Developer Guide and Reference

  • 2022.1
  • 04/11/2022
  • Public Content
Contents

struct dnnl_rnn_packed_desc_t

Description of tensor of packed weights for rnn.
#include <dnnl_types.h> struct dnnl_rnn_packed_desc_t { // fields dnnl_rnn_packed_memory_format_t format; int n_parts; int n; int ldb; int parts[DNNL_RNN_MAX_N_PARTS]; size_t part_pack_size[DNNL_RNN_MAX_N_PARTS]; unsigned pack_part[DNNL_RNN_MAX_N_PARTS]; size_t offset_compensation; size_t size; char reserved[200]; };

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.