mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 03:09:34 +03:00
Minor performance fix for NEON RAID-Z
The NEON code replicates too closely the SSE code, including a masked 16-bits shift. But NEON, like AltiVec (#9539), has unsigned 8-bits shift, so use that instead and drop the masking. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Romain Dolbeau <romain.dolbeau@european-processor-initiative.eu> Closes #9725
This commit is contained in:
parent
fe564845c0
commit
118fc3ef07
@ -479,10 +479,8 @@ typedef struct v {
|
||||
/* upper part */ \
|
||||
"and v14.16b," VR0(r) ".16b,v15.16b\n" \
|
||||
"and v13.16b," VR1(r) ".16b,v15.16b\n" \
|
||||
"sshr " VR0(r) ".8h," VR0(r) ".8h,#4\n" \
|
||||
"sshr " VR1(r) ".8h," VR1(r) ".8h,#4\n" \
|
||||
"and " VR0(r) ".16b," VR0(r) ".16b,v15.16b\n" \
|
||||
"and " VR1(r) ".16b," VR1(r) ".16b,v15.16b\n" \
|
||||
"ushr " VR0(r) ".16b," VR0(r) ".16b,#4\n" \
|
||||
"ushr " VR1(r) ".16b," VR1(r) ".16b,#4\n" \
|
||||
\
|
||||
"tbl v12.16b,{v10.16b}," VR0(r) ".16b\n" \
|
||||
"tbl v10.16b,{v10.16b}," VR1(r) ".16b\n" \
|
||||
|
Loading…
Reference in New Issue
Block a user