commit
7621e38bf3c58b2d0359545f1f2898017fd89d05
Author: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
Date: Tue Jan 29 17:43:45 2019 +0000
Add generic hp-timing support
removed the clock_gettime option. Restore the clock_gettime option for
some x86 CPUs on which value from RDTSC may not be incremented at a fixed
rate.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
CPPFLAGS-nonlib += -DDURATION=$(BENCH_DURATION) -D_ISOMAC
+# Use clock_gettime to measure performance of functions. The default is
+# to use the architecture-specific high precision timing instructions.
+ifdef USE_CLOCK_GETTIME
+CPPFLAGS-nonlib += -DUSE_CLOCK_GETTIME
+else
# On x86 processors, use RDTSCP, instead of RDTSC, to measure performance
# of functions. All x86 processors since 2010 support RDTSCP instruction.
ifdef USE_RDTSCP
CPPFLAGS-nonlib += -DUSE_RDTSCP
endif
+endif
DETAILED_OPT :=
The benchmark suite does function call measurements using architecture-specific
high precision timing instructions whenever available. When such support is
-not available, it uses clock_gettime (CLOCK_MONOTONIC).
+not available, it uses clock_gettime (CLOCK_MONOTONIC). One can force the
+benchmark to use clock_gettime by invoking make as follows:
+
+ $ make USE_CLOCK_GETTIME=1 bench
+
+Again, one must run `make bench-clean' before changing the measurement method.
On x86 processors, RDTSCP instruction provides more precise timing data
than RDTSC instruction. All x86 processors since 2010 support RDTSCP
#undef attribute_hidden
#define attribute_hidden
-#include <hp-timing.h>
+#ifdef USE_CLOCK_GETTIME
+# include <sysdeps/generic/hp-timing.h>
+#else
+# include <hp-timing.h>
+#endif
#include <stdint.h>
#define GL(x) _##x