1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 19:52:54 +01:00
llvm-mirror/lib/Support/Parallel.cpp
Rafael Espindola e01aed9846 Bring r314809 back.
But now include a check for CPU_COUNT so we still build on 10 year old
versions of glibc.

Original message:

Use sched_getaffinity instead of std:🧵:hardware_concurrency.

The issue with std:🧵: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: 314931
2017-10-04 20:27:01 +00:00

139 lines
3.2 KiB
C++

//===- llvm/Support/Parallel.cpp - Parallel algorithms --------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "llvm/Support/Parallel.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/Support/Threading.h"
#include <atomic>
#include <stack>
#include <thread>
using namespace llvm;
namespace {
/// \brief An abstract class that takes closures and runs them asynchronously.
class Executor {
public:
virtual ~Executor() = default;
virtual void add(std::function<void()> func) = 0;
static Executor *getDefaultExecutor();
};
#if !LLVM_ENABLE_THREADS
class SyncExecutor : public Executor {
public:
virtual void add(std::function<void()> F) { F(); }
};
Executor *Executor::getDefaultExecutor() {
static SyncExecutor Exec;
return &Exec;
}
#elif defined(_MSC_VER)
/// \brief An Executor that runs tasks via ConcRT.
class ConcRTExecutor : public Executor {
struct Taskish {
Taskish(std::function<void()> Task) : Task(Task) {}
std::function<void()> Task;
static void run(void *P) {
Taskish *Self = static_cast<Taskish *>(P);
Self->Task();
concurrency::Free(Self);
}
};
public:
virtual void add(std::function<void()> F) {
Concurrency::CurrentScheduler::ScheduleTask(
Taskish::run, new (concurrency::Alloc(sizeof(Taskish))) Taskish(F));
}
};
Executor *Executor::getDefaultExecutor() {
static ConcRTExecutor exec;
return &exec;
}
#else
/// \brief An implementation of an Executor that runs closures on a thread pool
/// in filo order.
class ThreadPoolExecutor : public Executor {
public:
explicit ThreadPoolExecutor(unsigned ThreadCount = hardware_concurrency())
: Done(ThreadCount) {
// Spawn all but one of the threads in another thread as spawning threads
// can take a while.
std::thread([&, ThreadCount] {
for (size_t i = 1; i < ThreadCount; ++i) {
std::thread([=] { work(); }).detach();
}
work();
}).detach();
}
~ThreadPoolExecutor() override {
std::unique_lock<std::mutex> Lock(Mutex);
Stop = true;
Lock.unlock();
Cond.notify_all();
// Wait for ~Latch.
}
void add(std::function<void()> F) override {
std::unique_lock<std::mutex> Lock(Mutex);
WorkStack.push(F);
Lock.unlock();
Cond.notify_one();
}
private:
void work() {
while (true) {
std::unique_lock<std::mutex> Lock(Mutex);
Cond.wait(Lock, [&] { return Stop || !WorkStack.empty(); });
if (Stop)
break;
auto Task = WorkStack.top();
WorkStack.pop();
Lock.unlock();
Task();
}
Done.dec();
}
std::atomic<bool> Stop{false};
std::stack<std::function<void()>> WorkStack;
std::mutex Mutex;
std::condition_variable Cond;
parallel::detail::Latch Done;
};
Executor *Executor::getDefaultExecutor() {
static ThreadPoolExecutor exec;
return &exec;
}
#endif
}
#if LLVM_ENABLE_THREADS
void parallel::detail::TaskGroup::spawn(std::function<void()> F) {
L.inc();
Executor::getDefaultExecutor()->add([&, F] {
F();
L.dec();
});
}
#endif