Mojo function

output_reg_to_smem

output_reg_to_smem[output_type: DType, accum_type: DType, num_m_mmas: Int, o_frag_size: Int, //, BM: Int, BN: Int, padded_depth: Int, swizzle: Swizzle, num_consumer: Int](tid: UInt32, local_warp_group_idx: UInt32, warp_y: UInt32, q_smem: LegacyUnsafePointer[Scalar[output_type], address_space=AddressSpace.SHARED], output_reg_tile: LayoutTensor[accum_type, Layout.row_major(num_m_mmas, o_frag_size), MutAnyOrigin, address_space=AddressSpace.LOCAL]) -> LayoutTensor[output_type, Layout.row_major(BM, padded_depth), MutAnyOrigin, address_space=AddressSpace.SHARED]

Returns:

LayoutTensor

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit