Benchmark with DaCe cpu and gpu backends

.gitmodules

@@ -1,6 +1,6 @@
 [submodule "external/gt4py"]
 	path = external/gt4py
 	url = https://github.com/gridtools/gt4py.git
-[submodule "external/dace"]
+[submodule "dacecpufix"]
 	path = external/dace
-	url = https://github.com/spcl/dace.git
+	url = https://github.com/FlorianDeconinck/dace.git

constraints.txt

@@ -81,7 +81,7 @@ coverage==5.5
     #   pytest-cov
 cytoolz==0.12.1
     # via gt4py
-dace==0.14.4
+dace==0.15.1
     # via
     #   -r requirements_dev.txt
     #   pace-dsl
@@ -184,7 +184,7 @@ googleapis-common-protos==1.53.0
     # via google-api-core
 gprof2dot==2021.2.21
     # via pytest-profiling
-gridtools-cpp==2.3.0
+gridtools-cpp==2.3.1
     # via gt4py
 h5netcdf==0.11.0
     # via -r util/requirements.txt

driver/examples/configs/baroclinic_c12_orch_cpu.yaml

@@ -14,10 +14,30 @@ performance_config:
 nx_tile: 12
 nz: 79
 dt_atmos: 225
-minutes: 5
+seconds: 675
 layout:
-  - 1
-  - 1
+  - 2
+  - 2
+diagnostics_config:
+  path: output
+  output_format: netcdf
+  names:
+    - u
+    - v
+    - ua
+    - va
+    - pt
+    - delp
+    - qvapor
+    - qliquid
+    - qice
+    - qrain
+    - qsnow
+    - qgraupel
+  z_select:
+    - level: 65
+      names:
+        - pt
 dycore_config:
   a_imp: 1.0
   beta: 0.

driver/examples/configs/baroclinic_c384_cpu.yaml

@@ -15,11 +15,10 @@ performance_config:
 nx_tile: 384
 nz: 79
 dt_atmos: 450
-minutes: 7
-seconds: 30
+days: 9
 layout:
-  - 1
-  - 1
+  - 16
+  - 16
 diagnostics_config:
   path: output
   output_format: netcdf
@@ -72,7 +71,7 @@ dycore_config:
   nwat: 6
   p_fac: 0.1
   rf_cutoff: 800.
-  rf_fast: false
+  rf_fast: true
   tau: 5.
   vtdm4: 0.06
   z_tracer: true

driver/examples/configs/baroclinic_c384_gpu.yaml

@@ -71,7 +71,7 @@ dycore_config:
   nwat: 6
   p_fac: 0.1
   rf_cutoff: 800.
-  rf_fast: false
+  rf_fast: true
   tau: 5.
   vtdm4: 0.06
   z_tracer: true

physics/pace/physics/stencils/microphysics.py

@@ -14,7 +14,7 @@
 import pace.physics.functions.microphysics_funcs as functions
 import pace.util
 import pace.util.constants as constants
-from pace.dsl.dace.orchestration import orchestrate
+from pace.dsl.dace.orchestration import dace_inhibitor, orchestrate
 from pace.dsl.stencil import StencilFactory
 from pace.dsl.typing import Float, FloatField, FloatFieldIJ, Int
 from pace.util import X_DIM, Y_DIM, Z_DIM
@@ -2227,6 +2227,7 @@ def setupm(self, dt_atmos: float):
         self._ces0 = constants.EPS * es0
         self._set_timestep(dt_atmos)
 
+    @dace_inhibitor
     def _update_timestep_if_needed(self, timestep: float):
         if timestep != self._timestep:
             self._set_timestep(timestep=timestep)

tests/main/driver/test_example_configs.py

@@ -28,6 +28,10 @@
     "baroclinic_c12_orch_cpu.yaml",
     "tropical_read_restart_fortran.yml",
     "tropicalcyclone_c128.yaml",
+    "baroclinic_c384_cpu.yaml",
+    "baroclinic_c384_gpu.yaml",
+    "baroclinic_c3072_cpu.yaml",
+    "baroclinic_c3072_gpu.yaml",
 ]
 
 JENKINS_CONFIGS_DIR = os.path.join(dirname, "../../../.jenkins/driver_configs/")