i965/vec4: Reduce working set size of live variables computation.

Orbital Explorer was generating a 4000 instruction geometry shader, which
was taking 275 trips through dead code elimination and register
coalescing, each of which updated live variables to get its work done, and
invalidated those live variables afterwards.

By using bitfields instead of bools (reducing the working set size by a
factor of 8) in live variables analysis, it drops from 88% of the profile
to 57%, and reduces overall runtime from I-got-bored-and-killed-it (Paul
says 3+ minutes) to 10.5 seconds.

Compare to f179f419d1d0a03fad36c2b0a58e8b853bae6118 on the FS side.

Reviewed-by: Paul Berry <stereotype441@gmail.com>

1 files changed, 6 insertions, 4 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_live_variables.h b/src/mesa/drivers/dri/i965/brw_vec4_live_variables.h
index 296468a..b2d8b33 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_live_variables.h
+++ b/src/mesa/drivers/dri/i965/brw_vec4_live_variables.h
@@ -25,6 +25,7 @@
  *
  */
 
+#include "main/bitset.h"
 #include "brw_vec4.h"
 
 namespace brw {
@@ -36,18 +37,18 @@ struct block_data {
     * Note that for our purposes, "defined" means unconditionally, completely
     * defined.
     */
-   bool *def;
+   BITSET_WORD *def;
 
    /**
     * Which variables are used before being defined in the block.
     */
-   bool *use;
+   BITSET_WORD *use;
 
    /** Which defs reach the entry point of the block. */
-   bool *livein;
+   BITSET_WORD *livein;
 
    /** Which defs reach the exit point of the block. */
-   bool *liveout;
+   BITSET_WORD *liveout;
 };
 
 class vec4_live_variables {
@@ -65,6 +66,7 @@ public:
    void *mem_ctx;
 
    int num_vars;
+   int bitset_words;
 
    /** Per-basic-block information on live variables */
    struct block_data *bd;