%XMM4,%XMM1

(1504) 0x48c3c7 ADDPD	%XMM3,%XMM1

(1504) 0x48c3cb MOVAPD	%XMM5,%XMM0

(1504) 0x48c3cf MOVAPD	%XMM5,%XMM11

(1504) 0x48c3d4 MULPD	%XMM4,%XMM0

(1504) 0x48c3d8 ADDPD	%XMM2,%XMM0

(1504) 0x48c3dc MOVUPD	%XMM1,0x10(%RAX,%R13,8)

(1504) 0x48c3e3 MOVUPD	%XMM0,(%RAX,%R13,8)

(1504) 0x48c3e9 MOVUPD	0x18(%R14),%XMM3

(1504) 0x48c3ef MOVUPD	0x20(%R14),%XMM4

(1504) 0x48c3f5 MOVUPD	0x28(%R14),%XMM2

(1504) 0x48c3fb UNPCKLPD	%XMM3,%XMM3

(1504) 0x48c3ff MOVAPD	%XMM3,%XMM5

(1504) 0x48c403 MULPD	%XMM6,%XMM3

(1504) 0x48c407 MOVAPD	%XMM6,%XMM9

(1504) 0x48c40c MULPD	%XMM7,%XMM5

(1504) 0x48c410 UNPCKLPD	%XMM4,%XMM4

(1504) 0x48c414 MOVAPD	%XMM4,%XMM6

(1504) 0x48c418 MULPD	%XMM10,%XMM4

(1504) 0x48c41d MULPD	%XMM8,%XMM6

(1504) 0x48c422 ADDPD	%XMM3,%XMM4

(1504) 0x48c426 UNPCKLPD	%XMM2,%XMM2

(1504) 0x48c42a MOVAPD	%XMM2,%XMM3

(1504) 0x48c42e ADDPD	%XMM5,%XMM6

(1504) 0x48c432 MULPD	%XMM12,%XMM3

(1504) 0x48c437 ADDPD	%XMM4,%XMM3

(1504) 0x48c43b MULPD	%XMM11,%XMM2

(1504) 0x48c440 ADDPD	%XMM6,%XMM2

(1504) 0x48c444 MOVUPD	%XMM3,0x10(%RDI,%R13,8)

(1504) 0x48c44b MOVUPD	%XMM2,(%RDI,%R13,8)

(1504) 0x48c451 MOVUPD	0x30(%R14),%XMM5

(1504) 0x48c457 MOVUPD	0x38(%R14),%XMM6

(1504) 0x48c45d MOVUPD	0x40(%R14),%XMM4

(1504) 0x48c463 UNPCKLPD	%XMM5,%XMM5

(1504) 0x48c467 MULPD	%XMM5,%XMM7

(1504) 0x48c46b MULPD	%XMM9,%XMM5

(1504) 0x48c470 UNPCKLPD	%XMM6,%XMM6

(1504) 0x48c474 MULPD	%XMM6,%XMM8

(1504) 0x48c479 MULPD	%XMM10,%XMM6

(1504) 0x48c47e ADDPD	%XMM7,%XMM8

(1504) 0x48c483 ADDPD	%XMM5,%XMM6

(1504) 0x48c487 UNPCKLPD	%XMM4,%XMM4

(1504) 0x48c48b MOVAPD	%XMM12,%XMM5

(1504) 0x48c490 MULPD	%XMM4,%XMM5

(1504) 0x48c494 ADDPD	%XMM6,%XMM5

(1504) 0x48c498 MULPD	%XMM11,%XMM4

(1504) 0x48c49d ADDPD	%XMM8,%XMM4

(1504) 0x48c4a2 MULPD	%XMM1,%XMM1

(1504) 0x48c4a6 MOVUPD	%XMM5,0x10(%RBX,%R13,8)

(1504) 0x48c4ad MULPD	%XMM0,%XMM0

(1504) 0x48c4b1 MULPD	%XMM3,%XMM3

(1504) 0x48c4b5 ADDPD	%XMM1,%XMM3

(1504) 0x48c4b9 MOVUPD	%XMM4,(%RBX,%R13,8)

(1504) 0x48c4bf MULPD	%XMM2,%XMM2

(1504) 0x48c4c3 ADDPD	%XMM0,%XMM2

(1504) 0x48c4c7 MULPD	%XMM4,%XMM4

(1504) 0x48c4cb ADDPD	%XMM2,%XMM4

(1504) 0x48c4cf MULPD	%XMM5,%XMM5

(1504) 0x48c4d3 ADDPD	%XMM3,%XMM5

(1504) 0x48c4d7 SQRTPD	%XMM4,%XMM0

(1504) 0x48c4db SQRTPD	%XMM5,%XMM1

(1504) 0x48c4df MOV	-0x98(%RBP),%RAX

(1504) 0x48c4e6 MOVUPD	%XMM1,0x10(%RAX,%R13,8)

(1504) 0x48c4ed MOVUPD	%XMM0,(%RAX,%R13,8)

(1504) 0x48c4f3 ADD	$0x4,%R15D

(1504) 0x48c4f7 CMP	-0x78(%RBP),%R15D

(1504) 0x48c4fb JBE	48c070

0x48c501 CMP	%R12D,-0x74(%RBP)

0x48c505 MOV	-0x98(%RBP),%R15

0x48c50c MOV	0x10(%RBP),%R13D

0x48c510 MOVAPD	-0x170(%RBP),%XMM0

0x48c518 MOVAPD	-0x160(%RBP),%XMM1

0x48c520 MOVAPD	-0x150(%RBP),%XMM2

0x48c528 MOVAPD	-0x140(%RBP),%XMM3

0x48c530 MOVAPD	-0x100(%RBP),%XMM4

0x48c538 MOVAPD	-0xf0(%RBP),%XMM5

0x48c540 MOVAPD	-0xe0(%RBP),%XMM6

0x48c548 MOVAPD	-0x1a0(%RBP),%XMM9

0x48c551 MOVAPD	-0x190(%RBP),%XMM10

0x48c55a MOVAPD	-0x180(%RBP),%XMM11

0x48c563 JNE	48c56d

0x48c565 JMP	48c771

0x48c56a XOR	%R12D,%R12D

0x48c56d UNPCKLPD	%XMM11,%XMM4

0x48c572 UNPCKLPD	%XMM9,%XMM5

0x48c577 UNPCKLPD	%XMM10,%XMM6

0x48c57c ADD	%R9D,%R12D

0x48c57f MOVAPD	%XMM4,-0x100(%RBP)

0x48c587 MOVAPD	%XMM5,-0xf0(%RBP)

0x48c58f MOVAPD	%XMM6,-0xe0(%RBP)

0x48c597 NOPW	(%RAX,%RAX,1)

(1503) 0x48c5a0 MOVSXD	%R12D,%R12

(1503) 0x48c5a3 MOVSD	(%RCX,%R12,8),%XMM8

(1503) 0x48c5a9 SUBSD	%XMM1,%XMM8

(1503) 0x48c5ae MOVSD	(%RDX,%R12,8),%XMM7

(1503) 0x48c5b4 MOVHPD	(%RSI,%R12,8),%XMM7

(1503) 0x48c5ba SUBPD	%XMM0,%XMM7

(1503) 0x48c5be MOVAPD	%XMM2,%XMM0

(1503) 0x48c5c2 MULSD	%XMM7,%XMM0

(1503) 0x48c5c6 MOVAPD	%XMM7,%XMM1

(1503) 0x48c5ca SHUFPD	$0x1,%XMM7,%XMM1

(1503) 0x48c5cf MULPD	%XMM5,%XMM1

(1503) 0x48c5d3 MOVAPD	%XMM4,%XMM2

(1503) 0x48c5d7 MULPD	%XMM7,%XMM2

(1503) 0x48c5db SHUFPD	$0x1,%XMM8,%XMM7

(1503) 0x48c5e1 MULPD	%XMM3,%XMM7

(1503) 0x48c5e5 ADDSD	%XMM7,%XMM0

(1503) 0x48c5e9 UNPCKHPD	%XMM7,%XMM7

(1503) 0x48c5ed ADDSD	%XMM0,%XMM7

(1503) 0x48c5f1 MOVAPD	%XMM7,%XMM0

(1503) 0x48c5f5 MOVAPD	%XMM7,-0x50(%RBP)

(1503) 0x48c5fa UNPCKLPD	%XMM8,%XMM8

(1503) 0x48c5ff MULPD	%XMM6,%XMM8

(1503) 0x48c604 ADDPD	%XMM2,%XMM8

(1503) 0x48c609 ADDPD	%XMM1,%XMM8

(1503) 0x48c60e MOVAPD	%XMM8,-0x60(%RBP)

(1503) 0x48c614 CALL	506ad0 <round>

(1503) 0x48c619 MOVAPD	-0x50(%RBP),%XMM1

(1503) 0x48c61e SUBSD	%XMM0,%XMM1

(1503) 0x48c622 MOVAPD	%XMM1,-0x50(%RBP)

(1503) 0x48c627 MOVAPS	-0x60(%RBP),%XMM0

(1503) 0x48c62b CALL	506ad0 <round>

(1503) 0x48c630 MOVAPS	%XMM0,-0x70(%RBP)

(1503) 0x48c634 MOVAPD	-0x60(%RBP),%XMM0

(1503) 0x48c639 UNPCKHPD	%XMM0,%XMM0

(1503) 0x48c63d CALL	506ad0 <round>

(1503) 0x48c642 MOVAPD	-0x2a0(%RBP),%XMM8

(1503) 0x48c64b MOVAPD	-0x2b0(%RBP),%XMM7

(1503) 0x48c653 MOVAPD	-0xe0(%RBP),%XMM6

(1503) 0x48c65b MOVAPD	-0xf0(%RBP),%XMM5

(1503) 0x48c663 MOVAPD	-0x100(%RBP),%XMM4

(1503) 0x48c66b MOV	-0xb0(%RBP),%RSI

(1503) 0x48c672 MOV	-0xb8(%RBP),%RDX

(1503) 0x48c679 MOV	-0xc0(%RBP),%RCX

(1503) 0x48c680 MOVAPD	-0x70(%RBP),%XMM1

(1503) 0x48c685 UNPCKLPD	%XMM0,%XMM1

(1503) 0x48c689 MOVAPD	-0x60(%RBP),%XMM3

(1503) 0x48c68e SUBPD	%XMM1,%XMM3

(1503) 0x48c692 MOVAPD	%XMM7,%XMM1

(1503) 0x48c696 MOVAPD	-0x50(%RBP),%XMM2

(1503) 0x48c69b MULSD	%XMM2,%XMM1

(1503) 0x48c69f MOVAPD	%XMM8,%XMM0

(1503) 0x48c6a4 MULPD	%XMM3,%XMM0

(1503) 0x48c6a8 MOVAPD	%XMM3,%XMM10

(1503) 0x48c6ad ADDSD	%XMM0,%XMM1

(1503) 0x48c6b1 UNPCKHPD	%XMM0,%XMM0

(1503) 0x48c6b5 ADDSD	%XMM1,%XMM0

(1503) 0x48c6b9 MOV	-0xa8(%RBP),%RAX

(1503) 0x48c6c0 MOVSD	%XMM0,(%RAX,%R12,8)

(1503) 0x48c6c6 MOVSD	0x18(%R14),%XMM1

(1503) 0x48c6cc MULSD	%XMM2,%XMM1

(1503) 0x48c6d0 MOVAPD	%XMM2,%XMM9

(1503) 0x48c6d5 MOVUPD	0x20(%R14),%XMM2

(1503) 0x48c6db MULPD	%XMM3,%XMM2

(1503) 0x48c6df MOVAPD	%XMM2,%XMM3

(1503) 0x48c6e3 UNPCKHPD	%XMM2,%XMM3

(1503) 0x48c6e7 ADDSD	%XMM2,%XMM3

(1503) 0x48c6eb ADDSD	%XMM1,%XMM3

(1503) 0x48c6ef MOV	-0xa0(%RBP),%RAX

(1503) 0x48c6f6 MOVSD	%XMM3,(%RAX,%R12,8)

(1503) 0x48c6fc MULSD	0x30(%R14),%XMM9

(1503) 0x48c702 MOVUPD	0x38(%R14),%XMM1

(1503) 0x48c708 MULPD	%XMM10,%XMM1

(1503) 0x48c70d MOVAPD	%XMM1,%XMM2

(1503) 0x48c711 UNPCKHPD	%XMM1,%XMM2

(1503) 0x48c715 ADDSD	%XMM1,%XMM2

(1503) 0x48c719 MOVAPD	-0x160(%RBP),%XMM1

(1503) 0x48c721 ADDSD	%XMM9,%XMM2

(1503) 0x48c726 MOVSD	%XMM2,(%RBX,%R12,8)

(1503) 0x48c72c MULSD	%XMM0,%XMM0

(1503) 0x48c730 MULSD	%XMM3,%XMM3

(1503) 0x48c734 ADDSD	%XMM0,%XMM3

(1503) 0x48c738 MULSD	%XMM2,%XMM2

(1503) 0x48c73c ADDSD	%XMM3,%XMM2

(1503) 0x48c740 MOVAPD	-0x140(%RBP),%XMM3

(1503) 0x48c748 XORPS	%XMM0,%XMM0

(1503) 0x48c74b SQRTSD	%XMM2,%XMM0

(1503) 0x48c74f MOVAPD	-0x150(%RBP),%XMM2

(1503) 0x48c757 MOVSD	%XMM0,(%R15,%R12,8)

(1503) 0x48c75d MOVAPD	-0x170(%RBP),%XMM0

(1503) 0x48c765 INC	%R12D

(1503) 0x48c768 CMP	%R12D,%R13D

(1503) 0x48c76b JNE	48c5a0

0x48c771 ADD	$0x288,%RSP

0x48c778 POP	%RBX

0x48c779 POP	%R12

0x48c77b POP	%R13

0x48c77d POP	%R14

0x48c77f POP	%R15

0x48c781 POP	%RBP

0x48c782 RET

0x48c783 NOPW	%CS:(%RAX,%RAX,1)

0x48c78d NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►40.15+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableAAOMPTarget.h:283	exec
○	_ZN11qmcplusplus11ParticleSet2[...]	ParticleSet.cpp:343	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►39.44+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableAAOMPTarget.h:275	exec
○	_ZN11qmcplusplus11ParticleSet2[...]	ParticleSet.cpp:343	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►8.43+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableAAOMPTarget.h:185	exec
○	_ZN11qmcplusplus11ParticleSet6[...]	ParticleSet.cpp:242	exec
○	main.extracted.112	miniqmc.cpp:396	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►4.00+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableABOMPTarget.h:366	exec
○	_ZN11qmcplusplus11ParticleSet2[...]	ParticleSet.cpp:343	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►3.46+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableABOMPTarget.h:361	exec
○	_ZN11qmcplusplus11ParticleSet2[...]	ParticleSet.cpp:343	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►1.36+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableAAOMPTarget.h:283	exec
○	_ZN11qmcplusplus11ParticleSet2[...]	ParticleSet.cpp:343	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stl_uninitialized.h:99	exec
►1.26+	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableAAOMPTarget.h:275	exec
○	_ZN11qmcplusplus11ParticleSet2[...]	ParticleSet.cpp:343	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	stl_uninitialized.h:99	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 icx_3

Source file and lines	ParticleBConds3DSoa.h:221-257
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:221-224,234-257
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 17.25 to 15.00 cycles (1.15x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is partially vectorized. Only 18% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 17.25 to 3.75 cycles (4.60x speedup).

Details

51% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

50% of SSE/AVX loads are used in vector version.
76% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
12% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 17.25 to 15.75 cycles (1.10x speedup).

Workaround

Read less array elements
Write less array elements

No data for this section

Vector unaligned load/store instructions

Detected 3 suboptimal vector unaligned load/store instructions.

Details

MOVUPD: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:222
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:241
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:251

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Use vector aligned instructions:
1. align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
2. inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

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 332 bytes. The binary function is storing 544 bytes.

General properties

nb instructions	130
nb uops	126
loop length	734
used x86 registers	15
used mmx registers	0
used xmm registers	13
used ymm registers	0
used zmm registers	0
nb stack references	37

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	15.75 cycles
front end	15.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	3.00	3.00	3.00	3.00	3.00	3.00	17.25	17.25	17.25	17.25	4.50	4.50	4.50	4.50	15.00	15.00
cycles	3.00	3.00	3.00	3.00	3.00	3.00	17.25	17.25	17.25	17.25	4.50	4.50	4.50	4.50	15.00	15.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	15.75
Dispatch	17.25
Overall L1	17.25

Vectorization ratios

INT

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

all	63%
load	59%
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	14%

INT+FP

all	51%
load	50%
store	76%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Vector efficiency ratios

INT

all	9%
load	7%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	20%
load	19%
store	25%
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	14%

INT+FP

all	18%
load	18%
store	21%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 17.25 cycles. At this rate:

7% of peak load performance is reached (19.25 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
24% of peak store performance is reached (31.54 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 48be50

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x288,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x10(%RBP),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV %R13D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %R9D,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 48c771 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x921>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RCX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVUPD (%RSI),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVSD 0x10(%RSI),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x8(%RDX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RDX,%RCX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x4,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x8(%R8),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RAX,%RBX,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDI,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
SAL $0x4,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %RAX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSD 0x48(%R14),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVUPD 0x50(%R14),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVSD 0x60(%R14),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x68(%R14),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x78(%R14),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x80(%R14),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x70(%R14),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x88(%R14),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD (%R14),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVUPD 0x8(%R14),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %R10D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R12D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVAPD %XMM0,-0x170(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM1,-0x160(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM2,-0x150(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM3,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM7,-0x2b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM8,-0x2a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
JE 48c56a <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x71a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R10D,-0x74(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
LEA -0x1(%R12),%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %EAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
MOVAPD %XMM0,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM0,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM12,-0x290(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKHPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM0,-0x280(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM1,-0x270(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM2,-0x260(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM0,-0x250(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKHPD %XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM3,-0x240(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM4,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM4,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM4,-0x230(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM5,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM5,-0x220(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM6,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM6,-0x210(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM9,-0x1a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM9,-0x200(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM11,-0x180(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM11,-0x1f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM10,-0x190(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM10,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM10,-0x1e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM7,-0x1d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM8,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM8,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM0,-0x1c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKHPD %XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM8,-0x1b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOV %R15,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %RBX,-0x128(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R12D,-0x74(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (6.3%)
MOV -0x98(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x10(%RBP),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOVAPD -0x170(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x160(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x150(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x140(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x100(%RBP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xf0(%RBP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xe0(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x1a0(%RBP),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x190(%RBP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x180(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
JNE 48c56d <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x71d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 48c771 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x921>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
UNPCKLPD %XMM11,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
UNPCKLPD %XMM9,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
UNPCKLPD %XMM10,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
ADD %R9D,%R12D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVAPD %XMM4,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM5,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM6,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x288,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_3

Source file and lines	ParticleBConds3DSoa.h:221-257
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:221-224,234-257
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:271-273

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

51% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

50% of SSE/AVX loads are used in vector version.
76% of SSE/AVX stores are used in vector version.
0% of SSE/AVX addition or subtraction instructions are used in vector version.
12% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 17.25 to 15.75 cycles (1.10x speedup).

Workaround

Read less array elements
Write less array elements

No data for this section

Vector unaligned load/store instructions

Detected 3 suboptimal vector unaligned load/store instructions.

Details

MOVUPD: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:222
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:241
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Particle/Lattice/ParticleBConds3DSoa.h:251

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Use vector aligned instructions:
1. align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
2. inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

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 332 bytes. The binary function is storing 544 bytes.

General properties

nb instructions	130
nb uops	126
loop length	734
used x86 registers	15
used mmx registers	0
used xmm registers	13
used ymm registers	0
used zmm registers	0
nb stack references	37

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	15.75 cycles
front end	15.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	3.00	3.00	3.00	3.00	3.00	3.00	17.25	17.25	17.25	17.25	4.50	4.50	4.50	4.50	15.00	15.00
cycles	3.00	3.00	3.00	3.00	3.00	3.00	17.25	17.25	17.25	17.25	4.50	4.50	4.50	4.50	15.00	15.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	15.75
Dispatch	17.25
Overall L1	17.25

Vectorization ratios

INT

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

all	63%
load	59%
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	14%

INT+FP

all	51%
load	50%
store	76%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

Vector efficiency ratios

INT

all	9%
load	7%
store	11%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	7%

all	20%
load	19%
store	25%
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	14%

INT+FP

all	18%
load	18%
store	21%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	13%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 17.25 cycles. At this rate:

7% of peak load performance is reached (19.25 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
24% of peak store performance is reached (31.54 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 48be50

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x288,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x10(%RBP),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOV %R13D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %R9D,%R10D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JLE 48c771 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x921>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RCX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVUPD (%RSI),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVSD 0x10(%RSI),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV 0x8(%RDX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA (%RDX,%RCX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
SAL $0x4,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x8(%R8),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA (%RAX,%RBX,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RDI,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
SAL $0x4,%RBX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
ADD %RAX,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVSD 0x48(%R14),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVUPD 0x50(%R14),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVSD 0x60(%R14),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x68(%R14),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x78(%R14),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x80(%R14),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x70(%R14),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD 0x88(%R14),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVSD (%R14),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVUPD 0x8(%R14),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOV %R10D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R12D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RCX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RDX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV %RSI,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVAPD %XMM0,-0x170(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM1,-0x160(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM2,-0x150(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM3,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM7,-0x2b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM8,-0x2a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
JE 48c56a <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x71a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R10D,-0x74(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
LEA -0x1(%R12),%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %EAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (6.3%)
MOVAPD %XMM0,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM0,%XMM12	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM12,-0x290(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKHPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM0,-0x280(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM1,-0x270(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM2,-0x260(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM3,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM0,-0x250(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKHPD %XMM3,%XMM3	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM3,-0x240(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM4,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM4,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM4,-0x230(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM5,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM5,-0x220(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM6,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM6,-0x210(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM9,-0x1a0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM9,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM9,-0x200(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM11,-0x180(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM11,%XMM11	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM11,-0x1f0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM10,-0x190(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM10,%XMM10	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM10,-0x1e0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKLPD %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM7,-0x1d0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM8,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
UNPCKLPD %XMM8,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM0,-0x1c0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
UNPCKHPD %XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
MOVAPD %XMM8,-0x1b0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOV %R15,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
XOR %R15D,%R15D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
MOV %RBX,-0x128(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %R12D,-0x74(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (6.3%)
MOV -0x98(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x10(%RBP),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (6.3%)
MOVAPD -0x170(%RBP),%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x160(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x150(%RBP),%XMM2	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x140(%RBP),%XMM3	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x100(%RBP),%XMM4	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xf0(%RBP),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0xe0(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x1a0(%RBP),%XMM9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x190(%RBP),%XMM10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
MOVAPD -0x180(%RBP),%XMM11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.50	vect (25.0%)
JNE 48c56d <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x71d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 48c771 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi40EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii+0x921>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
UNPCKLPD %XMM11,%XMM4	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
UNPCKLPD %XMM9,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
UNPCKLPD %XMM10,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	scal (12.5%)
ADD %R9D,%R12D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVAPD %XMM4,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM5,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
MOVAPD %XMM6,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	4	2	vect (25.0%)
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x288,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼void qmcplusplus::DTD_BConds::computeDistances, qmcplusplus::VectorSoAContainer >, qmcplusplus::VectorSoAContainer–	1.09	1.82
○Loop 1504 - ParticleBConds3DSoa.h:234-255 - exec	1.09	1.81
○Loop 1503 - ParticleBConds3DSoa.h:235-255 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Vector unaligned load/store instructions

Details

Workaround

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

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Vector unaligned load/store instructions

Details

Workaround

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