[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

@@ -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)) {
+  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;
+  }
 
-      // 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);
-
-      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");

clang/test/CodeGenOpenCL/as_type.cl

@@ -0,0 +1,68 @@
+// RUN: %clang_cc1 %s -emit-llvm -triple spir-unknown-unknown -o - | FileCheck %s
+
+typedef __attribute__(( ext_vector_type(3) )) char char3;
+typedef __attribute__(( ext_vector_type(4) )) char char4;
+typedef __attribute__(( ext_vector_type(16) )) char char16;
+typedef __attribute__(( ext_vector_type(3) )) int int3;
+
+//CHECK: define spir_func <3 x i8> @f1(<4 x i8> %[[x:.*]])
+//CHECK: %[[astype:.*]] = shufflevector <4 x i8> %[[x]], <4 x i8> undef, <3 x i32> <i32 0, i32 1, i32 2>
+//CHECK: ret <3 x i8> %[[astype]]
+char3 f1(char4 x) {
+  return  __builtin_astype(x, char3);
+}
+
+//CHECK: define spir_func <4 x i8> @f2(<3 x i8> %[[x:.*]])
+//CHECK: %[[astype:.*]] = shufflevector <3 x i8> %[[x]], <3 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
+//CHECK: ret <4 x i8> %[[astype]]
+char4 f2(char3 x) {
+  return __builtin_astype(x, char4);
+}
+
+//CHECK: define spir_func <3 x i8> @f3(i32 %[[x:.*]])
+//CHECK: %[[cast:.*]] = bitcast i32 %[[x]] to <4 x i8>
+//CHECK: %[[astype:.*]] = shufflevector <4 x i8> %[[cast]], <4 x i8> undef, <3 x i32> <i32 0, i32 1, i32 2>
+//CHECK: ret <3 x i8> %[[astype]]
+char3 f3(int x) {
+  return __builtin_astype(x, char3);
+}
+
+//CHECK: define spir_func <4 x i8> @f4(i32 %[[x:.*]])
+//CHECK: %[[astype:.*]] = bitcast i32 %[[x]] to <4 x i8>
+//CHECK-NOT: shufflevector
+//CHECK: ret <4 x i8> %[[astype]]
+char4 f4(int x) {
+  return __builtin_astype(x, char4);
+}
+
+//CHECK: define spir_func i32 @f5(<3 x i8> %[[x:.*]])
+//CHECK: %[[shuffle:.*]] = shufflevector <3 x i8> %[[x]], <3 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
+//CHECK: %[[astype:.*]] = bitcast <4 x i8> %[[shuffle]] to i32
+//CHECK: ret i32 %[[astype]]
+int f5(char3 x) {
+  return __builtin_astype(x, int);
+}
+
+//CHECK: define spir_func i32 @f6(<4 x i8> %[[x:.*]])
+//CHECK: %[[astype]] = bitcast <4 x i8> %[[x]] to i32
+//CHECK-NOT: shufflevector
+//CHECK: ret i32 %[[astype]]
+int f6(char4 x) {
+  return __builtin_astype(x, int);
+}
+
+//CHECK: define spir_func <3 x i8> @f7(<3 x i8> %[[x:.*]])
+//CHECK-NOT: bitcast
+//CHECK-NOT: shufflevector
+//CHECK: ret <3 x i8> %[[x]]
+char3 f7(char3 x) {
+  return __builtin_astype(x, char3);
+}
+
+//CHECK: define spir_func <3 x i32> @f8(<16 x i8> %[[x:.*]])
+//CHECK: %[[cast:.*]] = bitcast <16 x i8> %[[x]] to <4 x i32>
+//CHECK: %[[astype:.*]] = shufflevector <4 x i32> %[[cast]], <4 x i32> undef, <3 x i32> <i32 0, i32 1, i32 2>
+//CHECK: ret <3 x i32> %[[astype]]
+int3 f8(char16 x) {
+  return __builtin_astype(x, int3);
+}

clang/test/SemaOpenCL/as_type.cl

@@ -0,0 +1,13 @@
+// RUN: %clang_cc1 %s -emit-llvm -triple spir-unknown-unknown -o - -verify -fsyntax-only
+
+typedef __attribute__(( ext_vector_type(3) )) char char3;
+typedef __attribute__(( ext_vector_type(16) )) char char16;
+
+char3 f1(char16 x) {
+  return  __builtin_astype(x, char3); // expected-error{{invalid reinterpretation: sizes of 'char3' (vector of 3 'char' values) and 'char16' (vector of 16 'char' values) must match}}
+}
+
+char16 f3(int x) {
+  return __builtin_astype(x, char16); // expected-error{{invalid reinterpretation: sizes of 'char16' (vector of 16 'char' values) and 'int' must match}}
+}
+