From 7069532e3b944c25707d4f69998e68a739eabff9 Mon Sep 17 00:00:00 2001 From: Vijay Date: Thu, 14 Jul 2016 16:51:36 +0100 Subject: [PATCH] target-arm: Use Neon for zero checking Use Neon instructions to perform zero checking of buffer. This is helps in reducing total migration time. Use case: Idle VM live migration with 4 VCPUS and 8GB ram running CentOS 7. Without Neon, the Total migration time is 3.5 Sec Migration status: completed total time: 3560 milliseconds downtime: 33 milliseconds setup: 5 milliseconds transferred ram: 297907 kbytes throughput: 685.76 mbps remaining ram: 0 kbytes total ram: 8519872 kbytes duplicate: 2062760 pages skipped: 0 pages normal: 69808 pages normal bytes: 279232 kbytes dirty sync count: 3 With Neon, the total migration time is 2.9 Sec Migration status: completed total time: 2960 milliseconds downtime: 65 milliseconds setup: 4 milliseconds transferred ram: 299869 kbytes throughput: 830.19 mbps remaining ram: 0 kbytes total ram: 8519872 kbytes duplicate: 2064313 pages skipped: 0 pages normal: 70294 pages normal bytes: 281176 kbytes dirty sync count: 3 Signed-off-by: Vijaya Kumar K Signed-off-by: Suresh Acked-by: Paolo Bonzini Message-id: 1467190029-694-2-git-send-email-vijayak@cavium.com Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- util/cutils.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/util/cutils.c b/util/cutils.c index 5830a688dc..7505fdaa81 100644 --- a/util/cutils.c +++ b/util/cutils.c @@ -184,6 +184,13 @@ int qemu_fdatasync(int fd) #define SPLAT(p) _mm_set1_epi8(*(p)) #define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF) #define VEC_OR(v1, v2) (_mm_or_si128(v1, v2)) +#elif defined(__aarch64__) +#include "arm_neon.h" +#define VECTYPE uint64x2_t +#define ALL_EQ(v1, v2) \ + ((vgetq_lane_u64(v1, 0) == vgetq_lane_u64(v2, 0)) && \ + (vgetq_lane_u64(v1, 1) == vgetq_lane_u64(v2, 1))) +#define VEC_OR(v1, v2) ((v1) | (v2)) #else #define VECTYPE unsigned long #define SPLAT(p) (*(p) * (~0UL / 255))