diff options
| author |  Xiaoqiang Zheng <zhengxq@google.com> | 2016-11-03 14:45:38 -0800 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2016-11-03 16:04:02 -0700 |
| commit | 703fce57eaae725c4ae4b0bd23629c4f04a9de16 (patch) | |
| tree | 4e35bad60529401ff4b61f1235194994df4bcb2e /tensorflow/python/kernel_tests/embedding_ops_test.py | |
| parent | 2d26b09f5c1637857ef309ca58a9126ec44b6008 (diff) | |
Add a fused adjust_hue that is 6-7 times faster on CPU. The GPU kernel will be
added in a separate CL. For now, the fused implementation can be chosen with
the environmental variable "TF_ADJUST_HUE_FUSED=1"
Before the CL:
benchmarkAdjustHue_299_299_3_cpu1 step_time: 15951.86 us
benchmarkAdjustHue_299_299_3_cpu_all step_time: 2732.68 us
After the CL:
benchmarkAdjustHue_299_299_3_cpu1 step_time: 2450.50 us
benchmarkAdjustHue_299_299_3_cpu_all step_time: 399.18 us
Change: 138128641
Diffstat (limited to 'tensorflow/python/kernel_tests/embedding_ops_test.py')
0 files changed, 0 insertions, 0 deletions