Lynn Boger
f99c8df09e
This adds an asm implementation for poly1305 on ppc64le, based on
the amd64 asm implementation using the mac interface.
The improvements on a power8 based on the poly1305 benchmarks are:
name old time/op new time/op delta
64 172ns ± 0% 78ns ± 0% -54.77% (p=1.000 n=1+1)
1K 1.47µs ± 0% 0.59µs ± 0% -59.69% (p=1.000 n=1+1)
2M 2.84ms ± 0% 1.12ms ± 0% -60.47% (p=1.000 n=1+1)
64Unaligned 172ns ± 0% 78ns ± 0% -54.59% (p=1.000 n=1+1)
1KUnaligned 1.47µs ± 0% 0.59µs ± 0% -59.69% (p=1.000 n=1+1)
2MUnaligned 2.84ms ± 0% 1.13ms ± 0% -60.23% (p=1.000 n=1+1)
Write64 100ns ± 0% 46ns ± 0% -53.80% (p=1.000 n=1+1)
Write1K 1.40µs ± 0% 0.56µs ± 0% -59.90% (p=1.000 n=1+1)
Write2M 2.84ms ± 0% 1.12ms ± 0% -60.46% (p=1.000 n=1+1)
Write64Unaligned 100ns ± 0% 46ns ± 0% -53.60% (p=1.000 n=1+1)
Write1KUnaligned 1.40µs ± 0% 0.56µs ± 0% -59.90% (p=1.000 n=1+1)
Write2MUnaligned 2.84ms ± 0% 1.13ms ± 0% -60.22% (p=1.000 n=1+1)
Change-Id: I77cc9bb3645a6b1a6edc414b5651dc37ae4a7410
Reviewed-on: https://go-review.googlesource.com/c/crypto/+/173421
Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Michael Munday <mike.munday@ibm.com>
69 lines
1.5 KiB
Go
69 lines
1.5 KiB
Go
// Copyright 2019 The Go Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
// +build ppc64le,!gccgo,!appengine
|
|
|
|
package poly1305
|
|
|
|
//go:noescape
|
|
func initialize(state *[7]uint64, key *[32]byte)
|
|
|
|
//go:noescape
|
|
func update(state *[7]uint64, msg []byte)
|
|
|
|
//go:noescape
|
|
func finalize(tag *[TagSize]byte, state *[7]uint64)
|
|
|
|
// Sum generates an authenticator for m using a one-time key and puts the
|
|
// 16-byte result into out. Authenticating two different messages with the same
|
|
// key allows an attacker to forge messages at will.
|
|
func Sum(out *[16]byte, m []byte, key *[32]byte) {
|
|
h := newMAC(key)
|
|
h.Write(m)
|
|
h.Sum(out)
|
|
}
|
|
|
|
func newMAC(key *[32]byte) (h mac) {
|
|
initialize(&h.state, key)
|
|
return
|
|
}
|
|
|
|
type mac struct {
|
|
state [7]uint64 // := uint64{ h0, h1, h2, r0, r1, pad0, pad1 }
|
|
|
|
buffer [TagSize]byte
|
|
offset int
|
|
}
|
|
|
|
func (h *mac) Write(p []byte) (n int, err error) {
|
|
n = len(p)
|
|
if h.offset > 0 {
|
|
remaining := TagSize - h.offset
|
|
if n < remaining {
|
|
h.offset += copy(h.buffer[h.offset:], p)
|
|
return n, nil
|
|
}
|
|
copy(h.buffer[h.offset:], p[:remaining])
|
|
p = p[remaining:]
|
|
h.offset = 0
|
|
update(&h.state, h.buffer[:])
|
|
}
|
|
if nn := len(p) - (len(p) % TagSize); nn > 0 {
|
|
update(&h.state, p[:nn])
|
|
p = p[nn:]
|
|
}
|
|
if len(p) > 0 {
|
|
h.offset += copy(h.buffer[h.offset:], p)
|
|
}
|
|
return n, nil
|
|
}
|
|
|
|
func (h *mac) Sum(out *[16]byte) {
|
|
state := h.state
|
|
if h.offset > 0 {
|
|
update(&state, h.buffer[:h.offset])
|
|
}
|
|
finalize(out, &state)
|
|
}
|