1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
llvm-mirror/lib/Support/ThreadPool.cpp
Alexandre Ganea ae05eb086d [Support] On Windows, ensure hardware_concurrency() extends to all CPU sockets and all NUMA groups
The goal of this patch is to maximize CPU utilization on multi-socket or high core count systems, so that parallel computations such as LLD/ThinLTO can use all hardware threads in the system. Before this patch, on Windows, a maximum of 64 hardware threads could be used at most, in some cases dispatched only on one CPU socket.

== Background ==
Windows doesn't have a flat cpu_set_t like Linux. Instead, it projects hardware CPUs (or NUMA nodes) to applications through a concept of "processor groups". A "processor" is the smallest unit of execution on a CPU, that is, an hyper-thread if SMT is active; a core otherwise. There's a limit of 32-bit processors on older 32-bit versions of Windows, which later was raised to 64-processors with 64-bit versions of Windows. This limit comes from the affinity mask, which historically is represented by the sizeof(void*). Consequently, the concept of "processor groups" was introduced for dealing with systems with more than 64 hyper-threads.

By default, the Windows OS assigns only one "processor group" to each starting application, in a round-robin manner. If the application wants to use more processors, it needs to programmatically enable it, by assigning threads to other "processor groups". This also means that affinity cannot cross "processor group" boundaries; one can only specify a "preferred" group on start-up, but the application is free to allocate more groups if it wants to.

This creates a peculiar situation, where newer CPUs like the AMD EPYC 7702P (64-cores, 128-hyperthreads) are projected by the OS as two (2) "processor groups". This means that by default, an application can only use half of the cores. This situation could only get worse in the years to come, as dies with more cores will appear on the market.

== The problem ==
The heavyweight_hardware_concurrency() API was introduced so that only *one hardware thread per core* was used. Once that API returns, that original intention is lost, only the number of threads is retained. Consider a situation, on Windows, where the system has 2 CPU sockets, 18 cores each, each core having 2 hyper-threads, for a total of 72 hyper-threads. Both heavyweight_hardware_concurrency() and hardware_concurrency() currently return 36, because on Windows they are simply wrappers over std:🧵:hardware_concurrency() -- which can only return processors from the current "processor group".

== The changes in this patch ==
To solve this situation, we capture (and retain) the initial intention until the point of usage, through a new ThreadPoolStrategy class. The number of threads to use is deferred as late as possible, until the moment where the std::threads are created (ThreadPool in the case of ThinLTO).

When using hardware_concurrency(), setting ThreadCount to 0 now means to use all the possible hardware CPU (SMT) threads. Providing a ThreadCount above to the maximum number of threads will have no effect, the maximum will be used instead.
The heavyweight_hardware_concurrency() is similar to hardware_concurrency(), except that only one thread per hardware *core* will be used.

When LLVM_ENABLE_THREADS is OFF, the threading APIs will always return 1, to ensure any caller loops will be exercised at least once.

Differential Revision: https://reviews.llvm.org/D71775
2020-02-14 10:24:22 -05:00

141 lines
4.6 KiB
C++

//==-- llvm/Support/ThreadPool.cpp - A ThreadPool implementation -*- C++ -*-==//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements a crude C++11 based thread pool.
//
//===----------------------------------------------------------------------===//
#include "llvm/Support/ThreadPool.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/Support/Threading.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
#if LLVM_ENABLE_THREADS
ThreadPool::ThreadPool(ThreadPoolStrategy S)
: ActiveThreads(0), EnableFlag(true),
ThreadCount(S.compute_thread_count()) {
// Create ThreadCount threads that will loop forever, wait on QueueCondition
// for tasks to be queued or the Pool to be destroyed.
Threads.reserve(ThreadCount);
for (unsigned ThreadID = 0; ThreadID < ThreadCount; ++ThreadID) {
Threads.emplace_back([S, ThreadID, this] {
S.apply_thread_strategy(ThreadID);
while (true) {
PackagedTaskTy Task;
{
std::unique_lock<std::mutex> LockGuard(QueueLock);
// Wait for tasks to be pushed in the queue
QueueCondition.wait(LockGuard,
[&] { return !EnableFlag || !Tasks.empty(); });
// Exit condition
if (!EnableFlag && Tasks.empty())
return;
// Yeah, we have a task, grab it and release the lock on the queue
// We first need to signal that we are active before popping the queue
// in order for wait() to properly detect that even if the queue is
// empty, there is still a task in flight.
{
std::unique_lock<std::mutex> LockGuard(CompletionLock);
++ActiveThreads;
}
Task = std::move(Tasks.front());
Tasks.pop();
}
// Run the task we just grabbed
Task();
{
// Adjust `ActiveThreads`, in case someone waits on ThreadPool::wait()
std::unique_lock<std::mutex> LockGuard(CompletionLock);
--ActiveThreads;
}
// Notify task completion, in case someone waits on ThreadPool::wait()
CompletionCondition.notify_all();
}
});
}
}
void ThreadPool::wait() {
// Wait for all threads to complete and the queue to be empty
std::unique_lock<std::mutex> LockGuard(CompletionLock);
// The order of the checks for ActiveThreads and Tasks.empty() matters because
// any active threads might be modifying the Tasks queue, and this would be a
// race.
CompletionCondition.wait(LockGuard,
[&] { return !ActiveThreads && Tasks.empty(); });
}
std::shared_future<void> ThreadPool::asyncImpl(TaskTy Task) {
/// Wrap the Task in a packaged_task to return a future object.
PackagedTaskTy PackagedTask(std::move(Task));
auto Future = PackagedTask.get_future();
{
// Lock the queue and push the new task
std::unique_lock<std::mutex> LockGuard(QueueLock);
// Don't allow enqueueing after disabling the pool
assert(EnableFlag && "Queuing a thread during ThreadPool destruction");
Tasks.push(std::move(PackagedTask));
}
QueueCondition.notify_one();
return Future.share();
}
// The destructor joins all threads, waiting for completion.
ThreadPool::~ThreadPool() {
{
std::unique_lock<std::mutex> LockGuard(QueueLock);
EnableFlag = false;
}
QueueCondition.notify_all();
for (auto &Worker : Threads)
Worker.join();
}
#else // LLVM_ENABLE_THREADS Disabled
// No threads are launched, issue a warning if ThreadCount is not 0
ThreadPool::ThreadPool(ThreadPoolStrategy S)
: ActiveThreads(0), ThreadCount(S.compute_thread_count()) {
if (ThreadCount != 1) {
errs() << "Warning: request a ThreadPool with " << ThreadCount
<< " threads, but LLVM_ENABLE_THREADS has been turned off\n";
}
}
void ThreadPool::wait() {
// Sequential implementation running the tasks
while (!Tasks.empty()) {
auto Task = std::move(Tasks.front());
Tasks.pop();
Task();
}
}
std::shared_future<void> ThreadPool::asyncImpl(TaskTy Task) {
// Get a Future with launch::deferred execution using std::async
auto Future = std::async(std::launch::deferred, std::move(Task)).share();
// Wrap the future so that both ThreadPool::wait() can operate and the
// returned future can be sync'ed on.
PackagedTaskTy PackagedTask([Future]() { Future.get(); });
Tasks.push(std::move(PackagedTask));
return Future;
}
ThreadPool::~ThreadPool() { wait(); }
#endif