Clang warns: vector initializers are not compatible with NEON intrinsics
in big endian mode [-Wnonportable-vector-initialization]
While this is usually the case, it's not an issue for this case since
we're initializing the uint8x16_t (16x uint8_t's) with the same value.
Instead, use vdupq_n_u8 which both compilers lower into a single movi
instruction: https://godbolt.org/z/vBrgzt
This avoids the static storage for a constant value.
Link: https://github.com/ClangBuiltLinux/linux/issues/214
Suggested-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The P/Q left side optimization in the delta syndrome simply involves
repeatedly multiplying a value by polynomial 'x' in GF(2^8). Given
that 'x * x * x * x' equals 'x^4' even in the polynomial world, we
can accelerate this substantially by performing up to 4 such operations
at once, using the NEON instructions for polynomial multiplication.
Results on a Cortex-A57 running in 64-bit mode:
Before:
-------
raid6: neonx1 xor() 1680 MB/s
raid6: neonx2 xor() 2286 MB/s
raid6: neonx4 xor() 3162 MB/s
raid6: neonx8 xor() 3389 MB/s
After:
------
raid6: neonx1 xor() 2281 MB/s
raid6: neonx2 xor() 3362 MB/s
raid6: neonx4 xor() 3787 MB/s
raid6: neonx8 xor() 4239 MB/s
While we're at it, simplify MASK() by using a signed shift rather than
a vector compare involving a temp register.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Rebased/reworked a patch contributed by Rob Herring that uses
NEON intrinsics to perform the RAID-6 syndrome calculations.
It uses the existing unroll.awk code to generate several
unrolled versions of which the best performing one is selected
at boot time.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Cc: hpa@linux.intel.com
ndesaulniers@google.com