tvm
|
Utilities for manipulating thread pool threads. More...
#include <tvm/runtime/c_backend_api.h>
#include <algorithm>
#include <functional>
#include <memory>
#include <vector>
Go to the source code of this file.
Classes | |
class | tvm::runtime::threading::ThreadGroup |
A platform-agnostic abstraction for managing a collection of thread pool threads. More... | |
Namespaces | |
tvm | |
runtime implementation for LibTorch/TorchScript. | |
tvm::runtime | |
tvm::runtime::threading | |
Functions | |
void | tvm::runtime::threading::Yield () |
Platform-agnostic no-op. More... | |
int | tvm::runtime::threading::MaxConcurrency () |
void | tvm::runtime::threading::SetMaxConcurrency (int value) |
Setting the maximum number of available cores. More... | |
void | tvm::runtime::threading::ResetThreadPool () |
Reset the threads in the pool. All current threads are destroyed and new ones are created. More... | |
void | tvm::runtime::threading::Configure (tvm::runtime::threading::ThreadGroup::AffinityMode mode, int nthreads, std::vector< unsigned int > cpus) |
Configuring the CPU affinity mode for the working threads. More... | |
int32_t | tvm::runtime::threading::NumThreads () |
Get the number of threads being used by the TVM runtime. More... | |
template<typename T > | |
void | tvm::runtime::parallel_for_with_threading_backend (T flambda, int64_t begin, int64_t end) |
Utilities for manipulating thread pool threads.