Ginkgo  Generated from pipelines/1330831941 branch based on master. Ginkgo version 1.8.0
A numerical linear algebra library targeting many-core architectures
The multigrid-preconditioned-solver program

The preconditioned solver example..

This example depends on preconditioned-solver.

Table of contents
  1. Introduction
  2. The commented program
  1. Results
  2. The plain program

This example shows how to use the multigrid preconditioner.

In this example, we first read in a matrix from a file. The preconditioned CG solver is enhanced with a multigrid preconditioner. The example features the generating time and runtime of the CG solver.

The commented program

{"omp", [] { return gko::OmpExecutor::create(); }},
{"cuda",
[] {
return gko::CudaExecutor::create(0,
gko::OmpExecutor::create());
}},
{"hip",
[] {
return gko::HipExecutor::create(0, gko::OmpExecutor::create());
}},
{"dpcpp",
[] {
return gko::DpcppExecutor::create(
0, gko::ReferenceExecutor::create());
}},
{"reference", [] { return gko::ReferenceExecutor::create(); }}};

executor where Ginkgo will perform the computation

const auto exec = exec_map.at(executor_string)(); // throws if not valid

Read data

auto A = share(gko::read<mtx>(std::ifstream("data/A.mtx"), exec));

Create RHS as 1 and initial guess as 0

gko::size_type size = A->get_size()[0];
auto host_x = vec::create(exec->get_master(), gko::dim<2>(size, 1));
auto host_b = vec::create(exec->get_master(), gko::dim<2>(size, 1));
for (auto i = 0; i < size; i++) {
host_x->at(i, 0) = 0.;
host_b->at(i, 0) = 1.;
}
auto x = vec::create(exec);
auto b = vec::create(exec);
x->copy_from(host_x);
b->copy_from(host_b);

Calculate initial residual by overwriting b

auto one = gko::initialize<vec>({1.0}, exec);
auto neg_one = gko::initialize<vec>({-1.0}, exec);
auto initres = gko::initialize<vec>({0.0}, exec);
A->apply(one, x, neg_one, b);
b->compute_norm2(initres);

copy b again

b->copy_from(host_b);

Create multigrid factory

std::shared_ptr<gko::LinOpFactory> multigrid_gen;
multigrid_gen =
mg::build()
.with_mg_level(pgm::build().with_deterministic(true))
.with_criteria(gko::stop::Iteration::build().with_max_iters(1u))
.on(exec);
const gko::remove_complex<ValueType> tolerance = 1e-8;
auto solver_gen =
cg::build()
.with_criteria(gko::stop::Iteration::build().with_max_iters(100u),
gko::stop::ResidualNorm<ValueType>::build()
.with_baseline(gko::stop::mode::absolute)
.with_reduction_factor(tolerance))
.with_preconditioner(multigrid_gen)
.on(exec);

Create solver

std::chrono::nanoseconds gen_time(0);
auto gen_tic = std::chrono::steady_clock::now();
auto solver = solver_gen->generate(A);
exec->synchronize();
auto gen_toc = std::chrono::steady_clock::now();
gen_time +=
std::chrono::duration_cast<std::chrono::nanoseconds>(gen_toc - gen_tic);

Add logger

std::shared_ptr<const gko::log::Convergence<ValueType>> logger =
gko::log::Convergence<ValueType>::create();
solver->add_logger(logger);

Solve system

exec->synchronize();
std::chrono::nanoseconds time(0);
auto tic = std::chrono::steady_clock::now();
solver->apply(b, x);
exec->synchronize();
auto toc = std::chrono::steady_clock::now();
time += std::chrono::duration_cast<std::chrono::nanoseconds>(toc - tic);

Calculate residual

auto res = gko::as<vec>(logger->get_residual_norm());
std::cout << "Initial residual norm sqrt(r^T r): \n";
write(std::cout, initres);
std::cout << "Final residual norm sqrt(r^T r): \n";
write(std::cout, res);

Print solver statistics

std::cout << "CG iteration count: " << logger->get_num_iterations()
<< std::endl;
std::cout << "CG generation time [ms]: "
<< static_cast<double>(gen_time.count()) / 1000000.0 << std::endl;
std::cout << "CG execution time [ms]: "
<< static_cast<double>(time.count()) / 1000000.0 << std::endl;
std::cout << "CG execution time per iteration[ms]: "
<< static_cast<double>(time.count()) / 1000000.0 /
logger->get_num_iterations()
<< std::endl;
}

Results

This is the expected output:

Initial residual norm sqrt(r^T r):
%%MatrixMarket matrix array real general
1 1
4.3589
Final residual norm sqrt(r^T r):
%%MatrixMarket matrix array real general
1 1
1.69858e-09
CG iteration count: 39
CG generation time [ms]: 2.04293
CG execution time [ms]: 22.3874
CG execution time per iteration[ms]: 0.574036

Comments about programming and debugging

The plain program

#include <ginkgo/ginkgo.hpp>
#include <fstream>
#include <iomanip>
#include <iostream>
#include <map>
#include <string>
int main(int argc, char* argv[])
{
using ValueType = double;
using IndexType = int;
using vec = gko::matrix::Dense<ValueType>;
using mtx = gko::matrix::Csr<ValueType, IndexType>;
using cg = gko::solver::Cg<ValueType>;
using mg = gko::solver::Multigrid;
using pgm = gko::multigrid::Pgm<ValueType, IndexType>;
std::cout << gko::version_info::get() << std::endl;
const auto executor_string = argc >= 2 ? argv[1] : "reference";
std::map<std::string, std::function<std::shared_ptr<gko::Executor>()>>
exec_map{
{"omp", [] { return gko::OmpExecutor::create(); }},
{"cuda",
[] {
return gko::CudaExecutor::create(0,
gko::OmpExecutor::create());
}},
{"hip",
[] {
return gko::HipExecutor::create(0, gko::OmpExecutor::create());
}},
{"dpcpp",
[] {
return gko::DpcppExecutor::create(
0, gko::ReferenceExecutor::create());
}},
{"reference", [] { return gko::ReferenceExecutor::create(); }}};
const auto exec = exec_map.at(executor_string)(); // throws if not valid
auto A = share(gko::read<mtx>(std::ifstream("data/A.mtx"), exec));
gko::size_type size = A->get_size()[0];
auto host_x = vec::create(exec->get_master(), gko::dim<2>(size, 1));
auto host_b = vec::create(exec->get_master(), gko::dim<2>(size, 1));
for (auto i = 0; i < size; i++) {
host_x->at(i, 0) = 0.;
host_b->at(i, 0) = 1.;
}
auto x = vec::create(exec);
auto b = vec::create(exec);
x->copy_from(host_x);
b->copy_from(host_b);
auto one = gko::initialize<vec>({1.0}, exec);
auto neg_one = gko::initialize<vec>({-1.0}, exec);
auto initres = gko::initialize<vec>({0.0}, exec);
A->apply(one, x, neg_one, b);
b->compute_norm2(initres);
b->copy_from(host_b);
std::shared_ptr<gko::LinOpFactory> multigrid_gen;
multigrid_gen =
mg::build()
.with_mg_level(pgm::build().with_deterministic(true))
.with_criteria(gko::stop::Iteration::build().with_max_iters(1u))
.on(exec);
const gko::remove_complex<ValueType> tolerance = 1e-8;
auto solver_gen =
cg::build()
.with_criteria(gko::stop::Iteration::build().with_max_iters(100u),
gko::stop::ResidualNorm<ValueType>::build()
.with_baseline(gko::stop::mode::absolute)
.with_reduction_factor(tolerance))
.with_preconditioner(multigrid_gen)
.on(exec);
std::chrono::nanoseconds gen_time(0);
auto gen_tic = std::chrono::steady_clock::now();
auto solver = solver_gen->generate(A);
exec->synchronize();
auto gen_toc = std::chrono::steady_clock::now();
gen_time +=
std::chrono::duration_cast<std::chrono::nanoseconds>(gen_toc - gen_tic);
std::shared_ptr<const gko::log::Convergence<ValueType>> logger =
gko::log::Convergence<ValueType>::create();
solver->add_logger(logger);
exec->synchronize();
std::chrono::nanoseconds time(0);
auto tic = std::chrono::steady_clock::now();
solver->apply(b, x);
exec->synchronize();
auto toc = std::chrono::steady_clock::now();
time += std::chrono::duration_cast<std::chrono::nanoseconds>(toc - tic);
auto res = gko::as<vec>(logger->get_residual_norm());
std::cout << "Initial residual norm sqrt(r^T r): \n";
write(std::cout, initres);
std::cout << "Final residual norm sqrt(r^T r): \n";
write(std::cout, res);
std::cout << "CG iteration count: " << logger->get_num_iterations()
<< std::endl;
std::cout << "CG generation time [ms]: "
<< static_cast<double>(gen_time.count()) / 1000000.0 << std::endl;
std::cout << "CG execution time [ms]: "
<< static_cast<double>(time.count()) / 1000000.0 << std::endl;
std::cout << "CG execution time per iteration[ms]: "
<< static_cast<double>(time.count()) / 1000000.0 /
logger->get_num_iterations()
<< std::endl;
}
gko::matrix::Csr
CSR is a matrix format which stores only the nonzero coefficients by compressing each row of the matr...
Definition: matrix.hpp:27
gko::log::profile_event_category::solver
Solver events.
gko::log::Convergence::create
static std::unique_ptr< Convergence > create(std::shared_ptr< const Executor >, const mask_type &enabled_events=Logger::criterion_events_mask|Logger::iteration_complete_mask)
Creates a convergence logger.
Definition: convergence.hpp:74
gko::layout_type::array
The matrix should be written as dense matrix in column-major order.
gko::matrix::Dense
Dense is a matrix format which explicitly stores all values of the matrix.
Definition: dense_cache.hpp:20
gko::size_type
std::size_t size_type
Integral type used for allocation quantities.
Definition: types.hpp:108
gko::solver::Multigrid
Multigrid methods have a hierarchy of many levels, whose corase level is a subset of the fine level,...
Definition: multigrid.hpp:108
gko::HipExecutor::create
static std::shared_ptr< HipExecutor > create(int device_id, std::shared_ptr< Executor > master, bool device_reset, allocation_mode alloc_mode=default_hip_alloc_mode, CUstream_st *stream=nullptr)
Creates a new HipExecutor.
gko::version_info::get
static const version_info & get()
Returns an instance of version_info.
Definition: version.hpp:140
gko::stop::ResidualNorm
The ResidualNorm class is a stopping criterion which stops the iteration process when the actual resi...
Definition: residual_norm.hpp:110
gko::multigrid::Pgm
Parallel graph match (Pgm) is the aggregate method introduced in the paper M.
Definition: matrix.hpp:37
gko::dim< 2 >
gko::solver::Cg
CG or the conjugate gradient method is an iterative type Krylov subspace method which is suitable for...
Definition: cg.hpp:49
gko::write
void write(StreamType &&os, MatrixPtrType &&matrix, layout_type layout=detail::mtx_io_traits< std::remove_cv_t< detail::pointee< MatrixPtrType >>>::default_layout)
Writes a matrix into an output stream in matrix market format.
Definition: mtx_io.hpp:296
gko::share
detail::shared_type< OwningPointer > share(OwningPointer &&p)
Marks the object pointed to by p as shared.
Definition: utils_helper.hpp:226
gko::CudaExecutor::create
static std::shared_ptr< CudaExecutor > create(int device_id, std::shared_ptr< Executor > master, bool device_reset, allocation_mode alloc_mode=default_cuda_alloc_mode, CUstream_st *stream=nullptr)
Creates a new CudaExecutor.
gko::OmpExecutor::create
static std::shared_ptr< OmpExecutor > create(std::shared_ptr< CpuAllocatorBase > alloc=std::make_shared< CpuAllocator >())
Creates a new OmpExecutor.
Definition: executor.hpp:1345
gko::remove_complex
typename detail::remove_complex_s< T >::type remove_complex
Obtain the type which removed the complex of complex/scalar type or the template parameter of class b...
Definition: math.hpp:326
gko::DpcppExecutor::create
static std::shared_ptr< DpcppExecutor > create(int device_id, std::shared_ptr< Executor > master, std::string device_type="all", dpcpp_queue_property property=dpcpp_queue_property::in_order)
Creates a new DpcppExecutor.
gko::real
constexpr auto real(const T &x)
Returns the real part of the object.
Definition: math.hpp:1013
gko::one
constexpr T one()
Returns the multiplicative identity for T.
Definition: math.hpp:775
Generated by   doxygen 1.8.16