This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
[PATCH] powerpc: small fix to POWER7 32-bit memset
- From: Luis Machado <luisgpm at linux dot vnet dot ibm dot com>
- To: libc-alpha <libc-alpha at sourceware dot org>
- Date: Mon, 24 May 2010 13:31:22 -0300
- Subject: [PATCH] powerpc: small fix to POWER7 32-bit memset
- Reply-to: luisgpm at linux dot vnet dot ibm dot com
Hi,
This is a little gotcha that slipped through on my previous memset
patch. It just makes things simpler by not having an additional load
immediate instruction.
Works just the same as the other version.
Regards,
Luis
2010-05-24 Luis Machado <luisgpm@br.ibm.com>
* sysdeps/powerpc/powerpc32/power7/memset.S: POWER7 32-bit memset fix.
diff --git a/sysdeps/powerpc/powerpc32/power7/memset.S b/sysdeps/powerpc/powerpc32/power7/memset.S
index 99d07ec..8aabb49 100644
--- a/sysdeps/powerpc/powerpc32/power7/memset.S
+++ b/sysdeps/powerpc/powerpc32/power7/memset.S
@@ -155,7 +155,6 @@ L(big_loop):
/* Now that we're probably past the LHS window, use the VSX to
speed up the loop. */
L(big_loop_fast_setup):
- li 0,0
li 11,24
li 6,16
lxvdsx 4,1,11
@@ -163,12 +162,12 @@ L(big_loop_fast_setup):
.align 4
L(big_loop_fast):
addi 12,10,32
- stxvd2x 4,10,0
+ stxvd2x 4,0,10
stxvd2x 4,10,6
bdz L(tail_bytes)
addi 10,10,64
- stxvd2x 4,12,0
+ stxvd2x 4,0,12
stxvd2x 4,12,6
bdnz L(big_loop_fast)