mirror of
https://github.com/android/ndk-samples
synced 2025-11-09 17:45:37 +08:00
f608813b05
This adds a new generic vectorization sample to replace hello-neon. Most importantly, it covers non-Neon options for SIMD. One of the useful things it shows, for example, is that there's actually no reason to write SIMD code the way that hello-neon does any more. This also solves a much simpler problem (small matrix multiplication), which makes it easier to see how to deal with the SIMD features rather than figuring out what a FIR filter is. Finally, this sample benchmarks each of the implementations so it's obvious what is and isn't worth doing. I was sort of surprised that auto-vectorization didn't do better, and was pleased to learn that there's no reason at all to write Neon intrinsics. I'll delete hello-neon after this merges and I've fixed up the doc links. https://github.com/android/ndk-samples/issues/1011
56 lines
1.8 KiB
C++
56 lines
1.8 KiB
C++
/*
|
|
* Copyright (C) 2024 The Android Open Source Project
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <stdint.h>
|
|
|
|
#include "matrix.h"
|
|
|
|
namespace samples::vectorization {
|
|
|
|
/**
|
|
* Multiplies two compatible matrices and returns the result.
|
|
*
|
|
* @tparam T The type of each matrix cell.
|
|
* @tparam M The number of rows in the left operand and the result.
|
|
* @tparam N The number of columns in the left operand, and the rows in the
|
|
* right operand.
|
|
* @tparam P The number of columns in the right operand and the result.
|
|
* @param lhs The left operand.
|
|
* @param rhs The right operand.
|
|
* @return The result of lhs * rhs.
|
|
*/
|
|
template <typename T, size_t M, size_t N, size_t P>
|
|
Matrix<M, P, T> MultiplyWithOpenMP(const Matrix<M, N, T>& lhs,
|
|
const Matrix<N, P, T>& rhs) {
|
|
Matrix<M, P, T> result;
|
|
#pragma omp simd
|
|
for (auto result_column_index = 0U; result_column_index < P;
|
|
result_column_index++) {
|
|
for (auto lhs_column_index = 0U; lhs_column_index < N; lhs_column_index++) {
|
|
auto lhs_column = lhs.column(lhs_column_index);
|
|
const T& scalar = rhs[lhs_column_index, result_column_index];
|
|
for (auto row = 0U; row < lhs_column.size(); row++) {
|
|
result[row, result_column_index] += lhs_column[row] * scalar;
|
|
}
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
} // namespace samples::vectorization
|