Mojo function
blackwell_matmul_tma_umma_warp_specialized
blackwell_matmul_tma_umma_warp_specialized[c_type: DType, c_shape: DimList, a_type: DType, a_shape: DimList, b_type: DType, b_shape: DimList, transpose_b: Bool, mma_shape: IndexList[3], *, config: MatmulConfig[a_type, b_type, c_type, transpose_b, mma_shape], cta_group: Int = 1, num_clc_pipeline_stages: UInt = UInt(2)](c_device: NDBuffer[c_type, 2, origin, c_shape], a_device: NDBuffer[a_type, 2, origin, a_shape], b_device: NDBuffer[b_type, 2, origin, b_shape], ctx: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!