Make classify_scalar to behave in the same way as it's vector counterpart:
move match check out of the inner loop, etc.
That makes scalar and vector code look more identical.
Plus it improves scalar code performance.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
transition0 = index_array[0];
transition1 = index_array[1];
transition0 = index_array[0];
transition1 = index_array[1];
+ while ((transition0 | transition1) & RTE_ACL_NODE_MATCH) {
+ transition0 = acl_match_check(transition0,
+ 0, ctx, parms, &flows, resolve_priority_scalar);
+ transition1 = acl_match_check(transition1,
+ 1, ctx, parms, &flows, resolve_priority_scalar);
+ }
+
while (flows.started > 0) {
input0 = GET_NEXT_4BYTES(parms, 0);
input1 = GET_NEXT_4BYTES(parms, 1);
for (n = 0; n < 4; n++) {
while (flows.started > 0) {
input0 = GET_NEXT_4BYTES(parms, 0);
input1 = GET_NEXT_4BYTES(parms, 1);
for (n = 0; n < 4; n++) {
- if (likely((transition0 & RTE_ACL_NODE_MATCH) == 0))
- transition0 = scalar_transition(flows.trans,
- transition0, (uint8_t)input0);
+ transition0 = scalar_transition(flows.trans,
+ transition0, (uint8_t)input0);
- if (likely((transition1 & RTE_ACL_NODE_MATCH) == 0))
- transition1 = scalar_transition(flows.trans,
- transition1, (uint8_t)input1);
-
+ transition1 = scalar_transition(flows.trans,
+ transition1, (uint8_t)input1);
- if ((transition0 | transition1) & RTE_ACL_NODE_MATCH) {
+
+ while ((transition0 | transition1) & RTE_ACL_NODE_MATCH) {
transition0 = acl_match_check(transition0,
0, ctx, parms, &flows, resolve_priority_scalar);
transition1 = acl_match_check(transition1,
1, ctx, parms, &flows, resolve_priority_scalar);
transition0 = acl_match_check(transition0,
0, ctx, parms, &flows, resolve_priority_scalar);
transition1 = acl_match_check(transition1,
1, ctx, parms, &flows, resolve_priority_scalar);