Initial Chacha20 AVX512 implementation done using XMM registers
only, handling only 64 bytes at a time.

Add N buffer functions for ZUC EEA3/EIA3,
which utilize the internal ZUC functions using
GFNI and VAES instructions.

Optimize ZUC internal functions by using the upcoming
GFNI/VAES instructions, alongside AVX512.

Due to the usage of the new GFNI instructions,
the minimum required version of NASM has been updated
from 2.13.03 to 2.14.

There are some public enums that are conflicting
with other enums defined in other libraries, due to
too generic naming.
In order to solve this issue, existing enums will be renamed.

In order to maintain backwards compatilibity for the next few
releases, the previous enums will be maintained,
so existing applications will not be broken.

A new compilation flag, NO_COMPAT_IMB_API_053, is added.
The previous enums can be removed if this compilation flag
is set (which is disabled by default), when building and linking
applications.

For applications which use various libraries, this flag
should be set, so no redefinition of enums will take place, by
passing -DNO_COMPAT_IMB_API_053 to its CFLAGS (or EXTRA_CFLAGS).

- Added README.md
- Updated existing README with output generated by pandoc
- Added README target to Makefile to create/update README using pandoc

Change-Id: I2f93fa56c2d528efe12ba31ad28d269cabe14f43

Change-Id: Ib2df496afaebc13104eb3523e572b48ed3d3ad4d

Change-Id: I651e7ccb3a79ea733b8738666e69c76802f3fbfe

Add functions which look up an 8-bit value
in a variable sized table (table must be multiple of 16 bytes),
in a constant time.

Change-Id: I99d7fed4b0933140f4720e67260be5ec4d7794fe

- libsso library references removed

Change-Id: I589efdbc60615aa2db6087f9e0ca1cb40633966e

Change-Id: I4bb261a1466f1236fb7031bef1ebd50b1f488d12

Added support for KASUMI F8 and KASUMI F9 algorithms.

Note that the input data length passed in the new functions
is in bits and bytes, depending on the functions used.

Change-Id: I8a532ecf23842e01701aef635521873652895f47

Updated README and Release Notes to reflect
the changes done in AES-CBC, adding the implementation
for AVX512/VAES.

Change-Id: I719789706314c3b9a05b53b5e33277ca06064022

This new application (ipsec_xvalid_test) performs tests on
various combinations of cipher and hash algorithms,
on different buffer sizes and using different architectures.

The basic test performed is the following:
- The message gets encrypted and a digest is generated from the ciphertext,
  using one architecture
- The output message (ciphertext) gets decrypted and another digest
  is generated from the ciphertext, using another architecture (can be the same
  as the first step)
- The decrypted message is compared against the original plaintext
- Both generated digests are compared
- The test fails if any of these comparison fails

By default, the test loops through:
- All cipher, hash and AEAD algorithms supported
- Buffer sizes between 16 and 2048 bytes, in steps of 16 bytes
- All architectures supported (SSE, AESNI_EMU, AVX, AVX2, AVX512)

Any of the combinations above can be set, performing a single test.
A sample command line to do this is the following:

./ipsec_xvalid_test --job-size 512 --enc-arch AVX512 --dec-arch AVX --aead-algo aes-gcm-128

This command performs a test using AES-GCM, on 512B buffers,
encrypting with AVX512 and decrypting with AVX.

The application can be also launched with no parameters, going through
all cipher+hash combinations and architectures.

Change-Id: I7f5c8e9b66a2312570862ce204fb1ed191f56182

OS support is extended with FreeBSD, alongside Linux and Windows.
No major code changes are required for FreeBSD,
since it uses same API/ABI as Linux.

Change-Id: I672316fbeed4f3eee997ffbe52974227ef5252d3

Change-Id: I00552e394f86c453341847ee683a6cdde95e04d7

Change-Id: I3eb74462c9000949fd769bc5d82d6110da97d1ea

- GCM_BIG_DATA compile flag added
  - disabled by default, number of ghash keys is 48 (key structure 1,152 bytes)
  - when ebaled, number of ghash keys is 128 (key sturcture 2,432 bytes)
- precomputing 128 or 48 GHASH keys (the structure is much bigger now)
  - When GCM_BIG_DATA is on and data >= 2,048 bytes reduction is done every 128 blocks
  - for data >= 768 bytes reduction is done every 48 blocks
  - for other cases reduction is done every 8 blocks
- added new macro handling 16 blocks of AES and GHASH in parallel
  - pipeline depth is 32 blocks
  - very large and large buffers leverage the macro
- initial N x 16 blocks macro implemented
  - pipelines cipher with GHASH
  - first runs cipher only as defined by depth of the pipeline
  - then runs stitched cipher and GHASH for the remaining number of blocks
- parallel cipher and ghash N x 16 blocks implemented
  - cipher and ghash always stitched
  - reduction done as defined by maximum number of blocks
  - depth of the pipeline maintained as in initial N x 16 macro
    - cipher is ahead of ghash by 32 blocks
- stack frame created to keep up to 128 blocks of cipher text
  - stack frame loads/stores are aligned
- gcm key data structure definition made more generic
- VX512STR and VX512LDR macros changed from vmovdqu64 to vmovdqu8
  in order to work correctly with masked operations

Change-Id: Idd83b911c9257bbd221c66ddd9297a4f2ae120c2

Change-Id: Ib7946530b63c930dfd585a1c2a2cc6b3d788e57a

Added support for ZUC-EEA3 and ZUC-EIA3
algorithms, in SSE and AVX.

Note that the input data length passed in the new functions
is in bits and not in bytes, as it is generally done
in the rest of the library.

Change-Id: Id0137ccad79734ceaa05da1ad6d710bce7dcd917

Handle 16 blocks in parallel, instead of 8,
improving throughput by increasing port utilization.

Change-Id: I2fcc530b2458c5c106375bee811e908b5a809635

Add SSE and AVX implementations of AES-ECB.

Change-Id: I47105414d73035c7090c70abd860831ffac015c0