gfor_helper_src= \
intrinsics/associated.c \
intrinsics/abort.c \
+intrinsics/access.c \
intrinsics/args.c \
intrinsics/bessel.c \
intrinsics/c99_functions.c \
intrinsics/chdir.c \
+intrinsics/chmod.c \
+intrinsics/clock.c \
intrinsics/cpu_time.c \
intrinsics/cshift0.c \
intrinsics/ctime.c \
intrinsics/unlink.c \
intrinsics/unpack_generic.c \
runtime/in_pack_generic.c \
-runtime/in_unpack_generic.c \
-runtime/normalize.c
+runtime/in_unpack_generic.c
gfor_src= \
runtime/compile_options.c \
generated/product_c10.c \
generated/product_c16.c
-i_dotprod_c= \
-generated/dotprod_i4.c \
-generated/dotprod_i8.c \
-generated/dotprod_i16.c \
-generated/dotprod_r4.c \
-generated/dotprod_r8.c \
-generated/dotprod_r10.c \
-generated/dotprod_r16.c
-
-i_dotprodl_c= \
-generated/dotprod_l4.c \
-generated/dotprod_l8.c \
-generated/dotprod_l16.c
-
-i_dotprodc_c= \
-generated/dotprod_c4.c \
-generated/dotprod_c8.c \
-generated/dotprod_c10.c \
-generated/dotprod_c16.c
-
i_matmul_c= \
generated/matmul_i4.c \
generated/matmul_i8.c \
generated/transpose_i4.c \
generated/transpose_i8.c \
generated/transpose_i16.c \
+generated/transpose_r4.c \
+generated/transpose_r8.c \
+generated/transpose_r10.c \
+generated/transpose_r16.c \
generated/transpose_c4.c \
generated/transpose_c8.c \
generated/transpose_c10.c \
generated/reshape_i4.c \
generated/reshape_i8.c \
generated/reshape_i16.c \
+generated/reshape_r4.c \
+generated/reshape_r8.c \
+generated/reshape_r10.c \
+generated/reshape_r16.c \
generated/reshape_c4.c \
generated/reshape_c8.c \
generated/reshape_c10.c \
m4_files= m4/iparm.m4 m4/ifunction.m4 m4/iforeach.m4 m4/all.m4 \
m4/any.m4 m4/count.m4 m4/maxloc0.m4 m4/maxloc1.m4 m4/maxval.m4 \
m4/minloc0.m4 m4/minloc1.m4 m4/minval.m4 m4/product.m4 m4/sum.m4 \
- m4/dotprod.m4 m4/dotprodl.m4 m4/dotprodc.m4 m4/matmul.m4 m4/matmull.m4 \
+ m4/matmul.m4 m4/matmull.m4 \
m4/ctrig.m4 m4/cexp.m4 m4/chyp.m4 m4/mtype.m4 \
m4/specific.m4 m4/specific2.m4 m4/head.m4 m4/shape.m4 m4/reshape.m4 \
m4/transpose.m4 m4/eoshift1.m4 m4/eoshift3.m4 m4/exponent.m4 \
gfor_built_src= $(i_all_c) $(i_any_c) $(i_count_c) $(i_maxloc0_c) \
$(i_maxloc1_c) $(i_maxval_c) $(i_minloc0_c) $(i_minloc1_c) $(i_minval_c) \
- $(i_product_c) $(i_sum_c) $(i_dotprod_c) $(i_dotprodl_c) $(i_dotprodc_c) \
+ $(i_product_c) $(i_sum_c) \
$(i_matmul_c) $(i_matmull_c) $(i_transpose_c) $(i_shape_c) $(i_eoshift1_c) \
$(i_eoshift3_c) $(i_cshift1_c) $(i_reshape_c) $(in_pack_c) $(in_unpack_c) \
$(i_exponent_c) $(i_fraction_c) $(i_nearest_c) $(i_set_exponent_c) \
generated/_mod_i8.F90 \
generated/_mod_i16.F90 \
generated/_mod_r4.F90 \
-generated/_mod_r8.F90
-# There are commented out due to a bug in the way the front-end
-# handles MOD
-#generated/_mod_r10.F90
-#generated/_mod_r16.F90
+generated/_mod_r8.F90 \
+generated/_mod_r10.F90 \
+generated/_mod_r16.F90
gfor_specific_src= \
$(gfor_built_specific_src) \
intrinsics/dprod_r8.f90 \
intrinsics/f2c_specifics.F90
-# Turn on vectorization for matmul.
-$(patsubst %.c,%.lo,$(notdir $(i_matmul_c))): AM_CFLAGS += -ftree-vectorize
+# No install-html support yet.
+.PHONY: install-html
+install-html:
+
+# Turn on vectorization and loop unrolling for matmul.
+$(patsubst %.c,%.lo,$(notdir $(i_matmul_c))): AM_CFLAGS += -ftree-vectorize -funroll-loops
+# Logical matmul doesn't vectorize.
+$(patsubst %.c,%.lo,$(notdir $(i_matmull_c))): AM_CFLAGS += -funroll-loops
BUILT_SOURCES=$(gfor_built_src) $(gfor_built_specific_src) \
$(gfor_built_specific2_src)
$(i_sum_c): m4/sum.m4 $(I_M4_DEPS1)
m4 -Dfile=$@ -I$(srcdir)/m4 sum.m4 > $(srcdir)/$@
-$(i_dotprod_c): m4/dotprod.m4 $(I_M4_DEPS)
- m4 -Dfile=$@ -I$(srcdir)/m4 dotprod.m4 > $(srcdir)/$@
-
-$(i_dotprodl_c): m4/dotprodl.m4 $(I_M4_DEPS)
- m4 -Dfile=$@ -I$(srcdir)/m4 dotprodl.m4 > $(srcdir)/$@
-
-$(i_dotprodc_c): m4/dotprodc.m4 $(I_M4_DEPS)
- m4 -Dfile=$@ -I$(srcdir)/m4 dotprodc.m4 > $(srcdir)/$@
-
$(i_matmul_c): m4/matmul.m4 $(I_M4_DEPS)
m4 -Dfile=$@ -I$(srcdir)/m4 matmul.m4 > $(srcdir)/$@
OSDN Git Service
