Home
last modified time | relevance | path

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

/aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/
H A DReduce.cuh1095 constexpr int max_values_per_thread = 256; in setReduceConfig() local
1097 ….values_per_thread() >= block_height * 16 || config.values_per_thread() >= max_values_per_thread) { in setReduceConfig()
1111 …if (config.input_mult[1] != 0 && config.values_per_thread() >= max_values_per_thread && grid <= ta… in setReduceConfig()
1120 int ctas_per_output3 = div_up(config.values_per_thread(), max_values_per_thread); in setReduceConfig()