Home
last modified time | relevance | path

Searched defs:C10_LAUNCH_BOUNDS_2 (Results 1 – 12 of 12) sorted by relevance

/external/pytorch/aten/src/ATen/native/sparse/cuda/
DSparseCUDAApplyUtils.cuh44 C10_LAUNCH_BOUNDS_2(cuda::getApplyBlockSize(), cuda::getApplyBlocksPerSM()) in C10_LAUNCH_BOUNDS_2() function
74 C10_LAUNCH_BOUNDS_2(cuda::getApplyBlockSize(), cuda::getApplyBlocksPerSM()) in C10_LAUNCH_BOUNDS_2() function
98 C10_LAUNCH_BOUNDS_2(cuda::getApplyBlockSize(), cuda::getApplyBlocksPerSM()) in C10_LAUNCH_BOUNDS_2() function
145 C10_LAUNCH_BOUNDS_2(cuda::getApplyBlockSize(), cuda::getApplyBlocksPerSM()) in C10_LAUNCH_BOUNDS_2() function
DSparseCUDATensorMath.cu505 C10_LAUNCH_BOUNDS_2(cuda::getApplyBlockSize(), cuda::getApplyBlocksPerSM()) in C10_LAUNCH_BOUNDS_2() function
/external/pytorch/aten/src/ATen/cuda/
DCUDAApplyUtils.cuh273 C10_LAUNCH_BOUNDS_2(AT_APPLY_THREADS_PER_BLOCK, AT_APPLY_BLOCKS_PER_SM) in C10_LAUNCH_BOUNDS_2() function
359 C10_LAUNCH_BOUNDS_2(max_threads_per_block, min_blocks_per_sm) in C10_LAUNCH_BOUNDS_2() function
/external/pytorch/aten/src/ATen/native/cuda/
DTensorTransformations.cu25 C10_LAUNCH_BOUNDS_2(cuda::getApplyBlockSize(), cuda::getApplyBlocksPerSM()) in C10_LAUNCH_BOUNDS_2() function
DFunctionOfAMatrixUtilsKernel.cu15 C10_LAUNCH_BOUNDS_2(n_threads, n_elems_per_thread) in C10_LAUNCH_BOUNDS_2() function
DLinearAlgebra.cu76 C10_LAUNCH_BOUNDS_2(n_threads, n_elems_per_thread) in C10_LAUNCH_BOUNDS_2() function
DUnfoldBackwardKernel.cu23 C10_LAUNCH_BOUNDS_2(n_threads, n_elems_per_thread) in C10_LAUNCH_BOUNDS_2() function
DSparseBinaryOpIntersectionKernel.cu47 C10_LAUNCH_BOUNDS_2(nt, vt) in C10_LAUNCH_BOUNDS_2() function
DDistributionTemplates.h65 C10_LAUNCH_BOUNDS_2(block_size_bound, grid_size_bound) in C10_LAUNCH_BOUNDS_2() function
DIndexKernel.cu27 C10_LAUNCH_BOUNDS_2(nt, launch_bound2) in C10_LAUNCH_BOUNDS_2() function
DScatterGatherKernel.cu87 C10_LAUNCH_BOUNDS_2(nt, vt) in C10_LAUNCH_BOUNDS_2() function
/external/pytorch/c10/macros/
DMacros.h316 #define C10_LAUNCH_BOUNDS_2(max_threads_per_block, min_blocks_per_sm) \ macro