Update attention fusion to support SDXL Clip2 pattern

[turneram]

@25 = gpu::code_object[code_object=5232,symbol_name=mlir_reshape_transpose_reshape_reshape_transpose_slice_reshape_transpose_dot,global=46080,local=256,](@23,@19,@24) -> half_type, {20, 77, 77}, {5929, 77, 1}, target_id=0
@26 = load[offset=591360,end=828520](@1) -> half_type, {1, 20, 77, 77}, {118580, 5929, 77, 1}, target_id=0
@27 = reshape_lazy[dims={1, 20, 77, 77}](@25) -> half_type, {1, 20, 77, 77}, {118580, 5929, 77, 1}, target_id=0
@28 = multibroadcast[out_lens={1, 20, 77, 77},out_dyn_dims={}](@20) -> float_type, {1, 20, 77, 77}, {5929, 0, 77, 1}, target_id=0
@29 = gpu::code_object[code_object=6056,symbol_name=convert_add_reduce_max_sub_exp_reduce_sum_div_convert_kernel,global=197120,local=128,](@27,@28,@26) -> half_type, {1, 20, 77, 77}, {118580, 5929, 77, 1}, target_id=0
@30 = load[offset=828528,end=1025648](@1) -> half_type, {1, 20, 77, 64}, {98560, 4928, 64, 1}, target_id=0
@31 = gpu::code_object[code_object=5656,symbol_name=mlir_reshape_transpose_slice_dot,global=25600,local=256,](@29,@19,@30) -> half_type, {1, 20, 77, 64}, {98560, 4928, 64, 1}, target_id=0