intel: Only set VectorMaskEnable when needed

For cases with lots of very small primitives, this may improve
performance because we're not executing those dead channels all the
time.

Shader-db reports no instruction or cycle-count changes.  However, by
hacking up the driver to report when this optimization triggers, it
appears to affect about 10% of shader-db.

v2 (Kenneth Graunke): Always enable VMask prior to XeHP for now,
because using VMask on those platforms allows us to perform the
eliminate_find_live_channel() optimization.  However, XeHP doesn't
seem to have packed fragment shader dispatch, so we lose that
optimization regardless, and there's no reason not to avoid vmask.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1054>

src/intel/compiler/brw_fs_generator.cpp

@@ -2411,21 +2411,27 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width,
          break;
 
       case SHADER_OPCODE_FIND_LIVE_CHANNEL: {
+         const bool uses_vmask =
+            stage == MESA_SHADER_FRAGMENT &&
+            brw_wm_prog_data(this->prog_data)->uses_vmask;
          const struct brw_reg mask =
             brw_stage_has_packed_dispatch(devinfo, stage,
                                           prog_data) ? brw_imm_ud(~0u) :
-            stage == MESA_SHADER_FRAGMENT ? brw_vmask_reg() :
-            brw_dmask_reg();
+            uses_vmask ? brw_vmask_reg() : brw_dmask_reg();
 
          brw_find_live_channel(p, dst, mask, false);
          break;
       }
       case SHADER_OPCODE_FIND_LAST_LIVE_CHANNEL: {
+         const bool uses_vmask =
+            stage == MESA_SHADER_FRAGMENT &&
+            brw_wm_prog_data(this->prog_data)->uses_vmask;
+
          /* ce0 doesn't consider the thread dispatch mask, so if we want
           * to find the true last enabled channel, we need to apply that too.
           */
          const struct brw_reg mask =
-            stage == MESA_SHADER_FRAGMENT ? brw_vmask_reg() : brw_dmask_reg();
+            uses_vmask ? brw_vmask_reg() : brw_dmask_reg();
 
          brw_find_live_channel(p, dst, mask, true);
          break;