[DSE,MSSA] Recognise init_trampoline in getLocForWriteEx

[john.brawn]

Summary

This fixes an instance where MemorySSA-using Dead Store Elimination is failing to do a transformation that the non-MemorySSA-using version does.

[fhahn]

LGTM, thanks! This is in line with what legacy DSE does.

llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp

if (auto *CB = dyn_cast<CallBase>(I)) {
         case LibFunc_strncpy:
         case LibFunc_strcat:
         case LibFunc_strncat:
           return {MemoryLocation(CB->getArgOperand(0))};
         default:
           break;
         }
       }
+      switch (CB->getIntrinsicID()) {
+      case Intrinsic::init_trampoline:
+        return {MemoryLocation(CB->getArgOperand(0))};
+      default:
+        break;
+      }
       return None;
     }
 
     return MemoryLocation::getOrNone(I);
   }
 
   /// Returns true if \p Use completely overwrites \p DefLoc.
   bool isCompleteOverwrite(MemoryLocation DefLoc, Instruction *UseInst) const {

llvm/test/Transforms/DeadStoreElimination/MSSA/simple-todo.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; XFAIL: *
 ; RUN: opt < %s -basic-aa -dse -enable-dse-memoryssa -S | FileCheck %s
 ; RUN: opt < %s -aa-pipeline=basic-aa -passes=dse -enable-dse-memoryssa -S | FileCheck %s
 target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
-declare void @llvm.memset.element.unordered.atomic.p0i8.i64(i8* nocapture, i8, i64, i32) nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
-declare void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
-declare void @llvm.init.trampoline(i8*, i8*, i8*)
-
-; DSE should delete the dead trampoline.
-declare void @test11f()
-define void @test11() {
-; CHECK-LABEL: @test11(
-; CHECK-NEXT:    ret void
-;
-  %storage = alloca [10 x i8], align 16    ; <[10 x i8]*> [#uses=1]
-  %cast = getelementptr [10 x i8], [10 x i8]* %storage, i32 0, i32 0    ; <i8*> [#uses=1]
-  call void @llvm.init.trampoline( i8* %cast, i8* bitcast (void ()* @test11f to i8*), i8* null )    ; <i8*> [#uses=1]
-  ret void
-}
-
-
-declare noalias i8* @malloc(i32)
-
-declare void @unknown_func()
-
 ; Remove redundant store if loaded value is in another block inside a loop.
 define i32 @test31(i1 %c, i32* %p, i32 %i) {
 ; CHECK-LABEL: @test31(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[BB1:%.*]]
 ; CHECK:       bb1:
 ; CHECK-NEXT:    br i1 undef, label [[BB1]], label [[BB2:%.*]]
 ; CHECK:       bb2:

llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll

 ; CHECK-NEXT:    ret double [[TMP_0]]
 ;
   %X_addr = alloca i8*
   store i8* %X, i8** %X_addr
   %tmp.0 = va_arg i8** %X_addr, double
   ret double %tmp.0
 }
 
+; DSE should delete the dead trampoline.
+declare void @test11f()
+define void @test11() {
+; CHECK-LABEL: @test11(
+; CHECK-NEXT:    ret void
+;
+  %storage = alloca [10 x i8], align 16    ; <[10 x i8]*> [#uses=1]
+  %cast = getelementptr [10 x i8], [10 x i8]* %storage, i32 0, i32 0    ; <i8*> [#uses=1]
+  call void @llvm.init.trampoline( i8* %cast, i8* bitcast (void ()* @test11f to i8*), i8* null )    ; <i8*> [#uses=1]
+  ret void
+}
+
 ; %P doesn't escape, the DEAD instructions should be removed.
 declare void @test13f()
 define i32* @test13() {
 ; CHECK-LABEL: @test13(
 ; CHECK-NEXT:    [[PTR:%.*]] = tail call i8* @malloc(i32 4)
 ; CHECK-NEXT:    [[P:%.*]] = bitcast i8* [[PTR]] to i32*
 ; CHECK-NEXT:    call void @test13f()
 ; CHECK-NEXT:    store i32 0, i32* [[P]], align 4