mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 00:21:07 +01:00
afb742382a
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/69394 Modified loops in files under fbsource/fbcode/caffe2/ from the format ``` for(TYPE var=x0;var<x_max;x++) ``` to the format ``` for(const auto var: irange(xmax)) ``` This was achieved by running r-barnes's loop upgrader script (D28874212) with some modification to exclude all files under /torch/jit and a number of reversions or unused variable suppression warnings added by hand. Test Plan: Sandcastle Reviewed By: malfet Differential Revision: D32837991 fbshipit-source-id: fc7c4f76d2f32a17a0faf329294b3fe7cb81df32
64 lines
1.8 KiB
C++
64 lines
1.8 KiB
C++
#include <gtest/gtest.h>
|
|
|
|
#include <torch/torch.h>
|
|
#include <ATen/native/Pow.h>
|
|
#include <c10/util/irange.h>
|
|
#include <torch/types.h>
|
|
#include <torch/utils.h>
|
|
#include <test/cpp/api/support.h>
|
|
#include <iostream>
|
|
#include <vector>
|
|
#include <type_traits>
|
|
#include <cstdlib>
|
|
|
|
|
|
struct DispatchTest : torch::test::SeedingFixture {};
|
|
|
|
TEST_F(DispatchTest, TestAVX2) {
|
|
const std::vector<int> ints {1, 2, 3, 4};
|
|
const std::vector<int> result {1, 4, 27, 256};
|
|
const auto vals_tensor = torch::tensor(ints);
|
|
const auto pows_tensor = torch::tensor(ints);
|
|
#ifdef _WIN32
|
|
_putenv("ATEN_CPU_CAPABILITY=avx2");
|
|
#else
|
|
setenv("ATEN_CPU_CAPABILITY", "avx2", 1);
|
|
#endif
|
|
const auto actual_pow_avx2 = vals_tensor.pow(pows_tensor);
|
|
for (const auto i : c10::irange(4)) {
|
|
ASSERT_EQ(result[i], actual_pow_avx2[i].item<int>());
|
|
}
|
|
}
|
|
|
|
TEST_F(DispatchTest, TestAVX512) {
|
|
const std::vector<int> ints {1, 2, 3, 4};
|
|
const std::vector<int> result {1, 4, 27, 256};
|
|
const auto vals_tensor = torch::tensor(ints);
|
|
const auto pows_tensor = torch::tensor(ints);
|
|
#ifdef _WIN32
|
|
_putenv("ATEN_CPU_CAPABILITY=avx512");
|
|
#else
|
|
setenv("ATEN_CPU_CAPABILITY", "avx512", 1);
|
|
#endif
|
|
const auto actual_pow_avx512 = vals_tensor.pow(pows_tensor);
|
|
for (const auto i : c10::irange(4)) {
|
|
ASSERT_EQ(result[i], actual_pow_avx512[i].item<int>());
|
|
}
|
|
}
|
|
|
|
TEST_F(DispatchTest, TestDefault) {
|
|
const std::vector<int> ints {1, 2, 3, 4};
|
|
const std::vector<int> result {1, 4, 27, 256};
|
|
const auto vals_tensor = torch::tensor(ints);
|
|
const auto pows_tensor = torch::tensor(ints);
|
|
#ifdef _WIN32
|
|
_putenv("ATEN_CPU_CAPABILITY=default");
|
|
#else
|
|
setenv("ATEN_CPU_CAPABILITY", "default", 1);
|
|
#endif
|
|
const auto actual_pow_default = vals_tensor.pow(pows_tensor);
|
|
for (const auto i : c10::irange(4)) {
|
|
ASSERT_EQ(result[i], actual_pow_default[i].item<int>());
|
|
}
|
|
}
|