0-hero's picture
Add files using upload-large-folder tool
00602c7 verified
module {
tt.func public @triton__0d1d2de(%arg0: !tt.ptr<bf16, 1> {tt.divisibility = 16 : i32}, %arg1: !tt.ptr<f32, 1> {tt.divisibility = 16 : i32}, %arg2: i32 {tt.divisibility = 16 : i32, tt.max_divisibility = 16 : i32}) attributes {noinline = false} {
%c1024_i32 = arith.constant 1024 : i32
%0 = tt.get_program_id x : i32
%1 = arith.muli %0, %c1024_i32 : i32
%2 = tt.make_range {end = 1024 : i32, start = 0 : i32} : tensor<1024xi32>
%3 = tt.splat %1 : (i32) -> tensor<1024xi32>
%4 = arith.addi %3, %2 : tensor<1024xi32>
%5 = tt.splat %arg0 : (!tt.ptr<bf16, 1>) -> tensor<1024x!tt.ptr<bf16, 1>>
%6 = tt.addptr %5, %4 : tensor<1024x!tt.ptr<bf16, 1>>, tensor<1024xi32>
%7 = tt.load %6 {cache = 1 : i32, evict = 1 : i32, isVolatile = false} : tensor<1024xbf16>
%8 = arith.extf %7 : tensor<1024xbf16> to tensor<1024xf32>
%9 = tt.splat %arg1 : (!tt.ptr<f32, 1>) -> tensor<1024x!tt.ptr<f32, 1>>
%10 = tt.addptr %9, %4 : tensor<1024x!tt.ptr<f32, 1>>, tensor<1024xi32>
tt.store %10, %8 {cache = 1 : i32, evict = 1 : i32} : tensor<1024xf32>
tt.return
}
}