OV - exec - Function miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)

	Function: miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcpl ...	Module: exec	Source: OneBodyJastrowRef.h:186-263 [...]	Coverage (incl. loops): 0.05% \| (excl. loops): 0.01%

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

94:     (const_cast<T1&>(a) += b);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 273 - 273

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

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

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h: 140 - 141

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

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1169 - 1169

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

1169:       { return _M_data_ptr(this->_M_impl._M_start); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h: 1028 - 1182

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

1028:       : _M_current(__i) { }

[...]

1182:     { return __lhs.base() != __rhs.base(); }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 169 - 169

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

169:   inline Type_t& operator[](unsigned int i) { return X[i]; }

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 186 - 263

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

186:     for (int jat = 0; jat < Nions; ++jat)

187:       lap += d2u[jat] + lapfac * du[jat];

188:     for (int idim = 0; idim < OHMMS_DIM; ++idim)

189:     {

190:       const valT* restrict dX = displ.data(idim);

191:       valT s                  = valT();

192:       for (int jat = 0; jat < Nions; ++jat)

193:         s += du[jat] * dX[jat];

194:       grad[idim] = s;

[...]

256:   {

257:     UpdateMode = ORB_PBYP_PARTIAL;

258:

259:     computeU3(P, iat, P.getDistTableAB(myTableID).getTempDists().data());

260:     curLap = accumulateGL(dU.data(), d2U.data(), P.getDistTableAB(myTableID).getTempDispls(), curGrad);

261:     curAt  = std::accumulate(U.begin(), U.begin() + Nions, valT());

262:     grad_iat += curGrad;

263:     return std::exp(Vat[iat] - curAt);

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

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

223:     return X[i];

[...]

249:   inline const_pointer data() const { return X; }

0x41d080 PUSH	%RBP

0x41d081 MOV	%RSP,%RBP

0x41d084 PUSH	%R15

0x41d086 PUSH	%R14

0x41d088 PUSH	%R13

0x41d08a PUSH	%R12

0x41d08c PUSH	%RBX

0x41d08d PUSH	%RAX

0x41d08e MOV	%RCX,%R14

0x41d091 MOV	%EDX,%EBX

0x41d093 MOV	%RSI,%R12

0x41d096 MOV	%RDI,%R15

0x41d099 MOVL	$0x2,0xc(%RDI)

0x41d0a0 MOV	0xa8(%RDI),%ESI

0x41d0a6 MOV	%R12,%RDI

0x41d0a9 CALL	460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x41d0ae MOV	0x90(%RAX),%RCX

0x41d0b5 MOV	%R15,%RDI

0x41d0b8 MOV	%R12,%RSI

0x41d0bb MOV	%EBX,-0x2c(%RBP)

0x41d0be MOV	%EBX,%EDX

0x41d0c0 CALL	41fa10 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>

0x41d0c5 MOV	0x118(%R15),%R13

0x41d0cc MOV	0x130(%R15),%RBX

0x41d0d3 MOV	0xa8(%R15),%ESI

0x41d0da MOV	%R12,%RDI

0x41d0dd CALL	460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x41d0e2 MOVSXD	0x90(%R15),%RCX

0x41d0e9 TEST	%RCX,%RCX

0x41d0ec JLE	41d142

0x41d0ee MOV	%RCX,%RDX

0x41d0f1 AND	$0x7ffffffc,%RDX

0x41d0f8 JE	41d17d

0x41d0fe VXORPD	%XMM0,%XMM0,%XMM0

0x41d102 XOR	%ESI,%ESI

0x41d104 VBROADCASTSD	0xe11ab(%RIP),%YMM1

0x41d10d NOPL	(%RAX)

(288) 0x41d110 VADDPD	(%RBX,%RSI,8),%YMM0,%YMM0

(288) 0x41d115 VFMADD231PD	(%R13,%RSI,8),%YMM1,%YMM0

(288) 0x41d11c ADD	$0x4,%RSI

(288) 0x41d120 CMP	%RDX,%RSI

(288) 0x41d123 JB	41d110

0x41d125 VEXTRACTF128	$0x1,%YMM0,%XMM1

0x41d12b VADDPD	%XMM1,%XMM0,%XMM0

0x41d12f VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

0x41d134 VADDSD	%XMM1,%XMM0,%XMM0

0x41d138 MOV	%RDX,%RSI

0x41d13b CMP	%RCX,%RDX

0x41d13e JNE	41d183

0x41d140 JMP	41d1a4

0x41d142 VXORPD	%XMM0,%XMM0,%XMM0

0x41d146 VMOVUPD	%XMM0,0xc0(%R15)

0x41d14f MOVQ	$0,0xd0(%R15)

0x41d15a VXORPD	%XMM0,%XMM0,%XMM0

0x41d15e VMOVSD	%XMM0,0xb8(%R15)

0x41d167 LEA	(,%RCX,8),%RAX

0x41d16f TEST	%RAX,%RAX

0x41d172 JNE	41d258

0x41d178 JMP	41d447

0x41d17d XOR	%ESI,%ESI

0x41d17f VXORPD	%XMM0,%XMM0,%XMM0

0x41d183 VMOVSD	0xe112d(%RIP),%XMM1

0x41d18b NOPL	(%RAX,%RAX,1)

(279) 0x41d190 VADDSD	(%RBX,%RSI,8),%XMM0,%XMM0

(279) 0x41d195 VFMADD231SD	(%R13,%RSI,8),%XMM1,%XMM0

(279) 0x41d19c INC	%RSI

(279) 0x41d19f CMP	%RSI,%RCX

(279) 0x41d1a2 JNE	41d190

0x41d1a4 MOV	0xa8(%RAX),%RSI

0x41d1ab MOV	0xb8(%RAX),%RAX

0x41d1b2 MOV	%RSI,%RDI

0x41d1b5 SAR	$0x3f,%RDI

0x41d1b9 ANDN	%RSI,%RDI,%R8

0x41d1be LEA	0xc0(%R15),%R9

0x41d1c5 XOR	%EDI,%EDI

0x41d1c7 TEST	%RSI,%RSI

0x41d1ca LEA	(%RCX,%R8,2),%R8

0x41d1ce LEA	-0x8(%RAX,%R8,8),%R8

0x41d1d3 CMOVS	%RSI,%RDI

0x41d1d7 CMP	%R9,%R8

0x41d1da JB	41d2b6

0x41d1e0 LEA	0xd0(%R15),%R8

0x41d1e7 SAL	$0x4,%RDI

0x41d1eb ADD	%RAX,%RDI

0x41d1ee CMP	%RDI,%R8

0x41d1f1 JB	41d2b6

0x41d1f7 SAL	$0x3,%RSI

0x41d1fb XOR	%EDX,%EDX

0x41d1fd NOPL	(%RAX)

(287) 0x41d200 VXORPD	%XMM1,%XMM1,%XMM1

(287) 0x41d204 XOR	%EDI,%EDI

(287) 0x41d206 NOPW	%CS:(%RAX,%RAX,1)

  (286) 0x41d210 VMOVSD	(%RAX,%RDI,8),%XMM2

  (286) 0x41d215 VFMADD231SD	(%R13,%RDI,8),%XMM2,%XMM1

  (286) 0x41d21c INC	%RDI

  (286) 0x41d21f CMP	%RDI,%RCX

  (286) 0x41d222 JNE	41d210

(287) 0x41d224 VMOVSD	%XMM1,0xc0(%R15,%RDX,8)

(287) 0x41d22e LEA	0x1(%RDX),%RDI

(287) 0x41d232 ADD	%RSI,%RAX

(287) 0x41d235 CMP	$0x2,%RDX

(287) 0x41d239 MOV	%RDI,%RDX

(287) 0x41d23c JNE	41d200

0x41d23e VMOVSD	%XMM0,0xb8(%R15)

0x41d247 LEA	(,%RCX,8),%RAX

0x41d24f TEST	%RAX,%RAX

0x41d252 JE	41d447

0x41d258 MOV	$0x1fffffffffffffff,%RDX

0x41d262 MOV	0x100(%R15),%RAX

0x41d269 ADD	%RDX,%RCX

0x41d26c AND	%RDX,%RCX

0x41d26f INC	%RCX

0x41d272 MOV	$0x3ffffffffffffffc,%RDX

0x41d27c AND	%RCX,%RDX

0x41d27f JE	41d302

0x41d285 VXORPD	%XMM0,%XMM0,%XMM0

0x41d289 XOR	%ESI,%ESI

0x41d28b NOPL	(%RAX,%RAX,1)

(278) 0x41d290 VADDPD	(%RAX,%RSI,8),%YMM0,%YMM0

(278) 0x41d295 ADD	$0x4,%RSI

(278) 0x41d299 CMP	%RDX,%RSI

(278) 0x41d29c JB	41d290

0x41d29e VEXTRACTF128	$0x1,%YMM0,%XMM1

0x41d2a4 VADDPD	%XMM1,%XMM0,%XMM0

0x41d2a8 VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

0x41d2ad VADDSD	%XMM1,%XMM0,%XMM0

0x41d2b1 JMP	41d455

0x41d2b6 TEST	%RDX,%RDX

0x41d2b9 JE	41d30d

0x41d2bb VXORPD	%XMM1,%XMM1,%XMM1

0x41d2bf XOR	%EDI,%EDI

0x41d2c1 NOPW	%CS:(%RAX,%RAX,1)

(285) 0x41d2d0 VMOVUPD	(%RAX,%RDI,8),%YMM2

(285) 0x41d2d5 VFMADD231PD	(%R13,%RDI,8),%YMM2,%YMM1

(285) 0x41d2dc ADD	$0x4,%RDI

(285) 0x41d2e0 CMP	%RDX,%RDI

(285) 0x41d2e3 JB	41d2d0

0x41d2e5 VEXTRACTF128	$0x1,%YMM1,%XMM2

0x41d2eb VADDPD	%XMM2,%XMM1,%XMM1

0x41d2ef VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

0x41d2f4 VADDSD	%XMM2,%XMM1,%XMM1

0x41d2f8 MOV	%RDX,%RDI

0x41d2fb CMP	%RCX,%RDX

0x41d2fe JNE	41d320

0x41d300 JMP	41d334

0x41d302 XOR	%EDX,%EDX

0x41d304 VXORPD	%XMM0,%XMM0,%XMM0

0x41d308 JMP	41d44d

0x41d30d VXORPD	%XMM1,%XMM1,%XMM1

0x41d311 XOR	%EDI,%EDI

0x41d313 NOPW	%CS:(%RAX,%RAX,1)

(280) 0x41d320 VMOVSD	(%RAX,%RDI,8),%XMM2

(280) 0x41d325 VFMADD231SD	(%R13,%RDI,8),%XMM2,%XMM1

(280) 0x41d32c INC	%RDI

(280) 0x41d32f CMP	%RDI,%RCX

(280) 0x41d332 JNE	41d320

0x41d334 VMOVSD	%XMM1,0xc0(%R15)

0x41d33d TEST	%RDX,%RDX

0x41d340 JE	41d383

0x41d342 LEA	(%RAX,%RSI,8),%RDI

0x41d346 VXORPD	%XMM1,%XMM1,%XMM1

0x41d34a XOR	%R8D,%R8D

0x41d34d NOPL	(%RAX)

(284) 0x41d350 VMOVUPD	(%RDI,%R8,8),%YMM2

(284) 0x41d356 VFMADD231PD	(%R13,%R8,8),%YMM2,%YMM1

(284) 0x41d35d ADD	$0x4,%R8

(284) 0x41d361 CMP	%RDX,%R8

(284) 0x41d364 JB	41d350

0x41d366 VEXTRACTF128	$0x1,%YMM1,%XMM2

0x41d36c VADDPD	%XMM2,%XMM1,%XMM1

0x41d370 VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

0x41d375 VADDSD	%XMM2,%XMM1,%XMM1

0x41d379 MOV	%RDX,%RDI

0x41d37c CMP	%RCX,%RDX

0x41d37f JNE	41d389

0x41d381 JMP	41d3a5

0x41d383 XOR	%EDI,%EDI

0x41d385 VXORPD	%XMM1,%XMM1,%XMM1

0x41d389 LEA	(%RAX,%RSI,8),%R8

0x41d38d NOPL	(%RAX)

(281) 0x41d390 VMOVSD	(%R8,%RDI,8),%XMM2

(281) 0x41d396 VFMADD231SD	(%R13,%RDI,8),%XMM2,%XMM1

(281) 0x41d39d INC	%RDI

(281) 0x41d3a0 CMP	%RDI,%RCX

(281) 0x41d3a3 JNE	41d390

0x41d3a5 VMOVSD	%XMM1,0xc8(%R15)

0x41d3ae TEST	%RDX,%RDX

0x41d3b1 JE	41d400

0x41d3b3 MOV	%RSI,%RDI

0x41d3b6 SAL	$0x4,%RDI

0x41d3ba ADD	%RAX,%RDI

0x41d3bd VXORPD	%XMM1,%XMM1,%XMM1

0x41d3c1 XOR	%R8D,%R8D

0x41d3c4 NOPW	%CS:(%RAX,%RAX,1)

(283) 0x41d3d0 VMOVUPD	(%RDI,%R8,8),%YMM2

(283) 0x41d3d6 VFMADD231PD	(%R13,%R8,8),%YMM2,%YMM1

(283) 0x41d3dd ADD	$0x4,%R8

(283) 0x41d3e1 CMP	%RDX,%R8

(283) 0x41d3e4 JB	41d3d0

0x41d3e6 VEXTRACTF128	$0x1,%YMM1,%XMM2

0x41d3ec VADDPD	%XMM2,%XMM1,%XMM1

0x41d3f0 VSHUFPD	$0x1,%XMM1,%XMM1,%XMM2

0x41d3f5 VADDSD	%XMM2,%XMM1,%XMM1

0x41d3f9 CMP	%RCX,%RDX

0x41d3fc JNE	41d406

0x41d3fe JMP	41d424

0x41d400 XOR	%EDX,%EDX

0x41d402 VXORPD	%XMM1,%XMM1,%XMM1

0x41d406 SAL	$0x4,%RSI

0x41d40a ADD	%RSI,%RAX

0x41d40d NOPL	(%RAX)

(282) 0x41d410 VMOVSD	(%RAX,%RDX,8),%XMM2

(282) 0x41d415 VFMADD231SD	(%R13,%RDX,8),%XMM2,%XMM1

(282) 0x41d41c INC	%RDX

(282) 0x41d41f CMP	%RDX,%RCX

(282) 0x41d422 JNE	41d410

0x41d424 VMOVSD	%XMM1,0xd0(%R15)

0x41d42d VMOVSD	%XMM0,0xb8(%R15)

0x41d436 LEA	(,%RCX,8),%RAX

0x41d43e TEST	%RAX,%RAX

0x41d441 JNE	41d258

0x41d447 VXORPD	%XMM0,%XMM0,%XMM0

0x41d44b JMP	41d45a

(277) 0x41d44d VADDSD	(%RAX,%RDX,8),%XMM0,%XMM0

(277) 0x41d452 INC	%RDX

(277) 0x41d455 CMP	%RDX,%RCX

(277) 0x41d458 JNE	41d44d

0x41d45a VMOVSD	%XMM0,0xb0(%R15)

0x41d463 VMOVSD	(%R14),%XMM1

0x41d468 VMOVSD	0x8(%R14),%XMM2

0x41d46e VADDSD	0xc0(%R15),%XMM1,%XMM1

0x41d477 VMOVSD	%XMM1,(%R14)

0x41d47c VADDSD	0xc8(%R15),%XMM2,%XMM1

0x41d485 VMOVSD	%XMM1,0x8(%R14)

0x41d48b VMOVSD	0x10(%R14),%XMM1

0x41d491 VADDSD	0xd0(%R15),%XMM1,%XMM1

0x41d49a VMOVSD	%XMM1,0x10(%R14)

0x41d4a0 MOVSXD	-0x2c(%RBP),%RAX

0x41d4a4 MOV	0xf0(%R15),%RCX

0x41d4ab VMOVSD	(%RCX,%RAX,8),%XMM1

0x41d4b0 VSUBSD	%XMM0,%XMM1,%XMM0

0x41d4b4 ADD	$0x8,%RSP

0x41d4b8 POP	%RBX

0x41d4b9 POP	%R12

0x41d4bb POP	%R13

0x41d4bd POP	%R14

0x41d4bf POP	%R15

0x41d4c1 POP	%RBP

0x41d4c2 VZEROUPPER

0x41d4c5 JMP	4df280

0x41d4ca NOPW	(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►98.05+	qmcplusplus::WaveFunction::rat[...]	WaveFunction.cpp:201	exec
○	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
►1.95+	main.extracted.107	refwrap.h:338	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

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	OneBodyJastrowRef.h:186-263
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:169
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186-194,256-263
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249

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 32.17 to 12.33 cycles (2.61x speedup).

Workaround

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

Vectorization

Your function is poorly vectorized. Only 16% of vector register length is used (average across all SSE/AVX instructions).

Details

35% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX loads are used in vector version.
7% of SSE/AVX stores are used in vector version.
35% of SSE/AVX addition or subtraction instructions are used in vector version.
48% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

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

512-bits vectorization

On some x86 processors supporting 512-bits vectorization, compilers are often too conservative and limit vectorization to 256 bits. Performance can then be improved by enforcing 512-bits vectorization, especially with many vectorized and high trip count loops. 512-bits vectorization performance overhead (compared to 256-bits) is generally lower on newer processors.

Workaround

Recompile with -mprefer-vector-width=512

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.

miniqmcreference::OneBodyJastrowRef
>::computeU3(qmcplusplus::ParticleSet&, int, double const*): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
qmcplusplus::ParticleSet::getDistTableAB(int) const: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:260

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:263

Vector unaligned load/store instructions

Detected 5 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 5 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:187
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:141
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:193
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:193
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:193

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

9 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time). 5 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in vector mode (two at a time).

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

The binary function is composed of 19 FP arithmetical operations:

19: addition or subtraction

The binary function is loading 144 bytes (18 double precision FP elements). The binary function is storing 112 bytes (14 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.07 FP operations per loaded or stored byte.

General properties

nb instructions	189
nb uops	193
loop length	848
used x86 registers	14
used mmx registers	0
used xmm registers	3
used ymm registers	2
used zmm registers	0
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	32.17 cycles
front end	32.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	14.10	13.90	8.67	8.67	12.00	13.90	14.10	12.00	12.00	12.00	14.00	8.67
cycles	14.10	13.90	8.67	8.67	12.00	13.90	14.10	12.00	12.00	12.00	14.00	8.67

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	32.17
Dispatch	14.10
Overall L1	32.17

Vectorization ratios

INT

all	3%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	3%

all	53%
load	0%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	35%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	95%

INT+FP

all	35%
load	0%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	35%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	48%

Vector efficiency ratios

INT

all	11%
load	12%
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	19%
load	12%
store	13%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	16%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	24%

INT+FP

all	16%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	16%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	17%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 32.17 cycles. At this rate:

2% of peak load performance is reached (4.48 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.48 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 32.17 to 14.10 cycles (2.28x speedup).

ASM code

In the binary file, the address of the function is: 41d080

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	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %EDX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0x2,0xc(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0xa8(%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x90(%RAX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R15,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EBX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CALL 41fa10 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x118(%R15),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x130(%R15),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0xa8(%R15),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOVSXD 0x90(%R15),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RCX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 41d142 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xc2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $0x7ffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
JE 41d17d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xfd>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VBROADCASTSD 0xe11ab(%RIP),%YMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	0.33	scal (12.5%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
MOV %RDX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d183 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x103>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d1a4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x124>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVUPD %XMM0,0xc0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ $0,0xd0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RCX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JNE 41d258 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d447 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3c7>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVSD 0xe112d(%RIP),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0xa8(%RAX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xb8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAR $0x3f,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ANDN %RSI,%RDI,%R8	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1-2	0.33	N/A
LEA 0xc0(%R15),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RSI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
LEA (%RCX,%R8,2),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x8(%RAX,%R8,8),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMOVS %RSI,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
CMP %R9,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41d2b6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x236>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA 0xd0(%R15),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %RAX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP %RDI,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41d2b6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x236>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x3,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RCX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d447 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3c7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x1fffffffffffffff,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
MOV 0x100(%R15),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
INC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x3ffffffffffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
AND %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
JE 41d302 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x282>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
JMP 41d455 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3d5>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
TEST %RDX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d30d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x28d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM1,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM1,%XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
MOV %RDX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d320 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d334 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 41d44d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3cd>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,0xc0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
TEST %RDX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d383 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x303>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RAX,%RSI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM1,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM1,%XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
MOV %RDX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d389 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x309>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d3a5 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x325>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
LEA (%RAX,%RSI,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,0xc8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
TEST %RDX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d400 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x380>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x4,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %RAX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM1,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM1,%XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d406 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x386>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d424 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SAL $0x4,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %RSI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,0xd0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RCX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JNE 41d258 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 41d45a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3da>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VMOVSD %XMM0,0xb0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%R14),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x8(%R14),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD 0xc0(%R15),%XMM1,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM1,(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VADDSD 0xc8(%R15),%XMM2,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM1,0x8(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD 0x10(%R14),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD 0xd0(%R15),%XMM1,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM1,0x10(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVSXD -0x2c(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xf0(%R15),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RCX,%RAX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD %XMM0,%XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
ADD $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	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
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP 4df280 <exp>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	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	OneBodyJastrowRef.h:186-263
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:169
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186-194,256-263
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249

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

Your function is poorly vectorized. Only 16% of vector register length is used (average across all SSE/AVX instructions).

Details

35% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX loads are used in vector version.
7% of SSE/AVX stores are used in vector version.
35% of SSE/AVX addition or subtraction instructions are used in vector version.
48% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Workaround

Read the "512-bits vectorization" report at "Potential" confidence level.

Execution units bottlenecks

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

512-bits vectorization

Workaround

Recompile with -mprefer-vector-width=512

CALL instructions

Detected function call instructions.

Details

miniqmcreference::OneBodyJastrowRef
>::computeU3(qmcplusplus::ParticleSet&, int, double const*): 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
qmcplusplus::ParticleSet::getDistTableAB(int) const: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:259
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:260

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VZEROUPPER: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:263

Vector unaligned load/store instructions

Detected 5 suboptimal vector unaligned load/store instructions.

Details

VEXTRACTF128: 5 occurrences►
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:187
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:141
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:193
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:193
- /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:193

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

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

The binary function is composed of 19 FP arithmetical operations:

19: addition or subtraction

The binary function is loading 144 bytes (18 double precision FP elements). The binary function is storing 112 bytes (14 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.07 FP operations per loaded or stored byte.

General properties

nb instructions	189
nb uops	193
loop length	848
used x86 registers	14
used mmx registers	0
used xmm registers	3
used ymm registers	2
used zmm registers	0
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	32.17 cycles
front end	32.17 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	14.10	13.90	8.67	8.67	12.00	13.90	14.10	12.00	12.00	12.00	14.00	8.67
cycles	14.10	13.90	8.67	8.67	12.00	13.90	14.10	12.00	12.00	12.00	14.00	8.67

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	32.17
Dispatch	14.10
Overall L1	32.17

Vectorization ratios

INT

all	3%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	3%

all	53%
load	0%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	35%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	95%

INT+FP

all	35%
load	0%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	35%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	48%

Vector efficiency ratios

INT

all	11%
load	12%
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	11%

all	19%
load	12%
store	13%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	16%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	24%

INT+FP

all	16%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	16%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	17%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 32.17 cycles. At this rate:

2% of peak load performance is reached (4.48 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.48 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 41d080

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	N/A
PUSH %R15	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %EDX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0x2,0xc(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV 0xa8(%RDI),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x90(%RAX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R15,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV %EBX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
CALL 41fa10 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOV 0x118(%R15),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0x130(%R15),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV 0xa8(%R15),%ESI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CALL 460b80 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
MOVSXD 0x90(%R15),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
TEST %RCX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JLE 41d142 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xc2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
AND $0x7ffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
JE 41d17d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xfd>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VBROADCASTSD 0xe11ab(%RIP),%YMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	0.33	scal (12.5%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
MOV %RDX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d183 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x103>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d1a4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x124>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVUPD %XMM0,0xc0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (25.0%)
MOVQ $0,0xd0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RCX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JNE 41d258 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d447 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3c7>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVSD 0xe112d(%RIP),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV 0xa8(%RAX),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xb8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAR $0x3f,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ANDN %RSI,%RDI,%R8	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1-2	0.33	N/A
LEA 0xc0(%R15),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RSI,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
LEA (%RCX,%R8,2),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x8(%RAX,%R8,8),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
CMOVS %RSI,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
CMP %R9,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41d2b6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x236>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA 0xd0(%R15),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %RAX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP %RDI,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 41d2b6 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x236>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x3,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RCX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d447 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3c7>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x1fffffffffffffff,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
MOV 0x100(%R15),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
AND %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
INC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x3ffffffffffffffc,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
AND %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
JE 41d302 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x282>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM0,%XMM1	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM0,%XMM0,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM1,%XMM0,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
JMP 41d455 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3d5>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
TEST %RDX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d30d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x28d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM1,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM1,%XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
MOV %RDX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d320 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2a0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d334 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2b4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 41d44d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3cd>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,0xc0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
TEST %RDX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d383 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x303>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%RAX,%RSI,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM1,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM1,%XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
MOV %RDX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d389 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x309>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d3a5 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x325>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
LEA (%RAX,%RSI,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,0xc8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
TEST %RDX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JE 41d400 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x380>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAL $0x4,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %RAX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VEXTRACTF128 $0x1,%YMM1,%XMM2	1	0	0	0	0	0	1	0	0	0	0	0	0	3	1	vect (25.0%)
VADDPD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	vect (25.0%)
VSHUFPD $0x1,%XMM1,%XMM1,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	1	0.50	vect (25.0%)
VADDSD %XMM2,%XMM1,%XMM1	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
CMP %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 41d406 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x386>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 41d424 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a4>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
VXORPD %XMM1,%XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
SAL $0x4,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
ADD %RSI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM1,0xd0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (,%RCX,8),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
TEST %RAX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	scal (12.5%)
JNE 41d258 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d8>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 41d45a <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3da>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
VMOVSD %XMM0,0xb0(%R15)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%R14),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD 0x8(%R14),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD 0xc0(%R15),%XMM1,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM1,(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VADDSD 0xc8(%R15),%XMM2,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM1,0x8(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD 0x10(%R14),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VADDSD 0xd0(%R15),%XMM1,%XMM1	1	0	0.50	0.33	0.33	0	0.50	0	0	0	0	0	0.33	3	0.50	scal (12.5%)
VMOVSD %XMM1,0x10(%R14)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOVSXD -0x2c(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xf0(%R15),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RCX,%RAX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD %XMM0,%XMM1,%XMM0	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
ADD $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	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
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP 4df280 <exp>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼miniqmcreference::OneBodyJastrowRef >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector&)–	0.05	0.04
○Loop 288 - OneBodyJastrowRef.h:186-187 - exec	0.01	0.01
○Loop 285 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.01
○Loop 283 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.01
○Loop 284 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.01
○Loop 278 - stl_numeric.h:140-141 - exec	0.00	0.01
○Loop 280 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 277 - stl_numeric.h:140-141 - exec	0.00	0.00
○Loop 282 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
○Loop 279 - OneBodyJastrowRef.h:186-187 - exec	0.00	0.00
○Loop 281 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00
▼Loop 287 - OneBodyJastrowRef.h:188-194 - exec–	0.00	0.00
○Loop 286 - OneBodyJastrowRef.h:192-193 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

512-bits vectorization

Workaround

CALL instructions

Details

Complex instructions

Details

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

Arithmetic intensity

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

512-bits vectorization

Workaround

CALL instructions

Details

Complex instructions

Details

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code