x86: Add thresholds for "rep movsb/stosb" to tunables

Add x86_rep_movsb_threshold and x86_rep_stosb_threshold to tunables
to update thresholds for "rep movsb" and "rep stosb" at run-time.

Note that the user specified threshold for "rep movsb" smaller than
the minimum threshold will be ignored.

Reviewed-by: Carlos O'Donell <carlos@redhat.com>

manual/tunables.texi

@@ -396,6 +396,22 @@ to set threshold in bytes for non temporal store.
 This tunable is specific to i386 and x86-64.
 @end deftp
 
+@deftp Tunable glibc.cpu.x86_rep_movsb_threshold
+The @code{glibc.cpu.x86_rep_movsb_threshold} tunable allows the user to
+set threshold in bytes to start using "rep movsb".  The value must be
+greater than zero, and currently defaults to 2048 bytes.
+
+This tunable is specific to i386 and x86-64.
+@end deftp
+
+@deftp Tunable glibc.cpu.x86_rep_stosb_threshold
+The @code{glibc.cpu.x86_rep_stosb_threshold} tunable allows the user to
+set threshold in bytes to start using "rep stosb".  The value must be
+greater than zero, and currently defaults to 2048 bytes.
+
+This tunable is specific to i386 and x86-64.
+@end deftp
+
 @deftp Tunable glibc.cpu.x86_ibt
 The @code{glibc.cpu.x86_ibt} tunable allows the user to control how
 indirect branch tracking (IBT) should be enabled.  Accepted values are

sysdeps/x86/cacheinfo.c

@@ -530,6 +530,12 @@ long int __x86_raw_shared_cache_size attribute_hidden = 1024 * 1024;
 /* Threshold to use non temporal store.  */
 long int __x86_shared_non_temporal_threshold attribute_hidden;
 
+/* Threshold to use Enhanced REP MOVSB.  */
+long int __x86_rep_movsb_threshold attribute_hidden = 2048;
+
+/* Threshold to use Enhanced REP STOSB.  */
+long int __x86_rep_stosb_threshold attribute_hidden = 2048;
+
 #ifndef DISABLE_PREFETCHW
 /* PREFETCHW support flag for use in memory and string routines.  */
 int __x86_prefetchw attribute_hidden;
@@ -872,6 +878,36 @@ init_cacheinfo (void)
     = (cpu_features->non_temporal_threshold != 0
        ? cpu_features->non_temporal_threshold
        : __x86_shared_cache_size * threads * 3 / 4);
+
+  /* NB: The REP MOVSB threshold must be greater than VEC_SIZE * 8.  */
+  unsigned int minimum_rep_movsb_threshold;
+  /* NB: The default REP MOVSB threshold is 2048 * (VEC_SIZE / 16).  */
+  unsigned int rep_movsb_threshold;
+  if (CPU_FEATURES_ARCH_P (cpu_features, AVX512F_Usable)
+      && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_AVX512))
+    {
+      rep_movsb_threshold = 2048 * (64 / 16);
+      minimum_rep_movsb_threshold = 64 * 8;
+    }
+  else if (CPU_FEATURES_ARCH_P (cpu_features,
+				AVX_Fast_Unaligned_Load))
+    {
+      rep_movsb_threshold = 2048 * (32 / 16);
+      minimum_rep_movsb_threshold = 32 * 8;
+    }
+  else
+    {
+      rep_movsb_threshold = 2048 * (16 / 16);
+      minimum_rep_movsb_threshold = 16 * 8;
+    }
+  if (cpu_features->rep_movsb_threshold > minimum_rep_movsb_threshold)
+    __x86_rep_movsb_threshold = cpu_features->rep_movsb_threshold;
+  else
+    __x86_rep_movsb_threshold = rep_movsb_threshold;
+
+# if HAVE_TUNABLES
+  __x86_rep_stosb_threshold = cpu_features->rep_stosb_threshold;
+# endif
 }
 
 #endif

sysdeps/x86/cpu-features.c

@@ -606,6 +606,10 @@ no_cpuid:
   TUNABLE_GET (hwcaps, tunable_val_t *, TUNABLE_CALLBACK (set_hwcaps));
   cpu_features->non_temporal_threshold
     = TUNABLE_GET (x86_non_temporal_threshold, long int, NULL);
+  cpu_features->rep_movsb_threshold
+    = TUNABLE_GET (x86_rep_movsb_threshold, long int, NULL);
+  cpu_features->rep_stosb_threshold
+    = TUNABLE_GET (x86_rep_stosb_threshold, long int, NULL);
   cpu_features->data_cache_size
     = TUNABLE_GET (x86_data_cache_size, long int, NULL);
   cpu_features->shared_cache_size

sysdeps/x86/cpu-features.h

@@ -102,6 +102,10 @@ struct cpu_features
   unsigned long int shared_cache_size;
   /* Threshold to use non temporal store.  */
   unsigned long int non_temporal_threshold;
+  /* Threshold to use "rep movsb".  */
+  unsigned long int rep_movsb_threshold;
+  /* Threshold to use "rep stosb".  */
+  unsigned long int rep_stosb_threshold;
 };
 
 /* Used from outside of glibc to get access to the CPU features

sysdeps/x86/dl-tunables.list

@@ -30,6 +30,30 @@ glibc {
     x86_non_temporal_threshold {
       type: SIZE_T
     }
+    x86_rep_movsb_threshold {
+      type: SIZE_T
+      # Since there is overhead to set up REP MOVSB operation, REP MOVSB
+      # isn't faster on short data.  The memcpy micro benchmark in glibc
+      # shows that 2KB is the approximate value above which REP MOVSB
+      # becomes faster than SSE2 optimization on processors with Enhanced
+      # REP MOVSB.  Since larger register size can move more data with a
+      # single load and store, the threshold is higher with larger register
+      # size.  Note: Since the REP MOVSB threshold must be greater than 8
+      # times of vector size, the minium value must be updated at run-time.
+      minval: 1
+      default: 2048
+    }
+    x86_rep_stosb_threshold {
+      type: SIZE_T
+      # Since there is overhead to set up REP STOSB operation, REP STOSB
+      # isn't faster on short data.  The memset micro benchmark in glibc
+      # shows that 2KB is the approximate value above which REP STOSB
+      # becomes faster on processors with Enhanced REP STOSB.  Since the
+      # stored value is fixed, larger register size has minimal impact
+      # on threshold.
+      minval: 1
+      default: 2048
+    }
     x86_data_cache_size {
       type: SIZE_T
     }

sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S

@@ -56,17 +56,6 @@
 # endif
 #endif
 
-/* Threshold to use Enhanced REP MOVSB.  Since there is overhead to set
-   up REP MOVSB operation, REP MOVSB isn't faster on short data.  The
-   memcpy micro benchmark in glibc shows that 2KB is the approximate
-   value above which REP MOVSB becomes faster than SSE2 optimization
-   on processors with Enhanced REP MOVSB.  Since larger register size
-   can move more data with a single load and store, the threshold is
-   higher with larger register size.  */
-#ifndef REP_MOVSB_THRESHOLD
-# define REP_MOVSB_THRESHOLD	(2048 * (VEC_SIZE / 16))
-#endif
-
 #ifndef PREFETCH
 # define PREFETCH(addr) prefetcht0 addr
 #endif
@@ -253,9 +242,6 @@ L(movsb):
 	leaq	(%rsi,%rdx), %r9
 	cmpq	%r9, %rdi
 	/* Avoid slow backward REP MOVSB.  */
-# if REP_MOVSB_THRESHOLD <= (VEC_SIZE * 8)
-#  error Unsupported REP_MOVSB_THRESHOLD and VEC_SIZE!
-# endif
 	jb	L(more_8x_vec_backward)
 1:
 	mov	%RDX_LP, %RCX_LP
@@ -331,7 +317,7 @@ L(between_2_3):
 
 #if defined USE_MULTIARCH && IS_IN (libc)
 L(movsb_more_2x_vec):
-	cmpq	$REP_MOVSB_THRESHOLD, %rdx
+	cmp	__x86_rep_movsb_threshold(%rip), %RDX_LP
 	ja	L(movsb)
 #endif
 L(more_2x_vec):

sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S

@@ -58,16 +58,6 @@
 # endif
 #endif
 
-/* Threshold to use Enhanced REP STOSB.  Since there is overhead to set
-   up REP STOSB operation, REP STOSB isn't faster on short data.  The
-   memset micro benchmark in glibc shows that 2KB is the approximate
-   value above which REP STOSB becomes faster on processors with
-   Enhanced REP STOSB.  Since the stored value is fixed, larger register
-   size has minimal impact on threshold.  */
-#ifndef REP_STOSB_THRESHOLD
-# define REP_STOSB_THRESHOLD		2048
-#endif
-
 #ifndef SECTION
 # error SECTION is not defined!
 #endif
@@ -181,7 +171,7 @@ ENTRY (MEMSET_SYMBOL (__memset, unaligned_erms))
 	ret
 
 L(stosb_more_2x_vec):
-	cmpq	$REP_STOSB_THRESHOLD, %rdx
+	cmp	__x86_rep_stosb_threshold(%rip), %RDX_LP
 	ja	L(stosb)
 #endif
 L(more_2x_vec):