[dpdk-dev] [PATCH v2 1/2] lib/eal: add amd epyc2 memcpy routine to eal

[Aman Kumar <aman.kumar@vvdntech.in>]

This patch provides rte_memcpy* calls optimized for
AMD EPYC platforms. Use config/x86/x86_amd_epyc_linux_gcc
as cross-file with meson to build dpdk for AMD EPYC platforms.

Signed-off-by: Aman Kumar <aman.kumar@vvdntech.in>
---
 config/x86/meson.build            |   7 +
 config/x86/x86_amd_epyc_linux_gcc |  16 +
 lib/eal/x86/include/rte_memcpy.h  | 502 ++++++++++++++++++++++++++++++
 3 files changed, 525 insertions(+)
 create mode 100644 config/x86/x86_amd_epyc_linux_gcc

diff --git a/config/x86/meson.build b/config/x86/meson.build
index 29f3dea181..598b0e62ce 100644
--- a/config/x86/meson.build
+++ b/config/x86/meson.build
@@ -72,3 +72,10 @@ endif
 dpdk_conf.set('RTE_CACHE_LINE_SIZE', 64)
 dpdk_conf.set('RTE_MAX_LCORE', 128)
 dpdk_conf.set('RTE_MAX_NUMA_NODES', 32)
+
+if meson.is_cross_build()
+	if meson.get_cross_property('platform') == 'amd-epyc'
+	    dpdk_conf.set('RTE_MAX_LCORE', 512)
+	    dpdk_conf.set('RTE_MEMCPY_AMDEPYC', 1)
+	endif
+endif
diff --git a/config/x86/x86_amd_epyc_linux_gcc b/config/x86/x86_amd_epyc_linux_gcc
new file mode 100644
index 0000000000..0b2453135f
--- /dev/null
+++ b/config/x86/x86_amd_epyc_linux_gcc
@@ -0,0 +1,16 @@
+[binaries]
+c = 'x86_64-linux-gnu-gcc'
+cpp = 'x86_64-linux-gnu-g++'
+ld = 'x86_64-linux-gnu-ld'
+ar = 'x86_64-linux-gnu-ar'
+strip = 'x86_64-linux-gnu-strip'
+pkgconfig = 'x86_64-linux-gnu-pkg-config'
+
+[host_machine]
+system = 'linux'
+cpu_family = 'x86_64'
+cpu = 'native'
+endian = 'little'
+
+[properties]
+platform = 'amd-epyc'
diff --git a/lib/eal/x86/include/rte_memcpy.h b/lib/eal/x86/include/rte_memcpy.h
index 79f381dd9b..8f66c115e3 100644
--- a/lib/eal/x86/include/rte_memcpy.h
+++ b/lib/eal/x86/include/rte_memcpy.h
@@ -368,6 +368,498 @@ rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
 	}
 }
 
+#if defined RTE_MEMCPY_AMDEPYC
+
+/**
+ * Copy 16 bytes from one location to another,
+ * with temporal stores
+ */
+static __rte_always_inline void
+rte_copy16_ts(uint8_t *dst, uint8_t *src)
+{
+	__m128i var128;
+
+	var128 = _mm_stream_load_si128((__m128i *)src);
+	_mm_storeu_si128((__m128i *)dst, var128);
+}
+
+/**
+ * Copy 32 bytes from one location to another,
+ * with temporal stores
+ */
+static __rte_always_inline void
+rte_copy32_ts(uint8_t *dst, uint8_t *src)
+{
+	__m256i ymm0;
+
+	ymm0 = _mm256_stream_load_si256((const __m256i *)src);
+	_mm256_storeu_si256((__m256i *)dst, ymm0);
+}
+
+/**
+ * Copy 64 bytes from one location to another,
+ * with temporal stores
+ */
+static __rte_always_inline void
+rte_copy64_ts(uint8_t *dst, uint8_t *src)
+{
+	rte_copy32_ts(dst + 0 * 32, src + 0 * 32);
+	rte_copy32_ts(dst + 1 * 32, src + 1 * 32);
+}
+
+/**
+ * Copy 128 bytes from one location to another,
+ * with temporal stores
+ */
+static __rte_always_inline void
+rte_copy128_ts(uint8_t *dst, uint8_t *src)
+{
+	rte_copy32_ts(dst + 0 * 32, src + 0 * 32);
+	rte_copy32_ts(dst + 1 * 32, src + 1 * 32);
+	rte_copy32_ts(dst + 2 * 32, src + 2 * 32);
+	rte_copy32_ts(dst + 3 * 32, src + 3 * 32);
+}
+
+/**
+ * Copy len bytes from one location to another,
+ * with temporal stores 16B aligned
+ */
+static __rte_always_inline void *
+rte_memcpy_aligned_tstore16_generic(void *dst, void *src, int len)
+{
+	void *dest = dst;
+
+	while (len >= 128) {
+		rte_copy128_ts((uint8_t *)dst, (uint8_t *)src);
+		dst = (uint8_t *)dst + 128;
+		src = (uint8_t *)src + 128;
+		len -= 128;
+	}
+	while (len >= 64) {
+		rte_copy64_ts((uint8_t *)dst, (uint8_t *)src);
+		dst = (uint8_t *)dst + 64;
+		src = (uint8_t *)src + 64;
+		len -= 64;
+	}
+	while (len >= 32) {
+		rte_copy32_ts((uint8_t *)dst, (uint8_t *)src);
+		dst = (uint8_t *)dst + 32;
+		src = (uint8_t *)src + 32;
+		len -= 32;
+	}
+	if (len >= 16) {
+		rte_copy16_ts((uint8_t *)dst, (uint8_t *)src);
+		dst = (uint8_t *)dst + 16;
+		src = (uint8_t *)src + 16;
+		len -= 16;
+	}
+	if (len >= 8) {
+		*(uint64_t *)dst = *(const uint64_t *)src;
+		dst = (uint8_t *)dst + 8;
+		src = (uint8_t *)src + 8;
+		len -= 8;
+	}
+	if (len >= 4) {
+		*(uint32_t *)dst = *(const uint32_t *)src;
+		dst = (uint8_t *)dst + 4;
+		src = (uint8_t *)src + 4;
+		len -= 4;
+	}
+	if (len != 0) {
+		dst = (uint8_t *)dst - (4 - len);
+		src = (uint8_t *)src - (4 - len);
+		*(uint32_t *)dst = *(const uint32_t *)src;
+	}
+
+	return dest;
+}
+
+static __rte_always_inline void *
+rte_memcpy_aligned_ntload_tstore16_amdepyc2(void *dst,
+					    const void *src,
+					    size_t size)
+{
+	asm volatile goto("movq %0, %%rsi\n\t"
+	"movq %1, %%rdi\n\t"
+	"movq %2, %%rdx\n\t"
+	"cmpq   $(128), %%rdx\n\t"
+	"jb     202f\n\t"
+	"201:\n\t"
+	"vmovntdqa (%%rsi), %%ymm0\n\t"
+	"vmovntdqa 32(%%rsi), %%ymm1\n\t"
+	"vmovntdqa 64(%%rsi), %%ymm2\n\t"
+	"vmovntdqa 96(%%rsi), %%ymm3\n\t"
+	"vmovdqu  %%ymm0, (%%rdi)\n\t"
+	"vmovdqu  %%ymm1, 32(%%rdi)\n\t"
+	"vmovdqu  %%ymm2, 64(%%rdi)\n\t"
+	"vmovdqu  %%ymm3, 96(%%rdi)\n\t"
+	"addq   $128, %%rsi\n\t"
+	"addq   $128, %%rdi\n\t"
+	"subq   $128, %%rdx\n\t"
+	"jz     %l[done]\n\t"
+	"cmpq   $128, %%rdx\n\t" /*Vector Size 32B.  */
+	"jae    201b\n\t"
+	"202:\n\t"
+	"cmpq   $64, %%rdx\n\t"
+	"jb     203f\n\t"
+	"vmovntdqa (%%rsi), %%ymm0\n\t"
+	"vmovntdqa 32(%%rsi), %%ymm1\n\t"
+	"vmovdqu  %%ymm0, (%%rdi)\n\t"
+	"vmovdqu  %%ymm1, 32(%%rdi)\n\t"
+	"addq   $64, %%rsi\n\t"
+	"addq   $64, %%rdi\n\t"
+	"subq   $64, %%rdx\n\t"
+	"jz     %l[done]\n\t"
+	"203:\n\t"
+	"cmpq   $32, %%rdx\n\t"
+	"jb     204f\n\t"
+	"vmovntdqa (%%rsi), %%ymm0\n\t"
+	"vmovdqu  %%ymm0, (%%rdi)\n\t"
+	"addq   $32, %%rsi\n\t"
+	"addq   $32, %%rdi\n\t"
+	"subq   $32, %%rdx\n\t"
+	"jz     %l[done]\n\t"
+	"204:\n\t"
+	"cmpb   $16, %%dl\n\t"
+	"jb     205f\n\t"
+	"vmovntdqa (%%rsi), %%xmm0\n\t"
+	"vmovdqu  %%xmm0, (%%rdi)\n\t"
+	"addq   $16, %%rsi\n\t"
+	"addq   $16, %%rdi\n\t"
+	"subq   $16, %%rdx\n\t"
+	"jz     %l[done]\n\t"
+	"205:\n\t"
+	"cmpb   $2, %%dl\n\t"
+	"jb     208f\n\t"
+	"cmpb   $4, %%dl\n\t"
+	"jbe    207f\n\t"
+	"cmpb   $8, %%dl\n\t"
+	"jbe    206f\n\t"
+	"movq   -8(%%rsi,%%rdx), %%rcx\n\t"
+	"movq   (%%rsi), %%rsi\n\t"
+	"movq   %%rcx, -8(%%rdi,%%rdx)\n\t"
+	"movq   %%rsi, (%%rdi)\n\t"
+	"jmp    %l[done]\n\t"
+	"206:\n\t"
+	"movl   -4(%%rsi,%%rdx), %%ecx\n\t"
+	"movl   (%%rsi), %%esi\n\t"
+	"movl   %%ecx, -4(%%rdi,%%rdx)\n\t"
+	"movl   %%esi, (%%rdi)\n\t"
+	"jmp    %l[done]\n\t"
+	"207:\n\t"
+	"movzwl -2(%%rsi,%%rdx), %%ecx\n\t"
+	"movzwl (%%rsi), %%esi\n\t"
+	"movw   %%cx, -2(%%rdi,%%rdx)\n\t"
+	"movw   %%si, (%%rdi)\n\t"
+	"jmp    %l[done]\n\t"
+	"208:\n\t"
+	"movzbl (%%rsi), %%ecx\n\t"
+	"movb   %%cl, (%%rdi)"
+	:
+	: "r"(src), "r"(dst), "r"(size)
+	: "rcx", "rdx", "rsi", "rdi", "ymm0", "ymm1", "ymm2", "ymm3", "memory"
+	: done
+	);
+done:
+	return dst;
+}
+
+static __rte_always_inline void *
+rte_memcpy_generic(void *dst, const void *src, size_t len)
+{
+	asm goto("movq	%0, %%rsi\n\t"
+	"movq	%1, %%rdi\n\t"
+	"movq	%2, %%rdx\n\t"
+	"movq    %%rdi, %%rax\n\t"
+	"cmp     $32, %%rdx\n\t"
+	"jb      101f\n\t"
+	"cmp     $(32 * 2), %%rdx\n\t"
+	"ja      108f\n\t"
+	"vmovdqu   (%%rsi), %%ymm0\n\t"
+	"vmovdqu   -32(%%rsi,%%rdx), %%ymm1\n\t"
+	"vmovdqu   %%ymm0, (%%rdi)\n\t"
+	"vmovdqu   %%ymm1, -32(%%rdi,%%rdx)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]\n\t"
+	"101:\n\t"
+	/* Less than 1 VEC.  */
+	"cmpb    $32, %%dl\n\t"
+	"jae     103f\n\t"
+	"cmpb    $16, %%dl\n\t"
+	"jae     104f\n\t"
+	"cmpb    $8, %%dl\n\t"
+	"jae     105f\n\t"
+	"cmpb    $4, %%dl\n\t"
+	"jae     106f\n\t"
+	"cmpb    $1, %%dl\n\t"
+	"ja      107f\n\t"
+	"jb      102f\n\t"
+	"movzbl  (%%rsi), %%ecx\n\t"
+	"movb    %%cl, (%%rdi)\n\t"
+	"102:\n\t"
+	"jmp %l[done]\n\t"
+	"103:\n\t"
+	/* From 32 to 63.  No branch when size == 32.  */
+	"vmovdqu (%%rsi), %%ymm0\n\t"
+	"vmovdqu -32(%%rsi,%%rdx), %%ymm1\n\t"
+	"vmovdqu %%ymm0, (%%rdi)\n\t"
+	"vmovdqu %%ymm1, -32(%%rdi,%%rdx)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]\n\t"
+	/* From 16 to 31.  No branch when size == 16.  */
+	"104:\n\t"
+	"vmovdqu (%%rsi), %%xmm0\n\t"
+	"vmovdqu -16(%%rsi,%%rdx), %%xmm1\n\t"
+	"vmovdqu %%xmm0, (%%rdi)\n\t"
+	"vmovdqu %%xmm1, -16(%%rdi,%%rdx)\n\t"
+	"jmp %l[done]\n\t"
+	"105:\n\t"
+	/* From 8 to 15.  No branch when size == 8.  */
+	"movq    -8(%%rsi,%%rdx), %%rcx\n\t"
+	"movq    (%%rsi), %%rsi\n\t"
+	"movq    %%rcx, -8(%%rdi,%%rdx)\n\t"
+	"movq    %%rsi, (%%rdi)\n\t"
+	"jmp %l[done]\n\t"
+	"106:\n\t"
+	/* From 4 to 7.  No branch when size == 4.  */
+	"movl    -4(%%rsi,%%rdx), %%ecx\n\t"
+	"movl    (%%rsi), %%esi\n\t"
+	"movl    %%ecx, -4(%%rdi,%%rdx)\n\t"
+	"movl    %%esi, (%%rdi)\n\t"
+	"jmp %l[done]\n\t"
+	"107:\n\t"
+	/* From 2 to 3.  No branch when size == 2.  */
+	"movzwl  -2(%%rsi,%%rdx), %%ecx\n\t"
+	"movzwl  (%%rsi), %%esi\n\t"
+	"movw    %%cx, -2(%%rdi,%%rdx)\n\t"
+	"movw    %%si, (%%rdi)\n\t"
+	"jmp %l[done]\n\t"
+	"108:\n\t"
+	/* More than 2 * VEC and there may be overlap between destination */
+	/* and source.  */
+	"cmpq    $(32 * 8), %%rdx\n\t"
+	"ja      111f\n\t"
+	"cmpq    $(32 * 4), %%rdx\n\t"
+	"jb      109f\n\t"
+	/* Copy from 4 * VEC to 8 * VEC, inclusively. */
+	"vmovdqu   (%%rsi), %%ymm0\n\t"
+	"vmovdqu   32(%%rsi), %%ymm1\n\t"
+	"vmovdqu   (32 * 2)(%%rsi), %%ymm2\n\t"
+	"vmovdqu   (32 * 3)(%%rsi), %%ymm3\n\t"
+	"vmovdqu   -32(%%rsi,%%rdx), %%ymm4\n\t"
+	"vmovdqu   -(32 * 2)(%%rsi,%%rdx), %%ymm5\n\t"
+	"vmovdqu   -(32 * 3)(%%rsi,%%rdx), %%ymm6\n\t"
+	"vmovdqu   -(32 * 4)(%%rsi,%%rdx), %%ymm7\n\t"
+	"vmovdqu   %%ymm0, (%%rdi)\n\t"
+	"vmovdqu   %%ymm1, 32(%%rdi)\n\t"
+	"vmovdqu   %%ymm2, (32 * 2)(%%rdi)\n\t"
+	"vmovdqu   %%ymm3, (32 * 3)(%%rdi)\n\t"
+	"vmovdqu   %%ymm4, -32(%%rdi,%%rdx)\n\t"
+	"vmovdqu   %%ymm5, -(32 * 2)(%%rdi,%%rdx)\n\t"
+	"vmovdqu   %%ymm6, -(32 * 3)(%%rdi,%%rdx)\n\t"
+	"vmovdqu   %%ymm7, -(32 * 4)(%%rdi,%%rdx)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]\n\t"
+	"109:\n\t"
+	/* Copy from 2 * VEC to 4 * VEC. */
+	"vmovdqu   (%%rsi), %%ymm0\n\t"
+	"vmovdqu   32(%%rsi), %%ymm1\n\t"
+	"vmovdqu   -32(%%rsi,%%rdx), %%ymm2\n\t"
+	"vmovdqu   -(32 * 2)(%%rsi,%%rdx), %%ymm3\n\t"
+	"vmovdqu   %%ymm0, (%%rdi)\n\t"
+	"vmovdqu   %%ymm1, 32(%%rdi)\n\t"
+	"vmovdqu   %%ymm2, -32(%%rdi,%%rdx)\n\t"
+	"vmovdqu   %%ymm3, -(32 * 2)(%%rdi,%%rdx)\n\t"
+	"vzeroupper\n\t"
+	"110:\n\t"
+	"jmp %l[done]\n\t"
+	"111:\n\t"
+	"cmpq    %%rsi, %%rdi\n\t"
+	"ja      113f\n\t"
+	/* Source == destination is less common.  */
+	"je      110b\n\t"
+	/* Load the first VEC and last 4 * VEC to
+	 * support overlapping addresses.
+	 */
+	"vmovdqu   (%%rsi), %%ymm4\n\t"
+	"vmovdqu   -32(%%rsi, %%rdx), %%ymm5\n\t"
+	"vmovdqu   -(32 * 2)(%%rsi, %%rdx), %%ymm6\n\t"
+	"vmovdqu   -(32 * 3)(%%rsi, %%rdx), %%ymm7\n\t"
+	"vmovdqu   -(32 * 4)(%%rsi, %%rdx), %%ymm8\n\t"
+	/* Save start and stop of the destination buffer.  */
+	"movq    %%rdi, %%r11\n\t"
+	"leaq    -32(%%rdi, %%rdx), %%rcx\n\t"
+	/* Align destination for aligned stores in the loop.  Compute */
+	/* how much destination is misaligned.  */
+	"movq    %%rdi, %%r8\n\t"
+	"andq    $(32 - 1), %%r8\n\t"
+	/* Get the negative of offset for alignment.  */
+	"subq    $32, %%r8\n\t"
+	/* Adjust source.  */
+	"subq    %%r8, %%rsi\n\t"
+	/* Adjust destination which should be aligned now.  */
+	"subq    %%r8, %%rdi\n\t"
+	/* Adjust length.  */
+	"addq    %%r8, %%rdx\n\t"
+	/* Check non-temporal store threshold.  */
+	"cmpq	 $(1024*1024), %%rdx\n\t"
+	"ja      115f\n\t"
+	"112:\n\t"
+	/* Copy 4 * VEC a time forward.  */
+	"vmovdqu   (%%rsi), %%ymm0\n\t"
+	"vmovdqu   32(%%rsi), %%ymm1\n\t"
+	"vmovdqu   (32 * 2)(%%rsi), %%ymm2\n\t"
+	"vmovdqu   (32 * 3)(%%rsi), %%ymm3\n\t"
+	"addq    $(32 * 4), %%rsi\n\t"
+	"subq    $(32 * 4), %%rdx\n\t"
+	"vmovdqa   %%ymm0, (%%rdi)\n\t"
+	"vmovdqa   %%ymm1, 32(%%rdi)\n\t"
+	"vmovdqa   %%ymm2, (32 * 2)(%%rdi)\n\t"
+	"vmovdqa   %%ymm3, (32 * 3)(%%rdi)\n\t"
+	"addq    $(32 * 4), %%rdi\n\t"
+	"cmpq    $(32 * 4), %%rdx\n\t"
+	"ja      112b\n\t"
+	/* Store the last 4 * VEC.  */
+	"vmovdqu   %%ymm5, (%%rcx)\n\t"
+	"vmovdqu   %%ymm6, -32(%%rcx)\n\t"
+	"vmovdqu   %%ymm7, -(32 * 2)(%%rcx)\n\t"
+	"vmovdqu   %%ymm8, -(32 * 3)(%%rcx)\n\t"
+	/* Store the first VEC.  */
+	"vmovdqu   %%ymm4, (%%r11)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]\n\t"
+	"113:\n\t"
+	/* Load the first 4*VEC and last VEC to support overlapping addresses.*/
+	"vmovdqu   (%%rsi), %%ymm4\n\t"
+	"vmovdqu   32(%%rsi), %%ymm5\n\t"
+	"vmovdqu   (32 * 2)(%%rsi), %%ymm6\n\t"
+	"vmovdqu   (32 * 3)(%%rsi), %%ymm7\n\t"
+	"vmovdqu   -32(%%rsi,%%rdx), %%ymm8\n\t"
+	/* Save stop of the destination buffer.  */
+	"leaq    -32(%%rdi, %%rdx), %%r11\n\t"
+	/* Align destination end for aligned stores in the loop.  Compute */
+	/* how much destination end is misaligned.  */
+	"leaq    -32(%%rsi, %%rdx), %%rcx\n\t"
+	"movq    %%r11, %%r9\n\t"
+	"movq    %%r11, %%r8\n\t"
+	"andq    $(32 - 1), %%r8\n\t"
+	/* Adjust source.  */
+	"subq    %%r8, %%rcx\n\t"
+	/* Adjust the end of destination which should be aligned now.  */
+	"subq    %%r8, %%r9\n\t"
+	/* Adjust length.  */
+	"subq    %%r8, %%rdx\n\t"
+	 /* Check non-temporal store threshold.  */
+	"cmpq	 $(1024*1024), %%rdx\n\t"
+	"ja      117f\n\t"
+	"114:\n\t"
+	/* Copy 4 * VEC a time backward.  */
+	"vmovdqu   (%%rcx), %%ymm0\n\t"
+	"vmovdqu   -32(%%rcx), %%ymm1\n\t"
+	"vmovdqu   -(32 * 2)(%%rcx), %%ymm2\n\t"
+	"vmovdqu   -(32 * 3)(%%rcx), %%ymm3\n\t"
+	"subq    $(32 * 4), %%rcx\n\t"
+	"subq    $(32 * 4), %%rdx\n\t"
+	"vmovdqa   %%ymm0, (%%r9)\n\t"
+	"vmovdqa   %%ymm1, -32(%%r9)\n\t"
+	"vmovdqa   %%ymm2, -(32 * 2)(%%r9)\n\t"
+	"vmovdqa   %%ymm3, -(32 * 3)(%%r9)\n\t"
+	"subq    $(32 * 4), %%r9\n\t"
+	"cmpq    $(32 * 4), %%rdx\n\t"
+	"ja      114b\n\t"
+	/* Store the first 4 * VEC. */
+	"vmovdqu   %%ymm4, (%%rdi)\n\t"
+	"vmovdqu   %%ymm5, 32(%%rdi)\n\t"
+	"vmovdqu   %%ymm6, (32 * 2)(%%rdi)\n\t"
+	"vmovdqu   %%ymm7, (32 * 3)(%%rdi)\n\t"
+	/* Store the last VEC. */
+	"vmovdqu   %%ymm8, (%%r11)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]\n\t"
+
+	"115:\n\t"
+	/* Don't use non-temporal store if there is overlap between */
+	/* destination and source since destination may be in cache */
+	/* when source is loaded. */
+	"leaq    (%%rdi, %%rdx), %%r10\n\t"
+	"cmpq    %%r10, %%rsi\n\t"
+	"jb      112b\n\t"
+	"116:\n\t"
+	/* Copy 4 * VEC a time forward with non-temporal stores.  */
+	"prefetcht0 (32*4*2)(%%rsi)\n\t"
+	"prefetcht0 (32*4*2 + 64)(%%rsi)\n\t"
+	"prefetcht0 (32*4*3)(%%rsi)\n\t"
+	"prefetcht0 (32*4*3 + 64)(%%rsi)\n\t"
+	"vmovdqu   (%%rsi), %%ymm0\n\t"
+	"vmovdqu   32(%%rsi), %%ymm1\n\t"
+	"vmovdqu   (32 * 2)(%%rsi), %%ymm2\n\t"
+	"vmovdqu   (32 * 3)(%%rsi), %%ymm3\n\t"
+	"addq    $(32*4), %%rsi\n\t"
+	"subq    $(32*4), %%rdx\n\t"
+	"vmovntdq  %%ymm0, (%%rdi)\n\t"
+	"vmovntdq  %%ymm1, 32(%%rdi)\n\t"
+	"vmovntdq  %%ymm2, (32 * 2)(%%rdi)\n\t"
+	"vmovntdq  %%ymm3, (32 * 3)(%%rdi)\n\t"
+	"addq    $(32*4), %%rdi\n\t"
+	"cmpq    $(32*4), %%rdx\n\t"
+	"ja      116b\n\t"
+	"sfence\n\t"
+	/* Store the last 4 * VEC.  */
+	"vmovdqu   %%ymm5, (%%rcx)\n\t"
+	"vmovdqu   %%ymm6, -32(%%rcx)\n\t"
+	"vmovdqu   %%ymm7, -(32 * 2)(%%rcx)\n\t"
+	"vmovdqu   %%ymm8, -(32 * 3)(%%rcx)\n\t"
+	/* Store the first VEC.  */
+	"vmovdqu   %%ymm4, (%%r11)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]\n\t"
+	"117:\n\t"
+	/* Don't use non-temporal store if there is overlap between */
+	/* destination and source since destination may be in cache */
+	/* when source is loaded.  */
+	"leaq    (%%rcx, %%rdx), %%r10\n\t"
+	"cmpq    %%r10, %%r9\n\t"
+	"jb      114b\n\t"
+	"118:\n\t"
+	/* Copy 4 * VEC a time backward with non-temporal stores. */
+	"prefetcht0 (-32 * 4 * 2)(%%rcx)\n\t"
+	"prefetcht0 (-32 * 4 * 2 - 64)(%%rcx)\n\t"
+	"prefetcht0 (-32 * 4 * 3)(%%rcx)\n\t"
+	"prefetcht0 (-32 * 4 * 3 - 64)(%%rcx)\n\t"
+	"vmovdqu   (%%rcx), %%ymm0\n\t"
+	"vmovdqu   -32(%%rcx), %%ymm1\n\t"
+	"vmovdqu   -(32 * 2)(%%rcx), %%ymm2\n\t"
+	"vmovdqu   -(32 * 3)(%%rcx), %%ymm3\n\t"
+	"subq    $(32*4), %%rcx\n\t"
+	"subq    $(32*4), %%rdx\n\t"
+	"vmovntdq  %%ymm0, (%%r9)\n\t"
+	"vmovntdq  %%ymm1, -32(%%r9)\n\t"
+	"vmovntdq  %%ymm2, -(32 * 2)(%%r9)\n\t"
+	"vmovntdq  %%ymm3, -(32 * 3)(%%r9)\n\t"
+	"subq    $(32 * 4), %%r9\n\t"
+	"cmpq    $(32 * 4), %%rdx\n\t"
+	"ja      118b\n\t"
+	"sfence\n\t"
+	/* Store the first 4 * VEC.  */
+	"vmovdqu   %%ymm4, (%%rdi)\n\t"
+	"vmovdqu   %%ymm5, 32(%%rdi)\n\t"
+	"vmovdqu   %%ymm6, (32 * 2)(%%rdi)\n\t"
+	"vmovdqu   %%ymm7, (32 * 3)(%%rdi)\n\t"
+	/* Store the last VEC.  */
+	"vmovdqu   %%ymm8, (%%r11)\n\t"
+	"vzeroupper\n\t"
+	"jmp %l[done]"
+	:
+	: "r"(src), "r"(dst), "r"(len)
+	: "rax", "rcx", "rdx", "rdi", "rsi", "r8", "r9", "r10", "r11", "r12", "ymm0",
+	"ymm1", "ymm2", "ymm3", "ymm4", "ymm5", "ymm6", "ymm7", "ymm8", "memory"
+	: done
+	);
+done:
+	return dst;
+}
+
+#else
 static __rte_always_inline void *
 rte_memcpy_generic(void *dst, const void *src, size_t n)
 {
@@ -479,6 +971,8 @@ rte_memcpy_generic(void *dst, const void *src, size_t n)
 	goto COPY_BLOCK_128_BACK31;
 }
 
+#endif /* RTE_MEMCPY_AMDEPYC */
+
 #else /* __AVX512F__ */
 
 #define ALIGNMENT_MASK 0x0F
@@ -874,6 +1368,14 @@ rte_memcpy(void *dst, const void *src, size_t n)
 		return rte_memcpy_generic(dst, src, n);
 }
 
+#if defined __AVX2__ && defined(RTE_MEMCPY_AMDEPYC)
+static __rte_always_inline void *
+rte_memcpy_aligned_tstore16(void *dst, void *src, int len)
+{
+	return rte_memcpy_aligned_ntload_tstore16_amdepyc2(dst, src, len);
+}
+#endif
+
 #if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION >= 100000)
 #pragma GCC diagnostic pop
 #endif
-- 
2.25.1