[libomptarget][nfc] Introduce SHARED, ALIGN macros

[JonChesterfield]

Summary

[libomptarget][nfc] Introduce SHARED, ALIGN macros
Move remaining cuda attributes behind such macros

[JonChesterfield]

• Drop nvptx suffix from filenames

[JonChesterfield]

Updated with a diff intended for D71073, will discard and try again.

openmp/libomptarget/deviceRTLs/common/omptarget.h

-//===---- omptarget-nvptx.h - NVPTX OpenMP GPU initialization ---- CUDA -*-===//
+//===---- omptarget.h - OpenMP GPU initialization ---------------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the declarations of all library macros, types,
 // and functions.
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef __OMPTARGET_NVPTX_H
-#define __OMPTARGET_NVPTX_H
+#ifndef OMPTARGET_H
+#define OMPTARGET_H
 
 // std includes
 #include <inttypes.h>
 #include <math.h>
 #include <stdlib.h>
 
 // local includes
 #include "target_impl.h"

 INLINE omptarget_nvptx_TaskDescr *
 getMyTopTaskDescriptor(bool isSPMDExecutionMode);
 INLINE omptarget_nvptx_TaskDescr *getMyTopTaskDescriptor(int globalThreadId);
 
 ////////////////////////////////////////////////////////////////////////////////
 // inlined implementation
 ////////////////////////////////////////////////////////////////////////////////
 
-#include "omptarget-nvptxi.h"
+#include "common/omptargeti.h"
 
 #endif

openmp/libomptarget/deviceRTLs/common/omptargeti.h

-//===---- omptarget-nvptxi.h - NVPTX OpenMP GPU initialization --- CUDA -*-===//
+//===---- omptargeti.h - OpenMP GPU initialization --------------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the declarations of all library macros, types,

openmp/libomptarget/deviceRTLs/common/src/loop.cu

 //===------------ loop.cu - NVPTX OpenMP loop constructs --------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the implementation of the KMPC interface
 // for the loop construct plus other worksharing constructs that use the same
 // interface as loops.
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "target_impl.h"
 
 ////////////////////////////////////////////////////////////////////////////////
 ////////////////////////////////////////////////////////////////////////////////
 // template class that encapsulate all the helper functions
 //
 // T is loop iteration type (32 | 64)  (unsigned | signed)
 // ST is the signed version of T

openmp/libomptarget/deviceRTLs/common/src/omptarget.cu

-//===--- omptarget-nvptx.cu - NVPTX OpenMP GPU initialization ---- CUDA -*-===//
+//===--- omptarget.cu - OpenMP GPU initialization ---------------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the initialization code for the GPU
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "target_impl.h"
 
 ////////////////////////////////////////////////////////////////////////////////
 // global data tables
 ////////////////////////////////////////////////////////////////////////////////
 
 extern __device__
     omptarget_nvptx_Queue<omptarget_nvptx_ThreadPrivateContext, OMP_STATE_COUNT>

openmp/libomptarget/deviceRTLs/common/src/task.cu

 //       task+sizeof(klegacy_TaskDescr)
 //        * private data *
 //    - shared: X. Accessed by shared ptr in klegacy_TaskDescr
 //        * pointer table to shared variables *
 //    - end
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 
 EXTERN kmp_TaskDescr *__kmpc_omp_task_alloc(
     kmp_Ident *loc,     // unused
     uint32_t global_tid, // unused
     int32_t flag, // unused (because in our impl, all are immediately exec
     size_t sizeOfTaskInclPrivate, size_t sizeOfSharedTable,
     kmp_TaskFctPtr taskSub) {
   PRINT(LD_IO,

openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt

if(LIBOMPTARGET_DEP_CUDA_FOUND)
   set(CUDA_PROPAGATE_HOST_FLAGS OFF)
 
   set(cuda_src_files
       ${devicertl_common_directory}/src/cancel.cu
       ${devicertl_common_directory}/src/critical.cu
       src/data_sharing.cu
       src/libcall.cu
       ${devicertl_common_directory}/src/loop.cu
-      src/omptarget-nvptx.cu
+      ${devicertl_common_directory}/src/omptarget.cu
       src/parallel.cu
       src/reduction.cu
       src/support.cu
       src/sync.cu
       ${devicertl_common_directory}/src/task.cu
   )
 
   set(omp_data_objects src/omp_data.cu)

openmp/libomptarget/deviceRTLs/nvptx/src/data_sharing.cu

 //===----- data_sharing.cu - NVPTX OpenMP debug utilities -------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the implementation of data sharing environments/
 //
 //===----------------------------------------------------------------------===//
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "target_impl.h"
 #include <stdio.h>
 
 // Return true if this is the first active thread in the warp.
 INLINE static bool IsWarpMasterActiveThread() {
   unsigned long long Mask = __kmpc_impl_activemask();
   unsigned long long ShNum = WARPSIZE - (GetThreadIdInBlock() % WARPSIZE);
   unsigned long long Sh = Mask << ShNum;

openmp/libomptarget/deviceRTLs/nvptx/src/libcall.cu

 //===------------ libcall.cu - NVPTX OpenMP user calls ----------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements the OpenMP runtime functions that can be
 // invoked by the user in an OpenMP region
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 
 // Timer precision is 1ns
 #define TIMER_PRECISION ((double)1E-9)
 
 EXTERN double omp_get_wtick(void) {
   PRINT(LD_IO, "omp_get_wtick() returns %g\n", TIMER_PRECISION);
   return TIMER_PRECISION;
 }

openmp/libomptarget/deviceRTLs/nvptx/src/omp_data.cu

 //===------------ omp_data.cu - NVPTX OpenMP GPU objects --------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the data objects used on the GPU device.
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "common/device_environment.h"
 
 ////////////////////////////////////////////////////////////////////////////////
 // global device environment
 ////////////////////////////////////////////////////////////////////////////////
 
 __device__ omptarget_device_environmentTy omptarget_device_environment;
 

openmp/libomptarget/deviceRTLs/nvptx/src/parallel.cu

 //    region, these non-included threads will cycle through the
 //    syncthread A. Thus they must preserve their current threadId that
 //    is larger than thread in team.
 //
 //    To make a long story short...
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "target_impl.h"
 
 typedef struct ConvergentSimdJob {
   omptarget_nvptx_TaskDescr taskDescr;
   omptarget_nvptx_TaskDescr *convHeadTaskDescr;
   uint16_t slimForNextSimd;
 } ConvergentSimdJob;
 

openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu

 //===---- reduction.cu - NVPTX OpenMP reduction implementation ---- CUDA
 //-*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains the implementation of reduction with KMPC interface.
 //
 //===----------------------------------------------------------------------===//
 
 #include <complex.h>
 #include <stdio.h>
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "target_impl.h"
 
 EXTERN
 void __kmpc_nvptx_end_reduce(int32_t global_tid) {}
 
 EXTERN
 void __kmpc_nvptx_end_reduce_nowait(int32_t global_tid) {}
 

openmp/libomptarget/deviceRTLs/nvptx/src/support.cu

 //===--------- support.cu - NVPTX OpenMP support functions ------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // Wrapper implementation to some functions natively supported by the GPU.
 //
 //===----------------------------------------------------------------------===//
 
 #include "common/support.h"
 #include "common/debug.h"
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 
 ////////////////////////////////////////////////////////////////////////////////
 // Execution Parameters
 ////////////////////////////////////////////////////////////////////////////////
 
 DEVICE void setExecutionParameters(ExecutionMode EMode, RuntimeMode RMode) {
   execution_param = EMode;
   execution_param |= RMode;

openmp/libomptarget/deviceRTLs/nvptx/src/sync.cu

 //===------------ sync.h - NVPTX OpenMP synchronizations --------- CUDA -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // Include all synchronization.
 //
 //===----------------------------------------------------------------------===//
 
-#include "omptarget-nvptx.h"
+#include "common/omptarget.h"
 #include "target_impl.h"
 
 ////////////////////////////////////////////////////////////////////////////////
 // KMP Ordered calls
 ////////////////////////////////////////////////////////////////////////////////
 
 EXTERN void __kmpc_ordered(kmp_Ident *loc, int32_t tid) {
   PRINT0(LD_IO, "call kmpc_ordered\n");