[Mlir-commits] [mlir] [mlir][gpu] Add `broadcast_lane` op (PR #152808)

[Jianhui Li]

Jianhui-Li wrote:

How is the broadcast first_lane semantics different than gpu.shuffle? 

idx example:
%cst0 = arith.constant 0 : i32
%7, %8 = gpu.shuffle idx %0, %cst0, %width : f32
Broadcasts the value from lane 0 to all lanes.

Can broadcast lane semantics be implemented by gpu.shuffle down + gpu.shffle idx? 

Why the compiler hint has to be part of broadcast op semantics as "all_lane"?   

https://github.com/llvm/llvm-project/pull/152808