import triton
import triton.language as tl

from torch._inductor.runtime import triton_helpers, triton_heuristics
from torch._inductor.runtime.triton_helpers import libdevice, math as tl_math
from torch._inductor.runtime.hints import AutotuneHint, ReductionHint, TileHint, DeviceProperties
triton_helpers.set_driver_to_gpu()

@triton_heuristics.pointwise(
    size_hints={'x': 2097152}, 
    filename=__file__,
    triton_meta={'signature': {'in_ptr0': '*bf16', 'out_ptr0': '*bf16', 'xnumel': 'i32', 'XBLOCK': 'constexpr'}, 'device': DeviceProperties(type='cuda', index=0, multi_processor_count=48, cc=121, major=12, regs_per_multiprocessor=65536, max_threads_per_multi_processor=1536, max_threads_per_block=1024, warp_size=32), 'constants': {}, 'native_matmul': False, 'enable_fp_fusion': True, 'launch_pdl': False, 'disable_ftz': False, 'configs': [{(0,): [['tt.divisibility', 16]], (1,): [['tt.divisibility', 16]], (2,): [['tt.divisibility', 16]]}]},
    inductor_meta={'grid_type': 'Grid1D', 'autotune_hints': set(), 'kernel_name': 'triton_poi_fused__to_copy_add_cat_index_index_put_mul_neg_select_split_transpose_view_142', 'mutated_arg_names': [], 'optimize_mem': True, 'no_x_dim': False, 'atomic_add_found': False, 'num_load': 1, 'num_store': 1, 'num_reduction': 0, 'backend_hash': 'BE9F3F68E84A48F2C239366BB10BBF3F0E1498DBECF7F747524E7B7961E82579', 'assert_indirect_indexing': True, 'autotune_local_cache': True, 'autotune_pointwise': True, 'autotune_remote_cache': None, 'force_disable_caches': False, 'dynamic_scale_rblock': True, 'max_autotune': False, 'max_autotune_pointwise': False, 'min_split_scan_rblock': 256, 'spill_threshold': 16, 'store_cubin': False, 'deterministic': False, 'force_filter_reduction_configs': False, 'mix_order_reduction_allow_multi_stages': False, 'are_deterministic_algorithms_enabled': False, 'tiling_scores': {'x': 12582912}},
    min_elem_per_thread=0
)
@triton.jit
def triton_poi_fused__to_copy_add_cat_index_index_put_mul_neg_select_split_transpose_view_142(in_ptr0, out_ptr0, xnumel, XBLOCK : tl.constexpr):
    xnumel = 2097152
    xoffset = tl.program_id(0) * XBLOCK
    xindex = xoffset + tl.arange(0, XBLOCK)[:]
    xmask = tl.full([XBLOCK], True, tl.int1)[:]
    x0 = xindex
    tmp0 = tl.load(in_ptr0 + (54525952 + x0), None).to(tl.float32)
    tl.store(out_ptr0 + (x0), tmp0, None)