[llvm] [AMDGPU] Support D16 folding for image.sample with multiple extractelement and fptrunc users (PR #141758)

[Harrison Hao via llvm-commits]

================
@@ -269,6 +269,68 @@ simplifyAMDGCNImageIntrinsic(const GCNSubtarget *ST,
                                        ArgTys[0] = User->getType();
                                      });
         }
+      } else {
+        // Only perform D16 folding if every user of the image sample is
+        // an ExtractElementInst immediately followed by an FPTrunc to half.
+        SmallVector<ExtractElementInst *, 4> Extracts;
+        SmallVector<FPTruncInst *, 4> Truncs;
+        bool AllHalfExtracts = true;
+
+        for (User *U : II.users()) {
+          auto *Ext = dyn_cast<ExtractElementInst>(U);
+          if (!Ext || !Ext->hasOneUse()) {
+            AllHalfExtracts = false;
+            break;
+          }
+          auto *Tr = dyn_cast<FPTruncInst>(*Ext->user_begin());
+          if (!Tr || !Tr->getType()->getScalarType()->isHalfTy()) {
+            AllHalfExtracts = false;
+            break;
+          }
+          Extracts.push_back(Ext);
+          Truncs.push_back(Tr);
+        }
+
+        if (AllHalfExtracts && !Extracts.empty()) {
+          auto *VecTy = cast<VectorType>(II.getType());
+          unsigned NElts = VecTy->getElementCount().getKnownMinValue();
+          Type *HalfVecTy =
+              VectorType::get(Type::getHalfTy(II.getContext()), NElts, false);
----------------
harrisonGPU wrote:

Thanks ! I have updated it.

https://github.com/llvm/llvm-project/pull/141758