[WIP][SYCL][CUDA] Fix LIT testing with CUDA devices

README.md

@@ -1,23 +1,23 @@
-# Intel Project for LLVM* technology
+# Codeplay CUDA Backend for LLVM SYCL
 
 ## Introduction
 
-Intel staging area for llvm.org contribution.
-Home for Intel LLVM-based projects:
- - SYCL* Compiler and Runtimes - compiler and runtime libraries for SYCL ([https://www.khronos.org/sycl/](https://www.khronos.org/sycl/)). See **sycl** branch.
+Codeplay staging area for CUDA Backend to LLVM SYCL:
+ - SYCL Compiler and Runtimes - compiler and runtime libraries for SYCL ([https://www.khronos.org/sycl/](https://www.khronos.org/sycl/)). See **cuda** branch.
+ - All issues and pull requests should be directed to https://github.com/intel/llvm/.
+ - For an introduction to this project and further details on the CUDA back-end implementation read [this blog post](https://www.codeplay.com/portal/02-03-20-codeplay-contribution-to-dpcpp-brings-sycl-support-for-nvidia-gpus).
+ - For any further information please contact [email protected]
 
 ## License
 See [LICENSE.txt](sycl/LICENSE.TXT) for details.
 
-
 ## Contributing
 See [CONTRIBUTING.md](CONTRIBUTING.md) for details.
 
 ## Sub-projects Documentation
  - SYCL Compiler and Runtimes - See [GetStartedWithSYCLCompiler.md](sycl/doc/GetStartedWithSYCLCompiler.md)
 
-*Other names and brands may be claimed as the property of others.
-
 ## SYCL Extension Proposal Documents
 
 See [sycl/doc/extensions](sycl/doc/extensions)
+

buildbot/configure.py

@@ -11,30 +11,49 @@ def do_configure(args):
     sycl_dir = os.path.join(args.src_dir, "sycl")
     spirv_dir = os.path.join(args.src_dir, "llvm-spirv")
     ocl_header_dir = os.path.join(args.obj_dir, "OpenCL-Headers")
-    icd_loader_lib = ''
+    icd_loader_lib = os.path.join(args.obj_dir, "OpenCL-ICD-Loader", "build")
+    llvm_targets_to_build = 'X86'
+    llvm_enable_projects = 'clang;llvm-spirv;sycl;opencl-aot'
+    libclc_targets_to_build = ''
+    sycl_build_pi_cuda = 'OFF'
+    llvm_enable_assertions = 'ON'
 
     if platform.system() == 'Linux':
-      icd_loader_lib = os.path.join(args.obj_dir, "OpenCL-ICD-Loader", "build", "libOpenCL.so")
+        icd_loader_lib = os.path.join(icd_loader_lib, "libOpenCL.so")
     else:
-      icd_loader_lib = os.path.join(args.obj_dir, "OpenCL-ICD-Loader", "build", "OpenCL.lib")
+        icd_loader_lib = os.path.join(icd_loader_lib, "OpenCL.lib")
+
+    if args.cuda:
+        llvm_targets_to_build += ';NVPTX'
+        llvm_enable_projects += ';libclc'
+        libclc_targets_to_build = 'nvptx64--;nvptx64--nvidiacl'
+        sycl_build_pi_cuda = 'ON'
+
+    if args.assertions:
+        llvm_enable_assertions = 'ON'
 
     install_dir = os.path.join(args.obj_dir, "install")
 
-    cmake_cmd = ["cmake",
-                 "-G", "Ninja",
-                 "-DCMAKE_BUILD_TYPE={}".format(args.build_type),
-                 "-DLLVM_EXTERNAL_PROJECTS=sycl;llvm-spirv;opencl-aot",
-                 "-DLLVM_EXTERNAL_SYCL_SOURCE_DIR={}".format(sycl_dir),
-                 "-DLLVM_EXTERNAL_LLVM_SPIRV_SOURCE_DIR={}".format(spirv_dir),
-                 "-DLLVM_ENABLE_PROJECTS=clang;sycl;llvm-spirv;opencl-aot",
-                 "-DOpenCL_INCLUDE_DIR={}".format(ocl_header_dir),
-                 "-DOpenCL_LIBRARY={}".format(icd_loader_lib),
-                 "-DLLVM_BUILD_TOOLS=ON",
-                 "-DSYCL_ENABLE_WERROR=ON",
-                 "-DLLVM_ENABLE_ASSERTIONS=ON",
-                 "-DCMAKE_INSTALL_PREFIX={}".format(install_dir),
-                 "-DSYCL_INCLUDE_TESTS=ON", # Explicitly include all kinds of SYCL tests.
-                 llvm_dir]
+    cmake_cmd = [
+        "cmake",
+        "-G", "Ninja",
+        "-DCMAKE_BUILD_TYPE={}".format(args.build_type),
+        "-DLLVM_ENABLE_ASSERTIONS={}".format(llvm_enable_assertions),
+        "-DLLVM_TARGETS_TO_BUILD={}".format(llvm_targets_to_build),
+        "-DLLVM_EXTERNAL_PROJECTS=sycl;llvm-spirv;opencl-aot",
+        "-DLLVM_EXTERNAL_SYCL_SOURCE_DIR={}".format(sycl_dir),
+        "-DLLVM_EXTERNAL_LLVM_SPIRV_SOURCE_DIR={}".format(spirv_dir),
+        "-DLLVM_ENABLE_PROJECTS={}".format(llvm_enable_projects),
+        "-DLIBCLC_TARGETS_TO_BUILD={}".format(libclc_targets_to_build),
+        "-DOpenCL_INCLUDE_DIR={}".format(ocl_header_dir),
+        "-DOpenCL_LIBRARY={}".format(icd_loader_lib),
+        "-DSYCL_BUILD_PI_CUDA={}".format(sycl_build_pi_cuda),
+        "-DLLVM_BUILD_TOOLS=ON",
+        "-DSYCL_ENABLE_WERROR=ON",
+        "-DCMAKE_INSTALL_PREFIX={}".format(install_dir),
+        "-DSYCL_INCLUDE_TESTS=ON", # Explicitly include all kinds of SYCL tests.
+        llvm_dir
+    ]
 
     print(cmake_cmd)
 
@@ -63,6 +82,8 @@ def main():
     parser.add_argument("-o", "--obj-dir", metavar="OBJ_DIR", required=True, help="build directory")
     parser.add_argument("-t", "--build-type",
                         metavar="BUILD_TYPE", required=True, help="build type, debug or release")
+    parser.add_argument("--cuda", action='store_true', help="switch from OpenCL to CUDA")
+    parser.add_argument("--assertions", action='store_true', help="build with assertions")
 
     args = parser.parse_args()
 
@@ -74,4 +95,3 @@ def main():
     ret = main()
     exit_code = 0 if ret else 1
     sys.exit(exit_code)
-

buildbot/testlist.cfg

@@ -0,0 +1,45 @@
+:test_accessor
+:test_address_space
+:test_atomic
+:test_buffer
+:test_context
+:test_device
+:test_device_event
+:test_device_selector
+:test_error
+:test_event
+:test_exception_handling
+:test_group
+:test_h_item
+:test_handler
+:test_header
+:test_hierarchical
+:test_id
+:test_image
+:test_invoke
+:test_item
+:test_kernel
+:test_kernel_args
+:test_math_builtin_api
+:test_multi_ptr
+:test_nd_item
+:test_nd_range
+:test_opencl_interop
+:test_platform
+:test_pointers
+:test_program
+:test_queue
+:test_range
+:test_sampler
+:test_scalars
+:test_std_classes
+:test_stream
+:test_vector_alias
+:test_vector_api
+:test_vector_constructors
+:test_vector_load_store
+# Disable test to speedup testing until JIT is optimized
+#:test_vector_operators
+:test_vector_swizzle_assignment
+:test_vector_swizzles
+:test_vector_swizzles_opencl

clang-tools-extra/clang-doc/tool/ClangDocMain.cpp

@@ -268,8 +268,7 @@ int main(int argc, const char **argv) {
   Error = false;
   llvm::sys::Mutex IndexMutex;
   // ExecutorConcurrency is a flag exposed by AllTUsExecution.h
-  llvm::ThreadPool Pool(ExecutorConcurrency == 0 ? llvm::hardware_concurrency()
-                                                 : ExecutorConcurrency);
+  llvm::ThreadPool Pool(llvm::hardware_concurrency(ExecutorConcurrency));
   for (auto &Group : USRToBitcode) {
     Pool.async([&]() {
       std::vector<std::unique_ptr<doc::Info>> Infos;

clang-tools-extra/clang-move/HelperDeclRefGraph.cpp

@@ -27,7 +27,7 @@ void HelperDeclRefGraph::print(raw_ostream &OS) const {
     OS << " (" << N << ") ";
     OS << " calls: ";
     for (auto CI = N->begin(), CE = N->end(); CI != CE; ++CI) {
-      (*CI)->print(OS);
+      CI->Callee->print(OS);
       OS << " (" << CI << ") ";
     }
     OS << '\n';
@@ -48,7 +48,7 @@ void HelperDeclRefGraph::addEdge(const Decl *Caller, const Decl *Callee) {
   // Allocate a new node, mark it as root, and process it's calls.
   CallGraphNode *CallerNode = getOrInsertNode(const_cast<Decl *>(Caller));
   CallGraphNode *CalleeNode = getOrInsertNode(const_cast<Decl *>(Callee));
-  CallerNode->addCallee(CalleeNode);
+  CallerNode->addCallee({CalleeNode, /*CallExpr=*/nullptr});
 }
 
 void HelperDeclRefGraph::dump() const { print(llvm::errs()); }

clang-tools-extra/clang-tidy/ClangTidyCheck.h

@@ -133,8 +133,8 @@ class ClangTidyCheck : public ast_matchers::MatchFinder::MatchCallback {
     /// ``CheckOptions``. If the corresponding key is not present, returns
     /// \p Default.
     template <typename T>
-    typename std::enable_if<std::is_integral<T>::value, T>::type
-    get(StringRef LocalName, T Default) const {
+    std::enable_if_t<std::is_integral<T>::value, T> get(StringRef LocalName,
+                                                        T Default) const {
       std::string Value = get(LocalName, "");
       T Result = Default;
       if (!Value.empty())
@@ -150,7 +150,7 @@ class ClangTidyCheck : public ast_matchers::MatchFinder::MatchCallback {
     /// present, falls back to get global option. If global option is not
     /// present either, returns Default.
     template <typename T>
-    typename std::enable_if<std::is_integral<T>::value, T>::type
+    std::enable_if_t<std::is_integral<T>::value, T>
     getLocalOrGlobal(StringRef LocalName, T Default) const {
       std::string Value = getLocalOrGlobal(LocalName, "");
       T Result = Default;

clang-tools-extra/clang-tidy/bugprone/InfiniteLoopCheck.cpp

@@ -152,6 +152,15 @@ static std::string getCondVarNames(const Stmt *Cond) {
   return Result;
 }
 
+static bool isKnownFalse(const Expr &Cond, const ASTContext &Ctx) {
+  if (Cond.isValueDependent())
+    return false;
+  bool Result = false;
+  if (Cond.EvaluateAsBooleanCondition(Result, Ctx))
+    return !Result;
+  return false;
+}
+
 void InfiniteLoopCheck::registerMatchers(MatchFinder *Finder) {
   const auto LoopCondition = allOf(
       hasCondition(
@@ -170,6 +179,9 @@ void InfiniteLoopCheck::check(const MatchFinder::MatchResult &Result) {
   const auto *LoopStmt = Result.Nodes.getNodeAs<Stmt>("loop-stmt");
   const auto *Func = Result.Nodes.getNodeAs<FunctionDecl>("func");
 
+  if (isKnownFalse(*Cond, *Result.Context))
+    return;
+
   bool ShouldHaveConditionVariables = true;
   if (const auto *While = dyn_cast<WhileStmt>(LoopStmt)) {
     if (const VarDecl *LoopVarDecl = While->getConditionVariable()) {

clang-tools-extra/clang-tidy/misc/CMakeLists.txt

@@ -5,6 +5,7 @@ add_clang_library(clangTidyMiscModule
   MiscTidyModule.cpp
   MisplacedConstCheck.cpp
   NewDeleteOverloadsCheck.cpp
+  NoRecursionCheck.cpp
   NonCopyableObjects.cpp
   NonPrivateMemberVariablesInClassesCheck.cpp
   RedundantExpressionCheck.cpp

clang-tools-extra/clang-tidy/misc/DefinitionsInHeadersCheck.cpp

@@ -134,6 +134,9 @@ void DefinitionsInHeadersCheck::check(const MatchFinder::MatchResult &Result) {
          DiagnosticIDs::Note)
         << FixItHint::CreateInsertion(FD->getInnerLocStart(), "inline ");
   } else if (const auto *VD = dyn_cast<VarDecl>(ND)) {
+    // C++14 variable templates are allowed.
+    if (VD->getDescribedVarTemplate())
+      return;
     // Static data members of a class template are allowed.
     if (VD->getDeclContext()->isDependentContext() && VD->isStaticDataMember())
       return;

clang-tools-extra/clang-tidy/misc/MiscTidyModule.cpp

@@ -12,6 +12,7 @@
 #include "DefinitionsInHeadersCheck.h"
 #include "MisplacedConstCheck.h"
 #include "NewDeleteOverloadsCheck.h"
+#include "NoRecursionCheck.h"
 #include "NonCopyableObjects.h"
 #include "NonPrivateMemberVariablesInClassesCheck.h"
 #include "RedundantExpressionCheck.h"
@@ -35,6 +36,7 @@ class MiscModule : public ClangTidyModule {
     CheckFactories.registerCheck<MisplacedConstCheck>("misc-misplaced-const");
     CheckFactories.registerCheck<NewDeleteOverloadsCheck>(
         "misc-new-delete-overloads");
+    CheckFactories.registerCheck<NoRecursionCheck>("misc-no-recursion");
     CheckFactories.registerCheck<NonCopyableObjectsCheck>(
         "misc-non-copyable-objects");
     CheckFactories.registerCheck<NonPrivateMemberVariablesInClassesCheck>(