[Mesa-dev] [PATCH 2/6] i965/fs: copy propagate 'NOT' instruction when used with logical operation

[Abdiel Janulgue]

On Broadwell, this reduces the instruction to 1 operation when NOT is used with
a logical instruction

Signed-off-by: Abdiel Janulgue <abdiel.janulgue at linux.intel.com>
---
 src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
index d3d59aa..09d5949 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
@@ -42,6 +42,7 @@ namespace { /* avoid conflict with opt_copy_propagation_elements */
 struct acp_entry : public exec_node {
    fs_reg dst;
    fs_reg src;
+   enum opcode opcode;
 };
 
 struct block_data {
@@ -341,6 +342,10 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
       inst->src[arg].negate ^= entry->src.negate;
    }
 
+   if (brw->gen >=8 && entry->opcode == BRW_OPCODE_NOT) {
+      inst->src[arg].negate ^= !entry->src.negate;
+   }
+
    return true;
 }
 
@@ -480,9 +485,10 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry)
 }
 
 static bool
-can_propagate_from(fs_inst *inst)
+can_propagate_from(struct brw_context *brw, fs_inst *inst)
 {
-   return (inst->opcode == BRW_OPCODE_MOV &&
+   return ((inst->opcode == BRW_OPCODE_MOV ||
+            (inst->opcode == BRW_OPCODE_NOT && brw->gen >=8)) &&
            inst->dst.file == GRF &&
            ((inst->src[0].file == GRF &&
              (inst->src[0].reg != inst->dst.reg ||
@@ -548,10 +554,11 @@ fs_visitor::opt_copy_propagate_local(void *copy_prop_ctx, bblock_t *block,
       /* If this instruction's source could potentially be folded into the
        * operand of another instruction, add it to the ACP.
        */
-      if (can_propagate_from(inst)) {
+      if (can_propagate_from(brw, inst)) {
 	 acp_entry *entry = ralloc(copy_prop_ctx, acp_entry);
 	 entry->dst = inst->dst;
 	 entry->src = inst->src[0];
+         entry->opcode = inst->opcode;
 	 acp[entry->dst.reg % ACP_HASH_SIZE].push_tail(entry);
       }
    }
-- 
1.9.1