diff options
| author | Ard Biesheuvel <ardb@kernel.org> | 2022-02-05 18:23:45 +0300 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2022-02-11 12:39:39 +0300 |
| commit | 297565aa22cfa80ab0f88c3569693aea0b6afb6d (patch) | |
| tree | 86c452349612ec00b52d83c78900bcf45b6bbd8d /arch/powerpc/lib/xor_vmx.c | |
| parent | e8bf24bd439da1ee7f37c2b03f44c6ad37c0c8c0 (diff) | |
| download | linux-297565aa22cfa80ab0f88c3569693aea0b6afb6d.tar.xz | |
lib/xor: make xor prototypes more friendly to compiler vectorization
Modern compilers are perfectly capable of extracting parallelism from
the XOR routines, provided that the prototypes reflect the nature of the
input accurately, in particular, the fact that the input vectors are
expected not to overlap. This is not documented explicitly, but is
implied by the interchangeability of the various C routines, some of
which use temporary variables while others don't: this means that these
routines only behave identically for non-overlapping inputs.
So let's decorate these input vectors with the __restrict modifier,
which informs the compiler that there is no overlap. While at it, make
the input-only vectors pointer-to-const as well.
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://github.com/ClangBuiltLinux/linux/issues/563
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/powerpc/lib/xor_vmx.c')
| -rw-r--r-- | arch/powerpc/lib/xor_vmx.c | 28 |
1 files changed, 18 insertions, 10 deletions
diff --git a/arch/powerpc/lib/xor_vmx.c b/arch/powerpc/lib/xor_vmx.c index 54e61979e80e..aab49d056d18 100644 --- a/arch/powerpc/lib/xor_vmx.c +++ b/arch/powerpc/lib/xor_vmx.c @@ -49,8 +49,9 @@ typedef vector signed char unative_t; V1##_3 = vec_xor(V1##_3, V2##_3); \ } while (0) -void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in) +void __xor_altivec_2(unsigned long bytes, + unsigned long * __restrict v1_in, + const unsigned long * __restrict v2_in) { DEFINE(v1); DEFINE(v2); @@ -67,8 +68,10 @@ void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in, } while (--lines > 0); } -void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in) +void __xor_altivec_3(unsigned long bytes, + unsigned long * __restrict v1_in, + const unsigned long * __restrict v2_in, + const unsigned long * __restrict v3_in) { DEFINE(v1); DEFINE(v2); @@ -89,9 +92,11 @@ void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in, } while (--lines > 0); } -void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in, - unsigned long *v4_in) +void __xor_altivec_4(unsigned long bytes, + unsigned long * __restrict v1_in, + const unsigned long * __restrict v2_in, + const unsigned long * __restrict v3_in, + const unsigned long * __restrict v4_in) { DEFINE(v1); DEFINE(v2); @@ -116,9 +121,12 @@ void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in, } while (--lines > 0); } -void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in, - unsigned long *v2_in, unsigned long *v3_in, - unsigned long *v4_in, unsigned long *v5_in) +void __xor_altivec_5(unsigned long bytes, + unsigned long * __restrict v1_in, + const unsigned long * __restrict v2_in, + const unsigned long * __restrict v3_in, + const unsigned long * __restrict v4_in, + const unsigned long * __restrict v5_in) { DEFINE(v1); DEFINE(v2); |