[Support] Move getHostNumPhysicalCores to Threading.h

This change is focussed on simplifying `Support/Host.h` to only do
target detection. In this case, this function is close in usage to
existing functions in `Support/Threading.h`, so I moved it into there.
The function is also renamed to `llvm::get_physical_cores()` to match
the style of threading's functions.

Differential Revision: https://reviews.llvm.org/D137836

clang-tools-extra/clangd/test/Inputs/BenchmarkHeader.h

@@ -7,11 +7,7 @@ class Dex;
 } // namespace clang
 
 namespace llvm {
-namespace sys {
-
-int getHostNumPhysicalCores();
-
-} // namespace sys
+int get_physical_cores();
 } // namespace llvm
 
 namespace {

llvm/include/llvm/Support/Host.h

@@ -54,11 +54,6 @@ namespace sys {
   /// \return - True on success.
   bool getHostCPUFeatures(StringMap<bool, MallocAllocator> &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();
-
   namespace detail {
   /// Helper functions to extract HostCPUName from /proc/cpuinfo on linux.
   StringRef getHostCPUNameForPowerPC(StringRef ProcCpuinfoContent);

llvm/include/llvm/Support/Threading.h

@@ -231,6 +231,11 @@ constexpr bool llvm_is_multithreaded() { return LLVM_ENABLE_THREADS; }
   /// Returns how many physical CPUs or NUMA groups the system has.
   unsigned get_cpus();
 
+  /// Returns how many 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 get_physical_cores();
+
   enum class ThreadPriority {
     /// Lower the current thread's priority as much as possible. Can be used
     /// for long-running tasks that are not time critical; more energy-

llvm/lib/Support/Host.cpp

@@ -1576,128 +1576,6 @@ VendorSignatures getVendorSignature(unsigned *MaxLeaf) {
 } // namespace llvm
 #endif
 
-#if defined(__linux__) && (defined(__i386__) || 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.
-static int computeHostNumPhysicalCores() {
-  // Enabled represents the number of physical id/core id pairs with at least
-  // one processor id enabled by the CPU affinity mask.
-  cpu_set_t Affinity, Enabled;
-  if (sched_getaffinity(0, sizeof(Affinity), &Affinity) != 0)
-    return -1;
-  CPU_ZERO(&Enabled);
-
-  // 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";
-    return -1;
-  }
-  SmallVector<StringRef, 8> strs;
-  (*Text)->getBuffer().split(strs, "\n", /*MaxSplit=*/-1,
-                             /*KeepEmpty=*/false);
-  int CurProcessor = -1;
-  int CurPhysicalId = -1;
-  int CurSiblings = -1;
-  int CurCoreId = -1;
-  for (StringRef Line : strs) {
-    std::pair<StringRef, StringRef> Data = Line.split(':');
-    auto Name = Data.first.trim();
-    auto Val = Data.second.trim();
-    // These fields are available if the kernel is configured with CONFIG_SMP.
-    if (Name == "processor")
-      Val.getAsInteger(10, CurProcessor);
-    else if (Name == "physical id")
-      Val.getAsInteger(10, CurPhysicalId);
-    else if (Name == "siblings")
-      Val.getAsInteger(10, CurSiblings);
-    else if (Name == "core id") {
-      Val.getAsInteger(10, CurCoreId);
-      // The processor id corresponds to an index into cpu_set_t.
-      if (CPU_ISSET(CurProcessor, &Affinity))
-        CPU_SET(CurPhysicalId * CurSiblings + CurCoreId, &Enabled);
-    }
-  }
-  return CPU_COUNT(&Enabled);
-}
-#elif defined(__linux__) && defined(__s390x__)
-static int computeHostNumPhysicalCores() {
-  return sysconf(_SC_NPROCESSORS_ONLN);
-}
-#elif defined(__linux__) && !defined(__ANDROID__)
-static int computeHostNumPhysicalCores() {
-  cpu_set_t Affinity;
-  if (sched_getaffinity(0, sizeof(Affinity), &Affinity) == 0)
-    return CPU_COUNT(&Affinity);
-
-  // The call to sched_getaffinity() may have failed because the Affinity
-  // mask is too small for the number of CPU's on the system (i.e. the
-  // system has more than 1024 CPUs). Allocate a mask large enough for
-  // twice as many CPUs.
-  cpu_set_t *DynAffinity;
-  DynAffinity = CPU_ALLOC(2048);
-  if (sched_getaffinity(0, CPU_ALLOC_SIZE(2048), DynAffinity) == 0) {
-    int NumCPUs = CPU_COUNT(DynAffinity);
-    CPU_FREE(DynAffinity);
-    return NumCPUs;
-  }
-  return -1;
-}
-#elif defined(__APPLE__)
-// Gets the number of *physical cores* on the machine.
-static int computeHostNumPhysicalCores() {
-  uint32_t count;
-  size_t len = sizeof(count);
-  sysctlbyname("hw.physicalcpu", &count, &len, NULL, 0);
-  if (count < 1) {
-    int nm[2];
-    nm[0] = CTL_HW;
-    nm[1] = HW_AVAILCPU;
-    sysctl(nm, 2, &count, &len, NULL, 0);
-    if (count < 1)
-      return -1;
-  }
-  return count;
-}
-#elif defined(__MVS__)
-static int computeHostNumPhysicalCores() {
-  enum {
-    // Byte offset of the pointer to the Communications Vector Table (CVT) in
-    // the Prefixed Save Area (PSA). The table entry is a 31-bit pointer and
-    // will be zero-extended to uintptr_t.
-    FLCCVT = 16,
-    // Byte offset of the pointer to the Common System Data Area (CSD) in the
-    // CVT. The table entry is a 31-bit pointer and will be zero-extended to
-    // uintptr_t.
-    CVTCSD = 660,
-    // Byte offset to the number of live CPs in the LPAR, stored as a signed
-    // 32-bit value in the table.
-    CSD_NUMBER_ONLINE_STANDARD_CPS = 264,
-  };
-  char *PSA = 0;
-  char *CVT = reinterpret_cast<char *>(
-      static_cast<uintptr_t>(reinterpret_cast<unsigned int &>(PSA[FLCCVT])));
-  char *CSD = reinterpret_cast<char *>(
-      static_cast<uintptr_t>(reinterpret_cast<unsigned int &>(CVT[CVTCSD])));
-  return reinterpret_cast<int &>(CSD[CSD_NUMBER_ONLINE_STANDARD_CPS]);
-}
-#elif defined(_WIN32) && LLVM_ENABLE_THREADS != 0
-// Defined in llvm/lib/Support/Windows/Threading.inc
-int computeHostNumPhysicalCores();
-#else
-// On other systems, return -1 to indicate unknown.
-static 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) {

llvm/lib/Support/Threading.cpp

@@ -13,8 +13,12 @@
 
 #include "llvm/Support/Threading.h"
 #include "llvm/ADT/Optional.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringRef.h"
 #include "llvm/Config/config.h"
-#include "llvm/Support/Host.h"
+#include "llvm/Config/llvm-config.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/raw_ostream.h"
 
 #include <cassert>
 #include <errno.h>
@@ -50,8 +54,8 @@ unsigned llvm::ThreadPoolStrategy::compute_thread_count() const {
 static int computeHostNumHardwareThreads();
 
 unsigned llvm::ThreadPoolStrategy::compute_thread_count() const {
-  int MaxThreadCount = UseHyperThreads ? computeHostNumHardwareThreads()
-                                       : sys::getHostNumPhysicalCores();
+  int MaxThreadCount =
+      UseHyperThreads ? computeHostNumHardwareThreads() : get_physical_cores();
   if (MaxThreadCount <= 0)
     MaxThreadCount = 1;
   if (ThreadsRequested == 0)
@@ -106,3 +110,125 @@ llvm::get_threadpool_strategy(StringRef Num, ThreadPoolStrategy Default) {
   S.ThreadsRequested = V;
   return S;
 }
+
+#if defined(__linux__) && (defined(__i386__) || 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.
+static int computeHostNumPhysicalCores() {
+  // Enabled represents the number of physical id/core id pairs with at least
+  // one processor id enabled by the CPU affinity mask.
+  cpu_set_t Affinity, Enabled;
+  if (sched_getaffinity(0, sizeof(Affinity), &Affinity) != 0)
+    return -1;
+  CPU_ZERO(&Enabled);
+
+  // 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";
+    return -1;
+  }
+  SmallVector<StringRef, 8> strs;
+  (*Text)->getBuffer().split(strs, "\n", /*MaxSplit=*/-1,
+                             /*KeepEmpty=*/false);
+  int CurProcessor = -1;
+  int CurPhysicalId = -1;
+  int CurSiblings = -1;
+  int CurCoreId = -1;
+  for (StringRef Line : strs) {
+    std::pair<StringRef, StringRef> Data = Line.split(':');
+    auto Name = Data.first.trim();
+    auto Val = Data.second.trim();
+    // These fields are available if the kernel is configured with CONFIG_SMP.
+    if (Name == "processor")
+      Val.getAsInteger(10, CurProcessor);
+    else if (Name == "physical id")
+      Val.getAsInteger(10, CurPhysicalId);
+    else if (Name == "siblings")
+      Val.getAsInteger(10, CurSiblings);
+    else if (Name == "core id") {
+      Val.getAsInteger(10, CurCoreId);
+      // The processor id corresponds to an index into cpu_set_t.
+      if (CPU_ISSET(CurProcessor, &Affinity))
+        CPU_SET(CurPhysicalId * CurSiblings + CurCoreId, &Enabled);
+    }
+  }
+  return CPU_COUNT(&Enabled);
+}
+#elif defined(__linux__) && defined(__s390x__)
+static int computeHostNumPhysicalCores() {
+  return sysconf(_SC_NPROCESSORS_ONLN);
+}
+#elif defined(__linux__) && !defined(__ANDROID__)
+static int computeHostNumPhysicalCores() {
+  cpu_set_t Affinity;
+  if (sched_getaffinity(0, sizeof(Affinity), &Affinity) == 0)
+    return CPU_COUNT(&Affinity);
+
+  // The call to sched_getaffinity() may have failed because the Affinity
+  // mask is too small for the number of CPU's on the system (i.e. the
+  // system has more than 1024 CPUs). Allocate a mask large enough for
+  // twice as many CPUs.
+  cpu_set_t *DynAffinity;
+  DynAffinity = CPU_ALLOC(2048);
+  if (sched_getaffinity(0, CPU_ALLOC_SIZE(2048), DynAffinity) == 0) {
+    int NumCPUs = CPU_COUNT(DynAffinity);
+    CPU_FREE(DynAffinity);
+    return NumCPUs;
+  }
+  return -1;
+}
+#elif defined(__APPLE__)
+// Gets the number of *physical cores* on the machine.
+static int computeHostNumPhysicalCores() {
+  uint32_t count;
+  size_t len = sizeof(count);
+  sysctlbyname("hw.physicalcpu", &count, &len, NULL, 0);
+  if (count < 1) {
+    int nm[2];
+    nm[0] = CTL_HW;
+    nm[1] = HW_AVAILCPU;
+    sysctl(nm, 2, &count, &len, NULL, 0);
+    if (count < 1)
+      return -1;
+  }
+  return count;
+}
+#elif defined(__MVS__)
+static int computeHostNumPhysicalCores() {
+  enum {
+    // Byte offset of the pointer to the Communications Vector Table (CVT) in
+    // the Prefixed Save Area (PSA). The table entry is a 31-bit pointer and
+    // will be zero-extended to uintptr_t.
+    FLCCVT = 16,
+    // Byte offset of the pointer to the Common System Data Area (CSD) in the
+    // CVT. The table entry is a 31-bit pointer and will be zero-extended to
+    // uintptr_t.
+    CVTCSD = 660,
+    // Byte offset to the number of live CPs in the LPAR, stored as a signed
+    // 32-bit value in the table.
+    CSD_NUMBER_ONLINE_STANDARD_CPS = 264,
+  };
+  char *PSA = 0;
+  char *CVT = reinterpret_cast<char *>(
+      static_cast<uintptr_t>(reinterpret_cast<unsigned int &>(PSA[FLCCVT])));
+  char *CSD = reinterpret_cast<char *>(
+      static_cast<uintptr_t>(reinterpret_cast<unsigned int &>(CVT[CVTCSD])));
+  return reinterpret_cast<int &>(CSD[CSD_NUMBER_ONLINE_STANDARD_CPS]);
+}
+#elif defined(_WIN32) && LLVM_ENABLE_THREADS != 0
+// Defined in llvm/lib/Support/Windows/Threading.inc
+int computeHostNumPhysicalCores();
+#else
+// On other systems, return -1 to indicate unknown.
+static int computeHostNumPhysicalCores() { return -1; }
+#endif
+
+int llvm::get_physical_cores() {
+  static int NumCores = computeHostNumPhysicalCores();
+  return NumCores;
+}

llvm/unittests/Support/Host.cpp

@@ -30,37 +30,6 @@
 
 using namespace llvm;
 
-class HostTest : public testing::Test {
-  Triple Host;
-
-protected:
-  bool isSupportedArchAndOS() {
-    // Initially this is only testing detection of the number of
-    // physical cores, which is currently only supported/tested on
-    // some systems.
-    return (Host.isOSWindows() && llvm_is_multithreaded()) ||
-           Host.isOSDarwin() || (Host.isX86() && Host.isOSLinux()) ||
-           (Host.isOSLinux() && !Host.isAndroid()) ||
-           (Host.isSystemZ() && Host.isOSzOS());
-  }
-
-  HostTest() : Host(Triple::normalize(sys::getProcessTriple())) {}
-};
-
-TEST_F(HostTest, NumPhysicalCoresSupported) {
-  if (!isSupportedArchAndOS())
-    GTEST_SKIP();
-  int Num = sys::getHostNumPhysicalCores();
-  ASSERT_GT(Num, 0);
-}
-
-TEST_F(HostTest, NumPhysicalCoresUnsupported) {
-  if (isSupportedArchAndOS())
-    GTEST_SKIP();
-  int Num = sys::getHostNumPhysicalCores();
-  ASSERT_EQ(Num, -1);
-}
-
 TEST(getLinuxHostCPUName, ARM) {
   StringRef CortexA9ProcCpuinfo = R"(
 processor       : 0
@@ -439,13 +408,13 @@ static bool runAndGetCommandOutput(
   return Success;
 }
 
-TEST_F(HostTest, DummyRunAndGetCommandOutputUse) {
+TEST(HostTest, DummyRunAndGetCommandOutputUse) {
   // Suppress defined-but-not-used warnings when the tests using the helper are
   // disabled.
   (void)&runAndGetCommandOutput;
 }
 
-TEST_F(HostTest, getMacOSHostVersion) {
+TEST(HostTest, getMacOSHostVersion) {
   llvm::Triple HostTriple(llvm::sys::getProcessTriple());
   if (!HostTriple.isMacOSX())
     GTEST_SKIP();
@@ -491,7 +460,7 @@ static void getAIXSystemVersion(VersionTuple &SystemVersion) {
           .getOSVersion();
 }
 
-TEST_F(HostTest, AIXHostVersionDetect) {
+TEST(HostTest, AIXHostVersionDetect) {
   llvm::Triple HostTriple(llvm::sys::getProcessTriple());
   if (HostTriple.getOS() != Triple::AIX)
     GTEST_SKIP();
@@ -517,7 +486,7 @@ TEST_F(HostTest, AIXHostVersionDetect) {
   ASSERT_EQ(SysMinor, HostVersion.getMinor());
 }
 
-TEST_F(HostTest, AIXTargetVersionDetect) {
+TEST(HostTest, AIXTargetVersionDetect) {
   llvm::Triple TargetTriple(llvm::sys::getDefaultTargetTriple());
   if (TargetTriple.getOS() != Triple::AIX)
     GTEST_SKIP();
@@ -535,7 +504,7 @@ TEST_F(HostTest, AIXTargetVersionDetect) {
   ASSERT_EQ(SystemVersion.getMinor(), TargetVersion.getMinor());
 }
 
-TEST_F(HostTest, AIXHostCPUDetect) {
+TEST(HostTest, AIXHostCPUDetect) {
   llvm::Triple HostTriple(llvm::sys::getProcessTriple());
   if (HostTriple.getOS() != Triple::AIX)
     GTEST_SKIP();