For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
load_b_tr
def load_b_tr[mma_shape: IndexList[Int(3)], swizzle: Optional[Swizzle] = Optional()](tile: LayoutTensor[address_space=AddressSpace.SHARED, element_layout=tile.element_layout, layout_int_type=tile.layout_int_type, linear_idx_type=tile.linear_idx_type, masked=tile.masked, alignment=tile.alignment]) -> SIMD[tile.dtype, SIMDLength(8)]
Loads the b operand tile for AMD tensor core MFMA instructions using transposed memory access.
This function supports double-rate MFMA shapes (32x32x16, 16x16x32) with bfloat16 input.
The input tile (shape = (mma_shape[2], mma_shape[1])) is split along the K dimension into
two halves of shape (MMA_K//2, MMA_N). Each half is loaded using _load_tr16_b64_warp, which
performs a transposed (column-major) load from shared memory. The resulting two 4-element SIMD
vectors are concatenated into a single SIMD[tile.dtype, 8] vector.
Parameters:
- mma_shape (
IndexList[Int(3)]): The MMA instruction tile shape (only 32x32x16 or 16x16x32 supported). - swizzle (
Optional[Swizzle]): Optional swizzle pattern for bank-conflict-free LDS access.
Args:
- tile (
LayoutTensor[address_space=AddressSpace.SHARED, element_layout=tile.element_layout, layout_int_type=tile.layout_int_type, linear_idx_type=tile.linear_idx_type, masked=tile.masked, alignment=tile.alignment]): ALayoutTensor, residing in shared memory, with shape (mma_shape[2], mma_shape[1]) and dtypeDType.bfloat16.
Returns:
SIMD[tile.dtype, SIMDLength(8)]: SIMD[tile.dtype, 8]: Concatenated transposed SIMD loads from both halves of the tile.