diff options
| author |   Jason A. Donenfeld <Jason@zx2c4.com> | 2018-10-04 04:33:45 +0200 |
|---|---|---|
| committer | Jason A. Donenfeld <Jason@zx2c4.com> | 2018-10-04 14:59:12 +0200 |
| commit | d0772d75534bdfb29435b043d6c665f58817e17d (patch) | |
| tree | aa4da11ab9f02a32b64117f27a20c3dbb89b1c86 /src/crypto/zinc | |
| parent | curve25519-arm: writeback to base register when possible (diff) | |
| download | wireguard-monolithic-historical-d0772d75534bdfb29435b043d6c665f58817e17d.tar.xz wireguard-monolithic-historical-d0772d75534bdfb29435b043d6c665f58817e17d.zip | |
curve25519-arm: rearrange multiplications for better in-order performance
Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Diffstat (limited to 'src/crypto/zinc')
| -rw-r--r-- | src/crypto/zinc/curve25519/curve25519-arm.S | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/src/crypto/zinc/curve25519/curve25519-arm.S b/src/crypto/zinc/curve25519/curve25519-arm.S index 4f53bbc..b63ac48 100644 --- a/src/crypto/zinc/curve25519/curve25519-arm.S +++ b/src/crypto/zinc/curve25519/curve25519-arm.S @@ -607,14 +607,14 @@ ENTRY(curve25519_neon) add r2, sp, #608 vld1.8 {d18-d19}, [r2, : 128] vmlal.s32 q2, d18, d7 - vmlal.s32 q2, d19, d6 vmlal.s32 q5, d18, d6 - vmlal.s32 q5, d19, d21 vmlal.s32 q1, d18, d21 - vmlal.s32 q1, d19, d29 vmlal.s32 q0, d18, d28 - vmlal.s32 q0, d19, d9 vmlal.s32 q6, d18, d29 + vmlal.s32 q2, d19, d6 + vmlal.s32 q5, d19, d21 + vmlal.s32 q1, d19, d29 + vmlal.s32 q0, d19, d9 vmlal.s32 q6, d19, d28 add r2, sp, #560 vld1.8 {d18-d19}, [r2, : 128] @@ -919,14 +919,14 @@ ENTRY(curve25519_neon) add r2, sp, #608 vld1.8 {d18-d19}, [r2, : 128] vmlal.s32 q2, d18, d7 - vmlal.s32 q2, d19, d6 vmlal.s32 q5, d18, d6 - vmlal.s32 q5, d19, d21 vmlal.s32 q1, d18, d21 - vmlal.s32 q1, d19, d29 vmlal.s32 q0, d18, d28 - vmlal.s32 q0, d19, d9 vmlal.s32 q6, d18, d29 + vmlal.s32 q2, d19, d6 + vmlal.s32 q5, d19, d21 + vmlal.s32 q1, d19, d29 + vmlal.s32 q0, d19, d9 vmlal.s32 q6, d19, d28 add r2, sp, #560 vld1.8 {d18-d19}, [r2, : 128] @@ -1381,14 +1381,14 @@ ENTRY(curve25519_neon) add r2, sp, #608 vld1.8 {d18-d19}, [r2, : 128] vmlal.s32 q2, d18, d7 - vmlal.s32 q2, d19, d6 vmlal.s32 q5, d18, d6 - vmlal.s32 q5, d19, d21 vmlal.s32 q1, d18, d21 - vmlal.s32 q1, d19, d29 vmlal.s32 q0, d18, d28 - vmlal.s32 q0, d19, d9 vmlal.s32 q6, d18, d29 + vmlal.s32 q2, d19, d6 + vmlal.s32 q5, d19, d21 + vmlal.s32 q1, d19, d29 + vmlal.s32 q0, d19, d9 vmlal.s32 q6, d19, d28 add r2, sp, #560 vld1.8 {d18-d19}, [r2, : 128] |