Home
last modified time | relevance | path

Searched refs:gpu_reduce_kernel (Results 1 – 11 of 11) sorted by relevance

/aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/
H A DReduceNormKernel.cu19 gpu_reduce_kernel<scalar_t, out_t>(iter, NormZeroOps<scalar_t, acc_t, out_t>(), 0); in norm_kernel_cuda_impl()
21 gpu_reduce_kernel<scalar_t, out_t>(iter, NormOneOps<scalar_t, acc_t, out_t>(), 0); in norm_kernel_cuda_impl()
23 gpu_reduce_kernel<scalar_t, out_t>(iter, NormTwoOps<scalar_t, acc_t, out_t>(), 0); in norm_kernel_cuda_impl()
25 gpu_reduce_kernel<scalar_t, out_t>(iter, AbsMaxOps<scalar_t, acc_t, out_t>(), 0); in norm_kernel_cuda_impl()
27 …gpu_reduce_kernel<scalar_t, out_t>(iter, AbsMinOps<scalar_t, acc_t, out_t>(), std::numeric_limits<… in norm_kernel_cuda_impl()
29 gpu_reduce_kernel<scalar_t, out_t>(iter, NormOps<scalar_t, acc_t, out_t>{acc_t(p)}, 0); in norm_kernel_cuda_impl()
H A DReduceSumProdKernel.cu16 gpu_reduce_kernel<scalar_t, out_t>( in operator ()()
44 gpu_reduce_kernel<scalar_t, scalar_t>(
55 gpu_reduce_kernel<scalar_t, out_t>( in operator ()()
76 gpu_reduce_kernel<scalar_t, acc_t>(
99 gpu_reduce_kernel<scalar_t, out_t>(
111 gpu_reduce_kernel<bool, bool>( in operator ()()
134 gpu_reduce_kernel<scalar_t, scalar_t>(
H A DReduceLogicKernel.cu14 gpu_reduce_kernel<scalar_t, bool>( in and_kernel_cuda()
26 gpu_reduce_kernel<scalar_t, bool>( in or_kernel_cuda()
H A DReduceAMinMaxKernel.cu22 gpu_reduce_kernel<scalar_t, scalar_t>( in _min_max_values_kernel_cuda_impl()
40 gpu_reduce_kernel<scalar_t, scalar_t>( in aminmax_launch_kernel()
H A DReduceMinValuesKernel.cu30 gpu_reduce_kernel<scalar_t, scalar_t>( in min_values_kernel_cuda_impl()
43 gpu_reduce_kernel<scalar_t, scalar_t>( in min_launch_kernel()
H A DReduceMaxValuesKernel.cu29 gpu_reduce_kernel<scalar_t, scalar_t>( in max_values_kernel_cuda_impl()
45 gpu_reduce_kernel<scalar_t, scalar_t>( in max_launch_kernel()
H A DReduceMomentKernel.cu20 gpu_reduce_kernel<scalar_t, out_t, 2>(iter, ops, typename ops_t::acc_t{}); in std_var_kernel_impl()
44 gpu_reduce_kernel<scalar_t, out_t>(iter, MeanOps<scalar_t, acc_t, factor_t, out_t> {factor}); in mean_kernel_impl()
H A DReduceArgMinKernel.cu22 gpu_reduce_kernel<scalar_t, int64_t>( in argmin_kernel_cuda_impl()
H A DReduceArgMaxKernel.cu22 gpu_reduce_kernel<scalar_t, int64_t>( in argmax_kernel_cuda_impl()
H A DReduce.cuh1133 inline void gpu_reduce_kernel(TensorIterator& iter, const ops_t& ops, ident_t ident=0, in gpu_reduce_kernel() function
1184 gpu_reduce_kernel<scalar_t, out_scalar_t, vt0>(sub_iter, ops, ident, in gpu_reduce_kernel()
/aosp_15_r20/external/pytorch/aten/src/ATen/native/sparse/cuda/
H A DSparseCsrTensorMath.cu640 gpu_reduce_kernel<scalar_t, scalar_t>(iter, func_wrapper<scalar_t>(rop), rop.identity_cpu()); in reduce_sparse_csr_dim01_cuda_template()