diff options
Diffstat (limited to 'vendor/gmp-6.3.0/mpn/alpha/ev6/nails/README')
| -rw-r--r-- | vendor/gmp-6.3.0/mpn/alpha/ev6/nails/README | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/vendor/gmp-6.3.0/mpn/alpha/ev6/nails/README b/vendor/gmp-6.3.0/mpn/alpha/ev6/nails/README new file mode 100644 index 0000000..b214ac5 --- /dev/null +++ b/vendor/gmp-6.3.0/mpn/alpha/ev6/nails/README @@ -0,0 +1,65 @@ +Copyright 2002, 2005 Free Software Foundation, Inc. + +This file is part of the GNU MP Library. + +The GNU MP Library is free software; you can redistribute it and/or modify +it under the terms of either: + + * the GNU Lesser General Public License as published by the Free + Software Foundation; either version 3 of the License, or (at your + option) any later version. + +or + + * the GNU General Public License as published by the Free Software + Foundation; either version 2 of the License, or (at your option) any + later version. + +or both in parallel, as here. + +The GNU MP Library is distributed in the hope that it will be useful, but +WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +You should have received copies of the GNU General Public License and the +GNU Lesser General Public License along with the GNU MP Library. If not, +see https://www.gnu.org/licenses/. + + + + + +This directory contains assembly code for nails-enabled 21264. The code is not +very well optimized. + +For addmul_N, as N grows larger, we could make multiple loads together, then do +about 3.3 i/c. 10 cycles after the last load, we can increase to 4 i/c. This +would surely allow addmul_4 to run at 2 c/l, but the same should be possible +also for addmul_3 and perhaps even addmul_2. + + + current fair best +Routine c/l unroll c/l unroll c/l i/c +mul_1 3.25 2.75 2.75 3.273 +addmul_1 4.0 4 3.5 4 14 3.25 3.385 +addmul_2 4.0 1 2.5 2 10 2.25 3.333 +addmul_3 3.0 1 2.33 2 14 2 3.333 +addmul_4 2.5 1 2.125 2 17 2 3.135 + +addmul_5 2 1 10 +addmul_6 2 1 12 +addmul_7 2 1 14 + +(The "best" column doesn't account for bookkeeping instructions and +thereby assumes infinite unrolling.) + +Basecase usages: + +1 addmul_1 +2 addmul_2 +3 addmul_3 +4 addmul_4 +5 addmul_3 + addmul_2 2.3998 +6 addmul_4 + addmul_2 +7 addmul_4 + addmul_3 |