liblzma: Add fast CRC64 for 32/64-bit x86 using SSSE3 + SSE4.1 + CLMUL.

It also works on E2K as it supports these intrinsics.

On x86-64 runtime detection is used so the code keeps working on
older processors too. A CLMUL-only build can be done by using
-msse4.1 -mpclmul in CFLAGS and this will reduce the library
size since the generic implementation and its 8 KiB lookup table
will be omitted.

On 32-bit x86 this isn't used by default for now because by default
on 32-bit x86 the separate assembly file crc64_x86.S is used.
If --disable-assembler is used then this new CLMUL code is used
the same way as on 64-bit x86. However, a CLMUL-only build
(-msse4.1 -mpclmul) won't omit the 8 KiB lookup table on
32-bit x86 due to a currently-missing check for disabled
assembler usage.

The configure.ac check should be such that the code won't be
built if something in the toolchain doesn't support it but
--disable-clmul-crc option can be used to unconditionally
disable this feature.

CLMUL speeds up decompression of files that have compressed very
well (assuming CRC64 is used as a check type). It is know that
the CLMUL code is significantly slower than the generic code for
tiny inputs (especially 1-8 bytes but up to 16 bytes). If that
is a real-world problem then there is already a commented-out
variant that uses the generic version for small inputs.

Thanks to Ilya Kurdyukov for the original patch which was
derived from a white paper from Intel [1] (published in 2009)
and public domain code from [2] (released in 2016).

[1] https://www.intel.com/content/dam/www/public/us/en/documents/white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
[2] https://github.com/rawrunprotected/crc

1 files changed, 12 insertions, 0 deletions

diff --git a/INSTALL b/INSTALL
index 2c94ece..bf1e9c3 100644
--- a/INSTALL
+++ b/INSTALL
@@ -370,6 +370,18 @@ XZ Utils Installation
                 pre-i686 systems, you may want to disable the assembler
                 code.
 
+    --disable-clmul-crc
+                Disable the use carryless multiplication for CRC
+                calculation even if compiler support for it is detected.
+                The code uses runtime detection of SSSE3, SSE4.1, and
+                CLMUL instructions on x86. On 32-bit x86 this currently
+                is used only if --disable-assembler is used (this might
+                be fixed in the future). The code works on E2K too.
+
+                If using compiler options that unconditionally allow the
+                required extensions (-msse4.1 -mpclmul) then runtime
+                detection isn't used and the generic code is omitted.
+
     --enable-unaligned-access
                 Allow liblzma to use unaligned memory access for 16-bit,
                 32-bit, and 64-bit loads and stores. This should be