From 57e422aa168bee7416965265c93fcd4934cd7041 Mon Sep 17 00:00:00 2001
From: "Field G. Van Zee" <field@cs.utexas.edu>
Date: Fri, 23 Aug 2019 14:17:52 -0500
Subject: [PATCH] Added libxsmm support to test/sup drivers.

Details:
- Modified test/sup/Makefile to build drivers that test the performance
  of skinny/small problems via libxsmm.
- Modified test/sup/runme.sh to run aforementioned drivers.
- Modified test/sup/test_gemm.c so that problem sizes are tested in
  reverse order (from largest to smallest). This can help avoid certain
  situations where the CPU frequency does not immediately throttle up
  to its maximum. Thanks to Robert van de Geijn for recommending this
  fix.
---
 test/sup/Makefile    | 23 ++++++++++++++++++++---
 test/sup/runme.sh    | 14 +++++++++++---
 test/sup/test_gemm.c |  3 ++-
 3 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/test/sup/Makefile b/test/sup/Makefile
index d2b3c7170..7934d7052 100644
--- a/test/sup/Makefile
+++ b/test/sup/Makefile
@@ -103,6 +103,9 @@ OPENBLASP_LIB  := $(HOME_LIB_PATH)/libopenblasp.a
 # BLASFEO
 BLASFEO_LIB    := $(HOME_LIB_PATH)/libblasfeo.a
 
+# libxsmm
+LIBXSMM_LIB    := $(HOME_LIB_PATH)/libxsmm.a
+
 # ATLAS
 ATLAS_LIB      := $(HOME_LIB_PATH)/libf77blas.a \
                   $(HOME_LIB_PATH)/libatlas.a
@@ -306,14 +309,18 @@ get-imp-defs = $(strip $(subst  blissup,-DSTR=\"$(1)\" -DBLIS -DSUP, \
                        $(subst    eigen,-DSTR=\"$(1)\" -DEIGEN, \
                        $(subst openblas,-DSTR=\"$(1)\" -DCBLAS, \
                        $(subst  blasfeo,-DSTR=\"$(1)\" -DCBLAS, \
-                       $(subst   vendor,-DSTR=\"$(1)\" -DCBLAS,$(1))))))))
+                       $(subst  libxsmm,-DSTR=\"$(1)\" -DBLAS, \
+                       $(subst   vendor,-DSTR=\"$(1)\" -DCBLAS,$(1)))))))))
 
 TRANS0  = $(call stripu,$(TRANS))
 STORS0  = $(call stripu,$(STORS))
 
 # Limit BLAS and Eigen to only using all row-stored, or all column-stored matrices.
+# Also, limit libxsmm to using all column-stored matrices since it does not offer
+# CBLAS interfaces.
 BSTORS0 = rrr ccc
 ESTORS0 = rrr ccc
+XSTORS0 = ccc
 
 
 #
@@ -339,6 +346,9 @@ OPENBLAS_ST_BINS := $(patsubst %.o,%.x,$(OPENBLAS_ST_OBJS))
 BLASFEO_ST_OBJS  := $(call get-st-objs,$(DTS),$(TRANS0),$(BSTORS0),$(SHAPES),$(SMS),$(SNS),$(SKS),blasfeo)
 BLASFEO_ST_BINS  := $(patsubst %.o,%.x,$(BLASFEO_ST_OBJS))
 
+LIBXSMM_ST_OBJS  := $(call get-st-objs,$(DTS),$(TRANS0),$(XSTORS0),$(SHAPES),$(SMS),$(SNS),$(SKS),libxsmm)
+LIBXSMM_ST_BINS  := $(patsubst %.o,%.x,$(LIBXSMM_ST_OBJS))
+
 VENDOR_ST_OBJS   := $(call get-st-objs,$(DTS),$(TRANS0),$(BSTORS0),$(SHAPES),$(SMS),$(SNS),$(SKS),vendor)
 VENDOR_ST_BINS   := $(patsubst %.o,%.x,$(VENDOR_ST_OBJS))
 
@@ -351,6 +361,7 @@ VENDOR_ST_BINS   := $(patsubst %.o,%.x,$(VENDOR_ST_OBJS))
                $(EIGEN_ST_OBJS) \
                $(OPENBLAS_ST_OBJS) \
                $(BLASFEO_ST_OBJS) \
+               $(LIBXSMM_ST_OBJS) \
                $(VENDOR_ST_OBJS)
 
 
@@ -365,9 +376,11 @@ blislpab:    blislpab-st
 eigen:       eigen-st
 openblas:    openblas-st
 blasfeo:     blasfeo-st
+libxsmm:     libxsmm-st
 vendor:      vendor-st
 
-st:          blissup-st blislpab-st eigen-st openblas-st blasfeo-st vendor-st
+st:          blissup-st blislpab-st \
+             eigen-st openblas-st blasfeo-st libxsmm-st vendor-st
 blis:        blissup-st blislpab-st
 
 blissup-st:  $(BLISSUP_ST_BINS)
@@ -375,13 +388,14 @@ blislpab-st: $(BLISLPAB_ST_BINS)
 eigen-st:    $(EIGEN_ST_BINS)
 openblas-st: $(OPENBLAS_ST_BINS)
 blasfeo-st:  $(BLASFEO_ST_BINS)
+libxsmm-st:  $(LIBXSMM_ST_BINS)
 vendor-st:   $(VENDOR_ST_BINS)
 
 
 # --Object file rules --
 
 # Define the implementations for which we will instantiate compilation rules.
-BIMPLS := blissup blislpab openblas blasfeo vendor
+BIMPLS := blissup blislpab openblas blasfeo libxsmm vendor
 EIMPLS := eigen
 
 #      1     2  3   4 567  8
@@ -447,6 +461,9 @@ test_%_openblas_st.x: test_%_openblas_st.o $(LIBBLIS_LINK)
 test_%_blasfeo_st.x:  test_%_blasfeo_st.o  $(LIBBLIS_LINK)
 	$(CC) $(strip $<  $(BLASFEO_LIB)       $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
 
+test_%_libxsmm_st.x:  test_%_libxsmm_st.o  $(LIBBLIS_LINK)
+	$(CC) $(strip $<  $(LIBXSMM_LIB)       $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
+
 test_%_vendor_st.x:   test_%_vendor_st.o   $(LIBBLIS_LINK)
 	$(CC) $(strip $<  $(VENDOR_LIB)        $(LIBBLIS_LINK) $(LDFLAGS) -o $@)
 
diff --git a/test/sup/runme.sh b/test/sup/runme.sh
index 9646e3ccc..912c50dc0 100755
--- a/test/sup/runme.sh
+++ b/test/sup/runme.sh
@@ -37,13 +37,14 @@ sns="8"
 sks="4"
 
 # Implementations to test.
-impls="vendor blissup blislpab openblas eigen"
+impls="vendor blissup blislpab openblas eigen libxsmm blasfeo"
 #impls="vendor openblas eigen"
 #impls="blislpab blissup"
-#mpls="openblas eigen vendor"
-#mpls="eigen"
+#impls="openblas eigen vendor"
+#impls="eigen"
 #impls="blissup"
 #impls="blasfeo"
+#impls="libxsmm"
 
 # Example: test_dgemm_nn_rrc_m6npkp_blissup_st.x
 
@@ -75,6 +76,13 @@ for th in ${threads}; do
 											continue;
 										fi
 
+										# Further limit execution of libxsmm to
+										# ccc storage cases.
+										if [ "${im:0:7}" = "libxsmm" ] && \
+										   [ "${st}" != "ccc" ]; then
+											continue;
+										fi
+
 										# Extract the shape chars for m, n, k.
 										chm=${sh:0:1}
 										chn=${sh:1:1}
diff --git a/test/sup/test_gemm.c b/test/sup/test_gemm.c
index 311e8552a..8c9f24c8a 100644
--- a/test/sup/test_gemm.c
+++ b/test/sup/test_gemm.c
@@ -158,7 +158,8 @@ int main( int argc, char** argv )
 	        ( unsigned long )0, 0.0 );
 
 
-	for ( p = p_begin; p <= p_max; p += p_inc )
+	//for ( p = p_begin; p <= p_max; p += p_inc )
+	for ( p = p_max; p_begin <= p; p -= p_inc )
 	{
 		obj_t  a, b, c;
 		obj_t  c_save;