diff options
| author | Anton Blanchard <anton@samba.org> | 2012-05-30 20:22:09 +0000 |
|---|---|---|
| committer | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2012-07-03 14:14:46 +1000 |
| commit | b3f271e86e5a440713716bb222e1aa1227994c50 (patch) | |
| tree | a215f44357cf20c9f2b342a7bdb840bb85ca4cb1 /arch/powerpc/lib/memcpy_64.S | |
| parent | bce4b4bd91efab9dca693ac37c8ddf88103280d8 (diff) | |
| download | op-kernel-dev-b3f271e86e5a440713716bb222e1aa1227994c50.zip op-kernel-dev-b3f271e86e5a440713716bb222e1aa1227994c50.tar.gz | |
powerpc: POWER7 optimised memcpy using VMX and enhanced prefetch
Implement a POWER7 optimised memcpy using VMX and enhanced prefetch
instructions.
This is a copy of the POWER7 optimised copy_to_user/copy_from_user
loop. Detailed implementation and performance details can be found in
commit a66086b8197d (powerpc: POWER7 optimised
copy_to_user/copy_from_user using VMX).
I noticed memcpy issues when profiling a RAID6 workload:
.memcpy
.async_memcpy
.async_copy_data
.__raid_run_ops
.handle_stripe
.raid5d
.md_thread
I created a simplified testcase by building a RAID6 array with 4 1GB
ramdisks (booting with brd.rd_size=1048576):
# mdadm -CR -e 1.2 /dev/md0 --level=6 -n4 /dev/ram[0-3]
I then timed how long it took to write to the entire array:
# dd if=/dev/zero of=/dev/md0 bs=1M
Before: 892 MB/s
After: 999 MB/s
A 12% improvement.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch/powerpc/lib/memcpy_64.S')
| -rw-r--r-- | arch/powerpc/lib/memcpy_64.S | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index 82fea39..d2bbbc8 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -11,7 +11,11 @@ .align 7 _GLOBAL(memcpy) +BEGIN_FTR_SECTION std r3,48(r1) /* save destination pointer for return value */ +FTR_SECTION_ELSE + b memcpy_power7 +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) PPC_MTOCRF(0x01,r5) cmpldi cr1,r5,16 neg r6,r3 # LS 3 bits = # bytes to 8-byte dest bdry |
