svn commit: r334537 - head/sys/amd64/amd64

[Mateusz Guzik]

Author: mjg
Date: Sat Jun  2 20:14:43 2018
New Revision: 334537
URL: https://svnweb.freebsd.org/changeset/base/334537

Log:
  amd64: add a mild depessimization to rep mov/stos users
  
  Currently all the primitives are waiting for a rewrite, tidy them up in the
  meantime.
  
  Vast majority of cases pass sizes which are multiple of 8. Which means the
  following rep stosb/movb has nothing to do. Turns out testing first if there
  is anything to do is a big win across the board (cpus with and without ERMS,
  Intel and AMD) while not pessimizing the case where there is work to do.
  
  Sample results for zeroing 64 bytes (ops/second):
  Ryzen Threadripper 1950X		91433212 -> 147265741
  Intel(R) Xeon(R) CPU X5675 @ 3.07GHz	90714044 -> 121992888
  
  bzero and bcopy are on their way out and were not modified. Nothing in the
  tree uses them.

Modified:
  head/sys/amd64/amd64/support.S

Modified: head/sys/amd64/amd64/support.S
==============================================================================
--- head/sys/amd64/amd64/support.S	Sat Jun  2 20:11:28 2018	(r334536)
+++ head/sys/amd64/amd64/support.S	Sat Jun  2 20:14:43 2018	(r334537)
@@ -205,6 +205,11 @@ ENTRY(memmove)
 	movsq
 	movq	%rdx,%rcx
 	andq	$7,%rcx				/* any bytes left? */
+	jne	2f
+	movq	%r9,%rax
+	POP_FRAME_POINTER
+	ret
+2:
 	rep
 	movsb
 	movq	%r9,%rax
@@ -248,6 +253,10 @@ ENTRY(memcpy)
 	movsq
 	movq	%rdx,%rcx
 	andq	$7,%rcx				/* any bytes left? */
+	jne	1f
+	POP_FRAME_POINTER
+	ret
+1:
 	rep
 	movsb
 	POP_FRAME_POINTER
@@ -269,6 +278,11 @@ ENTRY(memset)
 	stosq
 	movq	%rdx,%rcx
 	andq	$7,%rcx
+	jne	1f
+	movq	%r9,%rax
+	POP_FRAME_POINTER
+	ret
+1:
 	rep
 	stosb
 	movq	%r9,%rax
@@ -358,6 +372,7 @@ ENTRY(copyout)
 	movsq
 	movb	%dl,%cl
 	andb	$7,%cl
+	je	done_copyout
 	rep
 	movsb
 
@@ -406,6 +421,7 @@ ENTRY(copyin)
 	movsq
 	movb	%al,%cl
 	andb	$7,%cl				/* copy remaining bytes */
+	je	done_copyin
 	rep
 	movsb