ShuriZma
/
xemu
mirror of https://github.com/xemu-project/xemu.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

util/bufferiszero: Remove AVX512 variant 

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>
This commit is contained in:
Alexander Monakov 2024-02-14 10:34:24 -10:00 committed by Richard Henderson
parent 8a917b99d5
commit d018425c32
1 changed files with 3 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
util/bufferiszero.c
View File

@ -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> #include <immintrin.h>
/* Note that each of these vectorized functions require len >= 64. */ /* 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 */ #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 * Make sure that these variables are appropriately initialized when
* SSE2 is enabled on the compiler command-line, but the compiler is * SSE2 is enabled on the compiler command-line, but the compiler is
* too old to support CONFIG_AVX2_OPT. * 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_USED 0
# define INIT_LENGTH 0 # define INIT_LENGTH 0
# define INIT_ACCEL buffer_zero_int # define INIT_ACCEL buffer_zero_int
@ -188,9 +159,6 @@ select_accel_cpuinfo(unsigned info)
unsigned len; unsigned len;
bool (*fn)(const void *, size_t); bool (*fn)(const void *, size_t);
} all[] = { } all[] = {
#ifdef CONFIG_AVX512F_OPT
{ CPUINFO_AVX512F, 256, buffer_zero_avx512 },
#endif
#ifdef CONFIG_AVX2_OPT #ifdef CONFIG_AVX2_OPT
{ CPUINFO_AVX2, 128, buffer_zero_avx2 }, { CPUINFO_AVX2, 128, buffer_zero_avx2 },
#endif #endif
@ -208,7 +176,7 @@ select_accel_cpuinfo(unsigned info)
return 0; return 0;
} }
#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT) #if defined(CONFIG_AVX2_OPT)
static void __attribute__((constructor)) init_accel(void) static void __attribute__((constructor)) init_accel(void)
{ {
used_accel = select_accel_cpuinfo(cpuinfo_init()); used_accel = select_accel_cpuinfo(cpuinfo_init());