From 86b2e49082cad0a62e00af38b2dae1578cf5fbe8 Mon Sep 17 00:00:00 2001
From: Peter Hawkins <phawkins@google.com>
Date: Tue, 7 May 2019 12:02:50 -0700
Subject: [PATCH] [SE] Set denormal and rounding modes in HostStream thread.

Previously, HostStream used a TF ThreadPool, which sets denormal and rounding modes. A previous change switched from using a ThreadPool to using a Thread, which does not set denormal and rounding modes. This change restores the previous denormal/rounding behavior to unbreak tensorflow/compiler/xla/tests:exhaustive_op_test_cpu, pending a more complete fix.

PiperOrigin-RevId: 247064380
---
 tensorflow/stream_executor/host/BUILD          | 1 +
 tensorflow/stream_executor/host/host_stream.cc | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/tensorflow/stream_executor/host/BUILD b/tensorflow/stream_executor/host/BUILD
index 00fabe5772f..6ad06bb9bb9 100644
--- a/tensorflow/stream_executor/host/BUILD
+++ b/tensorflow/stream_executor/host/BUILD
@@ -67,6 +67,7 @@ cc_library(
         "host_stream.h",
     ],
     deps = [
+        "//tensorflow/core:lib_internal",
         "//tensorflow/stream_executor:kernel",
         "//tensorflow/stream_executor/lib",
         "@com_google_absl//absl/synchronization",
diff --git a/tensorflow/stream_executor/host/host_stream.cc b/tensorflow/stream_executor/host/host_stream.cc
index 0d8cb46f196..413edc6739a 100644
--- a/tensorflow/stream_executor/host/host_stream.cc
+++ b/tensorflow/stream_executor/host/host_stream.cc
@@ -18,6 +18,8 @@ limitations under the License.
 #include "tensorflow/stream_executor/host/host_stream.h"
 
 #include "absl/synchronization/notification.h"
+#include "tensorflow/core/platform/denormal.h"
+#include "tensorflow/core/platform/setround.h"
 
 namespace stream_executor {
 namespace host {
@@ -45,6 +47,11 @@ bool HostStream::EnqueueTask(std::function<void()> fn) {
 bool HostStream::WorkAvailable() { return !work_queue_.empty(); }
 
 void HostStream::WorkLoop() {
+  // Set denormal and rounding behavior to match the default TF ThreadPool
+  // behavior.
+  // TODO(phawkins, jlebar): it's not clear this is the best place to set this.
+  tensorflow::port::ScopedFlushDenormal flush;
+  tensorflow::port::ScopedSetRound round(FE_TONEAREST);
   while (true) {
     std::function<void()> fn;
     {