aboutsummaryrefslogtreecommitdiff
path: root/util
diff options
context:
space:
mode:
authorRichard Henderson <rth@twiddle.net>2016-08-29 11:46:19 -0700
committerPaolo Bonzini <pbonzini@redhat.com>2016-09-13 19:13:31 +0200
commit2250d3a293d36ed9d8143d4c3d3e94086c429af4 (patch)
tree9aab32cfb0fd5cc2351a7f5ee6f72da26a8949e1 /util
parent5e33a8722254f99cbce6ede73adb4b735d94f58f (diff)
downloadqemu-2250d3a293d36ed9d8143d4c3d3e94086c429af4.zip
qemu-2250d3a293d36ed9d8143d4c3d3e94086c429af4.tar.gz
qemu-2250d3a293d36ed9d8143d4c3d3e94086c429af4.tar.bz2
cutils: Remove aarch64 buffer zero checking
The revised integer version is 4 times faster than the neon version on an AppliedMicro Mustang. Even with hand scheduling and additional unrolling I cannot make any neon version run as fast as the integer. Signed-off-by: Richard Henderson <rth@twiddle.net> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'util')
-rw-r--r--util/bufferiszero.c15
1 files changed, 0 insertions, 15 deletions
diff --git a/util/bufferiszero.c b/util/bufferiszero.c
index 025cb8f..e6679b3 100644
--- a/util/bufferiszero.c
+++ b/util/bufferiszero.c
@@ -200,21 +200,6 @@ static bool select_accel_fn(const void *buf, size_t len)
return buffer_zero_int(buf, len);
}
-#elif defined(__aarch64__)
-#include "arm_neon.h"
-
-#define DO_NONZERO(X) (vgetq_lane_u64((X), 0) | vgetq_lane_u64((X), 1))
-ACCEL_BUFFER_ZERO(buffer_zero_neon, 128, uint64x2_t, DO_NONZERO)
-
-static bool select_accel_fn(const void *buf, size_t len)
-{
- uintptr_t ibuf = (uintptr_t)buf;
- if (len % 128 == 0 && ibuf % sizeof(uint64x2_t) == 0) {
- return buffer_zero_neon(buf, len);
- }
- return buffer_zero_int(buf, len);
-}
-
#else
#define select_accel_fn buffer_zero_int
#endif