Add support for multiple microarchitectures in single binary

 * compiler -march= parameter is changed from native to corei7
   so code is always genereted with instructions which are available
   on the Nehalem microarchitecture (up to SSE4.2)

 * compiler -mtune= parameter is added so code is optimized for
   corei7-avx which equals to Sandy Bridge microarchitecture

 * set of macros is added which allows run-time detection of available
   cpu instructions (e.g. clib_cpu_supports_avx())

 * set of macros is added which allows us to clone graph node funcitons
   where cloned function is optmized for different microarchitecture
   Those macros are using following attributes:
     __attribute__((flatten))
     __attribute__((target("arch=core-avx2)))

   I.e. If applied to foo_node_fn() macro will generate cloned
   functions foo_node_fn_avx2() and foo_node_fn_avx512() (future)
   It will also generate function void * foo_node_fn_multiarch_select()
   which detects available instruction set and returns pointer to the
   best matching function clone.

Change-Id: I2dce0ac92a5ede95fcb56f47f3d1f3c4c040bac0
Signed-off-by: Damjan Marion <damarion@cisco.com>

1 files changed, 7 insertions, 0 deletions

diff --git a/vnet/vnet/mpls-gre/interface.c b/vnet/vnet/mpls-gre/interface.c
index 408ca750..75cd022a 100644
--- a/vnet/vnet/mpls-gre/interface.c
+++ b/vnet/vnet/mpls-gre/interface.c
@@ -259,6 +259,9 @@ VNET_DEVICE_CLASS (mpls_gre_device_class) = {
 #endif
 };
 
+VLIB_DEVICE_TX_FUNCTION_MULTIARCH (mpls_gre_device_class,
+				   mpls_gre_interface_tx)
+
 VNET_HW_INTERFACE_CLASS (mpls_gre_hw_interface_class) = {
   .name = "MPLS-GRE",
   .format_header = format_mpls_gre_header_with_length,
@@ -510,6 +513,8 @@ VNET_DEVICE_CLASS (mpls_eth_device_class) = {
 #endif
 };
 
+VLIB_DEVICE_TX_FUNCTION_MULTIARCH (mpls_eth_device_class,
+				   mpls_eth_interface_tx)
 
 VNET_HW_INTERFACE_CLASS (mpls_eth_hw_interface_class) = {
   .name = "MPLS-ETH",
@@ -676,6 +681,8 @@ VLIB_REGISTER_NODE (mpls_post_rewrite_node) = {
   },
 };
 
+VLIB_NODE_FUNCTION_MULTIARCH (mpls_post_rewrite_node, mpls_post_rewrite)
+
 static u8 * mpls_gre_rewrite (mpls_main_t *mm, mpls_gre_tunnel_t * t)
 {
   ip4_header_t * ip0;