[OpenCL] Emit enqueued block as kernel

In OpenCL the kernel function and non-kernel function has different calling conventions.
For certain targets they have different argument ABIs. Also kernels have special function
attributes and metadata for runtime to launch them.

The blocks passed to enqueue_kernel is supposed to be executed as kernels. As such,
the block invoke function should be emitted as kernel with proper calling convention and
argument ABI.

This patch emits enqueued block as kernel. If a block is both called directly and passed
to enqueue_kernel, separate functions will be generated.

Differential Revision: https://reviews.llvm.org/D38134

llvm-svn: 315804

1 files changed, 21 insertions, 7 deletions

diff --git a/clang/lib/CodeGen/CGBlocks.cpp b/clang/lib/CodeGen/CGBlocks.cpp
index c4c5541e6a5..d15c66df789 100644
--- a/clang/lib/CodeGen/CGBlocks.cpp
+++ b/clang/lib/CodeGen/CGBlocks.cpp
@@ -738,16 +738,27 @@ void CodeGenFunction::destroyBlockInfos(CGBlockInfo *head) {
 }
 
 /// Emit a block literal expression in the current function.
-llvm::Value *CodeGenFunction::EmitBlockLiteral(const BlockExpr *blockExpr) {
+llvm::Value *CodeGenFunction::EmitBlockLiteral(const BlockExpr *blockExpr,
+                                               llvm::Function **InvokeF) {
   // If the block has no captures, we won't have a pre-computed
   // layout for it.
   if (!blockExpr->getBlockDecl()->hasCaptures()) {
-    if (llvm::Constant *Block = CGM.getAddrOfGlobalBlockIfEmitted(blockExpr))
+    // The block literal is emitted as a global variable, and the block invoke
+    // function has to be extracted from its initializer.
+    if (llvm::Constant *Block = CGM.getAddrOfGlobalBlockIfEmitted(blockExpr)) {
+      if (InvokeF) {
+        auto *GV = cast<llvm::GlobalVariable>(
+            cast<llvm::Constant>(Block)->stripPointerCasts());
+        auto *BlockInit = cast<llvm::ConstantStruct>(GV->getInitializer());
+        *InvokeF = cast<llvm::Function>(
+            BlockInit->getAggregateElement(2)->stripPointerCasts());
+      }
       return Block;
+    }
     CGBlockInfo blockInfo(blockExpr->getBlockDecl(), CurFn->getName());
     computeBlockInfo(CGM, this, blockInfo);
     blockInfo.BlockExpression = blockExpr;
-    return EmitBlockLiteral(blockInfo);
+    return EmitBlockLiteral(blockInfo, InvokeF);
   }
 
   // Find the block info for this block and take ownership of it.
@@ -756,10 +767,11 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const BlockExpr *blockExpr) {
                                          blockExpr->getBlockDecl()));
 
   blockInfo->BlockExpression = blockExpr;
-  return EmitBlockLiteral(*blockInfo);
+  return EmitBlockLiteral(*blockInfo, InvokeF);
 }
 
-llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
+llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo,
+                                               llvm::Function **InvokeF) {
   bool IsOpenCL = CGM.getContext().getLangOpts().OpenCL;
   auto GenVoidPtrTy =
       IsOpenCL ? CGM.getOpenCLRuntime().getGenericVoidPointerType() : VoidPtrTy;
@@ -768,9 +780,11 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
       CGM.getTarget().getPointerWidth(GenVoidPtrAddr) / 8);
   // Using the computed layout, generate the actual block function.
   bool isLambdaConv = blockInfo.getBlockDecl()->isConversionFromLambda();
-  llvm::Constant *blockFn = CodeGenFunction(CGM, true).GenerateBlockFunction(
+  auto *InvokeFn = CodeGenFunction(CGM, true).GenerateBlockFunction(
       CurGD, blockInfo, LocalDeclMap, isLambdaConv, blockInfo.CanBeGlobal);
-  blockFn = llvm::ConstantExpr::getPointerCast(blockFn, GenVoidPtrTy);
+  if (InvokeF)
+    *InvokeF = InvokeFn;
+  auto *blockFn = llvm::ConstantExpr::getPointerCast(InvokeFn, GenVoidPtrTy);
 
   // If there is nothing to capture, we can emit this as a global block.
   if (blockInfo.CanBeGlobal)