Add interface to compute number of physical cores on host system

Summary:
For now I have only added support for x86_64 Linux, but other systems
can be added incrementally.

This is to be used for setting the default parallelism for ThinLTO
backends (instead of thread::hardware_concurrency which includes
hyperthreading and is too aggressive). I'll send this as a follow-on
patch, and it will fall back to hardware_concurrency when the new
getHostNumPhysicalCores returns -1 (when not supported for a given
host system).

I also added an interface to MemoryBuffer to force reading a file
as a stream - this is required for /proc/cpuinfo which is a special
file that looks like a normal file but appears to have 0 size.
The existing readers of this file in Host.cpp are reading the first
1024 or so bytes from it, because the necessary info is near the top.
But for the new functionality we need to be able to read the entire
file. I can go back and change the other readers to use the new
getFileAsStream as a follow-on patch since it seems much more robust.

Added a unittest.

Reviewers: mehdi_amini

Subscribers: beanz, mgorny, llvm-commits, modocache

Differential Revision: https://reviews.llvm.org/D25564

llvm-svn: 284138

include/llvm/Support/Host.h

@@ -70,6 +70,11 @@ namespace sys {
   ///
   /// \return - True on success.
   bool getHostCPUFeatures(StringMap<bool> &Features);
+
+  /// Get the number of physical cores (as opposed to logical cores returned
+  /// from thread::hardware_concurrency(), which includes hyperthreads).
+  /// Returns -1 if unknown for the current host system.
+  int getHostNumPhysicalCores();
 }
 }
 

include/llvm/Support/MemoryBuffer.h

@@ -70,6 +70,12 @@ public:
   getFile(const Twine &Filename, int64_t FileSize = -1,
           bool RequiresNullTerminator = true, bool IsVolatileSize = false);
 
+  /// Read all of the specified file into a MemoryBuffer as a stream
+  /// (i.e. until EOF reached). This is useful for special files that
+  /// look like a regular file but have 0 size (e.g. /proc/cpuinfo on Linux).
+  static ErrorOr<std::unique_ptr<MemoryBuffer>>
+  getFileAsStream(const Twine &Filename);
+
   /// Given an already-open file descriptor, map some slice of it into a
   /// MemoryBuffer. The slice is specified by an \p Offset and \p MapSize.
   /// Since this is in the middle of a file, the buffer is not null terminated.

lib/Support/Host.cpp

@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Support/Host.h"
+#include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/StringSwitch.h"
@@ -19,9 +20,10 @@
 #include "llvm/Config/config.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/FileSystem.h"
+#include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/raw_ostream.h"
-#include <string.h>
 #include <assert.h>
+#include <string.h>
 
 // Include the platform-specific parts of this class.
 #ifdef LLVM_ON_UNIX
@@ -1188,6 +1190,60 @@ StringRef sys::getHostCPUName() {
 StringRef sys::getHostCPUName() { return "generic"; }
 #endif
 
+#if defined(__linux__) && defined(__x86_64__)
+// On Linux, the number of physical cores can be computed from /proc/cpuinfo,
+// using the number of unique physical/core id pairs. The following
+// implementation reads the /proc/cpuinfo format on an x86_64 system.
+int computeHostNumPhysicalCores() {
+  // Read /proc/cpuinfo as a stream (until EOF reached). It cannot be
+  // mmapped because it appears to have 0 size.
+  llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> Text =
+      llvm::MemoryBuffer::getFileAsStream("/proc/cpuinfo");
+  if (std::error_code EC = Text.getError()) {
+    llvm::errs() << "Can't read "
+                 << "/proc/cpuinfo: " << EC.message() << "\n";
+  }
+  SmallVector<StringRef, 8> strs;
+  (*Text)->getBuffer().split(strs, "\n", /*MaxSplit=*/-1,
+                             /*KeepEmpty=*/false);
+  int CurPhysicalId = -1;
+  int CurCoreId = -1;
+  SmallSet<std::pair<int, int>, 32> UniqueItems;
+  for (auto &Line : strs) {
+    Line = Line.trim();
+    if (!Line.startswith("physical id") && !Line.startswith("core id"))
+      continue;
+    std::pair<StringRef, StringRef> Data = Line.split(':');
+    auto Name = Data.first.trim();
+    auto Val = Data.second.trim();
+    if (Name == "physical id") {
+      assert(CurPhysicalId == -1 &&
+             "Expected a core id before seeing another physical id");
+      Val.getAsInteger(10, CurPhysicalId);
+    }
+    if (Name == "core id") {
+      assert(CurCoreId == -1 &&
+             "Expected a physical id before seeing another core id");
+      Val.getAsInteger(10, CurCoreId);
+    }
+    if (CurPhysicalId != -1 && CurCoreId != -1) {
+      UniqueItems.insert(std::make_pair(CurPhysicalId, CurCoreId));
+      CurPhysicalId = -1;
+      CurCoreId = -1;
+    }
+  }
+  return UniqueItems.size();
+}
+#else
+// On other systems, return -1 to indicate unknown.
+int computeHostNumPhysicalCores() { return -1; }
+#endif
+
+int sys::getHostNumPhysicalCores() {
+  static int NumCores = computeHostNumPhysicalCores();
+  return NumCores;
+}
+
 #if defined(__i386__) || defined(_M_IX86) || \
     defined(__x86_64__) || defined(_M_X64)
 bool sys::getHostCPUFeatures(StringMap<bool> &Features) {

lib/Support/MemoryBuffer.cpp

@@ -438,6 +438,18 @@ ErrorOr<std::unique_ptr<MemoryBuffer>> MemoryBuffer::getSTDIN() {
   return getMemoryBufferForStream(0, "<stdin>");
 }
 
+ErrorOr<std::unique_ptr<MemoryBuffer>>
+MemoryBuffer::getFileAsStream(const Twine &Filename) {
+  int FD;
+  std::error_code EC = sys::fs::openFileForRead(Filename, FD);
+  if (EC)
+    return EC;
+  ErrorOr<std::unique_ptr<MemoryBuffer>> Ret =
+      getMemoryBufferForStream(FD, Filename);
+  close(FD);
+  return Ret;
+}
+
 MemoryBufferRef MemoryBuffer::getMemBufferRef() const {
   StringRef Data = getBuffer();
   StringRef Identifier = getBufferIdentifier();

unittests/Support/CMakeLists.txt

@@ -19,6 +19,7 @@ add_llvm_unittest(SupportTests
   ErrorTest.cpp
   ErrorOrTest.cpp
   FileOutputBufferTest.cpp
+  Host.cpp
   LEB128Test.cpp
   LineIteratorTest.cpp
   LockFileManagerTest.cpp

unittests/Support/Host.cpp

@@ -0,0 +1,47 @@
+//========- unittests/Support/Host.cpp - Host.cpp tests --------------========//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/Host.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/Triple.h"
+
+#include "gtest/gtest.h"
+
+using namespace llvm;
+
+class HostTest : public testing::Test {
+  Triple Host;
+  SmallVector<std::pair<Triple::ArchType, Triple::OSType>, 4> SupportedArchAndOSs;
+
+protected:
+  bool isSupportedArchAndOS() {
+    if (is_contained(SupportedArchAndOSs, std::make_pair(Host.getArch(), Host.getOS())))
+      return true;
+
+    return false;
+  }
+
+  HostTest() {
+    Host.setTriple(Triple::normalize(sys::getProcessTriple()));
+
+    // Initially this is only testing detection of the number of
+    // physical cores, which is currently only supported for
+    // x86_64 Linux.
+    SupportedArchAndOSs.push_back(std::make_pair(Triple::x86_64, Triple::Linux));
+  }
+};
+
+TEST_F(HostTest, NumPhysicalCores) {
+  int Num = sys::getHostNumPhysicalCores();
+
+  if (isSupportedArchAndOS())
+    ASSERT_GT(Num, 0);
+  else
+    ASSERT_EQ(Num, -1);
+}