Use sched_getaffinity instead of std::thread::hardware_concurrency.

The issue with std::thread::hardware_concurrency is that it forwards
to libc and some implementations (like glibc) don't take thread
affinity into consideration.

With this change a llvm program that can execute in only 2 cores will
use 2 threads, even if the machine has 32 cores.

This makes benchmarking a lot easier, but should also help if someone
doesn't want to use all cores for compilation for example.

llvm-svn: 314809

1 files changed, 14 insertions, 0 deletions

diff --git a/llvm/lib/Support/Threading.cpp b/llvm/lib/Support/Threading.cpp
index 6a10b988d46..b3579b57548 100644
--- a/llvm/lib/Support/Threading.cpp
+++ b/llvm/lib/Support/Threading.cpp
@@ -47,6 +47,8 @@ void llvm::llvm_execute_on_thread(void (*Fn)(void *), void *UserData,
 
 unsigned llvm::heavyweight_hardware_concurrency() { return 1; }
 
+unsigned llvm::hardware_concurrency() { return 1; }
+
 uint64_t llvm::get_threadid() { return 0; }
 
 uint32_t llvm::get_max_thread_name_length() { return 0; }
@@ -71,6 +73,18 @@ unsigned llvm::heavyweight_hardware_concurrency() {
   return NumPhysical;
 }
 
+unsigned llvm::hardware_concurrency() {
+#ifdef HAVE_SCHED_GETAFFINITY
+  cpu_set_t Set;
+  if (sched_getaffinity(0, sizeof(Set), &Set))
+    return CPU_COUNT(&Set);
+#endif
+  // Guard against std::thread::hardware_concurrency() returning 0.
+  if (unsigned Val = std::thread::hardware_concurrency())
+    return Val;
+  return 1;
+}
+
 // Include the platform-specific parts of this class.
 #ifdef LLVM_ON_UNIX
 #include "Unix/Threading.inc"