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, 2 insertions, 2 deletions

diff --git a/llvm/tools/llvm-profdata/llvm-profdata.cpp b/llvm/tools/llvm-profdata/llvm-profdata.cpp
index eee242107da..8e21a7a9b4f 100644
--- a/llvm/tools/llvm-profdata/llvm-profdata.cpp
+++ b/llvm/tools/llvm-profdata/llvm-profdata.cpp
@@ -211,8 +211,8 @@ static void mergeInstrProfile(const WeightedFileVector &Inputs,
 
   // If NumThreads is not specified, auto-detect a good default.
   if (NumThreads == 0)
-    NumThreads = std::max(1U, std::min(std::thread::hardware_concurrency(),
-                                       unsigned(Inputs.size() / 2)));
+    NumThreads =
+        std::min(hardware_concurrency(), unsigned((Inputs.size() + 1) / 2));
 
   // Initialize the writer contexts.
   SmallVector<std::unique_ptr<WriterContext>, 4> Contexts;