[PATCH RFC V2] [x86] Optimize small size memcpy by avoding long latency from decode stage

[ling.ma.program@gmail.com]

From: Ma Ling <ling.ma.program@gmail.com>

CISC code has higher instruction density, saving memory and
improving i-cache hit rate. However decode become challenge,
only one mulitple-uops(2~3)instruction could be decoded in one cycle,
and instructions containing more 4 uops(rep movsq/b) have to be handled by MS-ROM,
the process take long time and eat up the advantage from it for small size. 

In order to avoid this disavantage, we take use of general instruction code
for small size copy. The result shows it can get 1~2x improvement
on Core2, Nehalem, Sandy Bridge, Ivy Bridge, Atom, and Bulldozer as well.

Signed-off-by: Ma Ling <ling.ma.program@gmail.com>
---
In this version we decrease warm up distance from 512 to 256 for coming CPUs,
which manage to reduce latency, but long time to decode is still consumed.

Thanks
Ling

 arch/x86/lib/memcpy_64.S |   14 +++++++++++++-
 1 files changed, 13 insertions(+), 1 deletions(-)

diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 1c273be..6a24c8c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -5,7 +5,6 @@
 #include <asm/cpufeature.h>
 #include <asm/dwarf2.h>
 #include <asm/alternative-asm.h>
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -19,6 +18,15 @@
  */
 
 /*
+ * memcpy_c() and memcpy_c_e() use rep movsq/movsb respectively,
+ * the instruction have to get micro ops from Microcode Sequencser Rom.
+ * And the decode  process take long latency, in order to avoid it, 
+ * we choose loop unrolling routine for small size.
+ * Could vary the warm up  distance.
+ */
+
+
+/*
  * memcpy_c() - fast string ops (REP MOVSQ) based variant.
  *
  * This gets patched over the unrolled variant (below) via the
@@ -26,6 +34,8 @@
  */
 	.section .altinstr_replacement, "ax", @progbits
 .Lmemcpy_c:
+	cmpq $256, %rdx
+	jbe  memcpy 	
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	shrq $3, %rcx
@@ -46,6 +56,8 @@
  */
 	.section .altinstr_replacement, "ax", @progbits
 .Lmemcpy_c_e:
+	cmpq $256, %rdx
+	jbe  memcpy
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
-- 
1.6.5.2