[Qemu-devel] [PATCH v3 8/9] cutils: Remove aarch64 buffer zero checking

[Richard Henderson <rth@twiddle.net>]

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>
---
 util/bufferiszero.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/util/bufferiszero.c b/util/bufferiszero.c
index 7fcc8e1..6d13d7f 100644
--- a/util/bufferiszero.c
+++ b/util/bufferiszero.c
@@ -355,21 +355,6 @@ 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
-- 
2.7.4