r300: Fix fragment program reordering

Do not move an instruction that writes to a temp forward past an instruction
that reads the same temporary.

diff --git a/src/mesa/drivers/dri/r300/r300_context.h b/src/mesa/drivers/dri/r300/r300_context.h
index bc43953ff38099800251cdd173b39b4749767933..29436ab9e0abb03a8ec9e8922cc0c2777bb7b820 100644 (file)
--- a/src/mesa/drivers/dri/r300/r300_context.h
+++ b/src/mesa/drivers/dri/r300/r300_context.h
@@ -674,6 +674,11 @@ struct reg_lifetime {
           emitted instruction that writes to the register */
        int vector_valid;
        int scalar_valid;
+       
+       /* Index to the slot where the register was last read.
+          This is also the first slot in which the register may be written again */
+       int vector_lastread;
+       int scalar_lastread;
 };
 
 

diff --git a/src/mesa/drivers/dri/r300/r300_fragprog.c b/src/mesa/drivers/dri/r300/r300_fragprog.c
index 3c5483031202b5153f2b4b3845b38f0e6d063b24..89e9f6531a9696773179a3f6b3db367a7942c042 100644 (file)
--- a/src/mesa/drivers/dri/r300/r300_fragprog.c
+++ b/src/mesa/drivers/dri/r300/r300_fragprog.c
@@ -1026,10 +1026,11 @@ static void emit_tex(struct r300_fragment_program *rp,
  */
 static int get_earliest_allowed_write(
                struct r300_fragment_program* rp,
-               GLuint dest)
+               GLuint dest, int mask)
 {
        COMPILE_STATE;
        int idx;
+       int pos;
        GLuint index = REG_GET_INDEX(dest);
        assert(REG_GET_VALID(dest));
 
@@ -1047,7 +1048,17 @@ static int get_earliest_allowed_write(
                        return 0;
        }
        
-       return cs->hwtemps[idx].reserved;
+       pos = cs->hwtemps[idx].reserved;
+       if (mask & WRITEMASK_XYZ) {
+               if (pos < cs->hwtemps[idx].vector_lastread)
+                       pos = cs->hwtemps[idx].vector_lastread;
+       }
+       if (mask & WRITEMASK_W) {
+               if (pos < cs->hwtemps[idx].scalar_lastread)
+                       pos = cs->hwtemps[idx].scalar_lastread;
+       }
+       
+       return pos;
 }
 
 
@@ -1070,7 +1081,8 @@ static int find_and_prepare_slot(struct r300_fragment_program* rp,
                GLboolean emit_sop,
                int argc,
                GLuint* src,
-               GLuint dest)
+               GLuint dest,
+               int mask)
 {
        COMPILE_STATE;
        int hwsrc[3];
@@ -1092,7 +1104,7 @@ static int find_and_prepare_slot(struct r300_fragment_program* rp,
        if (emit_sop)
                used |= SLOT_OP_SCALAR;
        
-       pos = get_earliest_allowed_write(rp, dest);
+       pos = get_earliest_allowed_write(rp, dest, mask);
        
        if (rp->node[rp->cur_node].alu_offset > pos)
                pos = rp->node[rp->cur_node].alu_offset;
@@ -1191,6 +1203,21 @@ static int find_and_prepare_slot(struct r300_fragment_program* rp,
                cs->slot[pos].ssrc[i] = tempssrc[i];
        }
        
+       for(i = 0; i < argc; ++i) {
+               if (REG_GET_TYPE(src[i]) == REG_TYPE_TEMP) {
+                       int regnr = hwsrc[i] & 31;
+                       
+                       if (used & (SLOT_SRC_VECTOR << i)) {
+                               if (cs->hwtemps[regnr].vector_lastread < pos)
+                                       cs->hwtemps[regnr].vector_lastread = pos;
+                       }
+                       if (used & (SLOT_SRC_SCALAR << i)) {
+                               if (cs->hwtemps[regnr].scalar_lastread < pos)
+                                       cs->hwtemps[regnr].scalar_lastread = pos;
+                       }
+               }
+       }
+       
        // Emit the source fetch code
        rp->alu.inst[pos].inst1 &= ~R300_FPI1_SRC_MASK;
        rp->alu.inst[pos].inst1 |=
@@ -1287,7 +1314,7 @@ static void emit_arith(struct r300_fragment_program *rp,
        if ((mask & WRITEMASK_W) || vop == R300_FPI0_OUTC_REPL_ALPHA)
                emit_sop = GL_TRUE;
 
-       pos = find_and_prepare_slot(rp, emit_vop, emit_sop, argc, src, dest);
+       pos = find_and_prepare_slot(rp, emit_vop, emit_sop, argc, src, dest, mask);
        if (pos < 0)
                return;