Blob Blame History Raw
commit 7cc65773f04e0f4252428c40dcbb784a39b58cd1
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Wed Oct 24 02:19:15 2018 -0700

    x86: Support RDTSCP for benchtests
    
    RDTSCP waits until all previous instructions have executed and all
    previous loads are globally visible before reading the counter.  RDTSC
    doesn't wait until all previous instructions have been executed before
    reading the counter.  All x86 processors since 2010 support RDTSCP
    instruction.  This patch adds RDTSCP support to benchtests.
    
            * benchtests/Makefile (CPPFLAGS-nonlib): Add -DUSE_RDTSCP if
            USE_RDTSCP is defined.
            * sysdeps/x86/hp-timing.h (HP_TIMING_NOW): Use RDTSCP if
            USE_RDTSCP is defined.

diff --git a/benchtests/Makefile b/benchtests/Makefile
index 28d6b0c43f5bd390..bde0caf140e8cf17 100644
--- a/benchtests/Makefile
+++ b/benchtests/Makefile
@@ -131,6 +131,12 @@ CPPFLAGS-nonlib += -DDURATION=$(BENCH_DURATION) -D_ISOMAC
 # HP_TIMING if it is available.
 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 :=
diff --git a/benchtests/README b/benchtests/README
index 4ddff794d136f65f..aaf0b659e2b25627 100644
--- a/benchtests/README
+++ b/benchtests/README
@@ -34,6 +34,15 @@ the benchmark to use clock_gettime by invoking make as follows:
 
 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
+instruction.  One can force the benchmark to use RDTSCP by invoking make
+as follows:
+
+  $ make USE_RDTSCP=1 bench
+
+One must run `make bench-clean' before changing the measurement method.
+
 Running benchmarks on another target:
 ====================================
 
diff --git a/sysdeps/x86/hp-timing.h b/sysdeps/x86/hp-timing.h
index 77a1360748ca4535..0aa6f5e3f83e0d34 100644
--- a/sysdeps/x86/hp-timing.h
+++ b/sysdeps/x86/hp-timing.h
@@ -40,7 +40,19 @@ typedef unsigned long long int hp_timing_t;
 
    NB: Use __builtin_ia32_rdtsc directly since including <x86intrin.h>
    makes building glibc very slow.  */
-# define HP_TIMING_NOW(Var)	((Var) = __builtin_ia32_rdtsc ())
+# ifdef USE_RDTSCP
+/* RDTSCP waits until all previous instructions have executed and all
+   previous loads are globally visible before reading the counter.
+   RDTSC doesn't wait until all previous instructions have been executed
+   before reading the counter.  */
+#  define HP_TIMING_NOW(Var) \
+  (__extension__ ({				\
+    unsigned int __aux;				\
+    (Var) = __builtin_ia32_rdtscp (&__aux);	\
+  }))
+# else
+#  define HP_TIMING_NOW(Var) ((Var) = __builtin_ia32_rdtsc ())
+# endif
 
 # include <hp-timing-common.h>
 #else