From 9370a04be5bb64990b873b0c1cb3fb1c137a23a1 Mon Sep 17 00:00:00 2001
From: Davide Valsecchi <davide.valsecchi@cern.ch>
Date: Wed, 13 Mar 2024 00:09:09 +0100
Subject: [PATCH 1/2] Checking if Nvidia GPUs are visible to TF when visible to
 cmssw

---
 PhysicsTools/TensorFlow/src/TensorFlow.cc | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/PhysicsTools/TensorFlow/src/TensorFlow.cc b/PhysicsTools/TensorFlow/src/TensorFlow.cc
index fcb09e2e9c449..786166ef407a9 100644
--- a/PhysicsTools/TensorFlow/src/TensorFlow.cc
+++ b/PhysicsTools/TensorFlow/src/TensorFlow.cc
@@ -42,6 +42,15 @@ namespace tensorflow {
     // NVidia GPU
     else if (backend == Backend::cuda) {
       if (not ri->nvidiaDriverVersion().empty()) {
+        // Check if one GPU device is visible to TF
+        // If not, an exception is raised --> this can happen in case of driver version mismatch
+        // or missing CUDA support in TF compilation
+        if ((*_options.config.mutable_device_count())["GPU"] == 0) {
+          edm::Exception ex(edm::errors::UnavailableAccelerator);
+          ex << "Cuda backend requested, NVIDIA GPU visible to cmssw, but not visible to TensorFlow in the job";
+          ex.addContext("Calling tensorflow::setBackend()");
+          throw ex;
+        }
         // Take only the first GPU in the CUDA_VISIBLE_DEVICE list
         (*_options.config.mutable_device_count())["GPU"] = 1;
         _options.config.mutable_gpu_options()->set_visible_device_list("0");

From fcc3e4fbb27693c684d5da32abb136b0be663edf Mon Sep 17 00:00:00 2001
From: Davide Valsecchi <davide.valsecchi@cern.ch>
Date: Tue, 12 Mar 2024 12:16:38 +0100
Subject: [PATCH 2/2] Make TF CUDA unit tests dependent on tf_cuda_support tool

---
 PhysicsTools/TensorFlow/test/BuildFile.xml | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/PhysicsTools/TensorFlow/test/BuildFile.xml b/PhysicsTools/TensorFlow/test/BuildFile.xml
index 03ca557c61619..c51046ba68ac9 100644
--- a/PhysicsTools/TensorFlow/test/BuildFile.xml
+++ b/PhysicsTools/TensorFlow/test/BuildFile.xml
@@ -5,7 +5,7 @@
   <use name="PhysicsTools/TensorFlow"/>
 </bin>
 
-<iftool name="cuda">
+<iftool name="tf_cuda_support">
   <bin name="testTFHelloWorldCUDA" file="testRunner.cpp,testHelloWorldCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>
@@ -29,7 +29,7 @@
   <use name="PhysicsTools/TensorFlow"/>
 </bin>
 
-<iftool name="cuda">
+<iftool name="tf_cuda_support">
   <bin name="testTFMetaGraphLoadingCUDA" file="testRunner.cpp,testMetaGraphLoadingCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>
@@ -52,7 +52,7 @@
   <use name="PhysicsTools/TensorFlow"/>
 </bin>
 
-<iftool name="cuda">
+<iftool name="tf_cuda_support">
   <bin name="testTFGraphLoadingCUDA" file="testRunner.cpp,testGraphLoadingCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>
@@ -75,7 +75,8 @@
   <use name="PhysicsTools/TensorFlow"/>
 </bin>
 
-<iftool name="cuda">
+
+<iftool name="tf_cuda_support">
   <bin name="testTFConstSessionCUDA" file="testRunner.cpp,testConstSessionCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>
@@ -98,7 +99,7 @@
   <use name="PhysicsTools/TensorFlow"/>
 </bin>
 
-<iftool name="cuda">
+<iftool name="tf_cuda_support">
   <bin name="testTFSessionCacheCUDA" file="testRunner.cpp,testSessionCacheCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>
@@ -121,7 +122,8 @@
   <use name="PhysicsTools/TensorFlow"/>
 </bin>
 
-<iftool name="cuda">
+
+<iftool name="tf_cuda_support">
   <bin name="testTFThreadPoolsCUDA" file="testRunner.cpp,testThreadPoolsCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>
@@ -145,7 +147,7 @@
 </bin>
 
 
-<iftool name="cuda">
+<iftool name="tf_cuda_support">
   <bin name="testTFVisibleDevicesCUDA" file="testRunner.cpp,testVisibleDevicesCUDA.cc">
     <use name="boost_filesystem"/>
     <use name="catch2"/>