| commit | c0c3e81608fc300027f2131e351e67ab118cf24c | |
| author | Haavard Skinnemoen <hskinnemoen@atmel.com> | |
| Wed, 14 Mar 2007 12:59:13 +0000 (14 13:59 +0100) | ||
| committer | Haavard Skinnemoen <hskinnemoen@atmel.com> | |
| Fri, 27 Apr 2007 11:44:15 +0000 (27 13:44 +0200) | ||
| tree | d1e7ebe582e7a554a6735cb17ed0a60c6be03c09 | treesnapshot (tar.gz zip) |
| parent | 9ca20a8366462c553c27216161c735937f9de108 | commitdiff |
[AVR32] Optimize the TLB miss handler
Reorder some instructions and change the register usage to reduce
the number of pipeline stalls. Also use the bfextu and bfins
instructions for bitfield manipulations instead of shifting and
masking.
This makes gzipping a 80MB file approximately 2% faster.
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Reorder some instructions and change the register usage to reduce
the number of pipeline stalls. Also use the bfextu and bfins
instructions for bitfield manipulations instead of shifting and
masking.
This makes gzipping a 80MB file approximately 2% faster.
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
| arch/avr32/kernel/entry-avr32b.S | diffblobblamehistory |