module {
  tt.func public @triton__0d1de(%arg0: !tt.ptr<f32, 1> {tt.divisibility = 16 : i32}, %arg1: i32 {tt.divisibility = 16 : i32, tt.max_divisibility = 16 : i32}) attributes {noinline = false} {
    %cst = arith.constant dense<0.000000e+00> : tensor<512xf32>
    %cst_0 = arith.constant dense<12865792> : tensor<512xi32>
    %c512_i32 = arith.constant 512 : i32
    %0 = tt.get_program_id x : i32
    %1 = arith.muli %0, %c512_i32 : i32
    %2 = tt.make_range {end = 512 : i32, start = 0 : i32} : tensor<512xi32>
    %3 = tt.splat %1 : (i32) -> tensor<512xi32>
    %4 = arith.addi %3, %2 : tensor<512xi32>
    %5 = arith.cmpi slt, %4, %cst_0 : tensor<512xi32>
    %6 = tt.splat %arg0 : (!tt.ptr<f32, 1>) -> tensor<512x!tt.ptr<f32, 1>>
    %7 = tt.addptr %6, %4 : tensor<512x!tt.ptr<f32, 1>>, tensor<512xi32>
    tt.store %7, %cst, %5 {cache = 1 : i32, evict = 1 : i32} : tensor<512xf32>
    tt.return
  }
}