From c564701fbd62bbd47b001564ace2649c19ae92ce Mon Sep 17 00:00:00 2001
From: Yaxun Liu <Yaxun.Liu@amd.com>
Date: Wed, 8 Jun 2016 15:11:21 +0000
Subject: [OpenCL] Fix __builtin_astype for vec3 types.

__builtin_astype does not generate correct LLVM IR for vec3 types. This patch inserts bitcasts to/from vec4 when necessary in addition to generating vector shuffle. Sema and codegen tests are added.

Differential Revision: http://reviews.llvm.org/D20133

llvm-svn: 272153
---
 clang/lib/CodeGen/CGExprScalar.cpp | 74 +++++++++++++++++++-------------------
 1 file changed, 36 insertions(+), 38 deletions(-)

(limited to 'clang/lib/CodeGen/CGExprScalar.cpp')

diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
index 0e49ce6aaf35..67ee517d6acb 100644
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -3382,50 +3382,48 @@ Value *ScalarExprEmitter::VisitBlockExpr(const BlockExpr *block) {
   return CGF.EmitBlockLiteral(block);
 }
 
+// Convert a vec3 to vec4, or vice versa.
+static Value *ConvertVec3AndVec4(CGBuilderTy &Builder, CodeGenFunction &CGF,
+                                 Value *Src, unsigned NumElementsDst) {
+  llvm::Value *UnV = llvm::UndefValue::get(Src->getType());
+  SmallVector<llvm::Constant*, 4> Args;
+  Args.push_back(Builder.getInt32(0));
+  Args.push_back(Builder.getInt32(1));
+  Args.push_back(Builder.getInt32(2));
+  if (NumElementsDst == 4)
+    Args.push_back(llvm::UndefValue::get(CGF.Int32Ty));
+  llvm::Constant *Mask = llvm::ConstantVector::get(Args);
+  return Builder.CreateShuffleVector(Src, UnV, Mask);
+}
+
 Value *ScalarExprEmitter::VisitAsTypeExpr(AsTypeExpr *E) {
   Value *Src  = CGF.EmitScalarExpr(E->getSrcExpr());
   llvm::Type *DstTy = ConvertType(E->getType());
 
-  // Going from vec4->vec3 or vec3->vec4 is a special case and requires
-  // a shuffle vector instead of a bitcast.
   llvm::Type *SrcTy = Src->getType();
-  if (isa<llvm::VectorType>(DstTy) && isa<llvm::VectorType>(SrcTy)) {
-    unsigned numElementsDst = cast<llvm::VectorType>(DstTy)->getNumElements();
-    unsigned numElementsSrc = cast<llvm::VectorType>(SrcTy)->getNumElements();
-    if ((numElementsDst == 3 && numElementsSrc == 4)
-        || (numElementsDst == 4 && numElementsSrc == 3)) {
-
-
-      // In the case of going from int4->float3, a bitcast is needed before
-      // doing a shuffle.
-      llvm::Type *srcElemTy =
-      cast<llvm::VectorType>(SrcTy)->getElementType();
-      llvm::Type *dstElemTy =
-      cast<llvm::VectorType>(DstTy)->getElementType();
-
-      if ((srcElemTy->isIntegerTy() && dstElemTy->isFloatTy())
-          || (srcElemTy->isFloatTy() && dstElemTy->isIntegerTy())) {
-        // Create a float type of the same size as the source or destination.
-        llvm::VectorType *newSrcTy = llvm::VectorType::get(dstElemTy,
-                                                                 numElementsSrc);
-
-        Src = Builder.CreateBitCast(Src, newSrcTy, "astypeCast");
-      }
-
-      llvm::Value *UnV = llvm::UndefValue::get(Src->getType());
-
-      SmallVector<llvm::Constant*, 3> Args;
-      Args.push_back(Builder.getInt32(0));
-      Args.push_back(Builder.getInt32(1));
-      Args.push_back(Builder.getInt32(2));
-
-      if (numElementsDst == 4)
-        Args.push_back(llvm::UndefValue::get(CGF.Int32Ty));
-
-      llvm::Constant *Mask = llvm::ConstantVector::get(Args);
+  unsigned NumElementsSrc = isa<llvm::VectorType>(SrcTy) ?
+    cast<llvm::VectorType>(SrcTy)->getNumElements() : 0;
+  unsigned NumElementsDst = isa<llvm::VectorType>(DstTy) ?
+    cast<llvm::VectorType>(DstTy)->getNumElements() : 0;
+
+  // Going from vec3 to non-vec3 is a special case and requires a shuffle
+  // vector to get a vec4, then a bitcast if the target type is different.
+  if (NumElementsSrc == 3 && NumElementsDst != 3) {
+    Src = ConvertVec3AndVec4(Builder, CGF, Src, 4);
+    Src = Builder.CreateBitCast(Src, DstTy);
+    Src->setName("astype");
+    return Src;
+  }
 
-      return Builder.CreateShuffleVector(Src, UnV, Mask, "astype");
-    }
+  // Going from non-vec3 to vec3 is a special case and requires a bitcast
+  // to vec4 if the original type is not vec4, then a shuffle vector to
+  // get a vec3.
+  if (NumElementsSrc != 3 && NumElementsDst == 3) {
+    auto Vec4Ty = llvm::VectorType::get(DstTy->getVectorElementType(), 4);
+    Src = Builder.CreateBitCast(Src, Vec4Ty);
+    Src = ConvertVec3AndVec4(Builder, CGF, Src, 3);
+    Src->setName("astype");
+    return Src;
   }
 
   return Builder.CreateBitCast(Src, DstTy, "astype");
-- 
cgit v1.2.3