i965/fs: Skip gen4 pre/post-send dependency workaronds for the first/last block.

We know that there cannot be any destination dependency race if we
reach the beginning or end of the program without having found any
other instruction the send could possibly race with.  This avoids
emitting a pile of useless moves at the beginning or end of the
program in the most common case in which the program has a single
basic block only.

On the original i965 I get the following shader-db results:

 total instructions in shared programs: 3354165 -> 3215637 (-4.13%)
 instructions in affected programs: 3183065 -> 3044537 (-4.35%)
 helped: 13498
 HURT: 0

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 1b484228e34bd3c35baf112d44552e39569f9941..d04eebc024c058a11eb915c44dce74ad0418a9b0 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -3163,7 +3163,7 @@ fs_visitor::insert_gen4_pre_send_dependency_workarounds(bblock_t *block,
       /* If we hit control flow, assume that there *are* outstanding
        * dependencies, and force their cleanup before our instruction.
        */
-      if (block->start() == scan_inst) {
+      if (block->start() == scan_inst && block->num != 0) {
          for (int i = 0; i < write_len; i++) {
             if (needs_dep[i])
                DEP_RESOLVE_MOV(fs_builder(this, block, inst),
@@ -3227,7 +3227,7 @@ fs_visitor::insert_gen4_post_send_dependency_workarounds(bblock_t *block, fs_ins
     */
    foreach_inst_in_block_starting_from(fs_inst, scan_inst, inst) {
       /* If we hit control flow, force resolve all remaining dependencies. */
-      if (block->end() == scan_inst) {
+      if (block->end() == scan_inst && block->num != cfg->num_blocks - 1) {
          for (int i = 0; i < write_len; i++) {
             if (needs_dep[i])
                DEP_RESOLVE_MOV(fs_builder(this, block, scan_inst),