i965: Add support for instruction compaction on Gen7.

Reduces l4d2 program size from 1195kb to 919kb.  Improves performance by 0.22%
+/- 0.11% (n=70).

v2: Rebase on compaction v2, fix up flag reg handling (by anholt).
v3: Fix uncompaction of the flag register number.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>

src/mesa/drivers/dri/i965/brw_eu.c

@@ -206,6 +206,8 @@ brw_init_compile(struct brw_context *brw, struct brw_compile *p, void *mem_ctx)
    p->loop_stack_array_size = 16;
    p->loop_stack = rzalloc_array(mem_ctx, int, p->loop_stack_array_size);
    p->if_depth_in_loop = rzalloc_array(mem_ctx, int, p->loop_stack_array_size);
+
+   brw_init_compaction_tables(&brw->intel);
 }
 
 

src/mesa/drivers/dri/i965/brw_eu.h

@@ -1108,6 +1108,7 @@ void brw_set_uip_jip(struct brw_compile *p);
 uint32_t brw_swap_cmod(uint32_t cmod);
 
 /* brw_eu_compact.c */
+void brw_init_compaction_tables(struct intel_context *intel);
 void brw_compact_instructions(struct brw_compile *p);
 void brw_uncompact_instruction(struct intel_context *intel,
 			       struct brw_instruction *dst,