diff options
| author |  Geoffrey Irving <geoffreyi@google.com> | 2016-02-19 17:10:09 -0800 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2016-02-19 20:32:43 -0800 |
| commit | fbf652193590d56ae556fbc1a3ea0ab5c7d5e154 (patch) | |
| tree | 741948245e394121b124029b8356e14d2a85a3f8 /.gitmodules | |
| parent | 28117ca16f60501feb1716f7c4b05cd3f20bee31 (diff) | |
Flush denormals to zero on both CPU and GPU
Two different mechanisms are required. On the CPU, we push and pop the
appropriate processor flags in the executor (for the master thread) *and*
in each threadpool thread, since the processor flags are thread local. On
the GPU, we set -ftz=true for both nvcc and gcudacc so that kernels that we
build flush denormals to zero using instruction flags.
Caveat: On GPU, only single precision denormals are flushed to zero; double
precision is unchanged.
Change: 115114845
Diffstat (limited to '.gitmodules')
0 files changed, 0 insertions, 0 deletions