Merge tag 'pull-misc-20240503' of https://gitlab.com/rth7680/qemu int…

…o staging

util/bufferiszero:
  - Remove sse4.1 and avx512 variants
  - Reorganize for early test for acceleration
  - Remove useless prefetches
  - Optimize sse2, avx2 and integer variants
  - Add simd acceleration for aarch64
  - Add bufferiszero-bench

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmY0/qMdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV+ULQf/T2JSdvG6/EjDCf4N
# cnSGiUV2MIeByw8tkrc/fWCNdlulHhk9gbg9l+f2muwK8H/k2BdynbrQnt1Ymmtk
# xzM6+PNOcByaovSAkvNweZVbrQX36Yih9S7f3n+xcxfVuvvYhKSLHXLkeqO96LMd
# rN+WRpxhReaU3n8/FO7o3S26SRpk7X9kRfShaT7U7ytHGjGsXUvMKIRs30hbsJTB
# yjed0a0u54FoSlN6AEqjWdgzaWP8nT65+8Yxe3dzB9hx09UiolZo60eHqYy7Mkno
# N6aMOB6gUUbCiKZ3Qk+1zEX97vl26NH3zt5tIIJTWDoIkC3f9qbg1x5hwWLQ3rra
# rM8h8w==
# =DnZO
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 03 May 2024 08:11:31 AM PDT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate]

* tag 'pull-misc-20240503' of https://gitlab.com/rth7680/qemu:
  tests/bench: Add bufferiszero-bench
  util/bufferiszero: Add simd acceleration for aarch64
  util/bufferiszero: Simplify test_buffer_is_zero_next_accel
  util/bufferiszero: Introduce biz_accel_fn typedef
  util/bufferiszero: Improve scalar variant
  util/bufferiszero: Optimize SSE2 and AVX2 variants
  util/bufferiszero: Remove useless prefetches
  util/bufferiszero: Reorganize for early test for acceleration
  util/bufferiszero: Remove AVX512 variant
  util/bufferiszero: Remove SSE4.1 variant

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

include/qemu/cutils.h

@@ -187,9 +187,39 @@ char *freq_to_str(uint64_t freq_hz);
 /* used to print char* safely */
 #define STR_OR_NULL(str) ((str) ? (str) : "null")
 
-bool buffer_is_zero(const void *buf, size_t len);
+/*
+ * Check if a buffer is all zeroes.
+ */
+
+bool buffer_is_zero_ool(const void *vbuf, size_t len);
+bool buffer_is_zero_ge256(const void *vbuf, size_t len);
 bool test_buffer_is_zero_next_accel(void);
 
+static inline bool buffer_is_zero_sample3(const char *buf, size_t len)
+{
+    /*
+     * For any reasonably sized buffer, these three samples come from
+     * three different cachelines.  In qemu-img usage, we find that
+     * each byte eliminates more than half of all buffer testing.
+     * It is therefore critical to performance that the byte tests
+     * short-circuit, so that we do not pull in additional cache lines.
+     * Do not "optimize" this to !(a | b | c).
+     */
+    return !buf[0] && !buf[len - 1] && !buf[len / 2];
+}
+
+#ifdef __OPTIMIZE__
+static inline bool buffer_is_zero(const void *buf, size_t len)
+{
+    return (__builtin_constant_p(len) && len >= 256
+            ? buffer_is_zero_sample3(buf, len) &&
+              buffer_is_zero_ge256(buf, len)
+            : buffer_is_zero_ool(buf, len));
+}
+#else
+#define buffer_is_zero  buffer_is_zero_ool
+#endif
+
 /*
  * Implementation of ULEB128 (http://en.wikipedia.org/wiki/LEB128)
  * Input is limited to 14-bit numbers

tests/bench/bufferiszero-bench.c

@@ -0,0 +1,47 @@
+/*
+ * QEMU buffer_is_zero speed benchmark
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.  See the COPYING file in the
+ * top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "qemu/cutils.h"
+#include "qemu/units.h"
+
+static void test(const void *opaque)
+{
+    size_t max = 64 * KiB;
+    void *buf = g_malloc0(max);
+    int accel_index = 0;
+
+    do {
+        if (accel_index != 0) {
+            g_test_message("%s", "");  /* gnu_printf Werror for simple "" */
+        }
+        for (size_t len = 1 * KiB; len <= max; len *= 4) {
+            double total = 0.0;
+
+            g_test_timer_start();
+            do {
+                buffer_is_zero_ge256(buf, len);
+                total += len;
+            } while (g_test_timer_elapsed() < 0.5);
+
+            total /= MiB;
+            g_test_message("buffer_is_zero #%d: %2zuKB %8.0f MB/sec",
+                           accel_index, len / (size_t)KiB,
+                           total / g_test_timer_last());
+        }
+        accel_index++;
+    } while (test_buffer_is_zero_next_accel());
+
+    g_free(buf);
+}
+
+int main(int argc, char **argv)
+{
+    g_test_init(&argc, &argv, NULL);
+    g_test_add_data_func("/cutils/bufferiszero/speed", NULL, test);
+    return g_test_run();
+}

tests/bench/meson.build

@@ -21,6 +21,7 @@ benchs = {}
 
 if have_block
   benchs += {
+     'bufferiszero-bench': [],
      'benchmark-crypto-hash': [crypto],
      'benchmark-crypto-hmac': [crypto],
      'benchmark-crypto-cipher': [crypto],