Fix conditional on when DtoH forces copy occur

d2d4a50b4c636c203028c5bff311924ec15e7825 introduced performance
regression with forces copied from device to host on each step.
This fixes the issue by reinstantiating proper condition on the
copy call.

Fixes #4001
Refs #2608

diff --git a/src/gromacs/nbnxm/nbnxm_gpu_data_mgmt.cpp b/src/gromacs/nbnxm/nbnxm_gpu_data_mgmt.cpp
index afd969ee7f8d7c34cd1c52211993cd7ce3bb5106..63f8317443314c3886a53f24a1a8724d6324b55c 100644 (file)
--- a/src/gromacs/nbnxm/nbnxm_gpu_data_mgmt.cpp
+++ b/src/gromacs/nbnxm/nbnxm_gpu_data_mgmt.cpp
@@ -815,17 +815,21 @@ void gpu_launch_cpyback(NbnxmGpu*                nb,
     }
 
     /* DtoH f */
-    static_assert(sizeof(*nbatom->out[0].f.data()) == sizeof(float),
-                  "The host force buffer should be in single precision to match device data size.");
-    copyFromDeviceBuffer(reinterpret_cast<Float3*>(nbatom->out[0].f.data()) + atomsRange.begin(),
-                         &adat->f,
-                         atomsRange.begin(),
-                         atomsRange.size(),
-                         deviceStream,
-                         GpuApiCallBehavior::Async,
-                         bDoTime ? timers->xf[atomLocality].nb_d2h.fetchNextEvent() : nullptr);
-
-    issueClFlushInStream(deviceStream);
+    if (!stepWork.useGpuFBufferOps)
+    {
+        static_assert(
+                sizeof(*nbatom->out[0].f.data()) == sizeof(float),
+                "The host force buffer should be in single precision to match device data size.");
+        copyFromDeviceBuffer(reinterpret_cast<Float3*>(nbatom->out[0].f.data()) + atomsRange.begin(),
+                             &adat->f,
+                             atomsRange.begin(),
+                             atomsRange.size(),
+                             deviceStream,
+                             GpuApiCallBehavior::Async,
+                             bDoTime ? timers->xf[atomLocality].nb_d2h.fetchNextEvent() : nullptr);
+
+        issueClFlushInStream(deviceStream);
+    }
 
     /* After the non-local D2H is launched the nonlocal_done event can be
        recorded which signals that the local D2H can proceed. This event is not