> Remove unnecessary type casting in functions.
>
> Tested on Ubuntu (14.04 x86_64) with "make test".
> "make test" results match the results with baseline.
> "Memcpy perf" results match the results with baseline.
>
> Signed-off-by: Ravi Kerur <rkerur at gmail.com>
> Acked-by: Stephen Hemminger <stephen at networkplumber.org>
>
> ---
> .../common/include/arch/x86/rte_memcpy.h | 340 +++++++++++----------
> 1 file changed, 175 insertions(+), 165 deletions(-)
>
> diff --git a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
> b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
> index 6a57426..839d4ec 100644
> --- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
> +++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
[...]
> /**
> @@ -150,13 +150,16 @@ rte_mov64blocks(uint8_t *dst, const uint8_t *src,
> size_t n)
> __m256i ymm0, ymm1;
>
> while (n >= 64) {
> - ymm0 = _mm256_loadu_si256((const __m256i *)((const uint8_t
> *)src + 0 * 32));
> +
> + ymm0 = _mm256_loadu_si256((const __m256i *)(src + 0 * 32));
> + ymm1 = _mm256_loadu_si256((const __m256i *)(src + 1 * 32));
> +
> + _mm256_storeu_si256((__m256i *)(dst + 0 * 32), ymm0);
> + _mm256_storeu_si256((__m256i *)(dst + 1 * 32), ymm1);
> +
Any particular reason to change the order of the statements here? :)
Overall this patch looks good.
> n -= 64;
> - ymm1 = _mm256_loadu_si256((const __m256i *)((const uint8_t
> *)src + 1 * 32));
> - src = (const uint8_t *)src + 64;
> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32), ymm0);
> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32), ymm1);
> - dst = (uint8_t *)dst + 64;
> + src = src + 64;
> + dst = dst + 64;
> }
> }
>
