#pragma once #include "helpers.h" #include #define CHECK_CUDA(x) TORCH_CHECK(x.is_cuda(), #x " must be a CUDA tensor") #define CHECK_CONTIGUOUS(x) \ TORCH_CHECK(x.is_contiguous(), #x " must be contiguous") #define CHECK_INPUT(x) \ CHECK_CUDA(x); \ CHECK_CONTIGUOUS(x) #define CUDA_GET_THREAD_ID(tid, Q) \ const int tid = blockIdx.x * blockDim.x + threadIdx.x; \ if (tid >= Q) \ return #define CUDA_N_BLOCKS_NEEDED(Q, CUDA_N_THREADS) ((Q - 1) / CUDA_N_THREADS + 1) #define DEVICE_GUARD(_ten) \ const at::cuda::OptionalCUDAGuard device_guard(device_of(_ten));