diff mbox series

[v4,02/10] util/bufferiszero: Remove AVX512 variant

Message ID 20240215081449.848220-3-richard.henderson@linaro.org
State Superseded
Headers show
Series Optimize buffer_is_zero | expand

Commit Message

Richard Henderson Feb. 15, 2024, 8:14 a.m. UTC 
From: Alexander Monakov <amonakov@ispras.ru>

Thanks to early checks in the inline buffer_is_zero wrapper, the SIMD
routines are invoked much more rarely in normal use when most buffers
are non-zero. This makes use of AVX512 unprofitable, as it incurs extra
frequency and voltage transition periods during which the CPU operates
at reduced performance, as described in
https://travisdowns.github.io/blog/2020/01/17/avxfreq1.html

Signed-off-by: Mikhail Romanov <mmromanov@ispras.ru>
Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20240206204809.9859-4-amonakov@ispras.ru>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 util/bufferiszero.c | 38 +++-----------------------------------
 1 file changed, 3 insertions(+), 35 deletions(-)
diff mbox series

Patch

diff --git a/util/bufferiszero.c b/util/bufferiszero.c
index f5a3634f9a..641d5f9b9e 100644
--- a/util/bufferiszero.c
+++ b/util/bufferiszero.c
@@ -64,7 +64,7 @@  buffer_zero_int(const void *buf, size_t len)
     }
 }
 
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT) || defined(__SSE2__)
+#if defined(CONFIG_AVX2_OPT) || defined(__SSE2__)
 #include <immintrin.h>
 
 /* Note that each of these vectorized functions require len >= 64.  */
@@ -128,41 +128,12 @@  buffer_zero_avx2(const void *buf, size_t len)
 }
 #endif /* CONFIG_AVX2_OPT */
 
-#ifdef CONFIG_AVX512F_OPT
-static bool __attribute__((target("avx512f")))
-buffer_zero_avx512(const void *buf, size_t len)
-{
-    /* Begin with an unaligned head of 64 bytes.  */
-    __m512i t = _mm512_loadu_si512(buf);
-    __m512i *p = (__m512i *)(((uintptr_t)buf + 5 * 64) & -64);
-    __m512i *e = (__m512i *)(((uintptr_t)buf + len) & -64);
-
-    /* Loop over 64-byte aligned blocks of 256.  */
-    while (p <= e) {
-        __builtin_prefetch(p);
-        if (unlikely(_mm512_test_epi64_mask(t, t))) {
-            return false;
-        }
-        t = p[-4] | p[-3] | p[-2] | p[-1];
-        p += 4;
-    }
-
-    t |= _mm512_loadu_si512(buf + len - 4 * 64);
-    t |= _mm512_loadu_si512(buf + len - 3 * 64);
-    t |= _mm512_loadu_si512(buf + len - 2 * 64);
-    t |= _mm512_loadu_si512(buf + len - 1 * 64);
-
-    return !_mm512_test_epi64_mask(t, t);
-
-}
-#endif /* CONFIG_AVX512F_OPT */
-
 /*
  * Make sure that these variables are appropriately initialized when
  * SSE2 is enabled on the compiler command-line, but the compiler is
  * too old to support CONFIG_AVX2_OPT.
  */
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT)
+#if defined(CONFIG_AVX2_OPT)
 # define INIT_USED     0
 # define INIT_LENGTH   0
 # define INIT_ACCEL    buffer_zero_int
@@ -188,9 +159,6 @@  select_accel_cpuinfo(unsigned info)
         unsigned len;
         bool (*fn)(const void *, size_t);
     } all[] = {
-#ifdef CONFIG_AVX512F_OPT
-        { CPUINFO_AVX512F, 256, buffer_zero_avx512 },
-#endif
 #ifdef CONFIG_AVX2_OPT
         { CPUINFO_AVX2,    128, buffer_zero_avx2 },
 #endif
@@ -208,7 +176,7 @@  select_accel_cpuinfo(unsigned info)
     return 0;
 }
 
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT)
+#if defined(CONFIG_AVX2_OPT)
 static void __attribute__((constructor)) init_accel(void)
 {
     used_accel = select_accel_cpuinfo(cpuinfo_init());