GitHub-Proxy/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-05-03 01:04:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix a couple of typos in the code.

Browse Source
This commit is contained in:
Benoit Steiner 2016-03-07 14:31:27 -08:00
parent e5f25622e2
commit 7f87cc3a3b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
View File

@ -220,7 +220,7 @@ EIGEN_DEVICE_FUNC inline void TensorExecutor<Expression, GpuDevice, false>::run(
if (needs_assign) if (needs_assign)
{ {
const int block_size = device.maxCudaThreadsPerBlock(); const int block_size = device.maxCudaThreadsPerBlock();
const int max_blocks = numext::maxi<int>(device.maxBlocks(), device.getNumCudaMultiProcessors() * device.maxCudaThreadsPerMultiProcessor() / block_size); const int max_blocks = numext::mini<int>(device.maxBlocks(), device.getNumCudaMultiProcessors() * device.maxCudaThreadsPerMultiProcessor() / block_size);
const Index size = array_prod(evaluator.dimensions()); const Index size = array_prod(evaluator.dimensions());
// Create a least one block to ensure we won't crash if we're called with tensors of size 0. // Create a least one block to ensure we won't crash if we're called with tensors of size 0.
const int num_blocks = numext::maxi<int>(numext::mini<int>(max_blocks, (size + block_size - 1) / block_size), 1); const int num_blocks = numext::maxi<int>(numext::mini<int>(max_blocks, (size + block_size - 1) / block_size), 1);
@ -239,7 +239,7 @@ EIGEN_DEVICE_FUNC inline void TensorExecutor<Expression, GpuDevice, true>::run(c
if (needs_assign) if (needs_assign)
{ {
const int block_size = device.maxCudaThreadsPerBlock(); const int block_size = device.maxCudaThreadsPerBlock();
const int max_blocks = numext::maxi<int>(device.maxBlocks(), device.getNumCudaMultiProcessors() * device.maxCudaThreadsPerMultiProcessor() / block_size); const int max_blocks = numext::mini<int>(device.maxBlocks(), device.getNumCudaMultiProcessors() * device.maxCudaThreadsPerMultiProcessor() / block_size);
const Index size = array_prod(evaluator.dimensions()); const Index size = array_prod(evaluator.dimensions());
// Create a least one block to ensure we won't crash if we're called with tensors of size 0. // Create a least one block to ensure we won't crash if we're called with tensors of size 0.
const int num_blocks = numext::maxi<int>(numext::mini<int>(max_blocks, (size + block_size - 1) / block_size), 1); const int num_blocks = numext::maxi<int>(numext::mini<int>(max_blocks, (size + block_size - 1) / block_size), 1);