/**
* @file
*
- * Functions for SSE/AVX/AVX2 implementation of memcpy().
+ * Functions for SSE/AVX/AVX2/AVX512 implementation of memcpy().
*/
#include <stdio.h>
#include <stdint.h>
#include <string.h>
#include <rte_vect.h>
+#include <rte_common.h>
#ifdef __cplusplus
extern "C" {
* @return
* Pointer to the destination data.
*/
-static inline void *
-rte_memcpy(void *dst, const void *src, size_t n) __attribute__((always_inline));
+static __rte_always_inline void *
+rte_memcpy(void *dst, const void *src, size_t n);
+
+#ifdef RTE_MACHINE_CPUFLAG_AVX512F
-#ifdef RTE_MACHINE_CPUFLAG_AVX2
+#define ALIGNMENT_MASK 0x3F
/**
- * AVX2 implementation below
+ * AVX512 implementation below
*/
/**
static inline void
rte_mov64(uint8_t *dst, const uint8_t *src)
{
- rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32);
- rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32);
+ __m512i zmm0;
+
+ zmm0 = _mm512_loadu_si512((const void *)src);
+ _mm512_storeu_si512((void *)dst, zmm0);
}
/**
static inline void
rte_mov128(uint8_t *dst, const uint8_t *src)
{
- rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32);
- rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32);
- rte_mov32((uint8_t *)dst + 2 * 32, (const uint8_t *)src + 2 * 32);
- rte_mov32((uint8_t *)dst + 3 * 32, (const uint8_t *)src + 3 * 32);
+ rte_mov64(dst + 0 * 64, src + 0 * 64);
+ rte_mov64(dst + 1 * 64, src + 1 * 64);
}
/**
static inline void
rte_mov256(uint8_t *dst, const uint8_t *src)
{
- rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32);
- rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32);
- rte_mov32((uint8_t *)dst + 2 * 32, (const uint8_t *)src + 2 * 32);
- rte_mov32((uint8_t *)dst + 3 * 32, (const uint8_t *)src + 3 * 32);
- rte_mov32((uint8_t *)dst + 4 * 32, (const uint8_t *)src + 4 * 32);
- rte_mov32((uint8_t *)dst + 5 * 32, (const uint8_t *)src + 5 * 32);
- rte_mov32((uint8_t *)dst + 6 * 32, (const uint8_t *)src + 6 * 32);
- rte_mov32((uint8_t *)dst + 7 * 32, (const uint8_t *)src + 7 * 32);
+ rte_mov64(dst + 0 * 64, src + 0 * 64);
+ rte_mov64(dst + 1 * 64, src + 1 * 64);
+ rte_mov64(dst + 2 * 64, src + 2 * 64);
+ rte_mov64(dst + 3 * 64, src + 3 * 64);
}
/**
- * Copy 64-byte blocks from one location to another,
+ * Copy 128-byte blocks from one location to another,
* locations should not overlap.
*/
static inline void
-rte_mov64blocks(uint8_t *dst, const uint8_t *src, size_t n)
+rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
{
- __m256i ymm0, ymm1;
-
- while (n >= 64) {
- ymm0 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 0 * 32));
- n -= 64;
- ymm1 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 1 * 32));
- src = (const uint8_t *)src + 64;
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32), ymm0);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32), ymm1);
- dst = (uint8_t *)dst + 64;
+ __m512i zmm0, zmm1;
+
+ while (n >= 128) {
+ zmm0 = _mm512_loadu_si512((const void *)(src + 0 * 64));
+ n -= 128;
+ zmm1 = _mm512_loadu_si512((const void *)(src + 1 * 64));
+ src = src + 128;
+ _mm512_storeu_si512((void *)(dst + 0 * 64), zmm0);
+ _mm512_storeu_si512((void *)(dst + 1 * 64), zmm1);
+ dst = dst + 128;
}
}
/**
- * Copy 256-byte blocks from one location to another,
+ * Copy 512-byte blocks from one location to another,
* locations should not overlap.
*/
static inline void
-rte_mov256blocks(uint8_t *dst, const uint8_t *src, size_t n)
+rte_mov512blocks(uint8_t *dst, const uint8_t *src, size_t n)
{
- __m256i ymm0, ymm1, ymm2, ymm3, ymm4, ymm5, ymm6, ymm7;
-
- while (n >= 256) {
- ymm0 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 0 * 32));
- n -= 256;
- ymm1 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 1 * 32));
- ymm2 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 2 * 32));
- ymm3 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 3 * 32));
- ymm4 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 4 * 32));
- ymm5 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 5 * 32));
- ymm6 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 6 * 32));
- ymm7 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 7 * 32));
- src = (const uint8_t *)src + 256;
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32), ymm0);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32), ymm1);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 2 * 32), ymm2);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 3 * 32), ymm3);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 4 * 32), ymm4);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 5 * 32), ymm5);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 6 * 32), ymm6);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 7 * 32), ymm7);
- dst = (uint8_t *)dst + 256;
+ __m512i zmm0, zmm1, zmm2, zmm3, zmm4, zmm5, zmm6, zmm7;
+
+ while (n >= 512) {
+ zmm0 = _mm512_loadu_si512((const void *)(src + 0 * 64));
+ n -= 512;
+ zmm1 = _mm512_loadu_si512((const void *)(src + 1 * 64));
+ zmm2 = _mm512_loadu_si512((const void *)(src + 2 * 64));
+ zmm3 = _mm512_loadu_si512((const void *)(src + 3 * 64));
+ zmm4 = _mm512_loadu_si512((const void *)(src + 4 * 64));
+ zmm5 = _mm512_loadu_si512((const void *)(src + 5 * 64));
+ zmm6 = _mm512_loadu_si512((const void *)(src + 6 * 64));
+ zmm7 = _mm512_loadu_si512((const void *)(src + 7 * 64));
+ src = src + 512;
+ _mm512_storeu_si512((void *)(dst + 0 * 64), zmm0);
+ _mm512_storeu_si512((void *)(dst + 1 * 64), zmm1);
+ _mm512_storeu_si512((void *)(dst + 2 * 64), zmm2);
+ _mm512_storeu_si512((void *)(dst + 3 * 64), zmm3);
+ _mm512_storeu_si512((void *)(dst + 4 * 64), zmm4);
+ _mm512_storeu_si512((void *)(dst + 5 * 64), zmm5);
+ _mm512_storeu_si512((void *)(dst + 6 * 64), zmm6);
+ _mm512_storeu_si512((void *)(dst + 7 * 64), zmm7);
+ dst = dst + 512;
}
}
static inline void *
-rte_memcpy(void *dst, const void *src, size_t n)
+rte_memcpy_generic(void *dst, const void *src, size_t n)
{
uintptr_t dstu = (uintptr_t)dst;
uintptr_t srcu = (uintptr_t)src;
srcu = (uintptr_t)((const uint32_t *)srcu + 1);
dstu = (uintptr_t)((uint32_t *)dstu + 1);
}
- if (n & 0x08) {
+ if (n & 0x08)
*(uint64_t *)dstu = *(const uint64_t *)srcu;
- }
return ret;
}
*/
if (n <= 32) {
rte_mov16((uint8_t *)dst, (const uint8_t *)src);
- rte_mov16((uint8_t *)dst - 16 + n, (const uint8_t *)src - 16 + n);
+ rte_mov16((uint8_t *)dst - 16 + n,
+ (const uint8_t *)src - 16 + n);
return ret;
}
if (n <= 64) {
rte_mov32((uint8_t *)dst, (const uint8_t *)src);
- rte_mov32((uint8_t *)dst - 32 + n, (const uint8_t *)src - 32 + n);
+ rte_mov32((uint8_t *)dst - 32 + n,
+ (const uint8_t *)src - 32 + n);
return ret;
}
if (n <= 512) {
src = (const uint8_t *)src + 128;
dst = (uint8_t *)dst + 128;
}
- if (n >= 64) {
- n -= 64;
+COPY_BLOCK_128_BACK63:
+ if (n > 64) {
rte_mov64((uint8_t *)dst, (const uint8_t *)src);
- src = (const uint8_t *)src + 64;
- dst = (uint8_t *)dst + 64;
- }
-COPY_BLOCK_64_BACK31:
- if (n > 32) {
- rte_mov32((uint8_t *)dst, (const uint8_t *)src);
- rte_mov32((uint8_t *)dst - 32 + n, (const uint8_t *)src - 32 + n);
+ rte_mov64((uint8_t *)dst - 64 + n,
+ (const uint8_t *)src - 64 + n);
return ret;
}
- if (n > 0) {
- rte_mov32((uint8_t *)dst - 32 + n, (const uint8_t *)src - 32 + n);
- }
+ if (n > 0)
+ rte_mov64((uint8_t *)dst - 64 + n,
+ (const uint8_t *)src - 64 + n);
return ret;
}
/**
* Make store aligned when copy size exceeds 512 bytes
*/
- dstofss = 32 - ((uintptr_t)dst & 0x1F);
- n -= dstofss;
- rte_mov32((uint8_t *)dst, (const uint8_t *)src);
- src = (const uint8_t *)src + dstofss;
- dst = (uint8_t *)dst + dstofss;
+ dstofss = ((uintptr_t)dst & 0x3F);
+ if (dstofss > 0) {
+ dstofss = 64 - dstofss;
+ n -= dstofss;
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ src = (const uint8_t *)src + dstofss;
+ dst = (uint8_t *)dst + dstofss;
+ }
/**
- * Copy 256-byte blocks.
+ * Copy 512-byte blocks.
* Use copy block function for better instruction order control,
* which is important when load is unaligned.
*/
- rte_mov256blocks((uint8_t *)dst, (const uint8_t *)src, n);
+ rte_mov512blocks((uint8_t *)dst, (const uint8_t *)src, n);
bits = n;
- n = n & 255;
+ n = n & 511;
bits -= n;
src = (const uint8_t *)src + bits;
dst = (uint8_t *)dst + bits;
/**
- * Copy 64-byte blocks.
+ * Copy 128-byte blocks.
* Use copy block function for better instruction order control,
* which is important when load is unaligned.
*/
- if (n >= 64) {
- rte_mov64blocks((uint8_t *)dst, (const uint8_t *)src, n);
+ if (n >= 128) {
+ rte_mov128blocks((uint8_t *)dst, (const uint8_t *)src, n);
bits = n;
- n = n & 63;
+ n = n & 127;
bits -= n;
src = (const uint8_t *)src + bits;
dst = (uint8_t *)dst + bits;
/**
* Copy whatever left
*/
- goto COPY_BLOCK_64_BACK31;
+ goto COPY_BLOCK_128_BACK63;
}
-#else /* RTE_MACHINE_CPUFLAG_AVX2 */
+#elif defined RTE_MACHINE_CPUFLAG_AVX2
+
+#define ALIGNMENT_MASK 0x1F
+
+/**
+ * AVX2 implementation below
+ */
+
+/**
+ * Copy 16 bytes from one location to another,
+ * locations should not overlap.
+ */
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+ __m128i xmm0;
+
+ xmm0 = _mm_loadu_si128((const __m128i *)src);
+ _mm_storeu_si128((__m128i *)dst, xmm0);
+}
+
+/**
+ * Copy 32 bytes from one location to another,
+ * locations should not overlap.
+ */
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+ __m256i ymm0;
+
+ ymm0 = _mm256_loadu_si256((const __m256i *)src);
+ _mm256_storeu_si256((__m256i *)dst, ymm0);
+}
+
+/**
+ * Copy 64 bytes from one location to another,
+ * locations should not overlap.
+ */
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32);
+ rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32);
+}
+
+/**
+ * Copy 128 bytes from one location to another,
+ * locations should not overlap.
+ */
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+ rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32);
+ rte_mov32((uint8_t *)dst + 1 * 32, (const uint8_t *)src + 1 * 32);
+ rte_mov32((uint8_t *)dst + 2 * 32, (const uint8_t *)src + 2 * 32);
+ rte_mov32((uint8_t *)dst + 3 * 32, (const uint8_t *)src + 3 * 32);
+}
+
+/**
+ * Copy 128-byte blocks from one location to another,
+ * locations should not overlap.
+ */
+static inline void
+rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
+{
+ __m256i ymm0, ymm1, ymm2, ymm3;
+
+ while (n >= 128) {
+ ymm0 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 0 * 32));
+ n -= 128;
+ ymm1 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 1 * 32));
+ ymm2 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 2 * 32));
+ ymm3 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 3 * 32));
+ src = (const uint8_t *)src + 128;
+ _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32), ymm0);
+ _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32), ymm1);
+ _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 2 * 32), ymm2);
+ _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 3 * 32), ymm3);
+ dst = (uint8_t *)dst + 128;
+ }
+}
+
+static inline void *
+rte_memcpy_generic(void *dst, const void *src, size_t n)
+{
+ uintptr_t dstu = (uintptr_t)dst;
+ uintptr_t srcu = (uintptr_t)src;
+ void *ret = dst;
+ size_t dstofss;
+ size_t bits;
+
+ /**
+ * Copy less than 16 bytes
+ */
+ if (n < 16) {
+ if (n & 0x01) {
+ *(uint8_t *)dstu = *(const uint8_t *)srcu;
+ srcu = (uintptr_t)((const uint8_t *)srcu + 1);
+ dstu = (uintptr_t)((uint8_t *)dstu + 1);
+ }
+ if (n & 0x02) {
+ *(uint16_t *)dstu = *(const uint16_t *)srcu;
+ srcu = (uintptr_t)((const uint16_t *)srcu + 1);
+ dstu = (uintptr_t)((uint16_t *)dstu + 1);
+ }
+ if (n & 0x04) {
+ *(uint32_t *)dstu = *(const uint32_t *)srcu;
+ srcu = (uintptr_t)((const uint32_t *)srcu + 1);
+ dstu = (uintptr_t)((uint32_t *)dstu + 1);
+ }
+ if (n & 0x08) {
+ *(uint64_t *)dstu = *(const uint64_t *)srcu;
+ }
+ return ret;
+ }
+
+ /**
+ * Fast way when copy size doesn't exceed 256 bytes
+ */
+ if (n <= 32) {
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov16((uint8_t *)dst - 16 + n,
+ (const uint8_t *)src - 16 + n);
+ return ret;
+ }
+ if (n <= 48) {
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov16((uint8_t *)dst + 16, (const uint8_t *)src + 16);
+ rte_mov16((uint8_t *)dst - 16 + n,
+ (const uint8_t *)src - 16 + n);
+ return ret;
+ }
+ if (n <= 64) {
+ rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov32((uint8_t *)dst - 32 + n,
+ (const uint8_t *)src - 32 + n);
+ return ret;
+ }
+ if (n <= 256) {
+ if (n >= 128) {
+ n -= 128;
+ rte_mov128((uint8_t *)dst, (const uint8_t *)src);
+ src = (const uint8_t *)src + 128;
+ dst = (uint8_t *)dst + 128;
+ }
+COPY_BLOCK_128_BACK31:
+ if (n >= 64) {
+ n -= 64;
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ src = (const uint8_t *)src + 64;
+ dst = (uint8_t *)dst + 64;
+ }
+ if (n > 32) {
+ rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov32((uint8_t *)dst - 32 + n,
+ (const uint8_t *)src - 32 + n);
+ return ret;
+ }
+ if (n > 0) {
+ rte_mov32((uint8_t *)dst - 32 + n,
+ (const uint8_t *)src - 32 + n);
+ }
+ return ret;
+ }
+
+ /**
+ * Make store aligned when copy size exceeds 256 bytes
+ */
+ dstofss = (uintptr_t)dst & 0x1F;
+ if (dstofss > 0) {
+ dstofss = 32 - dstofss;
+ n -= dstofss;
+ rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+ src = (const uint8_t *)src + dstofss;
+ dst = (uint8_t *)dst + dstofss;
+ }
+
+ /**
+ * Copy 128-byte blocks
+ */
+ rte_mov128blocks((uint8_t *)dst, (const uint8_t *)src, n);
+ bits = n;
+ n = n & 127;
+ bits -= n;
+ src = (const uint8_t *)src + bits;
+ dst = (uint8_t *)dst + bits;
+
+ /**
+ * Copy whatever left
+ */
+ goto COPY_BLOCK_128_BACK31;
+}
+
+#else /* RTE_MACHINE_CPUFLAG */
+
+#define ALIGNMENT_MASK 0x0F
/**
* SSE & AVX implementation below
* - __m128i <xmm0> ~ <xmm8> must be pre-defined
*/
#define MOVEUNALIGNED_LEFT47_IMM(dst, src, len, offset) \
-({ \
+__extension__ ({ \
int tmp; \
while (len >= 128 + 16 - offset) { \
xmm0 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 0 * 16)); \
* - __m128i <xmm0> ~ <xmm8> used in MOVEUNALIGNED_LEFT47_IMM must be pre-defined
*/
#define MOVEUNALIGNED_LEFT47(dst, src, len, offset) \
-({ \
+__extension__ ({ \
switch (offset) { \
case 0x01: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x01); break; \
case 0x02: MOVEUNALIGNED_LEFT47_IMM(dst, src, n, 0x02); break; \
})
static inline void *
-rte_memcpy(void *dst, const void *src, size_t n)
+rte_memcpy_generic(void *dst, const void *src, size_t n)
{
__m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, xmm8;
uintptr_t dstu = (uintptr_t)dst;
* unaligned copy functions require up to 15 bytes
* backwards access.
*/
- dstofss = 16 - ((uintptr_t)dst & 0x0F) + 16;
- n -= dstofss;
- rte_mov32((uint8_t *)dst, (const uint8_t *)src);
- src = (const uint8_t *)src + dstofss;
- dst = (uint8_t *)dst + dstofss;
+ dstofss = (uintptr_t)dst & 0x0F;
+ if (dstofss > 0) {
+ dstofss = 16 - dstofss + 16;
+ n -= dstofss;
+ rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+ src = (const uint8_t *)src + dstofss;
+ dst = (uint8_t *)dst + dstofss;
+ }
srcofs = ((uintptr_t)src & 0x0F);
/**
goto COPY_BLOCK_64_BACK15;
}
-#endif /* RTE_MACHINE_CPUFLAG_AVX2 */
+#endif /* RTE_MACHINE_CPUFLAG */
+
+static inline void *
+rte_memcpy_aligned(void *dst, const void *src, size_t n)
+{
+ void *ret = dst;
+
+ /* Copy size <= 16 bytes */
+ if (n < 16) {
+ if (n & 0x01) {
+ *(uint8_t *)dst = *(const uint8_t *)src;
+ src = (const uint8_t *)src + 1;
+ dst = (uint8_t *)dst + 1;
+ }
+ if (n & 0x02) {
+ *(uint16_t *)dst = *(const uint16_t *)src;
+ src = (const uint16_t *)src + 1;
+ dst = (uint16_t *)dst + 1;
+ }
+ if (n & 0x04) {
+ *(uint32_t *)dst = *(const uint32_t *)src;
+ src = (const uint32_t *)src + 1;
+ dst = (uint32_t *)dst + 1;
+ }
+ if (n & 0x08)
+ *(uint64_t *)dst = *(const uint64_t *)src;
+
+ return ret;
+ }
+
+ /* Copy 16 <= size <= 32 bytes */
+ if (n <= 32) {
+ rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov16((uint8_t *)dst - 16 + n,
+ (const uint8_t *)src - 16 + n);
+
+ return ret;
+ }
+
+ /* Copy 32 < size <= 64 bytes */
+ if (n <= 64) {
+ rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+ rte_mov32((uint8_t *)dst - 32 + n,
+ (const uint8_t *)src - 32 + n);
+
+ return ret;
+ }
+
+ /* Copy 64 bytes blocks */
+ for (; n >= 64; n -= 64) {
+ rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+ dst = (uint8_t *)dst + 64;
+ src = (const uint8_t *)src + 64;
+ }
+
+ /* Copy whatever left */
+ rte_mov64((uint8_t *)dst - 64 + n,
+ (const uint8_t *)src - 64 + n);
+
+ return ret;
+}
+
+static inline void *
+rte_memcpy(void *dst, const void *src, size_t n)
+{
+ if (!(((uintptr_t)dst | (uintptr_t)src) & ALIGNMENT_MASK))
+ return rte_memcpy_aligned(dst, src, n);
+ else
+ return rte_memcpy_generic(dst, src, n);
+}
#ifdef __cplusplus
}
git.droids-corp.org / dpdk.git / blobdiff