[Mesa-dev] [PATCH v2 2/6] i965/fs: skip copy-propate for logical instructions with negated src entries

[Abdiel Janulgue]

The negation source modifier on src registers has changed meaning in Broadwell when
used with logical operations. Don't copy propagate when negate src modifier is set
and when the destination instruction is a logical op.

Signed-off-by: Abdiel Janulgue <abdiel.janulgue at linux.intel.com>
---
 src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

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..aa506f5 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 {
@@ -272,6 +273,15 @@ fs_copy_prop_dataflow::dump_block_data() const
    }
 }
 
+static bool
+is_logic_op(enum opcode opcode)
+{
+   return (opcode == BRW_OPCODE_AND ||
+           opcode == BRW_OPCODE_OR  ||
+           opcode == BRW_OPCODE_XOR ||
+           opcode == BRW_OPCODE_NOT);
+}
+
 bool
 fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
 {
@@ -330,6 +340,14 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
    if (has_source_modifiers && entry->dst.type != inst->src[arg].type)
       return false;
 
+   if (brw->gen >= 8) {
+      if (entry->src.negate) {
+         if (is_logic_op(inst->opcode)) {
+            return false;
+         }
+      }
+   }
+
    inst->src[arg].file = entry->src.file;
    inst->src[arg].reg = entry->src.reg;
    inst->src[arg].reg_offset = entry->src.reg_offset;
@@ -552,6 +570,7 @@ fs_visitor::opt_copy_propagate_local(void *copy_prop_ctx, bblock_t *block,
 	 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