Pass -O3 when building tensorflow with clang -c opt. (This isn't hooked

up to the OSS build yet, we're working on it.)
Change: 123248081

2 files changed, 14 insertions, 0 deletions

diff --git a/tensorflow/tensorflow.bzl b/tensorflow/tensorflow.bzl
index acc01eae84..1e73e00a3f 100644
--- a/tensorflow/tensorflow.bzl
+++ b/tensorflow/tensorflow.bzl
@@ -314,6 +314,11 @@ def _cuda_copts():
                 "--cuda-gpu-arch=sm_35",
             ]
         ),
+    }) + select({
+        # Pass -O3 when building CUDA code with clang; some important
+        # optimizations are not enabled at O2.
+        "//third_party/gpus/cuda:using_clang_opt": ["-O3"],
+        "//conditions:default": [],
     })
 
 # Build defs for TensorFlow kernels
diff --git a/third_party/gpus/cuda/BUILD b/third_party/gpus/cuda/BUILD
index a0d1d6561b..b68104385d 100644
--- a/third_party/gpus/cuda/BUILD
+++ b/third_party/gpus/cuda/BUILD
@@ -31,6 +31,15 @@ config_setting(
     },
 )
 
+# Equivalent to using_clang && -c opt.
+config_setting(
+    name = "using_clang_opt",
+    values = {
+        "define": "using_cuda_clang=true",
+        "compilation_mode": "opt",
+    },
+)
+
 config_setting(
     name = "darwin",
     values = {"cpu": "darwin"},