[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::thread::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
diff --git a/llvm/include/llvm/LTO/LTO.h b/llvm/include/llvm/LTO/LTO.h
index e864e05..df28533 100644
--- a/llvm/include/llvm/LTO/LTO.h
+++ b/llvm/include/llvm/LTO/LTO.h
@@ -227,7 +227,8 @@
AddStreamFn AddStream, NativeObjectCache Cache)>;
/// This ThinBackend runs the individual backend jobs in-process.
-ThinBackend createInProcessThinBackend(unsigned ParallelismLevel);
+/// The default value means to use one job per hardware core (not hyper-thread).
+ThinBackend createInProcessThinBackend(unsigned ParallelismLevel = 0);
/// This ThinBackend writes individual module indexes to files, instead of
/// running the individual backend jobs. This backend is for distributed builds
diff --git a/llvm/include/llvm/Support/ThreadPool.h b/llvm/include/llvm/Support/ThreadPool.h
index 4bcbaa3..2036f46 100644
--- a/llvm/include/llvm/Support/ThreadPool.h
+++ b/llvm/include/llvm/Support/ThreadPool.h
@@ -13,7 +13,9 @@
#ifndef LLVM_SUPPORT_THREAD_POOL_H
#define LLVM_SUPPORT_THREAD_POOL_H
+#include "llvm/ADT/BitVector.h"
#include "llvm/Config/llvm-config.h"
+#include "llvm/Support/Threading.h"
#include "llvm/Support/thread.h"
#include <future>
@@ -38,12 +40,11 @@
using TaskTy = std::function<void()>;
using PackagedTaskTy = std::packaged_task<void()>;
- /// Construct a pool with the number of threads found by
- /// hardware_concurrency().
- ThreadPool();
-
- /// Construct a pool of \p ThreadCount threads
- ThreadPool(unsigned ThreadCount);
+ /// Construct a pool using the hardware strategy \p S for mapping hardware
+ /// execution resources (threads, cores, CPUs)
+ /// Defaults to using the maximum execution resources in the system, but
+ /// excluding any resources contained in the affinity mask.
+ ThreadPool(ThreadPoolStrategy S = hardware_concurrency());
/// Blocking destructor: the pool will wait for all the threads to complete.
~ThreadPool();
@@ -68,6 +69,8 @@
/// It is an error to try to add new tasks while blocking on this call.
void wait();
+ unsigned getThreadCount() const { return ThreadCount; }
+
private:
/// Asynchronous submission of a task to the pool. The returned future can be
/// used to wait for the task to finish and is *non-blocking* on destruction.
@@ -94,6 +97,8 @@
/// Signal for the destruction of the pool, asking thread to exit.
bool EnableFlag;
#endif
+
+ unsigned ThreadCount;
};
}
diff --git a/llvm/include/llvm/Support/Threading.h b/llvm/include/llvm/Support/Threading.h
index bacab8f..d3d4a37 100644
--- a/llvm/include/llvm/Support/Threading.h
+++ b/llvm/include/llvm/Support/Threading.h
@@ -14,6 +14,7 @@
#ifndef LLVM_SUPPORT_THREADING_H
#define LLVM_SUPPORT_THREADING_H
+#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/FunctionExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Config/llvm-config.h" // for LLVM_ON_UNIX
@@ -143,20 +144,52 @@
#endif
}
- /// Get the amount of currency to use for tasks requiring significant
- /// memory or other resources. Currently based on physical cores, if
- /// available for the host system, otherwise falls back to
- /// thread::hardware_concurrency().
- /// Returns 1 when LLVM is configured with LLVM_ENABLE_THREADS=OFF
- unsigned heavyweight_hardware_concurrency();
+ /// This tells how a thread pool will be used
+ class ThreadPoolStrategy {
+ public:
+ // The default value (0) means all available threads should be used,
+ // excluding affinity mask. If set, this value only represents a suggested
+ // high bound, the runtime might choose a lower value (not higher).
+ unsigned ThreadsRequested = 0;
- /// Get the number of threads that the current program can execute
- /// concurrently. On some systems std::thread::hardware_concurrency() returns
- /// the total number of cores, without taking affinity into consideration.
- /// Returns 1 when LLVM is configured with LLVM_ENABLE_THREADS=OFF.
- /// Fallback to std::thread::hardware_concurrency() if sched_getaffinity is
- /// not available.
- unsigned hardware_concurrency();
+ // If SMT is active, use hyper threads. If false, there will be only one
+ // std::thread per core.
+ bool UseHyperThreads = true;
+
+ /// Retrieves the max available threads for the current strategy. This
+ /// accounts for affinity masks and takes advantage of all CPU sockets.
+ unsigned compute_thread_count() const;
+
+ /// Assign the current thread to an ideal hardware CPU or NUMA node. In a
+ /// multi-socket system, this ensures threads are assigned to all CPU
+ /// sockets. \p ThreadPoolNum represents a number bounded by [0,
+ /// compute_thread_count()).
+ void apply_thread_strategy(unsigned ThreadPoolNum) const;
+ };
+
+ /// Returns a thread strategy for tasks requiring significant memory or other
+ /// resources. To be used for workloads where hardware_concurrency() proves to
+ /// be less efficient. Avoid this strategy if doing lots of I/O. Currently
+ /// based on physical cores, if available for the host system, otherwise falls
+ /// back to hardware_concurrency(). Returns 1 when LLVM is configured with
+ /// LLVM_ENABLE_THREADS = OFF
+ inline ThreadPoolStrategy
+ heavyweight_hardware_concurrency(unsigned ThreadCount = 0) {
+ ThreadPoolStrategy S;
+ S.UseHyperThreads = false;
+ S.ThreadsRequested = ThreadCount;
+ return S;
+ }
+
+ /// Returns a default thread strategy where all available hardware ressources
+ /// are to be used, except for those initially excluded by an affinity mask.
+ /// This function takes affinity into consideration. Returns 1 when LLVM is
+ /// configured with LLVM_ENABLE_THREADS=OFF.
+ inline ThreadPoolStrategy hardware_concurrency(unsigned ThreadCount = 0) {
+ ThreadPoolStrategy S;
+ S.ThreadsRequested = ThreadCount;
+ return S;
+ }
/// Return the current thread id, as used in various OS system calls.
/// Note that not all platforms guarantee that the value returned will be
@@ -184,6 +217,14 @@
/// the operation succeeded or failed is returned.
void get_thread_name(SmallVectorImpl<char> &Name);
+ /// Returns a mask that represents on which hardware thread, core, CPU, NUMA
+ /// group, the calling thread can be executed. On Windows, threads cannot
+ /// cross CPU boundaries.
+ llvm::BitVector get_thread_affinity_mask();
+
+ /// Returns how many physical CPUs or NUMA groups the system has.
+ unsigned get_cpus();
+
enum class ThreadPriority {
Background = 0,
Default = 1,
diff --git a/llvm/lib/CodeGen/ParallelCG.cpp b/llvm/lib/CodeGen/ParallelCG.cpp
index 7dbd830..c19ed1f 100644
--- a/llvm/lib/CodeGen/ParallelCG.cpp
+++ b/llvm/lib/CodeGen/ParallelCG.cpp
@@ -51,7 +51,7 @@
// Create ThreadPool in nested scope so that threads will be joined
// on destruction.
{
- ThreadPool CodegenThreadPool(OSs.size());
+ ThreadPool CodegenThreadPool(hardware_concurrency(OSs.size()));
int ThreadCount = 0;
SplitModule(
diff --git a/llvm/lib/DWARFLinker/DWARFLinker.cpp b/llvm/lib/DWARFLinker/DWARFLinker.cpp
index 03919c8..715ad24 100644
--- a/llvm/lib/DWARFLinker/DWARFLinker.cpp
+++ b/llvm/lib/DWARFLinker/DWARFLinker.cpp
@@ -2446,7 +2446,7 @@
}
EmitLambda();
} else {
- ThreadPool Pool(2);
+ ThreadPool Pool(hardware_concurrency(2));
Pool.async(AnalyzeAll);
Pool.async(CloneAll);
Pool.wait();
diff --git a/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp b/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp
index e01b6b6..c3bf71f 100644
--- a/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp
+++ b/llvm/lib/DebugInfo/GSYM/DwarfTransformer.cpp
@@ -445,7 +445,7 @@
// Now parse all DIEs in case we have cross compile unit references in a
// thread pool.
- ThreadPool pool(NumThreads);
+ ThreadPool pool(hardware_concurrency(NumThreads));
for (const auto &CU : DICtx.compile_units())
pool.async([&CU]() { CU->getUnitDIE(false /*CUDieOnly*/); });
pool.wait();
diff --git a/llvm/lib/ExecutionEngine/Orc/LLJIT.cpp b/llvm/lib/ExecutionEngine/Orc/LLJIT.cpp
index f81e584..4218ca4 100644
--- a/llvm/lib/ExecutionEngine/Orc/LLJIT.cpp
+++ b/llvm/lib/ExecutionEngine/Orc/LLJIT.cpp
@@ -157,7 +157,8 @@
if (S.NumCompileThreads > 0) {
TransformLayer->setCloneToNewContextOnEmit(true);
- CompileThreads = std::make_unique<ThreadPool>(S.NumCompileThreads);
+ CompileThreads =
+ std::make_unique<ThreadPool>(hardware_concurrency(S.NumCompileThreads));
ES->setDispatchMaterialization(
[this](JITDylib &JD, std::unique_ptr<MaterializationUnit> MU) {
// FIXME: Switch to move capture once we have c++14.
diff --git a/llvm/lib/LTO/LTO.cpp b/llvm/lib/LTO/LTO.cpp
index 1d23c6b..f8affcb 100644
--- a/llvm/lib/LTO/LTO.cpp
+++ b/llvm/lib/LTO/LTO.cpp
@@ -477,8 +477,7 @@
LTO::ThinLTOState::ThinLTOState(ThinBackend Backend)
: Backend(Backend), CombinedIndex(/*HaveGVs*/ false) {
if (!Backend)
- this->Backend =
- createInProcessThinBackend(llvm::heavyweight_hardware_concurrency());
+ this->Backend = createInProcessThinBackend();
}
LTO::LTO(Config Conf, ThinBackend Backend,
@@ -1095,7 +1094,8 @@
const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
AddStreamFn AddStream, NativeObjectCache Cache)
: ThinBackendProc(Conf, CombinedIndex, ModuleToDefinedGVSummaries),
- BackendThreadPool(ThinLTOParallelismLevel),
+ BackendThreadPool(
+ heavyweight_hardware_concurrency(ThinLTOParallelismLevel)),
AddStream(std::move(AddStream)), Cache(std::move(Cache)) {
for (auto &Name : CombinedIndex.cfiFunctionDefs())
CfiFunctionDefs.insert(
diff --git a/llvm/lib/LTO/LTOBackend.cpp b/llvm/lib/LTO/LTOBackend.cpp
index b854715..ec57744 100644
--- a/llvm/lib/LTO/LTOBackend.cpp
+++ b/llvm/lib/LTO/LTOBackend.cpp
@@ -375,7 +375,8 @@
void splitCodeGen(const Config &C, TargetMachine *TM, AddStreamFn AddStream,
unsigned ParallelCodeGenParallelismLevel,
std::unique_ptr<Module> Mod) {
- ThreadPool CodegenThreadPool(ParallelCodeGenParallelismLevel);
+ ThreadPool CodegenThreadPool(
+ heavyweight_hardware_concurrency(ParallelCodeGenParallelismLevel));
unsigned ThreadCount = 0;
const Target *T = &TM->getTarget();
diff --git a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
index a4f2702..152f0af 100644
--- a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
+++ b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
@@ -80,8 +80,8 @@
namespace {
-static cl::opt<int>
- ThreadCount("threads", cl::init(llvm::heavyweight_hardware_concurrency()));
+// Default to using one job per hardware core in the system
+static cl::opt<int> ThreadCount("threads", cl::init(0));
// Simple helper to save temporary files for debug.
static void saveTempBitcode(const Module &TheModule, StringRef TempDir,
@@ -1042,7 +1042,7 @@
// Parallel optimizer + codegen
{
- ThreadPool Pool(ThreadCount);
+ ThreadPool Pool(heavyweight_hardware_concurrency(ThreadCount));
for (auto IndexCount : ModulesOrdering) {
auto &Mod = Modules[IndexCount];
Pool.async([&](int count) {
diff --git a/llvm/lib/Support/Host.cpp b/llvm/lib/Support/Host.cpp
index ef38c1c..7e772b2 100644
--- a/llvm/lib/Support/Host.cpp
+++ b/llvm/lib/Support/Host.cpp
@@ -1266,7 +1266,7 @@
// 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() {
+int computeHostNumPhysicalCores() {
// 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 =
@@ -1312,7 +1312,7 @@
#include <sys/sysctl.h>
// Gets the number of *physical cores* on the machine.
-static int computeHostNumPhysicalCores() {
+int computeHostNumPhysicalCores() {
uint32_t count;
size_t len = sizeof(count);
sysctlbyname("hw.physicalcpu", &count, &len, NULL, 0);
@@ -1326,6 +1326,9 @@
}
return count;
}
+#elif defined(_WIN32)
+// Defined in llvm/lib/Support/Windows/Threading.inc
+int computeHostNumPhysicalCores();
#else
// On other systems, return -1 to indicate unknown.
static int computeHostNumPhysicalCores() { return -1; }
diff --git a/llvm/lib/Support/Parallel.cpp b/llvm/lib/Support/Parallel.cpp
index 523665d..0272a53 100644
--- a/llvm/lib/Support/Parallel.cpp
+++ b/llvm/lib/Support/Parallel.cpp
@@ -39,20 +39,21 @@
/// in filo order.
class ThreadPoolExecutor : public Executor {
public:
- explicit ThreadPoolExecutor(unsigned ThreadCount = hardware_concurrency()) {
+ explicit ThreadPoolExecutor(ThreadPoolStrategy S = hardware_concurrency()) {
+ unsigned ThreadCount = S.compute_thread_count();
// Spawn all but one of the threads in another thread as spawning threads
// can take a while.
Threads.reserve(ThreadCount);
Threads.resize(1);
std::lock_guard<std::mutex> Lock(Mutex);
- Threads[0] = std::thread([&, ThreadCount] {
- for (unsigned i = 1; i < ThreadCount; ++i) {
- Threads.emplace_back([=] { work(); });
+ Threads[0] = std::thread([this, ThreadCount, S] {
+ for (unsigned I = 1; I < ThreadCount; ++I) {
+ Threads.emplace_back([=] { work(S, I); });
if (Stop)
break;
}
ThreadsCreated.set_value();
- work();
+ work(S, 0);
});
}
@@ -90,7 +91,8 @@
}
private:
- void work() {
+ void work(ThreadPoolStrategy S, unsigned ThreadID) {
+ S.apply_thread_strategy(ThreadID);
while (true) {
std::unique_lock<std::mutex> Lock(Mutex);
Cond.wait(Lock, [&] { return Stop || !WorkStack.empty(); });
diff --git a/llvm/lib/Support/ThreadPool.cpp b/llvm/lib/Support/ThreadPool.cpp
index 40982d7..5aa5815 100644
--- a/llvm/lib/Support/ThreadPool.cpp
+++ b/llvm/lib/Support/ThreadPool.cpp
@@ -20,16 +20,15 @@
#if LLVM_ENABLE_THREADS
-// Default to hardware_concurrency
-ThreadPool::ThreadPool() : ThreadPool(hardware_concurrency()) {}
-
-ThreadPool::ThreadPool(unsigned ThreadCount)
- : ActiveThreads(0), EnableFlag(true) {
+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([&] {
+ Threads.emplace_back([S, ThreadID, this] {
+ S.apply_thread_strategy(ThreadID);
while (true) {
PackagedTaskTy Task;
{
@@ -108,12 +107,10 @@
#else // LLVM_ENABLE_THREADS Disabled
-ThreadPool::ThreadPool() : ThreadPool(0) {}
-
// No threads are launched, issue a warning if ThreadCount is not 0
-ThreadPool::ThreadPool(unsigned ThreadCount)
- : ActiveThreads(0) {
- if (ThreadCount) {
+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";
}
@@ -138,8 +135,6 @@
return Future;
}
-ThreadPool::~ThreadPool() {
- wait();
-}
+ThreadPool::~ThreadPool() { wait(); }
#endif
diff --git a/llvm/lib/Support/Threading.cpp b/llvm/lib/Support/Threading.cpp
index 48750ce..de5adad 100644
--- a/llvm/lib/Support/Threading.cpp
+++ b/llvm/lib/Support/Threading.cpp
@@ -45,10 +45,6 @@
Fn(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; }
@@ -57,6 +53,13 @@
void llvm::get_thread_name(SmallVectorImpl<char> &Name) { Name.clear(); }
+llvm::BitVector llvm::get_thread_affinity_mask() { return {}; }
+
+unsigned llvm::ThreadPoolStrategy::compute_thread_count() const {
+ // When threads are disabled, ensure clients will loop at least once.
+ return 1;
+}
+
#if LLVM_ENABLE_THREADS == 0
void llvm::llvm_execute_on_thread_async(
llvm::unique_function<void()> Func,
@@ -78,30 +81,19 @@
#else
-#include <thread>
-unsigned llvm::heavyweight_hardware_concurrency() {
- // Since we can't get here unless LLVM_ENABLE_THREADS == 1, it is safe to use
- // `std::thread` directly instead of `llvm::thread` (and indeed, doing so
- // allows us to not define `thread` in the llvm namespace, which conflicts
- // with some platforms such as FreeBSD whose headers also define a struct
- // called `thread` in the global namespace which can cause ambiguity due to
- // ADL.
- int NumPhysical = sys::getHostNumPhysicalCores();
- if (NumPhysical == -1)
- return std::thread::hardware_concurrency();
- return NumPhysical;
-}
+int computeHostNumHardwareThreads();
-unsigned llvm::hardware_concurrency() {
-#if defined(HAVE_SCHED_GETAFFINITY) && defined(HAVE_CPU_COUNT)
- 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;
+unsigned llvm::ThreadPoolStrategy::compute_thread_count() const {
+ int MaxThreadCount = UseHyperThreads ? computeHostNumHardwareThreads()
+ : sys::getHostNumPhysicalCores();
+ if (MaxThreadCount <= 0)
+ MaxThreadCount = 1;
+
+ // No need to create more threads than there are hardware threads, it would
+ // uselessly induce more context-switching and cache eviction.
+ if (!ThreadsRequested || ThreadsRequested > (unsigned)MaxThreadCount)
+ return MaxThreadCount;
+ return ThreadsRequested;
}
namespace {
diff --git a/llvm/lib/Support/Unix/Threading.inc b/llvm/lib/Support/Unix/Threading.inc
index afb887f..8cacaa8 100644
--- a/llvm/lib/Support/Unix/Threading.inc
+++ b/llvm/lib/Support/Unix/Threading.inc
@@ -267,3 +267,27 @@
#endif
return SetThreadPriorityResult::FAILURE;
}
+
+#include <thread>
+
+int computeHostNumHardwareThreads() {
+#if defined(HAVE_SCHED_GETAFFINITY) && defined(HAVE_CPU_COUNT)
+ 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;
+}
+
+void llvm::ThreadPoolStrategy::apply_thread_strategy(
+ unsigned ThreadPoolNum) const {}
+
+llvm::BitVector llvm::get_thread_affinity_mask() {
+ // FIXME: Implement
+ llvm_unreachable("Not implemented!");
+}
+
+unsigned llvm::get_cpus() { return 1; }
diff --git a/llvm/lib/Support/Windows/Threading.inc b/llvm/lib/Support/Windows/Threading.inc
index 9456efa..eb92296 100644
--- a/llvm/lib/Support/Windows/Threading.inc
+++ b/llvm/lib/Support/Windows/Threading.inc
@@ -16,6 +16,8 @@
#include "WindowsSupport.h"
#include <process.h>
+#include <bitset>
+
// Windows will at times define MemoryFence.
#ifdef MemoryFence
#undef MemoryFence
@@ -122,3 +124,163 @@
? SetThreadPriorityResult::SUCCESS
: SetThreadPriorityResult::FAILURE;
}
+
+struct ProcessorGroup {
+ unsigned ID;
+ unsigned AllThreads;
+ unsigned UsableThreads;
+ unsigned ThreadsPerCore;
+ uint64_t Affinity;
+};
+
+template <typename F>
+static bool IterateProcInfo(LOGICAL_PROCESSOR_RELATIONSHIP Relationship, F Fn) {
+ DWORD Len = 0;
+ BOOL R = ::GetLogicalProcessorInformationEx(Relationship, NULL, &Len);
+ if (R || GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
+ return false;
+ }
+ auto *Info = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)calloc(1, Len);
+ R = ::GetLogicalProcessorInformationEx(Relationship, Info, &Len);
+ if (R) {
+ auto *End =
+ (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)((uint8_t *)Info + Len);
+ for (auto *Curr = Info; Curr < End;
+ Curr = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)((uint8_t *)Curr +
+ Curr->Size)) {
+ if (Curr->Relationship != Relationship)
+ continue;
+ Fn(Curr);
+ }
+ }
+ free(Info);
+ return true;
+}
+
+static ArrayRef<ProcessorGroup> getProcessorGroups() {
+ auto computeGroups = []() {
+ SmallVector<ProcessorGroup, 4> Groups;
+
+ auto HandleGroup = [&](SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *ProcInfo) {
+ GROUP_RELATIONSHIP &El = ProcInfo->Group;
+ for (unsigned J = 0; J < El.ActiveGroupCount; ++J) {
+ ProcessorGroup G;
+ G.ID = Groups.size();
+ G.AllThreads = El.GroupInfo[J].MaximumProcessorCount;
+ G.UsableThreads = El.GroupInfo[J].ActiveProcessorCount;
+ assert(G.UsableThreads <= 64);
+ G.Affinity = El.GroupInfo[J].ActiveProcessorMask;
+ Groups.push_back(G);
+ }
+ };
+
+ if (!IterateProcInfo(RelationGroup, HandleGroup))
+ return std::vector<ProcessorGroup>();
+
+ auto HandleProc = [&](SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *ProcInfo) {
+ PROCESSOR_RELATIONSHIP &El = ProcInfo->Processor;
+ assert(El.GroupCount == 1);
+ unsigned NumHyperThreads = 1;
+ // If the flag is set, each core supports more than one hyper-thread.
+ if (El.Flags & LTP_PC_SMT)
+ NumHyperThreads = std::bitset<64>(El.GroupMask[0].Mask).count();
+ unsigned I = El.GroupMask[0].Group;
+ Groups[I].ThreadsPerCore = NumHyperThreads;
+ };
+
+ if (!IterateProcInfo(RelationProcessorCore, HandleProc))
+ return std::vector<ProcessorGroup>();
+
+ // If there's an affinity mask set on one of the CPUs, then assume the user
+ // wants to constrain the current process to only a single CPU.
+ for (auto &G : Groups) {
+ if (G.UsableThreads != G.AllThreads) {
+ ProcessorGroup NewG{G};
+ Groups.clear();
+ Groups.push_back(NewG);
+ break;
+ }
+ }
+
+ return std::vector<ProcessorGroup>(Groups.begin(), Groups.end());
+ };
+ static auto Groups = computeGroups();
+ return ArrayRef<ProcessorGroup>(Groups);
+}
+
+template <typename R, typename UnaryPredicate>
+static unsigned aggregate(R &&Range, UnaryPredicate P) {
+ unsigned I{};
+ for (const auto &It : Range)
+ I += P(It);
+ return I;
+}
+
+// for sys::getHostNumPhysicalCores
+int computeHostNumPhysicalCores() {
+ static unsigned Cores =
+ aggregate(getProcessorGroups(), [](const ProcessorGroup &G) {
+ return G.UsableThreads / G.ThreadsPerCore;
+ });
+ return Cores;
+}
+
+int computeHostNumHardwareThreads() {
+ static unsigned Threads =
+ aggregate(getProcessorGroups(),
+ [](const ProcessorGroup &G) { return G.UsableThreads; });
+ return Threads;
+}
+
+// Assign the current thread to a more appropriate CPU socket or CPU group
+void llvm::ThreadPoolStrategy::apply_thread_strategy(
+ unsigned ThreadPoolNum) const {
+ ArrayRef<ProcessorGroup> Groups = getProcessorGroups();
+
+ assert(ThreadPoolNum < compute_thread_count() &&
+ "The thread index is not within thread strategy's range!");
+
+ // In this mode, the ThreadNumber represents the core number, not the
+ // hyper-thread number. Assumes all NUMA groups have the same amount of
+ // hyper-threads.
+ if (!UseHyperThreads)
+ ThreadPoolNum *= Groups[0].ThreadsPerCore;
+
+ unsigned ThreadRangeStart = 0;
+ for (unsigned I = 0; I < Groups.size(); ++I) {
+ const ProcessorGroup &G = Groups[I];
+ if (ThreadPoolNum >= ThreadRangeStart &&
+ ThreadPoolNum < ThreadRangeStart + G.UsableThreads) {
+
+ GROUP_AFFINITY Affinity{};
+ Affinity.Group = G.ID;
+ Affinity.Mask = G.Affinity;
+ SetThreadGroupAffinity(GetCurrentThread(), &Affinity, nullptr);
+ }
+ ThreadRangeStart += G.UsableThreads;
+ }
+}
+
+llvm::BitVector llvm::get_thread_affinity_mask() {
+ GROUP_AFFINITY Affinity{};
+ GetThreadGroupAffinity(GetCurrentThread(), &Affinity);
+
+ static unsigned All =
+ aggregate(getProcessorGroups(),
+ [](const ProcessorGroup &G) { return G.AllThreads; });
+
+ unsigned StartOffset =
+ aggregate(getProcessorGroups(), [&](const ProcessorGroup &G) {
+ return G.ID < Affinity.Group ? G.AllThreads : 0;
+ });
+
+ llvm::BitVector V;
+ V.resize(All);
+ for (unsigned I = 0; I < sizeof(KAFFINITY) * 8; ++I) {
+ if ((Affinity.Mask >> I) & 1)
+ V.set(StartOffset + I);
+ }
+ return V;
+}
+
+unsigned llvm::get_cpus() { return getProcessorGroups().size(); }
diff --git a/llvm/tools/dsymutil/dsymutil.cpp b/llvm/tools/dsymutil/dsymutil.cpp
index 6b26081..54adeaa 100644
--- a/llvm/tools/dsymutil/dsymutil.cpp
+++ b/llvm/tools/dsymutil/dsymutil.cpp
@@ -258,7 +258,7 @@
if (opt::Arg *NumThreads = Args.getLastArg(OPT_threads))
Options.LinkOpts.Threads = atoi(NumThreads->getValue());
else
- Options.LinkOpts.Threads = thread::hardware_concurrency();
+ Options.LinkOpts.Threads = 0; // Use all available hardware threads
if (Options.DumpDebugMap || Options.LinkOpts.Verbose)
Options.LinkOpts.Threads = 1;
@@ -541,9 +541,10 @@
// Shared a single binary holder for all the link steps.
BinaryHolder BinHolder;
- unsigned ThreadCount =
- std::min<unsigned>(Options.LinkOpts.Threads, DebugMapPtrsOrErr->size());
- ThreadPool Threads(ThreadCount);
+ unsigned ThreadCount = Options.LinkOpts.Threads;
+ if (!ThreadCount)
+ ThreadCount = DebugMapPtrsOrErr->size();
+ ThreadPool Threads(hardware_concurrency(ThreadCount));
// If there is more than one link to execute, we need to generate
// temporary files.
diff --git a/llvm/tools/gold/gold-plugin.cpp b/llvm/tools/gold/gold-plugin.cpp
index f68f718..2a9398f 100644
--- a/llvm/tools/gold/gold-plugin.cpp
+++ b/llvm/tools/gold/gold-plugin.cpp
@@ -134,8 +134,8 @@
static unsigned OptLevel = 2;
// Default parallelism of 0 used to indicate that user did not specify.
// Actual parallelism default value depends on implementation.
- // Currently only affects ThinLTO, where the default is
- // llvm::heavyweight_hardware_concurrency.
+ // Currently only affects ThinLTO, where the default is the max cores in the
+ // system.
static unsigned Parallelism = 0;
// Default regular LTO codegen parallelism (number of partitions).
static unsigned ParallelCodeGenParallelismLevel = 1;
diff --git a/llvm/tools/llvm-cov/CodeCoverage.cpp b/llvm/tools/llvm-cov/CodeCoverage.cpp
index 52e9958..625e234 100644
--- a/llvm/tools/llvm-cov/CodeCoverage.cpp
+++ b/llvm/tools/llvm-cov/CodeCoverage.cpp
@@ -947,9 +947,7 @@
// If NumThreads is not specified, auto-detect a good default.
if (NumThreads == 0)
- NumThreads =
- std::max(1U, std::min(llvm::heavyweight_hardware_concurrency(),
- unsigned(SourceFiles.size())));
+ NumThreads = SourceFiles.size();
if (!ViewOpts.hasOutputDirectory() || NumThreads == 1) {
for (const std::string &SourceFile : SourceFiles)
@@ -957,7 +955,7 @@
ShowFilenames);
} else {
// In -output-dir mode, it's safe to use multiple threads to print files.
- ThreadPool Pool(NumThreads);
+ ThreadPool Pool(heavyweight_hardware_concurrency(NumThreads));
for (const std::string &SourceFile : SourceFiles)
Pool.async(&CodeCoverageTool::writeSourceFileView, this, SourceFile,
Coverage.get(), Printer.get(), ShowFilenames);
diff --git a/llvm/tools/llvm-cov/CoverageExporterJson.cpp b/llvm/tools/llvm-cov/CoverageExporterJson.cpp
index 216b5e3..ba8ff5c 100644
--- a/llvm/tools/llvm-cov/CoverageExporterJson.cpp
+++ b/llvm/tools/llvm-cov/CoverageExporterJson.cpp
@@ -163,11 +163,9 @@
ArrayRef<FileCoverageSummary> FileReports,
const CoverageViewOptions &Options) {
auto NumThreads = Options.NumThreads;
- if (NumThreads == 0) {
- NumThreads = std::max(1U, std::min(llvm::heavyweight_hardware_concurrency(),
- unsigned(SourceFiles.size())));
- }
- ThreadPool Pool(NumThreads);
+ if (NumThreads == 0)
+ NumThreads = SourceFiles.size();
+ ThreadPool Pool(heavyweight_hardware_concurrency(NumThreads));
json::Array FileArray;
std::mutex FileArrayMutex;
diff --git a/llvm/tools/llvm-cov/CoverageReport.cpp b/llvm/tools/llvm-cov/CoverageReport.cpp
index 8225954..187e2dc 100644
--- a/llvm/tools/llvm-cov/CoverageReport.cpp
+++ b/llvm/tools/llvm-cov/CoverageReport.cpp
@@ -356,11 +356,8 @@
// If NumThreads is not specified, auto-detect a good default.
if (NumThreads == 0)
- NumThreads =
- std::max(1U, std::min(llvm::heavyweight_hardware_concurrency(),
- unsigned(Files.size())));
-
- ThreadPool Pool(NumThreads);
+ NumThreads = Files.size();
+ ThreadPool Pool(heavyweight_hardware_concurrency(NumThreads));
std::vector<FileCoverageSummary> FileReports;
FileReports.reserve(Files.size());
diff --git a/llvm/tools/llvm-lto2/llvm-lto2.cpp b/llvm/tools/llvm-lto2/llvm-lto2.cpp
index 8deedd4..fc86fd9 100644
--- a/llvm/tools/llvm-lto2/llvm-lto2.cpp
+++ b/llvm/tools/llvm-lto2/llvm-lto2.cpp
@@ -65,8 +65,8 @@
"import files for the "
"distributed backend case"));
-static cl::opt<int> Threads("thinlto-threads",
- cl::init(llvm::heavyweight_hardware_concurrency()));
+// Default to using all hardware cores in the system.
+static cl::opt<int> Threads("thinlto-threads", cl::init(0));
static cl::list<std::string> SymbolResolutions(
"r",
diff --git a/llvm/tools/llvm-profdata/llvm-profdata.cpp b/llvm/tools/llvm-profdata/llvm-profdata.cpp
index 424edf4..f05c7e6 100644
--- a/llvm/tools/llvm-profdata/llvm-profdata.cpp
+++ b/llvm/tools/llvm-profdata/llvm-profdata.cpp
@@ -307,8 +307,11 @@
// If NumThreads is not specified, auto-detect a good default.
if (NumThreads == 0)
- NumThreads =
- std::min(hardware_concurrency(), unsigned((Inputs.size() + 1) / 2));
+ NumThreads = std::min(hardware_concurrency().compute_thread_count(),
+ unsigned((Inputs.size() + 1) / 2));
+ // FIXME: There's a bug here, where setting NumThreads = Inputs.size() fails
+ // the merge_empty_profile.test because the InstrProfWriter.ProfileKind isn't
+ // merged, thus the emitted file ends up with a PF_Unknown kind.
// Initialize the writer contexts.
SmallVector<std::unique_ptr<WriterContext>, 4> Contexts;
@@ -320,7 +323,7 @@
for (const auto &Input : Inputs)
loadInput(Input, Remapper, Contexts[0].get());
} else {
- ThreadPool Pool(NumThreads);
+ ThreadPool Pool(hardware_concurrency(NumThreads));
// Load the inputs in parallel (N/NumThreads serial steps).
unsigned Ctx = 0;
diff --git a/llvm/unittests/Support/Host.cpp b/llvm/unittests/Support/Host.cpp
index 2c17a50..6225234 100644
--- a/llvm/unittests/Support/Host.cpp
+++ b/llvm/unittests/Support/Host.cpp
@@ -37,7 +37,8 @@
// Initially this is only testing detection of the number of
// physical cores, which is currently only supported/tested for
// x86_64 Linux and Darwin.
- return (Host.getArch() == Triple::x86_64 &&
+ return Host.isOSWindows() ||
+ (Host.getArch() == Triple::x86_64 &&
(Host.isOSDarwin() || Host.getOS() == Triple::Linux));
}
diff --git a/llvm/unittests/Support/TaskQueueTest.cpp b/llvm/unittests/Support/TaskQueueTest.cpp
index 0a8aeca..4d8c3e4 100644
--- a/llvm/unittests/Support/TaskQueueTest.cpp
+++ b/llvm/unittests/Support/TaskQueueTest.cpp
@@ -22,7 +22,7 @@
};
TEST_F(TaskQueueTest, OrderedFutures) {
- ThreadPool TP(1);
+ ThreadPool TP(hardware_concurrency(1));
TaskQueue TQ(TP);
std::atomic<int> X{ 0 };
std::atomic<int> Y{ 0 };
@@ -66,7 +66,7 @@
}
TEST_F(TaskQueueTest, UnOrderedFutures) {
- ThreadPool TP(1);
+ ThreadPool TP(hardware_concurrency(1));
TaskQueue TQ(TP);
std::atomic<int> X{ 0 };
std::atomic<int> Y{ 0 };
@@ -96,7 +96,7 @@
}
TEST_F(TaskQueueTest, FutureWithReturnValue) {
- ThreadPool TP(1);
+ ThreadPool TP(hardware_concurrency(1));
TaskQueue TQ(TP);
std::future<std::string> F1 = TQ.async([&] { return std::string("Hello"); });
std::future<int> F2 = TQ.async([&] { return 42; });
diff --git a/llvm/unittests/Support/ThreadPool.cpp b/llvm/unittests/Support/ThreadPool.cpp
index a16adbb..237be87 100644
--- a/llvm/unittests/Support/ThreadPool.cpp
+++ b/llvm/unittests/Support/ThreadPool.cpp
@@ -8,11 +8,13 @@
#include "llvm/Support/ThreadPool.h"
+#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Support/Host.h"
#include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/Threading.h"
#include "gtest/gtest.h"
@@ -69,6 +71,8 @@
void SetUp() override { MainThreadReady = false; }
+ void TestAllThreads(ThreadPoolStrategy S);
+
std::condition_variable WaitMainThread;
std::mutex WaitMainThreadMutex;
bool MainThreadReady = false;
@@ -131,7 +135,7 @@
TEST_F(ThreadPoolTest, GetFuture) {
CHECK_UNSUPPORTED();
- ThreadPool Pool{2};
+ ThreadPool Pool(hardware_concurrency(2));
std::atomic_int i{0};
Pool.async([this, &i] {
waitForMainThread();
@@ -162,3 +166,45 @@
}
ASSERT_EQ(5, checked_in);
}
+
+#if LLVM_ENABLE_THREADS == 1
+
+void ThreadPoolTest::TestAllThreads(ThreadPoolStrategy S) {
+ // FIXME: Skip these tests on non-Windows because multi-socket system were not
+ // tested on Unix yet, and llvm::get_thread_affinity_mask() isn't implemented
+ // for Unix.
+ Triple Host(Triple::normalize(sys::getProcessTriple()));
+ if (!Host.isOSWindows())
+ return;
+
+ llvm::DenseSet<llvm::BitVector> ThreadsUsed;
+ std::mutex Lock;
+ unsigned Threads = 0;
+ {
+ ThreadPool Pool(S);
+ Threads = Pool.getThreadCount();
+ for (size_t I = 0; I < 10000; ++I) {
+ Pool.async([&] {
+ waitForMainThread();
+ std::lock_guard<std::mutex> Guard(Lock);
+ auto Mask = llvm::get_thread_affinity_mask();
+ ThreadsUsed.insert(Mask);
+ });
+ }
+ ASSERT_EQ(true, ThreadsUsed.empty());
+ setMainThreadReady();
+ }
+ ASSERT_EQ(llvm::get_cpus(), ThreadsUsed.size());
+}
+
+TEST_F(ThreadPoolTest, AllThreads_UseAllRessources) {
+ CHECK_UNSUPPORTED();
+ TestAllThreads({});
+}
+
+TEST_F(ThreadPoolTest, AllThreads_OneThreadPerCore) {
+ CHECK_UNSUPPORTED();
+ TestAllThreads(llvm::heavyweight_hardware_concurrency());
+}
+
+#endif
diff --git a/llvm/unittests/Support/Threading.cpp b/llvm/unittests/Support/Threading.cpp
index 183c9aa..c76e6e4 100644
--- a/llvm/unittests/Support/Threading.cpp
+++ b/llvm/unittests/Support/Threading.cpp
@@ -21,7 +21,8 @@
auto Num = heavyweight_hardware_concurrency();
// Since Num is unsigned this will also catch us trying to
// return -1.
- ASSERT_LE(Num, thread::hardware_concurrency());
+ ASSERT_LE(Num.compute_thread_count(),
+ hardware_concurrency().compute_thread_count());
}
#if LLVM_ENABLE_THREADS