Open
Description
Version:
xtensor version: 0.25.0
xsimd version: 13.0.0
xtl version: 0.7.7
Here is the gcc info
gcc -v ─╯
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-linux-gnu/13/lto-wrapper
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
OFFLOAD_TARGET_DEFAULT=1
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Ubuntu 13.1.0-8ubuntu1~22.04' --with-bugurl=file:///usr/share/doc/gcc-13/README.Bugs --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --prefix=/usr --with-gcc-major-version-only --program-suffix=-13 --program-prefix=x86_64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/libexec --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-bootstrap --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --enable-default-pie --with-system-zlib --enable-libphobos-checking=release --with-target-system-zlib=auto --enable-objc-gc=auto --enable-multiarch --disable-werror --enable-cet --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-offload-targets=nvptx-none=/build/gcc-13-IvzKaI/gcc-13-13.1.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-IvzKaI/gcc-13-13.1.0/debian/tmp-gcn/usr --enable-offload-defaulted --without-cuda-driver --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-build-config=bootstrap-lto-lean --enable-link-serialization=2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 13.1.0 (Ubuntu 13.1.0-8ubuntu1~22.04)
Here is the complile flag
-fPIC -Wno-array-bounds -std=gnu++20 -mno-avx512f -msse4.2 -mavx2 -mfma
Here is the test code:
TEST(cos, test) {
xt::xtensor<float, 2> test_data = xt::zeros<float>({180, 4});
for (int i = 0; i < 180; i++) {
test_data(i, 0) = i * M_PI / 180;
test_data(i, 1) = i * M_PI / 180;
test_data(i, 2) = i * M_PI / 180 + M_PI;
test_data(i, 3) = i * M_PI / 180 + M_PI;
}
xt::xtensor<float, 2> cos_data = xt::cos(test_data);
for (int i = 0; i < 180; i++) {
std::cout << cos_data(i, 0) << " " << cos_data(i, 1) << " " << cos_data(i, 2) << " " << cos_data(i, 3) << std::endl;
EXPECT_NEAR(cos_data(i, 0), std::cos(i * M_PI / 180), 1e-6);
// EXPECT_NEAR(cos_data(i, 1), std::cos(i * M_PI / 180), 1e-6);
// EXPECT_NEAR(cos_data(i, 2), std::cos(i * M_PI / 180 + M_PI), 1e-6);
// EXPECT_NEAR(cos_data(i, 3), std::cos(i * M_PI / 180 + M_PI), 1e-6);
}
}
Metadata
Metadata
Assignees
Labels
No labels