[dpdk-dev] [PATCH v7 03/13] vhost: try to unroll for each loop

[Marvin Liu]

Create macro for adding unroll pragma before for each loop. Batch
functions will be contained of several small loops which can be
optimized by compilers' loop unrolling pragma.

Signed-off-by: Marvin Liu <yong.liu at intel.com>

diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index 8623e91c0..87ce1fb27 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -16,6 +16,24 @@ CFLAGS += -I vhost_user
 CFLAGS += -fno-strict-aliasing
 LDLIBS += -lpthread
 
+ifeq ($(RTE_TOOLCHAIN), gcc)
+ifeq ($(shell test $(GCC_VERSION) -ge 83 && echo 1), 1)
+CFLAGS += -DVHOST_GCC_UNROLL_PRAGMA
+endif
+endif
+
+ifeq ($(RTE_TOOLCHAIN), clang)
+ifeq ($(shell test $(CLANG_MAJOR_VERSION)$(CLANG_MINOR_VERSION) -ge 37 && echo 1), 1)
+CFLAGS += -DVHOST_CLANG_UNROLL_PRAGMA
+endif
+endif
+
+ifeq ($(RTE_TOOLCHAIN), icc)
+ifeq ($(shell test $(ICC_MAJOR_VERSION) -ge 16 && echo 1), 1)
+CFLAGS += -DVHOST_ICC_UNROLL_PRAGMA
+endif
+endif
+
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
 LDLIBS += -lnuma
 endif
diff --git a/lib/librte_vhost/meson.build b/lib/librte_vhost/meson.build
index cb1123ae3..00435777e 100644
--- a/lib/librte_vhost/meson.build
+++ b/lib/librte_vhost/meson.build
@@ -8,6 +8,13 @@ endif
 if has_libnuma == 1
 	dpdk_conf.set10('RTE_LIBRTE_VHOST_NUMA', true)
 endif
+if (toolchain == 'gcc' and cc.version().version_compare('>=8.3.0'))
+	cflags += '-DVHOST_GCC_UNROLL_PRAGMA'
+elif (toolchain == 'clang' and cc.version().version_compare('>=3.7.0'))
+	cflags += '-DVHOST_CLANG_UNROLL_PRAGMA'
+elif (toolchain == 'icc' and cc.version().version_compare('>=16.0.0'))
+	cflags += '-DVHOST_ICC_UNROLL_PRAGMA'
+endif
 dpdk_conf.set('RTE_LIBRTE_VHOST_POSTCOPY',
 	      cc.has_header('linux/userfaultfd.h'))
 version = 4
diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 02b3c91ff..a2b9221e0 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -39,6 +39,30 @@
 
 #define VHOST_LOG_CACHE_NR 32
 
+#define PACKED_BATCH_SIZE (RTE_CACHE_LINE_SIZE / \
+			    sizeof(struct vring_packed_desc))
+#define PACKED_BATCH_MASK (PACKED_BATCH_SIZE - 1)
+
+#ifdef VHOST_GCC_UNROLL_PRAGMA
+#define vhost_for_each_try_unroll(iter, val, size) _Pragma("GCC unroll 4") \
+	for (iter = val; iter < size; iter++)
+#endif
+
+#ifdef VHOST_CLANG_UNROLL_PRAGMA
+#define vhost_for_each_try_unroll(iter, val, size) _Pragma("unroll 4") \
+	for (iter = val; iter < size; iter++)
+#endif
+
+#ifdef VHOST_ICC_UNROLL_PRAGMA
+#define vhost_for_each_try_unroll(iter, val, size) _Pragma("unroll (4)") \
+	for (iter = val; iter < size; iter++)
+#endif
+
+#ifndef vhost_for_each_try_unroll
+#define vhost_for_each_try_unroll(iter, val, num) \
+	for (iter = val; iter < num; iter++)
+#endif
+
 /**
  * Structure contains buffer address, length and descriptor index
  * from vring to do scatter RX.
-- 
2.17.1