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
ds_read_tr16_b64
def ds_read_tr16_b64[dtype: DType, //](shared_ptr: Pointer[Scalar[dtype], address_space=AddressSpace.SHARED]) -> SIMD[dtype, 4]
Reads a 64-bit LDS transpose block using TR16 layout and returns SIMD[dtype, 4] of 16-bit types.
Notes:
- Only supported on AMD GPUs.
- Maps directly to llvm.amdgcn.ds.read.tr16.b64 intrinsic.
- Result width is fixed to 4 elements of dtype.
Parameters:
- dtype (
DType): Data type of the elements (must be 16-bit type).
Args:
- shared_ptr (
Pointer[Scalar[dtype], address_space=AddressSpace.SHARED]): Pointer to the LDS transpose block.
Returns:
SIMD[dtype, 4]: SIMD[dtype, 4] of 16-bit types.