}
#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT) || defined(__SSE2__)
-/* Do not use push_options pragmas unnecessarily, because clang
- * does not support them.
- */
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT)
-#pragma GCC push_options
-#pragma GCC target("sse2")
-#endif
-#include <emmintrin.h>
+#include <immintrin.h>
/* Note that each of these vectorized functions require len >= 64. */
-static bool
+static bool __attribute__((target("sse2")))
buffer_zero_sse2(const void *buf, size_t len)
{
__m128i t = _mm_loadu_si128(buf);
return _mm_movemask_epi8(_mm_cmpeq_epi8(t, zero)) == 0xFFFF;
}
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT)
-#pragma GCC pop_options
-#endif
#ifdef CONFIG_AVX2_OPT
-/* Note that due to restrictions/bugs wrt __builtin functions in gcc <= 4.8,
- * the includes have to be within the corresponding push_options region, and
- * therefore the regions themselves have to be ordered with increasing ISA.
- */
-#pragma GCC push_options
-#pragma GCC target("sse4")
-#include <smmintrin.h>
-
-static bool
+static bool __attribute__((target("sse4")))
buffer_zero_sse4(const void *buf, size_t len)
{
__m128i t = _mm_loadu_si128(buf);
return _mm_testz_si128(t, t);
}
-#pragma GCC pop_options
-#pragma GCC push_options
-#pragma GCC target("avx2")
-#include <immintrin.h>
-
-static bool
+static bool __attribute__((target("avx2")))
buffer_zero_avx2(const void *buf, size_t len)
{
/* Begin with an unaligned head of 32 bytes. */
__m256i *p = (__m256i *)(((uintptr_t)buf + 5 * 32) & -32);
__m256i *e = (__m256i *)(((uintptr_t)buf + len) & -32);
- if (likely(p <= e)) {
- /* Loop over 32-byte aligned blocks of 128. */
- do {
- __builtin_prefetch(p);
- if (unlikely(!_mm256_testz_si256(t, t))) {
- return false;
- }
- t = p[-4] | p[-3] | p[-2] | p[-1];
- p += 4;
- } while (p <= e);
- } else {
- t |= _mm256_loadu_si256(buf + 32);
- if (len <= 128) {
- goto last2;
+ /* Loop over 32-byte aligned blocks of 128. */
+ while (p <= e) {
+ __builtin_prefetch(p);
+ if (unlikely(!_mm256_testz_si256(t, t))) {
+ return false;
}
- }
+ t = p[-4] | p[-3] | p[-2] | p[-1];
+ p += 4;
+ } ;
/* Finish the last block of 128 unaligned. */
t |= _mm256_loadu_si256(buf + len - 4 * 32);
t |= _mm256_loadu_si256(buf + len - 3 * 32);
- last2:
t |= _mm256_loadu_si256(buf + len - 2 * 32);
t |= _mm256_loadu_si256(buf + len - 1 * 32);
return _mm256_testz_si256(t, t);
}
-#pragma GCC pop_options
#endif /* CONFIG_AVX2_OPT */
#ifdef CONFIG_AVX512F_OPT
-#pragma GCC push_options
-#pragma GCC target("avx512f")
-#include <immintrin.h>
-
-static bool
+static bool __attribute__((target("avx512f")))
buffer_zero_avx512(const void *buf, size_t len)
{
/* Begin with an unaligned head of 64 bytes. */
return !_mm512_test_epi64_mask(t, t);
}
-#pragma GCC pop_options
-#endif
+#endif /* CONFIG_AVX512F_OPT */
/* Note that for test_buffer_is_zero_next_accel, the most preferred
}
if (cache & CACHE_AVX2) {
fn = buffer_zero_avx2;
- length_to_accel = 64;
+ length_to_accel = 128;
}
#endif
#ifdef CONFIG_AVX512F_OPT
static void __attribute__((constructor)) init_cpuid_cache(void)
{
- int max = __get_cpuid_max(0, NULL);
+ unsigned max = __get_cpuid_max(0, NULL);
int a, b, c, d;
unsigned cache = 0;
/* We must check that AVX is not just available, but usable. */
if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) {
- int bv;
- __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0));
+ unsigned bv = xgetbv_low(0);
__cpuid_count(7, 0, a, b, c, d);
if ((bv & 0x6) == 0x6 && (b & bit_AVX2)) {
cache |= CACHE_AVX2;