From d5aa3e6e0cd6259003790769c448d4fbb5b5c810 Mon Sep 17 00:00:00 2001 From: Ladi Prosek Date: Fri, 6 Jan 2017 09:08:53 +0100 Subject: [PATCH] net: optimize checksum computation Very simple loop optimization with a significant performance impact. Microbenchmark results, modern x86-64: buffer size | speed up ------------+--------- 1500 | 1.7x 64 | 1.5x 8 | 1.15x Microbenchmark results, POWER7: buffer size | speed up ------------+--------- 1500 | 5x 64 | 3.3x 8 | 1.13x There is a lot of room for further improvement at the expense of code complexity - aligned multibyte reads, LE/BE considerations, architecture-specific optimizations, etc. This patch still keeps things simple and readable. Signed-off-by: Ladi Prosek Reviewed-by: Dmitry Fleytman Signed-off-by: Jason Wang --- net/checksum.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/net/checksum.c b/net/checksum.c index 23323b0760..4da72a6a6c 100644 --- a/net/checksum.c +++ b/net/checksum.c @@ -22,17 +22,22 @@ uint32_t net_checksum_add_cont(int len, uint8_t *buf, int seq) { - uint32_t sum = 0; + uint32_t sum1 = 0, sum2 = 0; int i; - for (i = seq; i < seq + len; i++) { - if (i & 1) { - sum += (uint32_t)buf[i - seq]; - } else { - sum += (uint32_t)buf[i - seq] << 8; - } + for (i = 0; i < len - 1; i += 2) { + sum1 += (uint32_t)buf[i]; + sum2 += (uint32_t)buf[i + 1]; + } + if (i < len) { + sum1 += (uint32_t)buf[i]; + } + + if (seq & 1) { + return sum1 + (sum2 << 8); + } else { + return sum2 + (sum1 << 8); } - return sum; } uint16_t net_checksum_finish(uint32_t sum)