X-Git-Url: https://git.libre-soc.org/?a=blobdiff_plain;ds=sidebyside;f=src%2Fintel%2Fcompiler%2Fbrw_vec4_cse.cpp;h=accc037af8dead1c15a52a3f00a4f04bf1c3e4ac;hb=4064a6cd207811434e5400a613b3833fbda6b787;hp=2e65ef78548f2205d01f1748fd0f518a30a63a86;hpb=700bebb958e93f4d472c383de62ced9db8e64bec;p=mesa.git

diff --git a/src/intel/compiler/brw_vec4_cse.cpp b/src/intel/compiler/brw_vec4_cse.cpp
index 2e65ef78548..accc037af8d 100644
--- a/src/intel/compiler/brw_vec4_cse.cpp
+++ b/src/intel/compiler/brw_vec4_cse.cpp
@@ -104,6 +104,25 @@ operands_match(const vec4_instruction *a, const vec4_instruction *b)
       return xs[0].equals(ys[0]) &&
              ((xs[1].equals(ys[1]) && xs[2].equals(ys[2])) ||
               (xs[2].equals(ys[1]) && xs[1].equals(ys[2])));
+   } else if (a->opcode == BRW_OPCODE_MOV &&
+              xs[0].file == IMM &&
+              xs[0].type == BRW_REGISTER_TYPE_VF) {
+      src_reg tmp_x = xs[0];
+      src_reg tmp_y = ys[0];
+
+      /* Smash out the values that are not part of the writemask.  Otherwise
+       * the equals operator will fail due to mismatches in unused components.
+       */
+      const unsigned ab_writemask = a->dst.writemask & b->dst.writemask;
+      const uint32_t mask = ((ab_writemask & WRITEMASK_X) ? 0x000000ff : 0) |
+                            ((ab_writemask & WRITEMASK_Y) ? 0x0000ff00 : 0) |
+                            ((ab_writemask & WRITEMASK_Z) ? 0x00ff0000 : 0) |
+                            ((ab_writemask & WRITEMASK_W) ? 0xff000000 : 0);
+
+      tmp_x.ud &= mask;
+      tmp_y.ud &= mask;
+
+      return tmp_x.equals(tmp_y);
    } else if (!a->is_commutative()) {
       return xs[0].equals(ys[0]) && xs[1].equals(ys[1]) && xs[2].equals(ys[2]);
    } else {
@@ -112,6 +131,14 @@ operands_match(const vec4_instruction *a, const vec4_instruction *b)
    }
 }
 
+/**
+ * Checks if instructions match, exactly for sources, but loosely for
+ * destination writemasks.
+ *
+ * \param 'a' is the generating expression from the AEB entry.
+ * \param 'b' is the second occurrence of the expression that we're
+ *        considering eliminating.
+ */
 static bool
 instructions_match(vec4_instruction *a, vec4_instruction *b)
 {
@@ -127,7 +154,7 @@ instructions_match(vec4_instruction *a, vec4_instruction *b)
           a->base_mrf == b->base_mrf &&
           a->header_size == b->header_size &&
           a->shadow_compare == b->shadow_compare &&
-          a->dst.writemask == b->dst.writemask &&
+          ((a->dst.writemask & b->dst.writemask) == a->dst.writemask) &&
           a->force_writemask_all == b->force_writemask_all &&
           a->size_written == b->size_written &&
           a->exec_size == b->exec_size &&
@@ -136,7 +163,7 @@ instructions_match(vec4_instruction *a, vec4_instruction *b)
 }
 
 bool
-vec4_visitor::opt_cse_local(bblock_t *block)
+vec4_visitor::opt_cse_local(bblock_t *block, const vec4_live_variables &live)
 {
    bool progress = false;
    exec_list aeb;
@@ -261,7 +288,7 @@ vec4_visitor::opt_cse_local(bblock_t *block)
              * more -- a sure sign they'll fail operands_match().
              */
             if (src->file == VGRF) {
-               if (var_range_end(var_from_reg(alloc, dst_reg(*src)), 8) < ip) {
+               if (live.var_range_end(var_from_reg(alloc, dst_reg(*src)), 8) < ip) {
                   entry->remove();
                   ralloc_free(entry);
                   break;
@@ -282,15 +309,14 @@ bool
 vec4_visitor::opt_cse()
 {
    bool progress = false;
-
-   calculate_live_intervals();
+   const vec4_live_variables &live = live_analysis.require();
 
    foreach_block (block, cfg) {
-      progress = opt_cse_local(block) || progress;
+      progress = opt_cse_local(block, live) || progress;
    }
 
    if (progress)
-      invalidate_live_intervals();
+      invalidate_analysis(DEPENDENCY_INSTRUCTIONS | DEPENDENCY_VARIABLES);
 
    return progress;
 }