devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Minor cleanups: 1. Get rid of unused variables. 2. Get rid of last uses of EIGEN_USE_COST_MODEL.

Browse Source
This commit is contained in:
Rasmus Munk Larsen
2016-05-18 15:09:48 -07:00
parent 86ae94462e
commit 7df811cfe5
4 changed files with 6 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h
View File

@@ -248,16 +248,12 @@ struct FullReducer<Self, Op, ThreadPoolDevice, Vectorizable> {
*output = reducer.finalize(reducer.initialize());
return;
}
#ifdef EIGEN_USE_COST_MODEL
const TensorOpCost cost =
self.m_impl.costPerCoeff(Vectorizable) +
TensorOpCost(0, 0, internal::functor_traits<Op>::Cost, Vectorizable,
PacketSize);
const int num_threads = TensorCostModel<ThreadPoolDevice>::numThreads(
num_coeffs, cost, device.numThreads());
#else
const int num_threads = device.numThreads();
#endif
if (num_threads == 1) {
*output =
InnerMostDimReducer<Self, Op, Vectorizable>::reduce(self, 0, num_coeffs, reducer);
@@ -472,22 +468,14 @@ struct TensorEvaluator<const TensorReductionOp<Op, Dims, ArgType>, Device>
EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE const Dimensions& dimensions() const { return m_dimensions; }
static bool size_large_enough(Index total_size) {
#ifndef EIGEN_USE_COST_MODEL
return total_size > 1024 * 1024;
#else
return true || total_size;
#endif
}
EIGEN_STRONG_INLINE EIGEN_DEVICE_FUNC bool evalSubExprsIfNeeded(CoeffReturnType* data) {
m_impl.evalSubExprsIfNeeded(NULL);
// Use the FullReducer if possible.
if (RunningFullReduction && internal::FullReducer<Self, Op, Device>::HasOptimizedImplementation &&
if (RunningFullReduction &&
internal::FullReducer<Self, Op, Device>::HasOptimizedImplementation &&
((RunningOnGPU && (m_device.majorDeviceVersion() >= 3)) ||
(!RunningOnGPU && size_large_enough(internal::array_prod(m_impl.dimensions()))))) {
!RunningOnGPU)) {
bool need_assign = false;
if (!data) {
m_result = static_cast<CoeffReturnType*>(m_device.allocate(sizeof(CoeffReturnType)));