From 62a65a654e15a1388bfb571727e69b46e7cc07ab Mon Sep 17 00:00:00 2001 From: Romain Dolbeau Date: Mon, 3 Oct 2016 18:44:00 +0200 Subject: Add parity generation/rebuild using 128-bits NEON for Aarch64 This re-use the framework established for SSE2, SSSE3 and AVX2. However, GCC is using FP registers on Aarch64, so unlike SSE/AVX2 we can't rely on the registers being left alone between ASM statements. So instead, the NEON code uses C variables and GCC extended ASM syntax. Note that since the kernel explicitly disable vector registers, they have to be locally re-enabled explicitly. As we use the variable's number to define the symbolic name, and GCC won't allow duplicate symbolic names, numbers have to be unique. Even when the code is not going to be used (e.g. the case for 4 registers when using the macro with only 2). Only the actually used variables should be declared, otherwise the build will fails in debug mode. This requires the replacement of the XOR(X,X) syntax by a new ZERO(X) macro, which does the same thing but without repeating the argument. And perhaps someday there will be a machine where there is a more efficient way to zero a register than XOR with itself. This affects scalar, SSE2, SSSE3 and AVX2 as they need the new macro. It's possible to write faster implementations (different scheduling, different unrolling, interleaving NEON and scalar, ...) for various cores, but this one has the advantage of fitting in the current state of the code, and thus is likely easier to review/check/merge. The only difference between aarch64-neon and aarch64-neonx2 is that aarch64-neonx2 unroll some functions some more. Reviewed-by: Gvozden Neskovic Reviewed-by: Brian Behlendorf Signed-off-by: Romain Dolbeau Closes #4801 --- include/linux/Makefile.am | 1 + include/linux/simd_aarch64.h | 62 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 include/linux/simd_aarch64.h (limited to 'include/linux') diff --git a/include/linux/Makefile.am b/include/linux/Makefile.am index 9da9c068c..9bb0b3493 100644 --- a/include/linux/Makefile.am +++ b/include/linux/Makefile.am @@ -8,6 +8,7 @@ KERNEL_H = \ $(top_srcdir)/include/linux/utsname_compat.h \ $(top_srcdir)/include/linux/kmap_compat.h \ $(top_srcdir)/include/linux/simd_x86.h \ + $(top_srcdir)/include/linux/simd_aarch64.h \ $(top_srcdir)/include/linux/mod_compat.h USER_H = diff --git a/include/linux/simd_aarch64.h b/include/linux/simd_aarch64.h new file mode 100644 index 000000000..155ef6205 --- /dev/null +++ b/include/linux/simd_aarch64.h @@ -0,0 +1,62 @@ +/* + * CDDL HEADER START + * + * The contents of this file are subject to the terms of the + * Common Development and Distribution License (the "License"). + * You may not use this file except in compliance with the License. + * + * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE + * or http://www.opensolaris.org/os/licensing. + * See the License for the specific language governing permissions + * and limitations under the License. + * + * When distributing Covered Code, include this CDDL HEADER in each + * file and include the License file at usr/src/OPENSOLARIS.LICENSE. + * If applicable, add the following below this CDDL HEADER, with the + * fields enclosed by brackets "[]" replaced with your own identifying + * information: Portions Copyright [yyyy] [name of copyright owner] + * + * CDDL HEADER END + */ +/* + * Copyright (C) 2016 Romain Dolbeau . + */ + +/* + * USER API: + * + * Kernel fpu methods: + * kfpu_begin() + * kfpu_end() + */ + +#ifndef _SIMD_AARCH64_H +#define _SIMD_AARCH64_H + +#include + +#if defined(__aarch64__) + +#include + +#if defined(_KERNEL) +#include +#define kfpu_begin() \ +{ \ + kernel_neon_begin(); \ +} +#define kfpu_end() \ +{ \ + kernel_neon_end(); \ +} +#else +/* + * fpu dummy methods for userspace + */ +#define kfpu_begin() do {} while (0) +#define kfpu_end() do {} while (0) +#endif /* defined(_KERNEL) */ + +#endif /* __aarch64__ */ + +#endif /* _SIMD_AARCH64_H */ -- cgit v1.2.3