x86-64: Avoid rep movsb with short distance [BZ #27130]

When copying with "rep movsb", if the distance between source and
destination is N*4GB + [1..63] with N >= 0, performance may be very
slow.  This patch updates memmove-vec-unaligned-erms.S for AVX and
AVX512 versions with the distance in RCX:

	cmpl	$63, %ecx
	// Don't use "rep movsb" if ECX <= 63
	jbe	L(Don't use rep movsb")
	Use "rep movsb"

Benchtests data with bench-memcpy, bench-memcpy-large, bench-memcpy-random
and bench-memcpy-walk on Skylake, Ice Lake and Tiger Lake show that its
performance impact is within noise range as "rep movsb" is only used for
data size >= 4KB.

diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
index 7d54095f04459b1a32c00cdcc822cf179b2c5de6..0980c95378786a90806c4d18b8af6aeee897a858 100644 (file)
--- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
@@ -56,6 +56,13 @@
 # endif
 #endif
 
+/* Avoid short distance rep movsb only with non-SSE vector.  */
+#ifndef AVOID_SHORT_DISTANCE_REP_MOVSB
+# define AVOID_SHORT_DISTANCE_REP_MOVSB (VEC_SIZE > 16)
+#else
+# define AVOID_SHORT_DISTANCE_REP_MOVSB 0
+#endif
+
 #ifndef PREFETCH
 # define PREFETCH(addr) prefetcht0 addr
 #endif
@@ -243,7 +250,21 @@ L(movsb):
        cmpq    %r9, %rdi
        /* Avoid slow backward REP MOVSB.  */
        jb      L(more_8x_vec_backward)
+# if AVOID_SHORT_DISTANCE_REP_MOVSB
+       movq    %rdi, %rcx
+       subq    %rsi, %rcx
+       jmp     2f
+# endif
 1:
+# if AVOID_SHORT_DISTANCE_REP_MOVSB
+       movq    %rsi, %rcx
+       subq    %rdi, %rcx
+2:
+/* Avoid "rep movsb" if RCX, the distance between source and destination,
+   is N*4GB + [1..63] with N >= 0.  */
+       cmpl    $63, %ecx
+       jbe     L(more_2x_vec)  /* Avoid "rep movsb" if ECX <= 63.  */
+# endif
        mov     %RDX_LP, %RCX_LP
        rep movsb
 L(nop):