[Mlir-commits] [mlir] [MLIR][XeGPU] Remove create tdesc & update offset op from xegpu dialect (PR #182804)

[Nishant Patel]

================
@@ -766,17 +491,6 @@ gpu.func @subgroup_dpas_packed_b(%a : vector<8x16xf16>, %b: vector<8x16x2xf16>)
   gpu.return
 }
 
-// CHECK: gpu.func @subgroup_atomic_rmw(%[[arg0:.*]]: ui64, %[[arg1:.*]]: vector<16xf32>, %[[arg2:.*]]: vector<16xi1>)
-gpu.func @subgroup_atomic_rmw(%src: ui64, %value : vector<16xf32>, %mask : vector<16xi1>) {
----------------
nbpatel wrote:

I think thats a separate PR in itself...I cann do it when I remove offset version of load/store/prefetch ops...will add the tests back then

https://github.com/llvm/llvm-project/pull/182804