Loop id | Source Location | Source Function | Level | Coverage run_0 (%) | Max Time Over Threads run_0 (s) | Time w.r.t. Wall Time run_0 (s) | Nb Threads run_0 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing run_0 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect |
---|
831 | exec - MultiBsplineRef.hpp:70-73 | miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&) | Innermost | 30.21 | 0.29 | 0.29 | 1 | 100 | 50 | 1 | 1.2 | 2 | 1 | 0 | 5 | 0 | 0 | 0 |
1167 | exec - ParticleBConds.h:185-217 | void qmcplusplus::DTD_BConds<double, 3u, 39>::computeDistances<qmcplusplus::TinyVector<double, 3u>, qmcplusplus::VectorSoAContainer<double, 3u, 64ul, qmcplusplus::Mallocator<double, 64ul> >, qmcplusplus::VectorSoAContainer<dou... | Single | 23.44 | 0.22 | 0.22 | 1 | 92.54 | 46.22 | 1.04 | 1.7 | 2.07 | 1 | 9 | 0 | 0 | 0 | 1 |
840 | exec - MultiBsplineRef.hpp:249-270 [...] | miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<... | Innermost | 20.31 | 0.19 | 0.19 | 1 | 100 | 50 | 1.05 | 1.29 | 2 | 1 | 0 | 10 | 1 | 0 | 0 |
1469 | exec - | __intel_avx_rep_memset | Single | 1.56 | 0.01 | 0.01 | 1 | 100 | 50 | 1 | 1 | 2 | 1 | 0 | 1 | 0 | 0 | 0 |
1246 | exec - stl_tree.h:782-1952 [...] | std::map<qmcplusplus::StackKeyParam<2>, double, std::less<qmcplusplus::StackKeyParam<2> >, std::allocator<std::pair<qmcplusplus::StackKeyParam<2> const, double> > >::operator[](qmcplusplus::StackKeyParam<2> c... | Single | 1.56 | 0.01 | 0.01 | 1 | 0 | 12.5 | 1 | 1 | 8 | 1 | NA | NA | NA | NA | NA |
812 | exec - BsplineAllocator.hpp:179-180 | qmcplusplus::BsplineAllocator<double, 64ul, qmcplusplus::Mallocator<double, 64ul> >::setCoefficientsForOrbitals(int, int, Array<double, 3u>&, multi_UBspline_3d_d*) [clone .extracted] | Innermost | 1.56 | 0.01 | 0.01 | 1 | 100 | 50 | 1 | 1.25 | 2 | 1 | 0 | 2 | 0 | 0 | 0 |
302 | exec - BsplineFunctor.h:236-241 | qmcplusplus::BsplineFunctor<double>::evaluateV(int, int, int, double const*, double*) const | Single | 1.04 | 0.01 | 0.01 | 1 | 87.88 | 38.92 | 1.22 | 1 | 3.08 | 1 | 1 | 1 | 3 | 0 | 0 |
1244 | exec - NewTimer.cpp:99-100 | qmcplusplus::TimerType<qmcplusplus::CPUClock>::stop() | Single | 0.52 | 0 | 0 | 1 | 0 | 6.25 | 1 | 1 | 16 | 0 | 0 | 0 | 0 | 0 | 0 |
325 | exec - TwoBodyJastrowRef.h:340-345 | miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int) | Single | 0.52 | 0 | 0 | 1 | 100 | 50 | 1 | 1.33 | 2 | 0 | 0 | 5 | 0 | 0 | 0 |
240 | exec - OneBodyJastrowRef.h:196-197 | miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | Single | 0.52 | 0 | 0 | 1 | 100 | 50 | 1 | 1.54 | 2 | 0 | 0 | 2 | 0 | 0 | 0 |
955 | exec - inner_product.hpp:81-82 | miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratio(qmcplusplus::ParticleSet&, int) | Single | 0.52 | 0 | 0 | 1 | 100 | 50 | 1 | 1.54 | 2 | 0 | 0 | 2 | 0 | 0 | 0 |
1187 | exec - ParticleIOUtility.h:70-91 [...] | void qmcplusplus::expandSuperCell<qmcplusplus::ParticleSet>(qmcplusplus::ParticleSet&, qmcplusplus::Tensor<int, 3u> const&) | Innermost | 0.52 | 0 | 0 | 1 | 42.62 | 17.42 | 1.58 | 1.69 | 7.72 | 0 | NA | NA | NA | NA | NA |
323 | exec - TwoBodyJastrowRef.h:340-345 | miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int) | Single | 0.52 | 0 | 0 | 1 | 100 | 50 | 1 | 1.33 | 2 | 0 | 0 | 5 | 0 | 0 | 0 |
836 | exec - MultiBsplineRef.hpp:284-295 | miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<... | Innermost | 0.52 | 0 | 0 | 1 | 100 | 50 | 1 | 1 | 2 | 0 | 0 | 9 | 0 | 0 | 0 |
930 | exec - inner_product.hpp:210-211 | qmcplusplus::DiracMatrix<double, double>::invert_transpose(qmcplusplus::Matrix<double, std::allocator<double> > const&, qmcplusplus::Matrix<double, std::allocator<double> >&, double&, double&) | Innermost | 0.52 | 0 | 0 | 1 | 85.71 | 41.07 | 1.07 | 1 | 2.9 | 0 | 0 | 1 | 0 | 0 | 1 |
1468 | exec - | __intel_avx_rep_memcpy | Single | 0.52 | 0 | 0 | 1 | 100 | 50 | 1 | 1 | 2 | 0 | 0 | 2 | 0 | 0 | 0 |
834 | exec - TinyVectorOps.h:59-59 [...] | miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<... | Outermost | 0.52 | 0 | 0 | 1 | 35.91 | 17.88 | 1.52 | 1.4 | 6.85 | 0 | NA | NA | NA | NA | NA |
1173 | exec - DistanceTableBA.h:99-99 [...] | qmcplusplus::DistanceTableBA<double, 3u, 39>::evaluate(qmcplusplus::ParticleSet&) | Innermost | 0.52 | 0 | 0 | 1 | 36.84 | 18.88 | 1.02 | 1.44 | 5.19 | 0 | 2 | 0 | 0 | 0 | 8 |
957 | exec - inner_product.hpp:81-82 [...] | miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<... | Innermost | 0.52 | 0 | 0 | 1 | 25 | 15.63 | 1 | 2 | 6.86 | 0 | 0 | 2 | 1 | 0 | 0 |
833 | exec - einspline_spo_ref.hpp:223-227 [...] | miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<... | Innermost | 0.52 | 0 | 0 | 1 | 0 | 12.5 | 1 | 1 | 8 | 0 | 0 | 8 | 0 | 0 | 0 |