Skip to content

Commit

Permalink
Merge branch 'main' into improve_compilation_error_handling
Browse files Browse the repository at this point in the history
  • Loading branch information
@sbaldu
sbaldu authored Aug 4, 2024
2 parents 677bf4b + 9dac229 commit 3954883
Show file tree
Hide file tree
Showing 14 changed files with 202 additions and 1,115 deletions.
20 changes: 10 additions & 10 deletions CLUEstering/CLUEstering.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -262,7 +262,7 @@ def __init__(self, dc_: float, rhoc_: float, outlier_: float, ppbin: int = 10):
self.elapsed_time = 0.

def set_params(self, dc: float, rhoc: float,
outlier: float, ppbin: int = 10) -> None:
outlier: float, ppbin: int = 128) -> None:
self.dc_ = dc
self.rhoc = rhoc
self.outlier = outlier
Expand Down Expand Up @@ -292,19 +292,19 @@ def _read_array(self, input_data: Union[list, np.ndarray]) -> None:
if len(input_data) < 2 or len(input_data) > 11:
raise ValueError("Inadequate data. The supported dimensions are between" +
"1 and 10.")
self.clust_data = clustering_data(np.asarray(input_data[:-1]).T,
np.copy(np.asarray(input_data[:-1]).T),
np.asarray(input_data[-1]),
self.clust_data = clustering_data(np.asarray(input_data[:-1], dtype=float).T,
np.copy(np.asarray(input_data[:-1], dtype=float).T),
np.asarray(input_data[-1], dtype=float),
len(input_data[:-1]),
len(input_data[-1]))
# [[[x0, y0, z0, ...], [x1, y1, z1, ...], ...], [weights]]
else:
if len(input_data) != 2:
raise ValueError("Inadequate data. The data must contain a weight value" +
"for each point.")
self.clust_data = clustering_data(np.asarray(input_data[0]),
np.copy(np.asarray(input_data[0])),
np.asarray(input_data[-1]),
self.clust_data = clustering_data(np.asarray(input_data[0], dtype=float),
np.copy(np.asarray(input_data[0], dtype=float)),
np.asarray(input_data[-1], dtype=float),
len(input_data[0][0]),
len(input_data[-1]))

Expand All @@ -329,7 +329,7 @@ def _read_string(self, input_data: str) -> Union[pd.DataFrame,None]:

if not input_data.endswith('.csv'):
raise ValueError('Wrong type of file. The file is not a csv file.')
df_ = pd.read_csv(input_data)
df_ = pd.read_csv(input_data, dtype=float)
return df_

def _read_dict_df(self, input_data: Union[dict, pd.DataFrame]) -> pd.DataFrame:
Expand All @@ -351,7 +351,7 @@ def _read_dict_df(self, input_data: Union[dict, pd.DataFrame]) -> pd.DataFrame:
Dataframe containing the input data
"""

df_ = pd.DataFrame(input_data, copy=False)
df_ = pd.DataFrame(input_data, copy=False, dtype=float)
return df_

def _handle_dataframe(self, df_: pd.DataFrame) -> None:
Expand Down Expand Up @@ -1215,7 +1215,7 @@ def to_csv(self, output_folder: str, file_name: str) -> None:
df_.to_csv(out_path,index=False)

if __name__ == "__main__":
c = clusterer(0.4,5,1.)
c = clusterer(0.8, 5, 1.)
c.read_data('./blob.csv')
c.input_plotter()
c.run_clue(backend="cpu serial", verbose=True)
Expand Down
141 changes: 16 additions & 125 deletions CLUEstering/alpaka/BindingModules/binding_cpu.cc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,15 +2,11 @@
#include <alpaka/alpaka.hpp>
#include <vector>

#include "../CLUE/CLUEAlgoAlpaka.h"
#include "../CLUE/Run.h"
#include "../DataFormats/Points.h"
#include "../DataFormats/alpaka/PointsAlpaka.h"

#include <pybind11/pybind11.h>
#include <pybind11/stl.h>
#include <pybind11/functional.h>
#include <stdint.h>

namespace alpaka_serial_sync {
void listDevices(const std::string& backend) {
Expand All @@ -27,158 +23,53 @@ namespace alpaka_serial_sync {
}
}

template <typename Kernel>
std::vector<std::vector<int>> mainRun(float dc,
float rhoc,
float outlier,
int pPBin,
const std::vector<std::vector<float>>& coords,
const std::vector<float>& weights,
const FlatKernel& kernel,
const Kernel& kernel,
int Ndim,
size_t block_size,
size_t device_id) {
auto const dev_acc = alpaka::getDevByIdx<Acc1D>(device_id);
const auto dev_acc = alpaka::getDevByIdx<Acc1D>(device_id);

// Create the queue
Queue queue_(dev_acc);

// Running the clustering algorithm //
switch (Ndim) {
[[unlikely]] case (1):
return run1(
return run<1, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[likely]] case (2):
return run2(
return run<2, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[likely]] case (3):
return run3(
return run<3, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (4):
return run4(
return run<4, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (5):
return run5(
return run<5, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (6):
return run6(
return run<6, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (7):
return run7(
return run<7, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (8):
return run8(
return run<8, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (9):
return run9(
return run<9, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (10):
return run10(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] default:
std::cout << "This library only works up to 10 dimensions\n";
return {};
}
}

std::vector<std::vector<int>> mainRun(float dc,
float rhoc,
float outlier,
int pPBin,
const std::vector<std::vector<float>>& coords,
const std::vector<float>& weights,
const ExponentialKernel& kernel,
int Ndim,
size_t block_size,
size_t device_id) {
auto const dev_acc = alpaka::getDevByIdx<Acc1D>(device_id);

// Create the queue
Queue queue_(dev_acc);

// Running the clustering algorithm //
switch (Ndim) {
[[unlikely]] case (1):
return run1(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[likely]] case (2):
return run2(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[likely]] case (3):
return run3(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (4):
return run4(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (5):
return run5(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (6):
return run6(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (7):
return run7(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (8):
return run8(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (9):
return run9(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (10):
return run10(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] default:
std::cout << "This library only works up to 10 dimensions\n";
return {};
}
}

std::vector<std::vector<int>> mainRun(float dc,
float rhoc,
float outlier,
int pPBin,
const std::vector<std::vector<float>>& coords,
const std::vector<float>& weights,
const GaussianKernel& kernel,
int Ndim,
size_t block_size,
size_t device_id) {
auto const dev_acc = alpaka::getDevByIdx<Acc1D>(device_id);

// Create the queue
Queue queue_(dev_acc);

// Running the clustering algorithm //
switch (Ndim) {
[[unlikely]] case (1):
return run1(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[likely]] case (2):
return run2(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[likely]] case (3):
return run3(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (4):
return run4(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (5):
return run5(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (6):
return run6(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (7):
return run7(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (8):
return run8(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (9):
return run9(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] case (10):
return run10(
return run<10, Kernel>(
dc, rhoc, outlier, pPBin, coords, weights, kernel, queue_, block_size);
[[unlikely]] default:
std::cout << "This library only works up to 10 dimensions\n";
Expand All @@ -202,7 +93,7 @@ namespace alpaka_serial_sync {
const FlatKernel&,
int,
size_t,
size_t>(&mainRun),
size_t>(&mainRun<FlatKernel>),
"mainRun");
m.def("mainRun",
pybind11::overload_cast<float,
Expand All @@ -214,7 +105,7 @@ namespace alpaka_serial_sync {
const ExponentialKernel&,
int,
size_t,
size_t>(&mainRun),
size_t>(&mainRun<ExponentialKernel>),
"mainRun");
m.def("mainRun",
pybind11::overload_cast<float,
Expand All @@ -226,7 +117,7 @@ namespace alpaka_serial_sync {
const GaussianKernel&,
int,
size_t,
size_t>(&mainRun),
size_t>(&mainRun<GaussianKernel>),
"mainRun");
}
}; // namespace alpaka_serial_sync
Loading

0 comments on commit 3954883

Please sign in to comment.