[llvm] [DirectX] ForwardHandle needs to check if globals were stored on allocas (PR #151751)

[Justin Bogner via llvm-commits]

================
@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -dxil-forward-handle-accesses  %s | FileCheck %s
+
+%"class.hlsl::RWStructuredBuffer" = type { target("dx.RawBuffer", i32, 1, 0) }
+ at _ZL4dest = internal unnamed_addr global %"class.hlsl::RWStructuredBuffer" poison, align 4
+ at .str = private unnamed_addr constant [5 x i8] c"dest\00", align 1
+
+
+; NOTE: intent of this test is to confirm load target("dx.RawBuffer", i32, 1, 0)
+;       is replaced with call @llvm.dx.resource.getpointer
+define void @CSMain() local_unnamed_addr {
+; CHECK-LABEL: define void @CSMain() local_unnamed_addr {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[AGG_TMP_I1_SROA_0:%.*]] = alloca target("dx.RawBuffer", i32, 1, 0), align 8
+; CHECK-NEXT:    [[TMP0:%.*]] = tail call target("dx.RawBuffer", i32, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_i32_1_0t(i32 0, i32 3, i32 1, i32 0, i1 false, ptr nonnull @.str)
+; CHECK-NEXT:    store target("dx.RawBuffer", i32, 1, 0) [[TMP0]], ptr @_ZL4dest, align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call i32 @llvm.dx.thread.id(i32 0)
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr @_ZL4dest, align 4
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[AGG_TMP_I1_SROA_0]])
+; CHECK-NEXT:    store i32 [[TMP2]], ptr [[AGG_TMP_I1_SROA_0]], align 8
+; CHECK-NEXT:    [[TMP3:%.*]] = tail call noundef nonnull align 4 dereferenceable(4) ptr @llvm.dx.resource.getpointer.p0.tdx.RawBuffer_i32_1_0t(target("dx.RawBuffer", i32, 1, 0) [[TMP0]], i32 [[TMP1]])
+; CHECK-NEXT:    store i32 0, ptr [[TMP3]], align 4
+; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[AGG_TMP_I1_SROA_0]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %agg.tmp.i1.sroa.0 = alloca target("dx.RawBuffer", i32, 1, 0), align 8
+  %0 = tail call target("dx.RawBuffer", i32, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_i32_1_0t(i32 0, i32 3, i32 1, i32 0, i1 false, ptr nonnull @.str)
+  store target("dx.RawBuffer", i32, 1, 0) %0, ptr @_ZL4dest, align 4
+  %1 = tail call i32 @llvm.dx.thread.id(i32 0)
+  %2 = load i32, ptr @_ZL4dest, align 4
+  call void @llvm.lifetime.start.p0(i64 4, ptr nonnull %agg.tmp.i1.sroa.0)
+  store i32 %2, ptr %agg.tmp.i1.sroa.0, align 8
+  %agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0. = load target("dx.RawBuffer", i32, 1, 0), ptr %agg.tmp.i1.sroa.0, align 8
+  %3 = tail call noundef nonnull align 4 dereferenceable(4) ptr @llvm.dx.resource.getpointer.p0.tdx.RawBuffer_i32_1_0t(target("dx.RawBuffer", i32, 1, 0) %agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0., i32 %1)
+  store i32 0, ptr %3, align 4
+  call void @llvm.lifetime.end.p0(i64 4, ptr nonnull %agg.tmp.i1.sroa.0)
+  ret void
+}
----------------
bogner wrote:

This would be easier to follow if we give some of the intermediate values better names. The lifetime markers are also kind of irrelevant here, they can be dropped. Consider:
```llvm
entry:
  %alloca = alloca target("dx.RawBuffer", i32, 1, 0), align 8
  %handle = tail call target("dx.RawBuffer", i32, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_i32_1_0t(i32 0, i32 3, i32 1, i32 0, i1 false, ptr nonnull @name)
  store target("dx.RawBuffer", i32, 1, 0) %handle, ptr @global, align 4
  %val = load i32, ptr @global, align 4
  store i32 %val, ptr %alloca, align 8
  %indirect = load target("dx.RawBuffer", i32, 1, 0), ptr %alloca, align 8
  %buf = tail call noundef nonnull align 4 dereferenceable(4) ptr @llvm.dx.resource.getpointer.p0.tdx.RawBuffer_i32_1_0t(target("dx.RawBuffer", i32, 1, 0) %indirect, i32 0)
  store i32 0, ptr %buf, align 4
  ret void
```

That said, it does scare me a bit that this code doesn't appear to ever actually write to the global itself - the equivalence between the global and the alloca is entirely based on us copying the contents of the global buffer to a local buffer and then writing to that local buffer...

https://github.com/llvm/llvm-project/pull/151751