saymrwulf/curve25519-dalek-source
1
0
Fork 0
mirror of https://github.com/saymrwulf/curve25519-dalek-source.git synced 2026-09-04 20:24:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Delay all computations using x[0], y[0]

Browse source 
Since computation of the 0 term in reduction requires a multiplication with a
4-cycle latency, this ensures that the rest of the computation can start before
the 0 term is finished
This commit is contained in:
Henry de Valence 2018-11-14 12:36:34 -08:00
parent c925c76342
commit d90bb779ca
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
src/backend/vector/ifma/field.rs
View file

@ -197,8 +197,8 @@ impl<'a, 'b> Mul<&'b F51x4Reduced> for &'a F51x4Reduced {
let mut z9hi = u64x4::splat(0);
// Wave 0
z4lo = madd52lo(z4lo, x[4], y[0]);
z5hi = madd52hi(z5hi, x[4], y[0]);
z4lo = madd52lo(z4lo, x[2], y[2]);
z5hi = madd52hi(z5hi, x[2], y[2]);
z5lo = madd52lo(z5lo, x[4], y[1]);
z6hi = madd52hi(z6hi, x[4], y[1]);
z6lo = madd52lo(z6lo, x[4], y[2]);
@ -219,8 +219,8 @@ impl<'a, 'b> Mul<&'b F51x4Reduced> for &'a F51x4Reduced {
// Wave 2
z8lo = madd52lo(z8lo, x[4], y[4]);
z9hi = madd52hi(z9hi, x[4], y[4]);
z4lo = madd52lo(z4lo, x[2], y[2]);
z5hi = madd52hi(z5hi, x[2], y[2]);
z4lo = madd52lo(z4lo, x[4], y[0]);
z5hi = madd52hi(z5hi, x[4], y[0]);
z5lo = madd52lo(z5lo, x[2], y[3]);
z6hi = madd52hi(z6hi, x[2], y[3]);
z6lo = madd52lo(z6lo, x[2], y[4]);