[dpdk-dev] [PATCH 20.11 4/7] acl: add infrastructure to support AVX512 classify

[Konstantin Ananyev]

Add necessary changes to support new AVX512 specific ACL classify
algorithm:
 - changes in meson.build and Makefile to check that build tools
   (compiler, assembler, etc.) do properly support AVX512.
 - dummy rte_acl_classify_avx512() for targets where AVX512
   implementation couldn't be properly supported.

Signed-off-by: Konstantin Ananyev <konstantin.ananyev at intel.com>
---
 config/x86/meson.build          |  3 ++-
 lib/librte_acl/Makefile         | 26 ++++++++++++++++++++++
 lib/librte_acl/acl.h            |  4 ++++
 lib/librte_acl/acl_run_avx512.c | 17 ++++++++++++++
 lib/librte_acl/meson.build      | 39 +++++++++++++++++++++++++++++++++
 lib/librte_acl/rte_acl.c        | 17 ++++++++++++++
 lib/librte_acl/rte_acl.h        |  1 +
 7 files changed, 106 insertions(+), 1 deletion(-)
 create mode 100644 lib/librte_acl/acl_run_avx512.c

diff --git a/config/x86/meson.build b/config/x86/meson.build
index 6ec020ef6..c5626e914 100644
--- a/config/x86/meson.build
+++ b/config/x86/meson.build
@@ -23,7 +23,8 @@ foreach f:base_flags
 endforeach
 
 optional_flags = ['AES', 'PCLMUL',
-		'AVX', 'AVX2', 'AVX512F',
+		'AVX', 'AVX2',
+		'AVX512F', 'AVX512VL', 'AVX512CD', 'AVX512BW',
 		'RDRND', 'RDSEED']
 foreach f:optional_flags
 	if cc.get_define('__ at 0@__'.format(f), args: machine_args) == '1'
diff --git a/lib/librte_acl/Makefile b/lib/librte_acl/Makefile
index f4332b044..8bd469c2b 100644
--- a/lib/librte_acl/Makefile
+++ b/lib/librte_acl/Makefile
@@ -58,6 +58,32 @@ ifeq ($(CC_AVX2_SUPPORT), 1)
 	CFLAGS_rte_acl.o += -DCC_AVX2_SUPPORT
 endif
 
+# compile AVX512 version if:
+# we are building 64-bit binary AND binutils can generate proper code
+ifeq ($(CONFIG_RTE_ARCH_X86_64),y)
+
+	BINUTIL_OK=$(shell AS=as; \
+		$(RTE_SDK)/buildtools/binutils-avx512-check.sh && \
+		echo 1)
+	ifeq ($(BINUTIL_OK), 1)
+
+		# If the compiler supports AVX512 instructions,
+		# then add support for AVX512 classify method.
+
+		CC_AVX512_FLAGS=$(shell $(CC) \
+		-mavx512f -mavx512vl -mavx512cd -mavx512bw \
+		-dM -E - </dev/null 2>&1 | grep AVX512 | wc -l)
+		ifeq ($(CC_AVX512_FLAGS), 4)
+			CFLAGS_acl_run_avx512.o += -mavx512f
+			CFLAGS_acl_run_avx512.o += -mavx512vl
+			CFLAGS_acl_run_avx512.o += -mavx512cd
+			CFLAGS_acl_run_avx512.o += -mavx512bw
+			SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_run_avx512.c
+			CFLAGS_rte_acl.o += -DCC_AVX512_SUPPORT
+		endif
+	endif
+endif
+
 # install this header file
 SYMLINK-$(CONFIG_RTE_LIBRTE_ACL)-include := rte_acl_osdep.h
 SYMLINK-$(CONFIG_RTE_LIBRTE_ACL)-include += rte_acl.h
diff --git a/lib/librte_acl/acl.h b/lib/librte_acl/acl.h
index 39d45a0c2..2022cf253 100644
--- a/lib/librte_acl/acl.h
+++ b/lib/librte_acl/acl.h
@@ -201,6 +201,10 @@ int
 rte_acl_classify_avx2(const struct rte_acl_ctx *ctx, const uint8_t **data,
 	uint32_t *results, uint32_t num, uint32_t categories);
 
+int
+rte_acl_classify_avx512(const struct rte_acl_ctx *ctx, const uint8_t **data,
+	uint32_t *results, uint32_t num, uint32_t categories);
+
 int
 rte_acl_classify_neon(const struct rte_acl_ctx *ctx, const uint8_t **data,
 	uint32_t *results, uint32_t num, uint32_t categories);
diff --git a/lib/librte_acl/acl_run_avx512.c b/lib/librte_acl/acl_run_avx512.c
new file mode 100644
index 000000000..67274989d
--- /dev/null
+++ b/lib/librte_acl/acl_run_avx512.c
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Intel Corporation
+ */
+
+#include "acl_run_sse.h"
+
+int
+rte_acl_classify_avx512(const struct rte_acl_ctx *ctx, const uint8_t **data,
+	uint32_t *results, uint32_t num, uint32_t categories)
+{
+	if (num >= MAX_SEARCHES_SSE8)
+		return search_sse_8(ctx, data, results, num, categories);
+	if (num >= MAX_SEARCHES_SSE4)
+		return search_sse_4(ctx, data, results, num, categories);
+
+	return rte_acl_classify_scalar(ctx, data, results, num, categories);
+}
diff --git a/lib/librte_acl/meson.build b/lib/librte_acl/meson.build
index d1e2c184c..b2fd61cad 100644
--- a/lib/librte_acl/meson.build
+++ b/lib/librte_acl/meson.build
@@ -27,6 +27,45 @@ if dpdk_conf.has('RTE_ARCH_X86')
 		cflags += '-DCC_AVX2_SUPPORT'
 	endif
 
+	# compile AVX512 version if:
+	# we are building 64-bit binary AND binutils can generate proper code
+
+	if dpdk_conf.has('RTE_ARCH_X86_64') and binutils_ok.returncode() == 0
+
+		# compile AVX512 version if either:
+		# a. we have AVX512 supported in minimum instruction set
+		#    baseline
+		# b. it's not minimum instruction set, but supported by
+		#    compiler
+		#
+		# in former case, just add avx512 C file to files list
+		# in latter case, compile c file to static lib, using correct
+		# compiler flags, and then have the .o file from static lib
+		# linked into main lib.
+
+		if dpdk_conf.has('RTE_MACHINE_CPUFLAG_AVX512F') and \
+			dpdk_conf.has('RTE_MACHINE_CPUFLAG_AVX512VL') and \
+			dpdk_conf.has('RTE_MACHINE_CPUFLAG_AVX512CD') and \
+			dpdk_conf.has('RTE_MACHINE_CPUFLAG_AVX512BW')
+
+			sources += files('acl_run_avx512.c')
+			cflags += '-DCC_AVX512_SUPPORT'
+
+		elif cc.has_multi_arguments('-mavx512f', '-mavx512vl',
+					'-mavx512cd', '-mavx512bw')
+
+			avx512_tmplib = static_library('avx512_tmp',
+				'acl_run_avx512.c',
+				dependencies: static_rte_eal,
+				c_args: cflags +
+					['-mavx512f', '-mavx512vl',
+					 '-mavx512cd', '-mavx512bw'])
+			objs += avx512_tmplib.extract_objects(
+					'acl_run_avx512.c')
+			cflags += '-DCC_AVX512_SUPPORT'
+		endif
+	endif
+
 elif dpdk_conf.has('RTE_ARCH_ARM') or dpdk_conf.has('RTE_ARCH_ARM64')
 	cflags += '-flax-vector-conversions'
 	sources += files('acl_run_neon.c')
diff --git a/lib/librte_acl/rte_acl.c b/lib/librte_acl/rte_acl.c
index 715b02359..71b4afb08 100644
--- a/lib/librte_acl/rte_acl.c
+++ b/lib/librte_acl/rte_acl.c
@@ -16,6 +16,22 @@ static struct rte_tailq_elem rte_acl_tailq = {
 };
 EAL_REGISTER_TAILQ(rte_acl_tailq)
 
+#ifndef CC_AVX512_SUPPORT
+/*
+ * If the compiler doesn't support AVX512 instructions,
+ * then the dummy one would be used instead for AVX512 classify method.
+ */
+int
+rte_acl_classify_avx512(__rte_unused const struct rte_acl_ctx *ctx,
+	__rte_unused const uint8_t **data,
+	__rte_unused uint32_t *results,
+	__rte_unused uint32_t num,
+	__rte_unused uint32_t categories)
+{
+	return -ENOTSUP;
+}
+#endif
+
 #ifndef CC_AVX2_SUPPORT
 /*
  * If the compiler doesn't support AVX2 instructions,
@@ -77,6 +93,7 @@ static const rte_acl_classify_t classify_fns[] = {
 	[RTE_ACL_CLASSIFY_AVX2] = rte_acl_classify_avx2,
 	[RTE_ACL_CLASSIFY_NEON] = rte_acl_classify_neon,
 	[RTE_ACL_CLASSIFY_ALTIVEC] = rte_acl_classify_altivec,
+	[RTE_ACL_CLASSIFY_AVX512] = rte_acl_classify_avx512,
 };
 
 /* by default, use always available scalar code path. */
diff --git a/lib/librte_acl/rte_acl.h b/lib/librte_acl/rte_acl.h
index b814423a6..6f39042fc 100644
--- a/lib/librte_acl/rte_acl.h
+++ b/lib/librte_acl/rte_acl.h
@@ -241,6 +241,7 @@ enum rte_acl_classify_alg {
 	RTE_ACL_CLASSIFY_AVX2 = 3,    /**< requires AVX2 support. */
 	RTE_ACL_CLASSIFY_NEON = 4,    /**< requires NEON support. */
 	RTE_ACL_CLASSIFY_ALTIVEC = 5,    /**< requires ALTIVEC support. */
+	RTE_ACL_CLASSIFY_AVX512 = 6,    /**< requires AVX512 support. */
 };
 
 /**
-- 
2.17.1