diff --git a/llvm/lib/Transforms/Scalar/EarlyCSE.cpp b/llvm/lib/Transforms/Scalar/EarlyCSE.cpp
--- a/llvm/lib/Transforms/Scalar/EarlyCSE.cpp
+++ b/llvm/lib/Transforms/Scalar/EarlyCSE.cpp
@@ -140,7 +140,8 @@
              // correctness. However, it may block many other correct
              // optimizations. Revert this one when we detect the memory
              // accessing kind more precisely.
-             !CI->getFunction()->isPresplitCoroutine();
+             !CI->getFunction()->isPresplitCoroutine() &&
+             !CI->isConvergent();
     }
     return isa<CastInst>(Inst) || isa<UnaryOperator>(Inst) ||
            isa<BinaryOperator>(Inst) || isa<GetElementPtrInst>(Inst) ||
@@ -495,7 +496,8 @@
         // correctness. However, it may block many other correct
         // optimizations. Revert this one when we detect the memory
         // accessing kind more precisely.
-        CI->getFunction()->isPresplitCoroutine())
+        CI->getFunction()->isPresplitCoroutine() ||
+        CI->isConvergent())
       return false;
     return true;
   }
diff --git a/llvm/test/Transforms/EarlyCSE/AMDGPU/convergent-call.ll b/llvm/test/Transforms/EarlyCSE/AMDGPU/convergent-call.ll
--- a/llvm/test/Transforms/EarlyCSE/AMDGPU/convergent-call.ll
+++ b/llvm/test/Transforms/EarlyCSE/AMDGPU/convergent-call.ll
@@ -10,9 +10,10 @@
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[COND]], 0
 ; CHECK-NEXT:    br i1 [[CMP]], label [[IF:%.*]], label [[END:%.*]]
 ; CHECK:       if:
+; CHECK-NEXT:    [[Y1:%.*]] = call i32 @llvm.read_register.i32(metadata [[META0]]) #[[ATTR1]]
 ; CHECK-NEXT:    br label [[END]]
 ; CHECK:       end:
-; CHECK-NEXT:    [[Y2:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[X1]], [[IF]] ]
+; CHECK-NEXT:    [[Y2:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[Y1]], [[IF]] ]
 ; CHECK-NEXT:    [[RET:%.*]] = add i32 [[X1]], [[Y2]]
 ; CHECK-NEXT:    ret i32 [[RET]]
 ;