[OpenMP][libomptarget] Remove unused virtual functions in GenericKernelTy

The virtual functions getDefaultNumBlocks and getDefaultNumThreads from the kernels are only forwarding the call to the generic device's ones. This patch removes those two functions from the kernels (and their derived ones). Now calls are made to the device's functions directly. Differential Revision: https://reviews.llvm.org/D156905

Author: kevinsala

openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp

@@ -469,16 +469,6 @@ struct AMDGPUKernelTy : public GenericKernelTy {
  KernelArgsTy &KernelArgs, uint32_t NumThreads,
  uint64_t NumBlocks) const override;
 
- /// The default number of blocks is common to the whole device.
- uint32_t getDefaultNumBlocks(GenericDeviceTy &GenericDevice) const override {
- return GenericDevice.getDefaultNumBlocks();
- }
-
- /// The default number of threads is common to the whole device.
- uint32_t getDefaultNumThreads(GenericDeviceTy &GenericDevice) const override {
- return GenericDevice.getDefaultNumThreads();
- }
-
  /// Get group and private segment kernel size.
  uint32_t getGroupSize() const { return GroupSize; }
  uint32_t getPrivateSize() const { return PrivateSize; }

openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp

@@ -227,8 +227,7 @@ void AsyncInfoWrapperTy::finalize(Error &Err) {
 
 Error GenericKernelTy::init(GenericDeviceTy &GenericDevice,
  DeviceImageTy &Image) {
- PreferredNumThreads = getDefaultNumThreads(GenericDevice);
-
+ PreferredNumThreads = GenericDevice.getDefaultNumThreads();
  MaxNumThreads = GenericDevice.getThreadLimit();
 
  return initImpl(GenericDevice, Image);
@@ -318,7 +317,7 @@ uint64_t GenericKernelTy::getNumBlocks(GenericDeviceTy &GenericDevice,
  return std::min(NumTeamsClause[0], GenericDevice.getBlockLimit());
  }
 
- uint64_t DefaultNumBlocks = getDefaultNumBlocks(GenericDevice);
+ uint64_t DefaultNumBlocks = GenericDevice.getDefaultNumBlocks();
  uint64_t TripCountNumBlocks = std::numeric_limits<uint64_t>::max();
  if (LoopTripCount > 0) {
  if (isSPMDMode()) {

openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.h

@@ -318,10 +318,6 @@ struct GenericKernelTy {
  llvm::SmallVectorImpl<void *> &Args,
  llvm::SmallVectorImpl<void *> &Ptrs) const;
 
- /// Get the default number of threads and blocks for the kernel.
- virtual uint32_t getDefaultNumThreads(GenericDeviceTy &Device) const = 0;
- virtual uint32_t getDefaultNumBlocks(GenericDeviceTy &Device) const = 0;
-
  /// Get the number of threads and blocks for the kernel based on the
  /// user-defined threads and block clauses.
  uint32_t getNumThreads(GenericDeviceTy &GenericDevice,

openmp/libomptarget/plugins-nextgen/cuda/src/rtl.cpp

@@ -66,16 +66,6 @@ struct CUDAKernelTy : public GenericKernelTy {
  uint64_t NumBlocks, KernelArgsTy &KernelArgs, void *Args,
  AsyncInfoWrapperTy &AsyncInfoWrapper) const override;
 
- /// The default number of blocks is common to the whole device.
- uint32_t getDefaultNumBlocks(GenericDeviceTy &GenericDevice) const override {
- return GenericDevice.getDefaultNumBlocks();
- }
-
- /// The default number of threads is common to the whole device.
- uint32_t getDefaultNumThreads(GenericDeviceTy &GenericDevice) const override {
- return GenericDevice.getDefaultNumThreads();
- }
-
 private:
  /// The CUDA kernel function to execute.
  CUfunction Func;

openmp/libomptarget/plugins-nextgen/generic-elf-64bit/src/rtl.cpp

@@ -84,10 +84,6 @@ struct GenELF64KernelTy : public GenericKernelTy {
  return Plugin::success();
  }
 
- /// Get the default number of blocks and threads for the kernel.
- uint32_t getDefaultNumBlocks(GenericDeviceTy &) const override { return 1; }
- uint32_t getDefaultNumThreads(GenericDeviceTy &) const override { return 1; }
-
 private:
  /// The kernel function to execute.
  void (*Func)(void);