Ginkgo  Generated from pipelines/1330831941 branch based on master. Ginkgo version 1.8.0
A numerical linear algebra library targeting many-core architectures
The adaptiveprecision-blockjacobi 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 adaptive precision block-Jacobi preconditioner.

In this example, we first read in a matrix from file, then generate a right-hand side and an initial guess. The preconditioned CG solver is enhanced with a block-Jacobi preconditioner that optimizes the storage format for the distinct inverted diagonal blocks to the numerical requirements. The example features the iteration count and runtime of the CG solver.

The commented program

}
const auto executor_string = argc >= 2 ? argv[1] : "reference";

Figure out where to run the code

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::OmpExecutor::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 and initial guess as 1

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

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<real_vec>({0.0}, exec);
A->apply(one, x, neg_one, b);
b->compute_norm2(initres);

copy b again

b->copy_from(host_x);

Create solver factory

const RealValueType reduction_factor = 1e-7;
auto solver_gen =
cg::build()
.with_criteria(gko::stop::Iteration::build().with_max_iters(10000u),
gko::stop::ResidualNorm<ValueType>::build()
.with_reduction_factor(reduction_factor))

Add preconditioner, these 2 lines are the only difference from the simple solver example

.with_preconditioner(
bj::build().with_max_block_size(16u).with_storage_optimization(
gko::precision_reduction::autodetect()))
.on(exec);

Create solver

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

Solve system

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

Get residual

auto res = gko::as<real_vec>(logger->get_residual_norm());
auto impl_res = gko::as<real_vec>(logger->get_implicit_sq_resnorm());
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 << "Implicit residual norm squared (r^2):\n";
write(std::cout, impl_res);

Print solver statistics

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

Results

This is the expected output:

Initial residual norm sqrt(r^T r):
%%MatrixMarket matrix array real general
1 1
194.679
Final residual norm sqrt(r^T r):
%%MatrixMarket matrix array real general
1 1
5.69384e-06
Implicit residual norm squared (r^2):
%%MatrixMarket matrix array real general
1 1
1.27043e-15
CG iteration count: 5
CG execution time [ms]: 0.080041

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 RealValueType = gko::remove_complex<ValueType>;
using IndexType = int;
using vec = gko::matrix::Dense<ValueType>;
using real_vec = gko::matrix::Dense<RealValueType>;
using mtx = gko::matrix::Csr<ValueType, IndexType>;
using cg = gko::solver::Cg<ValueType>;
using bj = gko::preconditioner::Jacobi<ValueType, IndexType>;
std::cout << gko::version_info::get() << std::endl;
if (argc == 2 && (std::string(argv[1]) == "--help")) {
std::cerr << "Usage: " << argv[0] << " [executor]" << std::endl;
std::exit(-1);
}
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::OmpExecutor::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));
for (auto i = 0; i < size; i++) {
host_x->at(i, 0) = 1.;
}
auto x = gko::clone(exec, host_x);
auto b = gko::clone(exec, host_x);
auto one = gko::initialize<vec>({1.0}, exec);
auto neg_one = gko::initialize<vec>({-1.0}, exec);
auto initres = gko::initialize<real_vec>({0.0}, exec);
A->apply(one, x, neg_one, b);
b->compute_norm2(initres);
b->copy_from(host_x);
const RealValueType reduction_factor = 1e-7;
auto solver_gen =
cg::build()
.with_criteria(gko::stop::Iteration::build().with_max_iters(10000u),
gko::stop::ResidualNorm<ValueType>::build()
.with_reduction_factor(reduction_factor))
.with_preconditioner(
bj::build().with_max_block_size(16u).with_storage_optimization(
gko::precision_reduction::autodetect()))
.on(exec);
std::shared_ptr<const gko::log::Convergence<ValueType>> logger =
gko::log::Convergence<ValueType>::create();
solver_gen->add_logger(logger);
auto solver = solver_gen->generate(A);
exec->synchronize();
std::chrono::nanoseconds time(0);
auto tic = std::chrono::steady_clock::now();
solver->apply(b, x);
auto toc = std::chrono::steady_clock::now();
time += std::chrono::duration_cast<std::chrono::nanoseconds>(toc - tic);
auto res = gko::as<real_vec>(logger->get_residual_norm());
auto impl_res = gko::as<real_vec>(logger->get_implicit_sq_resnorm());
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 << "Implicit residual norm squared (r^2):\n";
write(std::cout, impl_res);
std::cout << "CG iteration count: " << logger->get_num_iterations()
<< std::endl;
std::cout << "CG execution time [ms]: "
<< static_cast<double>(time.count()) / 1000000.0 << 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::precision_reduction::autodetect
constexpr static precision_reduction autodetect() noexcept
Returns a special encoding which instructs the algorithm to automatically detect the best precision.
Definition: types.hpp:335
gko::size_type
std::size_t size_type
Integral type used for allocation quantities.
Definition: types.hpp:108
gko::clone
detail::cloned_type< Pointer > clone(const Pointer &p)
Creates a unique clone of the object pointed to by p.
Definition: utils_helper.hpp:175
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::preconditioner::Jacobi
A block-Jacobi preconditioner is a block-diagonal linear operator, obtained by inverting the diagonal...
Definition: jacobi.hpp:187
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::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