[OpenMP] Code cleanup for NVPTX OpenMP codegen

This patch cleans up private methods for NVPTX OpenMP codegen. It converts private
members to static functions to follow the coding style of CGOpenMPRuntime.cpp and
declutter the header file.

Reviewers: ABataev
Differential Revision: https://reviews.llvm.org/D28124

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@290904 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp b/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
index 451f9e9221ad2ca1310f5330a3636d7ca1a314e2..fe0e2acdfdbf2f6ee100ac1d55a5c37a0079b6fd 100644 (file)
--- a/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ b/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -20,53 +20,64 @@
 using namespace clang;
 using namespace CodeGen;
 
-/// \brief Get the GPU warp size.
-llvm::Value *CGOpenMPRuntimeNVPTX::getNVPTXWarpSize(CodeGenFunction &CGF) {
+namespace {
+enum OpenMPRTLFunctionNVPTX {
+  /// \brief Call to void __kmpc_kernel_init(kmp_int32 omp_handle,
+  /// kmp_int32 thread_limit);
+  OMPRTL_NVPTX__kmpc_kernel_init,
+};
+
+// NVPTX Address space
+enum AddressSpace {
+  AddressSpaceShared = 3,
+};
+} // namespace
+
+/// Get the GPU warp size.
+static llvm::Value *getNVPTXWarpSize(CodeGenFunction &CGF) {
   CGBuilderTy &Bld = CGF.Builder;
   return Bld.CreateCall(
       llvm::Intrinsic::getDeclaration(
-          &CGM.getModule(), llvm::Intrinsic::nvvm_read_ptx_sreg_warpsize),
+          &CGF.CGM.getModule(), llvm::Intrinsic::nvvm_read_ptx_sreg_warpsize),
       llvm::None, "nvptx_warp_size");
 }
 
-/// \brief Get the id of the current thread on the GPU.
-llvm::Value *CGOpenMPRuntimeNVPTX::getNVPTXThreadID(CodeGenFunction &CGF) {
+/// Get the id of the current thread on the GPU.
+static llvm::Value *getNVPTXThreadID(CodeGenFunction &CGF) {
   CGBuilderTy &Bld = CGF.Builder;
   return Bld.CreateCall(
       llvm::Intrinsic::getDeclaration(
-          &CGM.getModule(), llvm::Intrinsic::nvvm_read_ptx_sreg_tid_x),
+          &CGF.CGM.getModule(), llvm::Intrinsic::nvvm_read_ptx_sreg_tid_x),
       llvm::None, "nvptx_tid");
 }
 
-// \brief Get the maximum number of threads in a block of the GPU.
-llvm::Value *CGOpenMPRuntimeNVPTX::getNVPTXNumThreads(CodeGenFunction &CGF) {
+/// Get the maximum number of threads in a block of the GPU.
+static llvm::Value *getNVPTXNumThreads(CodeGenFunction &CGF) {
   CGBuilderTy &Bld = CGF.Builder;
   return Bld.CreateCall(
       llvm::Intrinsic::getDeclaration(
-          &CGM.getModule(), llvm::Intrinsic::nvvm_read_ptx_sreg_ntid_x),
+          &CGF.CGM.getModule(), llvm::Intrinsic::nvvm_read_ptx_sreg_ntid_x),
       llvm::None, "nvptx_num_threads");
 }
 
-/// \brief Get barrier to synchronize all threads in a block.
-void CGOpenMPRuntimeNVPTX::getNVPTXCTABarrier(CodeGenFunction &CGF) {
+/// Get barrier to synchronize all threads in a block.
+static void getNVPTXCTABarrier(CodeGenFunction &CGF) {
   CGBuilderTy &Bld = CGF.Builder;
   Bld.CreateCall(llvm::Intrinsic::getDeclaration(
-      &CGM.getModule(), llvm::Intrinsic::nvvm_barrier0));
+      &CGF.CGM.getModule(), llvm::Intrinsic::nvvm_barrier0));
 }
 
-// \brief Synchronize all GPU threads in a block.
-void CGOpenMPRuntimeNVPTX::syncCTAThreads(CodeGenFunction &CGF) {
-  getNVPTXCTABarrier(CGF);
-}
+/// Synchronize all GPU threads in a block.
+static void syncCTAThreads(CodeGenFunction &CGF) { getNVPTXCTABarrier(CGF); }
 
-/// \brief Get the thread id of the OMP master thread.
+/// Get the thread id of the OMP master thread.
 /// The master thread id is the first thread (lane) of the last warp in the
 /// GPU block.  Warp size is assumed to be some power of 2.
 /// Thread id is 0 indexed.
 /// E.g: If NumThreads is 33, master id is 32.
 ///      If NumThreads is 64, master id is 32.
 ///      If NumThreads is 1024, master id is 992.
-llvm::Value *CGOpenMPRuntimeNVPTX::getMasterThreadID(CodeGenFunction &CGF) {
+static llvm::Value *getMasterThreadID(CodeGenFunction &CGF) {
   CGBuilderTy &Bld = CGF.Builder;
   llvm::Value *NumThreads = getNVPTXNumThreads(CGF);
 
@@ -77,19 +88,6 @@ llvm::Value *CGOpenMPRuntimeNVPTX::getMasterThreadID(CodeGenFunction &CGF) {
                        Bld.CreateNot(Mask), "master_tid");
 }
 
-namespace {
-enum OpenMPRTLFunctionNVPTX {
-  /// \brief Call to void __kmpc_kernel_init(kmp_int32 omp_handle,
-  /// kmp_int32 thread_limit);
-  OMPRTL_NVPTX__kmpc_kernel_init,
-};
-
-// NVPTX Address space
-enum ADDRESS_SPACE {
-  ADDRESS_SPACE_SHARED = 3,
-};
-} // namespace
-
 CGOpenMPRuntimeNVPTX::WorkerFunctionState::WorkerFunctionState(
     CodeGenModule &CGM)
     : WorkerFn(nullptr), CGFI(nullptr) {
@@ -119,14 +117,14 @@ void CGOpenMPRuntimeNVPTX::initializeEnvironment() {
       CGM.getModule(), CGM.Int32Ty, /*isConstant=*/false,
       llvm::GlobalValue::CommonLinkage,
       llvm::Constant::getNullValue(CGM.Int32Ty), "__omp_num_threads", 0,
-      llvm::GlobalVariable::NotThreadLocal, ADDRESS_SPACE_SHARED);
+      llvm::GlobalVariable::NotThreadLocal, AddressSpaceShared);
   ActiveWorkers->setAlignment(DL.getPrefTypeAlignment(CGM.Int32Ty));
 
   WorkID = new llvm::GlobalVariable(
       CGM.getModule(), CGM.Int64Ty, /*isConstant=*/false,
       llvm::GlobalValue::CommonLinkage,
       llvm::Constant::getNullValue(CGM.Int64Ty), "__tgt_work_id", 0,
-      llvm::GlobalVariable::NotThreadLocal, ADDRESS_SPACE_SHARED);
+      llvm::GlobalVariable::NotThreadLocal, AddressSpaceShared);
   WorkID->setAlignment(DL.getPrefTypeAlignment(CGM.Int64Ty));
 }
 

diff --git a/lib/CodeGen/CGOpenMPRuntimeNVPTX.h b/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
index e18d28cdda9f1a7d8bb37dafacf9e294414e6cdf..a33fb27579f65490733b44fcb6030c2d1f45347f 100644 (file)
--- a/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
+++ b/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
@@ -49,38 +49,6 @@ public:
   void emitEntryFooter(CodeGenFunction &CGF, EntryFunctionState &EST);
 
 private:
-  //
-  // NVPTX calls.
-  //
-
-  /// \brief Get the GPU warp size.
-  llvm::Value *getNVPTXWarpSize(CodeGenFunction &CGF);
-
-  /// \brief Get the id of the current thread on the GPU.
-  llvm::Value *getNVPTXThreadID(CodeGenFunction &CGF);
-
-  // \brief Get the maximum number of threads in a block of the GPU.
-  llvm::Value *getNVPTXNumThreads(CodeGenFunction &CGF);
-
-  /// \brief Get barrier to synchronize all threads in a block.
-  void getNVPTXCTABarrier(CodeGenFunction &CGF);
-
-  // \brief Synchronize all GPU threads in a block.
-  void syncCTAThreads(CodeGenFunction &CGF);
-
-  //
-  // OMP calls.
-  //
-
-  /// \brief Get the thread id of the OMP master thread.
-  /// The master thread id is the first thread (lane) of the last warp in the
-  /// GPU block.  Warp size is assumed to be some power of 2.
-  /// Thread id is 0 indexed.
-  /// E.g: If NumThreads is 33, master id is 32.
-  ///      If NumThreads is 64, master id is 32.
-  ///      If NumThreads is 1024, master id is 992.
-  llvm::Value *getMasterThreadID(CodeGenFunction &CGF);
-
   //
   // Private state and methods.
   //