diff --git a/runtime/hsa-runtime/core/runtime/runtime.cpp b/runtime/hsa-runtime/core/runtime/runtime.cpp
index 5b61eaef5c..d0e2c5885a 100644
--- a/runtime/hsa-runtime/core/runtime/runtime.cpp
+++ b/runtime/hsa-runtime/core/runtime/runtime.cpp
@@ -1218,9 +1218,7 @@ hsa_status_t Runtime::Load() {
   // Load extensions
   LoadExtensions();
 
-  // Load tools libraries
-  LoadTools();
-
+  // Initialize per GPU scratch, blits, and trap handler
   for (core::Agent* agent : gpu_agents_) {
     hsa_status_t status =
         reinterpret_cast<amd::GpuAgentInt*>(agent)->PostToolsInit();
@@ -1230,6 +1228,9 @@ hsa_status_t Runtime::Load() {
     }
   }
 
+  // Load tools libraries
+  LoadTools();
+
   return HSA_STATUS_SUCCESS;
 }