[Mesa-dev] [PATCH 2/4] i965/fs: Improve CSE performance by expiring some available expressions.

[Eric Anholt]

We're already walking the list, and we can easily know when something
has no reason to be in the list any longer, so take a brief extra step
to reduce our worst-case runtime (an oglconform test that emits the
maximum instructions in a fragment program).  I don't actually know what
the worst-case runtime was, because it was too long and I got bored.
---
 src/mesa/drivers/dri/i965/brw_fs_cse.cpp |   20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
index 44479d8..09c7fa6 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
@@ -88,6 +88,7 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
 
    void *mem_ctx = ralloc_context(this->mem_ctx);
 
+   int ip = block->start_ip;
    for (fs_inst *inst = (fs_inst *)block->start;
 	inst != block->end->next;
 	inst = (fs_inst *) inst->next) {
@@ -153,18 +154,33 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
 	 }
       }
 
-      /* Kill all AEB entries that use the destination. */
       foreach_list_safe(entry_node, aeb) {
 	 aeb_entry *entry = (aeb_entry *)entry_node;
 
 	 for (int i = 0; i < 3; i++) {
+            fs_reg *src_reg = &entry->generator->src[i];
+
+            /* Kill all AEB entries that use the destination we just
+             * overwrote.
+             */
             if (inst->overwrites_reg(entry->generator->src[i])) {
 	       entry->remove();
 	       ralloc_free(entry);
 	       break;
 	    }
+
+            /* Kill any AEB entries using registers that don't get reused any
+             * more -- a sure sign they'll fail operands_match().
+             */
+            if (src_reg->file == GRF && virtual_grf_use[src_reg->reg] < ip) {
+               entry->remove();
+               ralloc_free(entry);
+	       break;
+            }
 	 }
       }
+
+      ip++;
    }
 
    ralloc_free(mem_ctx);
@@ -180,6 +196,8 @@ fs_visitor::opt_cse()
 {
    bool progress = false;
 
+   calculate_live_intervals();
+
    cfg_t cfg(this);
 
    for (int b = 0; b < cfg.num_blocks; b++) {
-- 
1.7.10.4