* std.crypto.onetimeauth.ghash: faster GHASH on modern CPUs
Carryless multiplication was slow on older Intel CPUs, justifying
the need for using Karatsuba multiplication.
This is not the case any more; using 4 multiplications to multiply
two 128-bit numbers is actually faster than 3 multiplications +
shifts and additions.
This is also true on aarch64.
Keep using Karatsuba only when targeting x86 (granted, this is a bit
of a brutal shortcut, we should really list all the CPU models that
had a slow clmul instruction).
Also remove useless agg_2 treshold and restore the ability to
precompute only H and H^2 in ReleaseSmall.
Finally, avoid using u256. Using 128-bit registers is actually faster.
* Use a switch, add some comments
In the process of 'remaining blocks',
the length of processed message can be from 1 to 79.
The value of 'n-1' is ranged from 0 to 3.
So, st.hx[i] must be initialized at least from st.hx[0] to st.hx[3]
These constants were read as a block count in initForBlockCount()
but at the same time, as a size in update().
The unit could be blocks or bytes, but we should use the same one
everywhere.
So, use blocks as intended.
Fixes#13506
* std.crypto: make ghash faster, esp. for small messages
Aggregated reduction requires 5 additional multiplications (to
precompute the powers of H), in order to save 2 multiplications
per batch.
So, only use large batches when it's actually interesting to do so.
For the last blocks, reuse the precomputations in order to perform
a single reduction.
Also, even in .ReleaseSmall, allow 2-block aggregation.
The speedup is worth it, and the code increase is reasonable.
And in .ReleaseFast, bump the upper batch size up to 16.
Leverage comptime by the way instead of duplicating code.
std/crypto/benchmark.zig on Apple M1:
Zig 0.10.0: 2769 MiB/s
Before: 6014 MiB/s
After: 7334 MiB/s
Normalize function names by the way.
* Change clmul() to accept the half to be processed
This avoids a bunch of truncate() calls.
* Add more ghash tests to check all code paths
Rewrite GHASH to use 128-bit multiplication over non-reversed
integers, and up to 8 blocks aggregated reduction.
lib/std/crypto/benchmark.zig results:
Xeon E5:
Before: 1604 MiB/s
After: 4005 MiB/s
Apple M1:
Before: 2769 MiB/s
After: 6014 MiB/s
This also makes AES-GCM faster by the way.
We already have a LICENSE file that covers the Zig Standard Library. We
no longer need to remind everyone that the license is MIT in every single
file.
Previously this was introduced to clarify the situation for a fork of
Zig that made Zig's LICENSE file harder to find, and replaced it with
their own license that required annual payments to their company.
However that fork now appears to be dead. So there is no need to
reinforce the copyright notice in every single file.
Conflicts:
* doc/langref.html.in
* lib/std/enums.zig
* lib/std/fmt.zig
* lib/std/hash/auto_hash.zig
* lib/std/math.zig
* lib/std/mem.zig
* lib/std/meta.zig
* test/behavior/alignof.zig
* test/behavior/bitcast.zig
* test/behavior/bugs/1421.zig
* test/behavior/cast.zig
* test/behavior/ptrcast.zig
* test/behavior/type_info.zig
* test/behavior/vector.zig
Master branch added `try` to a bunch of testing function calls, and some
lines also had changed how to refer to the native architecture and other
`@import("builtin")` stuff.
This is a trivial implementation that just does a or[xor] loop.
However, this pattern is used by virtually all crypto libraries and
in practice, even without assembly barriers, LLVM never turns it into
code with conditional jumps, even if one of the parameters is constant.
This has been verified to still be the case with LLVM 11.0.0.
- use `PascalCase` for all types. So, AES256GCM is now Aes256Gcm.
- consistently use `_length` instead of mixing `_size` and `_length` for the
constants we expose
- Use `minimum_key_length` when it represents an actual minimum length.
Otherwise, use `key_length`.
- Require output buffers (for ciphertexts, macs, hashes) to be of the right
size, not at least of that size in some functions, and the exact size elsewhere.
- Use a `_bits` suffix instead of `_length` when a size is represented as a
number of bits to avoid confusion.
- Functions returning a constant-sized slice are now defined as a slice instead
of a pointer + a runtime assertion. This is the case for most hash functions.
- Use `camelCase` for all functions instead of `snake_case`.
No functional changes, but these are breaking API changes.
Performance increases from ~400 MiB/s to 450 MiB/s at the expense of
extra code. Thus, aggregation is disabled on ReleaseSmall.
Since the multiplication cost is significant compared to the reduction,
aggregating more than 2 blocks is probably not worth it.
