Uses a more general interface for the RAID engine.

This commit is contained in:
Andrea Mazzoleni 2013-12-28 15:12:09 +01:00
parent 684edf2173
commit e80a5e868f
5 changed files with 108 additions and 56 deletions

View file

@ -163,7 +163,7 @@ void raid_par2_int64(int nd, size_t size, void **vv)
/*
* PAR3 (triple parity with Cauchy matrix) 8bit C implementation
*
* Note that instead of a generic multiplicationt table, likely resulting
* Note that instead of a generic multiplication table, likely resulting
* in multiple cache misses, a precomputed table could be used.
* But this is only a kind of reference function, and we are not really
* interested in speed.
@ -210,7 +210,7 @@ void raid_par3_int8(int nd, size_t size, void **vv)
/*
* PAR4 (quad parity with Cauchy matrix) 8bit C implementation
*
* Note that instead of a generic multiplicationt table, likely resulting
* Note that instead of a generic multiplication table, likely resulting
* in multiple cache misses, a precomputed table could be used.
* But this is only a kind of reference function, and we are not really
* interested in speed.
@ -262,7 +262,7 @@ void raid_par4_int8(int nd, size_t size, void **vv)
/*
* PAR5 (penta parity with Cauchy matrix) 8bit C implementation
*
* Note that instead of a generic multiplicationt table, likely resulting
* Note that instead of a generic multiplication table, likely resulting
* in multiple cache misses, a precomputed table could be used.
* But this is only a kind of reference function, and we are not really
* interested in speed.
@ -319,7 +319,7 @@ void raid_par5_int8(int nd, size_t size, void **vv)
/*
* PAR6 (hexa parity with Cauchy matrix) 8bit C implementation
*
* Note that instead of a generic multiplicationt table, likely resulting
* Note that instead of a generic multiplication table, likely resulting
* in multiple cache misses, a precomputed table could be used.
* But this is only a kind of reference function, and we are not really
* interested in speed.