Home
last modified time | relevance | path

Searched refs:kCUDABlockReduceMaxThreads (Results 1 – 4 of 4) sorted by relevance

/aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/
H A Dblock_reduce.cuh17 constexpr int kCUDABlockReduceMaxThreads = C10_WARP_SIZE * C10_WARP_SIZE; variable
H A DTensorModeKernel.cu210 num_threads <= cuda_utils::kCUDABlockReduceMaxThreads, ""); in handle_fused_mode()
H A DEmbedding.cu372 num_threads() <= cuda_utils::kCUDABlockReduceMaxThreads, in embedding_renorm_cuda_()
H A DMultinomialKernel.cu89 props->maxThreadsPerBlock, cuda_utils::kCUDABlockReduceMaxThreads); in renormRows()