-----Original Message-----
> Date: Mon, 27 Nov 2017 15:49:45 +0800
> From: Herbert Guan <herbert.g...@arm.com>
> To: jerin.ja...@caviumnetworks.com, jianbo....@arm.com, dev@dpdk.org
> CC: Herbert Guan <herbert.g...@arm.com>
> Subject: [PATCH] arch/arm: optimization for memcpy on AArch64
> X-Mailer: git-send-email 1.8.3.1
> +
> +/**************************************
> + * Beginning of customization section
> + **************************************/
> +#define ALIGNMENT_MASK 0x0F
> +#ifndef RTE_ARCH_ARM64_MEMCPY_STRICT_ALIGN
> +// Only src unalignment will be treaed as unaligned copy
C++ style comments. It may generate check patch errors.
> +#define IS_UNALIGNED_COPY(dst, src) ((uintptr_t)(dst) & ALIGNMENT_MASK)
> +#else
> +// Both dst and src unalignment will be treated as unaligned copy
> +#define IS_UNALIGNED_COPY(dst, src) \
> + (((uintptr_t)(dst) | (uintptr_t)(src)) & ALIGNMENT_MASK)
> +#endif
> +
> +
> +// If copy size is larger than threshold, memcpy() will be used.
> +// Run "memcpy_perf_autotest" to determine the proper threshold.
> +#define ALIGNED_THRESHOLD ((size_t)(0xffffffff))
> +#define UNALIGNED_THRESHOLD ((size_t)(0xffffffff))
Do you see any case where this threshold is useful.
> +
> +static inline void *__attribute__ ((__always_inline__))
> +rte_memcpy(void *restrict dst, const void *restrict src, size_t n)
> +{
> + if (n < 16) {
> + rte_memcpy_lt16((uint8_t *)dst, (const uint8_t *)src, n);
> + return dst;
> + }
> + if (n < 64) {
> + rte_memcpy_ge16_lt64((uint8_t *)dst, (const uint8_t *)src, n);
> + return dst;
> + }
Unfortunately we have 128B cache arm64 implementation too. Could you
please take care that based on RTE_CACHE_LINE_SIZE
> + __builtin_prefetch(src, 0, 0);
> + __builtin_prefetch(dst, 1, 0);
See above point and Please use DPDK equivalents. rte_prefetch*()
