The preconditioned solver example.
This example depends on preconditioned-solver.
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
{"cuda",
[] {
}},
{"hip",
[] {
}},
{"dpcpp",
[] {
0, gko::ReferenceExecutor::create());
}},
{"reference", [] { return gko::ReferenceExecutor::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.
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.
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.
static std::shared_ptr< OmpExecutor > create(std::shared_ptr< CpuAllocatorBase > alloc=std::make_shared< CpuAllocator >())
Creates a new OmpExecutor.
Definition executor.hpp:1396
executor where Ginkgo will perform the computation
const auto exec = exec_map.at(executor_string)();
Read data
std::unique_ptr< MatrixType > read(StreamType &&is, MatrixArgs &&... args)
Reads a matrix stored in matrix market format from an input stream.
Definition mtx_io.hpp:159
Create RHS as 1 and initial guess as 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);
std::size_t size_type
Integral type used for allocation quantities.
Definition types.hpp:89
A type representing the dimensions of a multidimensional object.
Definition dim.hpp:26
Calculate initial residual by overwriting b
A->apply(one, x, neg_one, b);
b->compute_norm2(initres);
std::unique_ptr< Matrix > initialize(size_type stride, std::initializer_list< typename Matrix::value_type > vals, std::shared_ptr< const Executor > exec, TArgs &&... create_args)
Creates and initializes a column-vector.
Definition dense.hpp:1565
copy b again
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);
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);
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:260
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 =
solver->add_logger(logger);
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:73
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
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::decay_t< T > * as(U *obj)
Performs polymorphic type conversion.
Definition utils_helper.hpp:307
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 <fstream>
#include <iomanip>
#include <iostream>
#include <map>
#include <string>
#include <ginkgo/ginkgo.hpp>
int main(int argc, char* argv[])
{
using ValueType = double;
using IndexType = int;
const auto executor_string = argc >= 2 ? argv[1] : "reference";
std::map<std::string, std::function<std::shared_ptr<gko::Executor>()>>
exec_map{
{"cuda",
[] {
}},
{"hip",
[] {
}},
{"dpcpp",
[] {
0, gko::ReferenceExecutor::create());
}},
{"reference", [] { return gko::ReferenceExecutor::create(); }}};
const auto exec = exec_map.at(executor_string)();
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);
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);
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 =
exec->synchronize();
std::chrono::nanoseconds time(0);
auto tic = std::chrono::steady_clock::now();
exec->synchronize();
auto toc = std::chrono::steady_clock::now();
time += std::chrono::duration_cast<std::chrono::nanoseconds>(toc - tic);
std::cout << "Initial residual norm sqrt(r^T r): \n";
write(std::cout, initres);
std::cout << "Final residual norm sqrt(r^T r): \n";
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;
}
CSR is a matrix format which stores only the nonzero coefficients by compressing each row of the matr...
Definition csr.hpp:121
Dense is a matrix format which explicitly stores all values of the matrix.
Definition dense.hpp:117
Parallel graph match (Pgm) is the aggregate method introduced in the paper M.
Definition pgm.hpp:52
CG or the conjugate gradient method is an iterative type Krylov subspace method which is suitable for...
Definition cg.hpp:50
Multigrid methods have a hierarchy of many levels, whose corase level is a subset of the fine level,...
Definition multigrid.hpp:110
static const version_info & get()
Returns an instance of version_info.
Definition version.hpp:139
@ solver
Solver events.
Definition profiler_hook.hpp:34
constexpr T one()
Returns the multiplicative identity for T.
Definition math.hpp:630
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:295
detail::shared_type< OwningPointer > share(OwningPointer &&p)
Marks the object pointed to by p as shared.
Definition utils_helper.hpp:224