XeTLA v0.3.6
IntelĀ® Xe Templates for Linear Algebra - API Definition Document
 
Loading...
Searching...
No Matches
gpu::xetla::subgroup::cooperative_load_helper_t< matAcc_t_, mem_layout_, num_cooperative_wg, arch_tag_, enable > Class Template Reference

Helper to do the cooperative workgroups load. More...

#include <cooperative_load_helper.hpp>

Detailed Description

template<typename matAcc_t_, mem_layout mem_layout_, uint32_t num_cooperative_wg, gpu_arch arch_tag_, class enable = void>
class gpu::xetla::subgroup::cooperative_load_helper_t< matAcc_t_, mem_layout_, num_cooperative_wg, arch_tag_, enable >

Helper to do the cooperative workgroups load.

Template Parameters
matAcc_tIs the input mat type.
tile_shapeIs the group-level tile shape.
mem_layoutIs the memory layout of input.
num_cooperative_wgIs the number of workgroups to do the cooperation.
arch_tagIs the HW architecture.