Begin porting string performance tests to benchtests

This is the initial support for string function performance tests,
along with copying tests for memcpy and memcpy-ifunc as proof of
concept.  The string function benchmarks perform operations at
different alignments and for different sizes and compare performance
between plain operations and the optimized string operations.  Due to
this their output is incompatible with the function benchmarks where
we're interested in fastest time, throughput, etc.

In future, the correctness checks in the benchmark tests can be
removed.  Same goes for the performance measurements in the
string/test-*.

1 files changed, 24 insertions, 3 deletions

diff --git a/benchtests/Makefile b/benchtests/Makefile
index 680440f429..27d83f45a7 100644
--- a/benchtests/Makefile
+++ b/benchtests/Makefile
@@ -23,6 +23,13 @@ subdir := benchtests
 bench := acos acosh asin asinh atan atanh cos cosh exp log modf pow rint sin \
 	 sinh tan tanh
 
+# String function benchmarks.
+string-bench := memcpy
+string-bench-ifunc := $(addsuffix -ifunc, $(string-bench))
+string-bench-all := $(string-bench) $(string-bench-ifunc)
+
+benchset := $(string-bench-all)
+
 acos-ARGLIST = double
 acos-RET = double
 LDFLAGS-bench-acos = -lm
@@ -92,10 +99,15 @@ LDFLAGS-bench-tanh = -lm
 # Rules to build and execute the benchmarks.  Do not put any benchmark
 # parameters beyond this point.
 
+# We don't want the benchmark programs to run in parallel since that could
+# affect their performance.
+.NOTPARALLEL:
+
 include ../Makeconfig
 include ../Rules
 
 binaries-bench := $(addprefix $(objpfx)bench-,$(bench))
+binaries-benchset := $(addprefix $(objpfx)bench-,$(benchset))
 
 # The default duration: 10 seconds.
 ifndef BENCH_DURATION
@@ -112,7 +124,7 @@ endif
 
 # This makes sure CPPFLAGS-nonlib and CFLAGS-nonlib are passed
 # for all these modules.
-cpp-srcs-left := $(binaries-bench:=.c)
+cpp-srcs-left := $(binaries-benchset:=.c) $(binaries-bench:=.c)
 lib := nonlib
 include $(patsubst %,$(..)cppflags-iterator.mk,$(cpp-srcs-left))
 
@@ -124,8 +136,17 @@ run-bench = $(test-wrapper-env) \
 
 bench-clean:
 	rm -f $(binaries-bench) $(addsuffix .o,$(binaries-bench))
+	rm -f $(binaries-benchset) $(addsuffix .o,$(binaries-benchset))
+
+bench: bench-set bench-func
+
+bench-set: $(binaries-benchset)
+	for run in $^; do \
+	  echo "Running $${run}"; \
+	  $(run-bench) > $${run}.out; \
+	done
 
-bench: $(binaries-bench)
+bench-func: $(binaries-bench)
 	{ for run in $^; do \
 	  echo "Running $${run}" >&2; \
 	  $(run-bench); \
@@ -135,7 +156,7 @@ bench: $(binaries-bench)
 	fi; \
 	mv -f $(objpfx)bench.out-tmp $(objpfx)bench.out
 
-$(binaries-bench): %: %.o \
+$(binaries-bench) $(binaries-benchset): %: %.o \
   $(sort $(filter $(common-objpfx)lib%,$(link-libc))) \
   $(addprefix $(csu-objpfx),start.o) $(+preinit) $(+postinit)
 	$(+link)