From 4f2d3f4b8772e7d14651ec4813b22675d07a509b Mon Sep 17 00:00:00 2001
From: noel <ndkeen@lbl.gov>
Date: Mon, 28 Aug 2017 16:55:27 -0700
Subject: [PATCH 1/2] For Intel builds, there are 7 HOMME fortran files we
 build with higher optimization flags. Add -fp-model fast to those 7 builds as
 this avoids the slow pow function on KNL, and may generally improve
 peformance for those files. Passes acme_developer and a HOMME test with
 create_test -g and -c

---
 config/acme/machines/Depends.intel   |  3 ++-
 config/acme/machines/Depends.intel18 | 36 ++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 1 deletion(-)
 create mode 100644 config/acme/machines/Depends.intel18

diff --git a/config/acme/machines/Depends.intel b/config/acme/machines/Depends.intel
index b706186930d..468ee8a4917 100644
--- a/config/acme/machines/Depends.intel
+++ b/config/acme/machines/Depends.intel
@@ -30,7 +30,8 @@ kissvec.o
 
 ifeq ($(DEBUG),FALSE)
   $(PERFOBJS): %.o: %.F90
-	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3  -no-prec-div $<
+	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3 -no-prec-div $<
+#	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3 -fp-model fast -no-prec-div $<
   $(REDUCED_OPT_OBJS): %.o: %.F90
 	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O1 $<
   $(REDUCED_PRECISION_OBJS): %.o: %.F90
diff --git a/config/acme/machines/Depends.intel18 b/config/acme/machines/Depends.intel18
new file mode 100644
index 00000000000..ad2af6fc5db
--- /dev/null
+++ b/config/acme/machines/Depends.intel18
@@ -0,0 +1,36 @@
+#
+PERFOBJS=\
+prim_advection_mod_base.o \
+vertremap_mod_base.o \
+edge_mod_base.o \
+derivative_mod_base.o \
+bndry_mod_base.o \
+prim_advance_mod.o \
+uwshcu.o
+
+# shr_wv_sat_mod does not need to have better than ~0.1% precision, and benefits
+# enormously from a lower precision in the vector functions.
+REDUCED_PRECISION_OBJS=\
+shr_wv_sat_mod.o
+
+SHR_RANDNUM_FORT_OBJS=\
+kissvec_mod.o \
+mersennetwister_mod.o \
+dSFMT_interface.o \
+shr_RandNum_mod.o
+
+SHR_RANDNUM_C_OBJS=\
+dSFMT.o \
+dSFMT_utils.o \
+kissvec.o
+
+ifeq ($(DEBUG),FALSE)
+  $(PERFOBJS): %.o: %.F90
+	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3 -fp-model fast -no-prec-div $<
+  $(REDUCED_PRECISION_OBJS): %.o: %.F90
+	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS) -fimf-precision=low -fp-model fast $<
+  $(SHR_RANDNUM_FORT_OBJS): %.o: %.F90
+	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS) -O3 -fp-model fast -no-prec-div -no-prec-sqrt -qoverride-limits $<
+  $(SHR_RANDNUM_C_OBJS): %.o: %.c
+	  $(CC) -c $(INCLDIR) $(INCS) $(CFLAGS) -O3 -fp-model fast $<
+endif

From b3d0c93e35dd779f050c0214c754d7e49cf65164 Mon Sep 17 00:00:00 2001
From: noel <ndkeen@lbl.gov>
Date: Mon, 28 Aug 2017 17:04:30 -0700
Subject: [PATCH 2/2] Whoops, I had the change I wanted commented out.

---
 config/acme/machines/Depends.intel | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/config/acme/machines/Depends.intel b/config/acme/machines/Depends.intel
index 468ee8a4917..0ce945caded 100644
--- a/config/acme/machines/Depends.intel
+++ b/config/acme/machines/Depends.intel
@@ -30,8 +30,7 @@ kissvec.o
 
 ifeq ($(DEBUG),FALSE)
   $(PERFOBJS): %.o: %.F90
-	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3 -no-prec-div $<
-#	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3 -fp-model fast -no-prec-div $<
+	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O3 -fp-model fast -no-prec-div $<
   $(REDUCED_OPT_OBJS): %.o: %.F90
 	  $(FC) -c $(INCLDIR) $(INCS) $(FFLAGS) $(FREEFLAGS)  -O1 $<
   $(REDUCED_PRECISION_OBJS): %.o: %.F90