[Mesa-dev] [PATCH v2 1/3] i965: add FS_OPCODE_OVERWRITE_DST

[Chia-I Wu]

From: Chia-I Wu <olv at lunarg.com>

FS_OPCODE_OVERWRITE_DST is used to indicate that the destination register is
(completely) overwritten.  No code is emitted, but the liveness analysis can
use it as a hint to add the destination register to DEF bitset.  This is
needed because it is hard to figure out if some partial writes combined
constitute a complete write during liveness analysis, while it is easier for
the FS visitor to know if that is the case.

Signed-off-by: Chia-I Wu <olv at lunarg.com>
---
 src/mesa/drivers/dri/i965/brw_defines.h                 | 1 +
 src/mesa/drivers/dri/i965/brw_fs_generator.cpp          | 4 ++++
 src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp     | 5 +++--
 src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp | 3 ++-
 src/mesa/drivers/dri/i965/brw_shader.cpp                | 3 +++
 5 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_defines.h b/src/mesa/drivers/dri/i965/brw_defines.h
index c1e7f31..753a9ec 100644
--- a/src/mesa/drivers/dri/i965/brw_defines.h
+++ b/src/mesa/drivers/dri/i965/brw_defines.h
@@ -793,6 +793,7 @@ enum opcode {
    FS_OPCODE_UNPACK_HALF_2x16_SPLIT_X,
    FS_OPCODE_UNPACK_HALF_2x16_SPLIT_Y,
    FS_OPCODE_PLACEHOLDER_HALT,
+   FS_OPCODE_OVERWRITE_DST,
 
    VS_OPCODE_URB_WRITE,
    VS_OPCODE_SCRATCH_READ,
diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index dbfbc11..4b37784 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -1547,6 +1547,10 @@ fs_generator::generate_code(exec_list *instructions)
          patch_discard_jumps_to_fb_writes();
          break;
 
+      case FS_OPCODE_OVERWRITE_DST:
+         /* This is to help liveness analysis. */
+         break;
+
       default:
 	 if (inst->opcode < (int) ARRAY_SIZE(opcode_descs)) {
 	    _mesa_problem(ctx, "Unsupported opcode `%s' in FS",
diff --git a/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp b/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp
index f5daab2..13891f8 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_live_variables.cpp
@@ -77,8 +77,9 @@ fs_live_variables::setup_def_use()
 	  * variable, and thus qualify for being in def[].
 	  */
 	 if (inst->dst.file == GRF &&
-	     inst->regs_written == v->virtual_grf_sizes[inst->dst.reg] &&
-	     !inst->is_partial_write()) {
+	     (inst->opcode == FS_OPCODE_OVERWRITE_DST ||
+	      (inst->regs_written == v->virtual_grf_sizes[inst->dst.reg] &&
+	       !inst->is_partial_write()))) {
 	    int reg = inst->dst.reg;
             if (!BITSET_TEST(bd[b].use, reg))
                BITSET_SET(bd[b].def, reg);
diff --git a/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp b/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp
index 5530683..4e59a10 100644
--- a/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp
+++ b/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp
@@ -562,7 +562,8 @@ fs_instruction_scheduler::calculate_deps()
       schedule_node *n = (schedule_node *)node;
       fs_inst *inst = (fs_inst *)n->inst;
 
-      if (inst->opcode == FS_OPCODE_PLACEHOLDER_HALT)
+      if (inst->opcode == FS_OPCODE_PLACEHOLDER_HALT ||
+          inst->opcode == FS_OPCODE_OVERWRITE_DST)
          add_barrier_deps(n);
 
       /* read-after-write deps. */
diff --git a/src/mesa/drivers/dri/i965/brw_shader.cpp b/src/mesa/drivers/dri/i965/brw_shader.cpp
index 61c4bf5..e226c94 100644
--- a/src/mesa/drivers/dri/i965/brw_shader.cpp
+++ b/src/mesa/drivers/dri/i965/brw_shader.cpp
@@ -485,6 +485,9 @@ brw_instruction_name(enum opcode op)
    case FS_OPCODE_PLACEHOLDER_HALT:
       return "placeholder_halt";
 
+   case FS_OPCODE_OVERWRITE_DST:
+      return "overwrite_dst";
+
    case VS_OPCODE_URB_WRITE:
       return "vs_urb_write";
    case VS_OPCODE_SCRATCH_READ:
-- 
1.8.3.1