Merge remote-tracking branch 'intel/sycl' into optimize-build

Author: bader

.github/workflows/sycl_linux_build_and_test.yml

@@ -40,7 +40,7 @@ on:
       build_configure_extra_args:
         type: string
         required: false
-        default: "--hip --hip-amd-arch=gfx906 --cuda"
+        default: "--hip --cuda"
       build_artifact_suffix:
         type: string
         required: true
@@ -86,7 +86,7 @@ jobs:
               \"build_cache_root\":\"/__w/\",
               \"build_cache_suffix\":\"default\",
               \"build_cache_size\":\"2G\",
-              \"build_configure_extra_args\":\"--hip --hip-amd-arch=gfx906 --cuda\",
+              \"build_configure_extra_args\":\"--hip --cuda\",
               \"build_artifact_suffix\":\"default\",
               \"build_upload_artifact\":\"false\",
               \"intel_drivers_image\":\"ghcr.io/intel/llvm/ubuntu2004_intel_drivers:latest\",

.github/workflows/sycl_nightly.yml

@@ -70,5 +70,5 @@ jobs:
       build_cache_root: "/__w/"
       build_cache_suffix: new_pm
       build_artifact_suffix: new_pm
-      build_configure_extra_args: '--hip --hip-amd-arch=gfx906 --cuda --cmake-opt=-DLLVM_ENABLE_NEW_PASS_MANAGER=ON'
+      build_configure_extra_args: '--hip --cuda --cmake-opt=-DLLVM_ENABLE_NEW_PASS_MANAGER=ON'
       lts_config: "hip_amdgpu;ocl_x64"

.github/workflows/sycl_stale_issues.yml

@@ -17,3 +17,5 @@ jobs:
         exempt-issue-labels: 'confirmed,hip,cuda,enhancement,help wanted,upstream'
         stale-issue-label: 'stale'
         exempt-all-issue-assignees: true
+        operations-per-run: 200
+

.github/workflows/sycl_windows_build_and_test.yml

@@ -17,6 +17,7 @@ jobs:
       run: |
         choco install -y cuda --version 11.6.0.51123
         choco install -y ninja
+        choco install -y sccache --version 0.2.15
         refreshenv
         echo CUDA_PATH=%CUDA_PATH%
         echo CUDA_PATH=%CUDA_PATH% >> %GITHUB_ENV%
@@ -49,6 +50,8 @@ jobs:
           --cmake-opt="-DCMAKE_C_COMPILER=cl" ^
           --cmake-opt="-DCMAKE_CXX_COMPILER=cl" ^
           --cmake-opt="-DCMAKE_INSTALL_PREFIX=%GITHUB_WORKSPACE%\install" ^
+          --cmake-opt="-DCMAKE_CXX_COMPILER_LAUNCHER=sccache" ^
+          --cmake-opt="-DCMAKE_C_COMPILER_LAUNCHER=sccache" ^
           --cuda
     - name: Build
       shell: cmd
@@ -64,4 +67,4 @@ jobs:
       uses: actions/upload-artifact@v2
       with:
         name: sycl_windows_default
-        path: install/**/*
+        path: install/**/*

README.md

@@ -28,3 +28,86 @@ See [LICENSE.txt](sycl/LICENSE.TXT) for details.
 See [CONTRIBUTING.md](CONTRIBUTING.md) for details.
 
 *\*Other names and brands may be claimed as the property of others.*
+
+This is an example work-flow and configuration to get and build the LLVM source:
+
+1. Checkout LLVM (including related sub-projects like Clang):
+
+     * ``git clone https://github.com/llvm/llvm-project.git``
+
+     * Or, on windows, ``git clone --config core.autocrlf=false
+    https://github.com/llvm/llvm-project.git``
+
+2. Configure and build LLVM and Clang:
+
+     * ``cd llvm-project``
+
+     * ``cmake -S llvm -B build -G <generator> [options]``
+
+        Some common build system generators are:
+
+        * ``Ninja`` --- for generating [Ninja](https://ninja-build.org)
+          build files. Most llvm developers use Ninja.
+        * ``Unix Makefiles`` --- for generating make-compatible parallel makefiles.
+        * ``Visual Studio`` --- for generating Visual Studio projects and
+          solutions.
+        * ``Xcode`` --- for generating Xcode projects.
+
+        Some common options:
+
+        * ``-DLLVM_ENABLE_PROJECTS='...'`` and ``-DLLVM_ENABLE_RUNTIMES='...'`` ---
+          semicolon-separated list of the LLVM sub-projects and runtimes you'd like to
+          additionally build. ``LLVM_ENABLE_PROJECTS`` can include any of: clang,
+          clang-tools-extra, cross-project-tests, flang, libc, libclc, lld, lldb,
+          mlir, openmp, polly, or pstl. ``LLVM_ENABLE_RUNTIMES`` can include any of
+          libcxx, libcxxabi, libunwind, compiler-rt, libc or openmp. Some runtime
+          projects can be specified either in ``LLVM_ENABLE_PROJECTS`` or in
+          ``LLVM_ENABLE_RUNTIMES``.
+
+          For example, to build LLVM, Clang, libcxx, and libcxxabi, use
+          ``-DLLVM_ENABLE_PROJECTS="clang" -DLLVM_ENABLE_RUNTIMES="libcxx;libcxxabi"``.
+
+        * ``-DCMAKE_INSTALL_PREFIX=directory`` --- Specify for *directory* the full
+          path name of where you want the LLVM tools and libraries to be installed
+          (default ``/usr/local``). Be careful if you install runtime libraries: if
+          your system uses those provided by LLVM (like libc++ or libc++abi), you
+          must not overwrite your system's copy of those libraries, since that
+          could render your system unusable. In general, using something like
+          ``/usr`` is not advised, but ``/usr/local`` is fine.
+
+        * ``-DCMAKE_BUILD_TYPE=type`` --- Valid options for *type* are Debug,
+          Release, RelWithDebInfo, and MinSizeRel. Default is Debug.
+
+        * ``-DLLVM_ENABLE_ASSERTIONS=On`` --- Compile with assertion checks enabled
+          (default is Yes for Debug builds, No for all other build types).
+
+      * ``cmake --build build [-- [options] <target>]`` or your build system specified above
+        directly.
+
+        * The default target (i.e. ``ninja`` or ``make``) will build all of LLVM.
+
+        * The ``check-all`` target (i.e. ``ninja check-all``) will run the
+          regression tests to ensure everything is in working order.
+
+        * CMake will generate targets for each tool and library, and most
+          LLVM sub-projects generate their own ``check-<project>`` target.
+
+        * Running a serial build will be **slow**.  To improve speed, try running a
+          parallel build.  That's done by default in Ninja; for ``make``, use the option
+          ``-j NNN``, where ``NNN`` is the number of parallel jobs, e.g. the number of
+          CPUs you have.
+
+      * For more information see [CMake](https://llvm.org/docs/CMake.html)
+
+Consult the
+[Getting Started with LLVM](https://llvm.org/docs/GettingStarted.html#getting-started-with-llvm)
+page for detailed information on configuring and compiling LLVM. You can visit
+[Directory Layout](https://llvm.org/docs/GettingStarted.html#directory-layout)
+to learn about the layout of the source code tree.
+
+## Getting in touch
+
+Join [LLVM Discourse forums](https://discourse.llvm.org/), [discord chat](https://discord.gg/xS7Z362) or #llvm IRC channel on [OFTC](https://oftc.net/).
+
+The LLVM project has adopted a [code of conduct](https://llvm.org/docs/CodeOfConduct.html) for
+participants to all modes of communication within the project.

bolt/docs/Heatmaps.md

@@ -23,11 +23,10 @@ $ perf record -e cycles:u -j any,u [-p PID|-a] -- sleep <interval>
 Note that at the moment running with LBR (`-j any,u` or `-b`) is
 a requirement.
 
-Once the run is complete, and `perf.data` is generated, run BOLT in
-a heatmap mode:
+Once the run is complete, and `perf.data` is generated, run llvm-bolt-heatmap:
 
 ```bash
-$ llvm-bolt heatmap -p perf.data <executable>
+$ llvm-bolt-heatmap -p perf.data <executable>
 ```
 
 By default the heatmap will be dumped to *stdout*. You can change it

bolt/docs/OptimizingClang.md

@@ -41,7 +41,7 @@ Collecting accurate profile requires running `perf` on a hardware that
 implements taken branch sampling (`-b/-j` flag). For that reason, it may not be possible to
 collect the accurate profile in a virtualized environment, e.g. in the cloud.
 We do support regular sampling profiles, but the performance
-improvements are expected to be more modest. 
+improvements are expected to be more modest.
 
 ```bash
 $ mkdir ${TOPLEV}/stage3
@@ -211,7 +211,8 @@ $ cd ${TOPLEV}/stage1
 $ cmake -G Ninja ${TOPLEV}/llvm-project/llvm -DLLVM_TARGETS_TO_BUILD=X86 \
       -DCMAKE_BUILD_TYPE=Release \
       -DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++ -DCMAKE_ASM_COMPILER=gcc \
-      -DLLVM_ENABLE_PROJECTS="clang;lld;compiler-rt" \
+      -DLLVM_ENABLE_PROJECTS="clang;lld" \
+      -DLLVM_ENABLE_RUNTIMES="compiler-rt" \
       -DCOMPILER_RT_BUILD_SANITIZERS=OFF -DCOMPILER_RT_BUILD_XRAY=OFF \
       -DCOMPILER_RT_BUILD_LIBFUZZER=OFF \
       -DCMAKE_INSTALL_PREFIX=${TOPLEV}/stage1/install

bolt/include/bolt/Passes/BinaryPasses.h

@@ -295,6 +295,16 @@ class ShortenInstructions : public BinaryFunctionPass {
 
 /// Perform simple peephole optimizations.
 class Peepholes : public BinaryFunctionPass {
+public:
+  enum PeepholeOpts : char {
+    PEEP_NONE = 0x0,
+    PEEP_DOUBLE_JUMPS = 0x2,
+    PEEP_TAILCALL_TRAPS = 0x4,
+    PEEP_USELESS_BRANCHES = 0x8,
+    PEEP_ALL = 0xf
+  };
+
+private:
   uint64_t NumDoubleJumps{0};
   uint64_t TailCallTraps{0};
   uint64_t NumUselessCondBranches{0};

bolt/include/bolt/Passes/LivenessAnalysis.h

@@ -11,6 +11,7 @@
 
 #include "bolt/Passes/DataflowAnalysis.h"
 #include "bolt/Passes/RegAnalysis.h"
+#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/Support/CommandLine.h"
 
 namespace opts {

bolt/include/bolt/Passes/ReachingDefOrUse.h

@@ -12,6 +12,7 @@
 #include "bolt/Passes/DataflowAnalysis.h"
 #include "bolt/Passes/RegAnalysis.h"
 #include "llvm/ADT/Optional.h"
+#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Timer.h"
 

bolt/include/bolt/Passes/ShrinkWrapping.h

@@ -10,6 +10,7 @@
 #define BOLT_PASSES_SHRINKWRAPPING_H
 
 #include "bolt/Passes/FrameAnalysis.h"
+#include "llvm/MC/MCRegisterInfo.h"
 
 namespace llvm {
 namespace bolt {

bolt/include/bolt/Rewrite/DWARFRewriter.h

@@ -10,6 +10,7 @@
 #define BOLT_REWRITE_DWARF_REWRITER_H
 
 #include "bolt/Core/DebugData.h"
+#include "llvm/MC/MCAsmLayout.h"
 #include <cstdint>
 #include <memory>
 #include <mutex>
@@ -108,9 +109,6 @@ class DWARFRewriter {
   /// Output .dwp files.
   void writeDWP(std::unordered_map<uint64_t, std::string> &DWOIdToName);
 
-  /// Abbreviations that were converted to use DW_AT_ranges.
-  std::set<const DWARFAbbreviationDeclaration *> ConvertedRangesAbbrevs;
-
   /// DWARFDie contains a pointer to a DIE and hence gets invalidated once the
   /// embedded DIE is destroyed. This wrapper class stores a DIE internally and
   /// could be cast to a DWARFDie that is valid even after the initial DIE is
@@ -135,8 +133,6 @@ class DWARFRewriter {
       const DWARFAbbreviationDeclaration *,
       std::vector<std::pair<DWARFDieWrapper, DebugAddressRange>>>;
 
-  PendingRangesType PendingRanges;
-
   /// Convert \p Abbrev from using a simple DW_AT_(low|high)_pc range to
   /// DW_AT_ranges with optional \p RangesBase.
   void convertToRangesPatchAbbrev(const DWARFUnit &Unit,
@@ -151,30 +147,10 @@ class DWARFRewriter {
                                      SimpleBinaryPatcher &DebugInfoPatcher,
                                      Optional<uint64_t> RangesBase = None);
 
-  /// Same as above, but takes a vector of \p Ranges as a parameter.
-  void convertToRanges(DWARFDie DIE, const DebugAddressRangesVector &Ranges,
-                       SimpleBinaryPatcher &DebugInfoPatcher);
-
   /// Patch DW_AT_(low|high)_pc values for the \p DIE based on \p Range.
   void patchLowHigh(DWARFDie DIE, DebugAddressRange Range,
-                    SimpleBinaryPatcher &DebugInfoPatcher);
-
-  /// Convert pending ranges associated with the given \p Abbrev.
-  void convertPending(const DWARFUnit &Unit,
-                      const DWARFAbbreviationDeclaration *Abbrev,
-                      SimpleBinaryPatcher &DebugInfoPatcher,
-                      DebugAbbrevWriter &AbbrevWriter);
-
-  /// Adds to Pending Ranges.
-  /// For Debug Fission also adding to .debug_addr to take care of a case where
-  /// some entries are not converted to ranges and left as
-  /// DW_AT_low_pc/DW_AT_high_pc.
-  void addToPendingRanges(const DWARFAbbreviationDeclaration *Abbrev,
-                          DWARFDie DIE, DebugAddressRangesVector &Ranges,
-                          Optional<uint64_t> DWOId);
-
-  /// Once all DIEs were seen, update DW_AT_(low|high)_pc values.
-  void flushPendingRanges(SimpleBinaryPatcher &DebugInfoPatcher);
+                    SimpleBinaryPatcher &DebugInfoPatcher,
+                    Optional<uint64_t> DWOId);
 
   /// Helper function for creating and returning per-DWO patchers/writers.
   template <class T, class Patcher>

bolt/include/bolt/Utils/CommandLineOpts.h

@@ -27,8 +27,7 @@ extern llvm::cl::OptionCategory BoltRelocCategory;
 extern llvm::cl::OptionCategory BoltOutputCategory;
 extern llvm::cl::OptionCategory AggregatorCategory;
 extern llvm::cl::OptionCategory BoltInstrCategory;
-
-extern llvm::cl::SubCommand HeatmapCommand;
+extern llvm::cl::OptionCategory HeatmapCategory;
 
 extern llvm::cl::opt<unsigned> AlignText;
 extern llvm::cl::opt<bool> AggregateOnly;
@@ -38,7 +37,6 @@ extern llvm::cl::opt<bool> EnableBAT;
 extern llvm::cl::opt<bool> RemoveSymtab;
 extern llvm::cl::opt<unsigned> ExecutionCountThreshold;
 extern llvm::cl::opt<unsigned> HeatmapBlock;
-extern llvm::cl::opt<std::string> HeatmapFile;
 extern llvm::cl::opt<unsigned long long> HeatmapMaxAddress;
 extern llvm::cl::opt<unsigned long long> HeatmapMinAddress;
 extern llvm::cl::opt<bool> HotData;

bolt/lib/Core/BinaryContext.cpp

@@ -26,8 +26,10 @@
 #include "llvm/MC/MCInstPrinter.h"
 #include "llvm/MC/MCObjectStreamer.h"
 #include "llvm/MC/MCObjectWriter.h"
+#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCStreamer.h"
+#include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Regex.h"

bolt/lib/Core/BinaryFunction.cpp

@@ -28,6 +28,7 @@
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstPrinter.h"
+#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"

bolt/lib/Core/DebugData.cpp

@@ -13,6 +13,7 @@
 #include "bolt/Core/DebugData.h"
 #include "bolt/Core/BinaryContext.h"
 #include "bolt/Utils/Utils.h"
+#include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCObjectStreamer.h"
 #include "llvm/Support/CommandLine.h"

bolt/lib/Core/MCPlusBuilder.cpp

@@ -16,6 +16,7 @@
 #include "llvm/MC/MCInstrAnalysis.h"
 #include "llvm/MC/MCInstrDesc.h"
 #include "llvm/MC/MCInstrInfo.h"
+#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/Support/Debug.h"
 #include <cstdint>
 #include <queue>

bolt/lib/Core/Relocation.cpp

@@ -12,7 +12,9 @@
 
 #include "bolt/Core/Relocation.h"
 #include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCStreamer.h"
+#include "llvm/MC/MCSymbol.h"
 #include "llvm/Object/ELF.h"
 
 using namespace llvm;