AMDGPU: llvm.amdgcn.interp.mov is a source of divergence

Summary:
While the result is constant across a single primitive, each pixel
shader wave can have pixels from multiple primitives.

Reviewers: tstellarAMD, arsenm

Subscribers: kzhuravl, wdng, yaxunl, llvm-commits, tony-tye

Differential Revision: https://reviews.llvm.org/D27572

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289447 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index e328e0c5a436b7d6a925ffb2087b0bb8ceb19655..a1a3526422427d87077ccfc2e36a78b9edbdc7f9 100644 (file)
--- a/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -241,6 +241,7 @@ static bool isIntrinsicSourceOfDivergence(const TargetIntrinsicInfo *TII,
   case Intrinsic::amdgcn_workitem_id_x:
   case Intrinsic::amdgcn_workitem_id_y:
   case Intrinsic::amdgcn_workitem_id_z:
+  case Intrinsic::amdgcn_interp_mov:
   case Intrinsic::amdgcn_interp_p1:
   case Intrinsic::amdgcn_interp_p2:
   case Intrinsic::amdgcn_mbcnt_hi: