diff --git a/src/gpu-compute/global_memory_pipeline.cc b/src/gpu-compute/global_memory_pipeline.cc
index a2b24e4b47..f6d60cf084 100644
--- a/src/gpu-compute/global_memory_pipeline.cc
+++ b/src/gpu-compute/global_memory_pipeline.cc
@@ -130,7 +130,7 @@ GlobalMemPipeline::exec()
         DPRINTF(GPUMem, "CU%d: WF[%d][%d]: Completing global mem instr %s\n",
                 m->cu_id, m->simdId, m->wfSlotId, m->disassemble());
         m->completeAcc(m);
-        if (m->isFlat() && m->isLoad()) {
+        if (m->isFlat() && (m->isLoad() || m->isAtomicRet())) {
             w->decLGKMInstsIssued();
         }
         w->decVMemInstsIssued();