https://github.com/Microsoft/CNTK
Revision 40af7bb68fa3ca245676b81938568aedefcb5ece authored by Bowen Bao on 18 September 2018, 01:10:34 UTC, committed by Bowen Bao on 18 September 2018, 01:10:34 UTC
* CPU.
  - Short-circuit the call to ComputeConvolveGeometryExplicit() when
    MKL is enabled.
  - Replace div/mod inside ComputeConvolveGeometryExplicit with
    fast_divmod.
* GPU.
  - Instead of creating a new CuDnnConvolutionEngine for every batch,
    just update the geometry related info, and try to reuse the
    workspacememory from previous run.
1 parent 1f28c7d
History
Tip revision: 40af7bb68fa3ca245676b81938568aedefcb5ece authored by Bowen Bao on 18 September 2018, 01:10:34 UTC
Improve conv performance with freedimension
Tip revision: 40af7bb
File Mode Size
Documentation
Examples
Manual
PretrainedModels
Scripts
Source
Tests
Tools
Tutorials
bindings
external
.clang-format -rw-r--r-- 951 bytes
.gitattributes -rw-r--r-- 3.4 KB
.gitignore -rw-r--r-- 8.4 KB
.gitmodules -rw-r--r-- 367 bytes
CMakeLists.txt -rw-r--r-- 269 bytes
CNTK.Common.props -rw-r--r-- 3.4 KB
CNTK.Cpp.props -rw-r--r-- 10.8 KB
CNTK.sln -rw-r--r-- 264.7 KB
CONTRIBUTING.md -rw-r--r-- 210 bytes
CppCntk.vssettings -rw-r--r-- 10.0 KB
LICENSE.md -rw-r--r-- 1.1 KB
Makefile -rw-r--r-- 70.4 KB
README.md -rw-r--r-- 17.0 KB
ThirdPartyNotices.md -rw-r--r-- 21.0 KB
configure -rwxr-xr-x 37.4 KB

README.md

back to top