[Mesa-dev] [PATCH] i965/vec4: do not trim dead channels on gen6 for math

[Tapani Pälli]

On GEN6 math operations require destination writemask to be WRITEMASK_XYZW.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=76883

Signed-off-by: Tapani Pälli <tapani.palli at intel.com>
---
 src/mesa/drivers/dri/i965/brw_vec4.cpp | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp
index 32a3892..3ed1bad 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
@@ -322,8 +322,10 @@ src_reg::equals(src_reg *r)
 }
 
 static bool
-try_eliminate_instruction(vec4_instruction *inst, int new_writemask)
+try_eliminate_instruction(vec4_instruction *inst, int new_writemask,
+                          const struct brw_context *brw)
 {
+
    if (new_writemask == 0) {
       /* Don't dead code eliminate instructions that write to the
        * accumulator as a side-effect. Instead just set the destination
@@ -344,6 +346,7 @@ try_eliminate_instruction(vec4_instruction *inst, int new_writemask)
       }
       return true;
    } else if (inst->dst.writemask != new_writemask) {
+
       switch (inst->opcode) {
       case SHADER_OPCODE_TXF_CMS:
       case SHADER_OPCODE_GEN4_SCRATCH_READ:
@@ -351,6 +354,10 @@ try_eliminate_instruction(vec4_instruction *inst, int new_writemask)
       case VS_OPCODE_PULL_CONSTANT_LOAD_GEN7:
          break;
       default:
+         /* On GEN6, vec4 backend for math requires a full mask. */
+         if (brw->gen == 6 && inst->is_math())
+            return false;
+
          if (!inst->is_tex()) {
             inst->dst.writemask = new_writemask;
             return true;
@@ -407,7 +414,8 @@ vec4_visitor::dead_code_eliminate()
             }
          }
 
-         progress = try_eliminate_instruction(inst, write_mask) || progress;
+         progress = try_eliminate_instruction(inst, write_mask, brw) ||
+                    progress;
       }
 
       if (seen_control_flow || inst->predicate || inst->prev == NULL)
@@ -456,7 +464,7 @@ vec4_visitor::dead_code_eliminate()
          if (inst->dst.reg == scan_inst->dst.reg) {
             int new_writemask = scan_inst->dst.writemask & ~dead_channels;
 
-            progress = try_eliminate_instruction(scan_inst, new_writemask) ||
+            progress = try_eliminate_instruction(scan_inst, new_writemask, brw) ||
                        progress;
          }
 
-- 
1.8.3.1