path: root/arch/arm/lib
diff options
authorRussell King <rmk+kernel@arm.linux.org.uk>2013-07-22 17:26:27 +0100
committerRussell King <rmk+kernel@arm.linux.org.uk>2013-07-22 17:46:40 +0100
commitb4f656eea63376da79b0b5a17660c4ce14b71b74 (patch)
tree36731cf326eca19cd2164f886b3eaa31449fe8fa /arch/arm/lib
parent3b2f64d00c46e1e4e9bd0bb9bb12619adac27a4b (diff)
parent7d11965ddb9b9b1e0a5d13c58345ada1ccbc663b (diff)
Pull branch 'for-rmk' of git://git.linaro.org/people/ardbiesheuvel/linux-arm into devel-stable
Comments from Ard Biesheuvel: I have included two use cases that I have been using, XOR and RAID-6 checksumming. The former gets a 60% performance boost on the NEON, the latter over 400%. ARM: add support for kernel mode NEON Adds kernel_neon_begin/end (renamed from kernel_vfp_begin/end in the previous version to de-emphasize the VFP part as VFP code that needs software assistance is not supported currently.) Introduces <asm/neon.h> and the Kconfig symbol KERNEL_MODE_NEON. This has been aligned with Catalin for arm64, so any NEON code that does not use assembly but intrinsics or the GCC vectorizer (such as my examples) can potentially be shared between arm and arm64 archs. ARM: move VFP init to an earlier boot stage This is needed so the NEON is enabled when the XOR and RAID-6 algo boot time benchmarks are run. ARM: be strict about FP exceptions in kernel mode This adds a check to vfp_support_entry() to flag unsupported uses of the NEON/VFP in kernel mode. FP exceptions (bounces) are flagged as a bug, this is because of their potentially intermittent nature. Exceptions caused by the fact that kernel_neon_begin has not been called are just routed through the undef handler. ARM: crypto: add NEON accelerated XOR implementation This is the xor_blocks() implementation built with -ftree-vectorize, 60% faster than optimized ARM code. It calls in_interrupt() to check whether the NEON flavor can be used: this should really not be necessary, but due to xor_blocks'squite generic nature, there is no telling how exactly people may be using it in the real world. lib/raid6: add ARM-NEON accelerated syndrome calculation This is a port of the RAID-6 checksumming code in altivec.uc ported to use NEON intrinsics. It is about 4x faster than the sequential code.
Diffstat (limited to 'arch/arm/lib')
2 files changed, 48 insertions, 0 deletions
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index af72969820b4..aaf3a8731136 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -45,3 +45,9 @@ lib-$(CONFIG_ARCH_SHARK) += io-shark.o
$(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S
$(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S
+ NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon
+ CFLAGS_xor-neon.o += $(NEON_FLAGS)
+ lib-$(CONFIG_XOR_BLOCKS) += xor-neon.o
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
new file mode 100644
index 000000000000..f485e5a2af4b
--- /dev/null
+++ b/arch/arm/lib/xor-neon.c
@@ -0,0 +1,42 @@
+ * linux/arch/arm/lib/xor-neon.c
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/raid/xor.h>
+#ifndef __ARM_NEON__
+#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+ * Pull in the reference implementations while instructing GCC (through
+ * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
+ * NEON instructions.
+ */
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC optimize "tree-vectorize"
+ * While older versions of GCC do not generate incorrect code, they fail to
+ * recognize the parallel nature of these functions, and emit plain ARM code,
+ * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ */
+#warning This code requires at least version 4.6 of GCC
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#include <asm-generic/xor.h>
+struct xor_block_template const xor_block_neon_inner = {
+ .name = "__inner_neon__",
+ .do_2 = xor_8regs_2,
+ .do_3 = xor_8regs_3,
+ .do_4 = xor_8regs_4,
+ .do_5 = xor_8regs_5,