options

Loops Index

188 loops have been discarded from the report because their ratio ((Max Inclusive Time Over Threads * 100) / Max Thread Active Time) is lower than the threshold set by object_coverage_threshold (0.01%). It represents about 0.44% of the application. To include them, change the value of object_coverage_threshold in the experiment directory configuration file, then rerun the command with the additionnal parameter --force-static-analysis

Columns Filter

Level Max Thread Time / Walltime armclang_1 (%) Exclusive Coverage armclang_1 (%) Inclusive Coverage armclang_1 (%) Max Exclusive Time Over Threads armclang_1 (s) Max Inclusive Time Over Threads armclang_1 (s) Exclusive Time w.r.t. Wall Time armclang_1 (s) Inclusive Time w.r.t. Wall Time armclang_1 (s) Nb Threads armclang_1 GFLOPS armclang_1 Vectorization Ratio (%) Vector Length Use (%) Speedup If No Scalar Integer Speedup If FP Vectorized Speedup If Fully Vectorized Speedup If Perfect Load Balancing armclang_1 Stride 0 Stride 1 Stride n Stride Unknown Stride Indirect Array Access Efficiency Level Max Thread Time / Walltime Exclusive Coverage Inclusive Coverage Max Exclusive Time Over Threads Max Inclusive Time Over Threads Exclusive Time w.r.t. Wall Time Inclusive Time w.r.t. Wall Time Nb Threads GFLOPS Vectorization Ratio Vector Length Use Speedup If No Scalar Integer Speedup If FP Vectorized Speedup If Fully Vectorized Speedup If Perfect Load Balancing Stride 0 Stride 1 Stride n Stride Unknown Stride Indirect Array Access Efficiency
Loop idSource LocationSource FunctionLevelMax Thread Time / Walltime armclang_1 (%)Exclusive Coverage armclang_1 (%)Inclusive Coverage armclang_1 (%)Max Exclusive Time Over Threads armclang_1 (s)Max Inclusive Time Over Threads armclang_1 (s)Exclusive Time w.r.t. Wall Time armclang_1 (s)Inclusive Time w.r.t. Wall Time armclang_1 (s)Nb Threads armclang_1GFLOPS armclang_1Vectorization Ratio (%)Vector Length Use (%)Speedup If No Scalar IntegerSpeedup If FP VectorizedSpeedup If Fully VectorizedSpeedup If Perfect Load Balancing armclang_1Stride 0Stride 1Stride nStride UnknownStride IndirectArray Access Efficiency
34845libarmpl_lp64.so - dgemm_sve_bigInnermost16.3416.7516.7525.7225.7225.4125.41641408.48000001.02000000.00
34844libarmpl_lp64.so - dgemm_sve_bigInBetween14.0514.1630.9122.1147.4621.4946.9164209.81000001.04000000.00
1794exec - VectorSoAContainer.h:244-263 [...]qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::update(int)Single8.198.248.2412.8912.8912.5012.50640.720251.1141.042042075.00
818exec - MultiBsplineRef.hpp:242-262void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, double*, double*, unsigned long)Innermost7.777.707.7012.2212.2211.6911.6964396.691001001111.0500014050.00
37166libarmpl_lp64.so - n_interleave_kernel_d8Innermost6.696.606.6010.5310.5310.0110.01640.00000001.06000000.00
812exec - MultiBsplineRef.hpp:68-71void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, unsigned long)Innermost6.045.975.979.509.509.069.066486.151001001111.060005050.00
809exec - MultiBsplineRef.hpp:68-71void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, unsigned long)Innermost5.995.935.939.439.439.009.006486.691001001111.050005050.00
810exec - MultiBsplineRef.hpp:68-71void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, unsigned long)Innermost5.975.855.859.409.408.888.886487.881001001111.070005050.00
811exec - MultiBsplineRef.hpp:68-71void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, unsigned long)Innermost6.015.855.859.469.468.888.886488.111001001111.070005050.00
2055exec - ParticleBConds3DSoa.h:280-298qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&)Innermost4.244.114.116.686.686.246.2464383.05941001111.080008050.00
1262exec - ParticleBConds3DSoa.h:235-255void qmcplusplus::DTD_BConds<double, 3u, 40>::computeDistances<qmcplusplus::TinyVector<double, 3u>, qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 32ul> >, qmcplusplus::VectorSoAContainer<double, 3...Single1.571.471.472.482.482.232.2364552.1389.0489.91111.121000712.50
303984libarmpl_lp64.so - void armpl::clag::gemv_a_cntg_first<false, armpl::clag::spec::sve_architecture_spec, double, double, double, double>(long, long, double, double const*, long, long, double const*, long, double, double*, long)Innermost1.531.441.442.402.402.182.1864102.47000001.11000000.00
324exec - BsplineFunctor.h:233-260 [...]miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)InBetween1.431.371.422.252.372.072.166431.77021.15316.791.1NANANANANA0.00
34842libarmpl_lp64.so - dgemm_sve_bigInnermost1.381.341.342.162.162.032.03641214.60000001.07000000.00
303664libarmpl_lp64.so - void armpl::clag::gemv_a_strd_first_impl<false, armpl::clag::spec::sve_architecture_spec, double, long, armpl::clag::(anonymous namespace)::step_val_fixed<1l>, double, armpl::clag::(anonymous namespace)::step_val_fixed<1l>, double, armpl::cl...Innermost0.880.800.801.381.381.211.2164117.55000001.15000000.00
304781libarmpl_lp64.so - auto armpl::clag::execute_strategy<15ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl...Innermost0.840.750.751.321.321.131.13640.25000001.17000000.00
303980libarmpl_lp64.so - void armpl::clag::gemv_a_cntg_first<false, armpl::clag::spec::sve_architecture_spec, double, double, double, double>(long, long, double, double const*, long, long, double const*, long, double, double*, long)Innermost0.690.620.621.091.090.940.946466.88000001.17000000.00
304835libarmpl_lp64.so - auto armpl::clag::execute_strategy<15ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl...Innermost0.670.600.601.051.050.920.92640.17000001.15000000.00
918exec - inner_product.hpp:155-155 [...]miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<...Innermost0.420.360.360.670.670.550.556465.3581.8259.0911.751.471.210011062.50
272exec - BsplineFunctor.h:291-298qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, double*, double*, double*, int*) constSingle0.440.360.360.690.690.550.556444.71022.921.25151.26001.50075.00
910exec - inner_product.hpp:155-155 [...]miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalGrad(qmcplusplus::ParticleSet&, int)Single0.460.350.350.730.730.530.536468.1181.8259.0911.751.471.370011062.50
802exec - inner_product.hpp:82-83qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<double, std::allocator<double> > const&, std::vector<double, st...Innermost0.370.320.320.580.580.480.486497.9685.7189.291111.220002050.00
801exec - 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<...Innermost0.370.310.310.570.570.470.47640.009.0926.142.3315.251.224045073.08
303666libarmpl_lp64.so - void armpl::clag::gemv_a_strd_first_impl<false, armpl::clag::spec::sve_architecture_spec, double, long, armpl::clag::(anonymous namespace)::step_val_fixed<1l>, double, armpl::clag::(anonymous namespace)::step_val_fixed<1l>, double, armpl::cl...Single0.330.280.280.520.520.420.4264124.77000001.24000000.00
314exec - TwoBodyJastrowRef.h:342-347miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)Single0.250.220.220.400.400.330.336492.1995.2496.431111.2100010050.00
315exec - TwoBodyJastrowRef.h:342-347miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)Single0.250.220.220.400.400.330.336491.4795.2496.431111.2300010050.00
313exec - TwoBodyJastrowRef.h:342-347miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)Single0.270.210.210.420.420.320.326494.8795.2496.431111.3200010050.00
919exec - inner_product.hpp:82-83miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<...Innermost0.240.200.200.390.390.300.306440.0185.7189.291111.280002050.00
316exec - TwoBodyJastrowRef.h:324-331miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)Single0.240.180.180.390.390.270.2764199.6997.1497.861111.4400016050.00
303660libarmpl_lp64.so - void armpl::clag::gemv_a_strd_first_impl<false, armpl::clag::spec::sve_architecture_spec, double, long, armpl::clag::(anonymous namespace)::step_val_fixed<1l>, double, armpl::clag::(anonymous namespace)::step_val_fixed<1l>, double, armpl::cl...Innermost0.220.160.160.340.340.250.2564102.85000001.4000000.00
42542libarmpl_lp64.so - dswap_Single0.220.160.160.340.340.250.25640.00000001.4000000.00
816exec - MultiBsplineRef.hpp:276-286void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, double*, double*, unsigned long)Single0.200.150.150.310.310.230.2364280.421001001111.350009050.00
304604libarmpl_lp64.so - auto armpl::clag::execute_strategy<16ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl...Innermost0.160.130.130.250.250.190.19640.35000001.32000000.00
300exec - TwoBodyJastrowRef.h:155-156miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.160.120.120.250.250.180.1864136.3685.7189.291111.370002050.00
301exec - TwoBodyJastrowRef.h:155-156miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.160.110.110.250.250.170.1764143.351001001111.480003050.00
302exec - TwoBodyJastrowRef.h:155-156miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.160.100.100.260.260.150.1564156.4785.7189.291111.670002050.00
63exec - NonLocalPP.hpp:122-135 [...]qmcplusplus::NonLocalPP<double>::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::WaveFunction&)Outermost0.120.080.090.190.190.130.13648.14022.79915.821.56NANANANANA0.00
912exec - inner_product.hpp:82-83miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.100.060.060.150.150.090.0964128.6785.7189.291111.610002050.00
892exec - inner_product.hpp:211-212qmcplusplus::DiracMatrix<double, double>::invert_transpose(qmcplusplus::Matrix<double, std::allocator<double> > const&, qmcplusplus::Matrix<double, std::allocator<double> >&, double&, double&)Innermost0.070.060.060.110.110.090.09640.000251141.240011062.50
904exec - inner_product.hpp:155-155 [...]miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateLog(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector&l...Innermost0.090.060.060.140.140.090.096484.4981.8259.0911.751.471.710011062.50
913exec - inner_product.hpp:155-155 [...]miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.080.060.060.130.130.080.0864426.3081.8259.0911.751.471.550011062.50
271exec - BsplineFunctor.h:303-336 [...]qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, double*, double*, double*, int*) constSingle0.080.040.040.120.120.060.0664607.7591.1498.1111.012.051003527.78
304833libarmpl_lp64.so - auto armpl::clag::execute_strategy<15ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl...InBetween0.070.040.640.111.100.060.98640.28000001.89000000.00
326exec - BsplineFunctor.h:246-260 [...]miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)Innermost0.060.040.040.100.100.060.0664690.677593.75111.031.710002225.00
277exec - BsplineFunctor.h:236-241qmcplusplus::BsplineFunctor<double>::evaluateV(int, int, int, double const*, double*) constSingle0.050.040.040.080.080.050.05646.66020.831.8161.47NANANANANA0.00
34841libarmpl_lp64.so - dgemm_sve_bigInBetween0.040.021.360.072.200.042.07631245.29000001.71000000.00
803exec - inner_product.hpp:82-83 [...]qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<double, std::allocator<double> > const&, std::vector<double, st...InBetween0.040.020.020.070.070.040.046041.99023.331.6715.271.65NANANANANA0.00
323exec - BsplineFunctor.h:233-260 [...]miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)Outermost0.040.021.440.062.420.032.195475.250251.2141.92NANANANANA0.00
2053exec - ParticleBConds3DSoa.h:280-298 [...]qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&)InBetween0.040.024.130.066.720.036.2754185.512.5924.033.1512.431.81NANANANANA0.00
224exec - OneBodyJastrowRef.h:192-193miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.040.020.020.060.060.030.035674.2885.7189.291111.920002050.00
304754libarmpl_lp64.so - auto armpl::clag::execute_strategy<15ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl...InBetween0.040.021.420.062.420.032.15528.68000001.91000000.00
334699libarmpl_lp64.so - void armpl::clag::lu_unblocked_direct_kernel<armpl::clag::spec::sve_architecture_spec, double, int>(long, long, double*, long, int*, int&)Innermost0.040.020.020.060.060.030.0354291.17000002.17000000.00
307exec - stl_numeric.h:140-141miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)Single0.030.020.020.050.050.020.0250374.948085111.121.60001050.00
905exec - inner_product.hpp:82-83miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateLog(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector&l...Innermost0.040.010.010.060.060.020.024684.6285.7189.291112.060004050.00
2052exec - SoaDistanceTableABOMPTarget.h:214-228 [...]qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&)Outermost0.030.014.140.056.730.026.294867.2458.8263.531.2111.211.85NANANANANA0.00
325exec - BsplineFunctor.h:233-260 [...]miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)InBetween0.030.010.060.050.140.020.094229.8963.7760.511.0311.212.04NANANANANA0.00
245exec - OneBodyJastrowRef.h:134-135 [...]miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)Single0.030.010.010.050.050.020.02382.13022.51.421.76.1823021171.43
33845libarmpl_lp64.so - daxpby_sve_kernelSingle0.030.010.010.050.050.020.0236169.83000001.94000000.00
×