[Mesa-dev] [PATCH 31/31] i965/fs: Remove FS_OPCODE_PACK_STENCIL_REF virtual instruction.

[Francisco Jerez]

It's just a byte MOV with strided source.
---
 src/mesa/drivers/dri/i965/brw_defines.h        |  1 -
 src/mesa/drivers/dri/i965/brw_fs.cpp           |  4 +--
 src/mesa/drivers/dri/i965/brw_fs.h             |  2 --
 src/mesa/drivers/dri/i965/brw_fs_generator.cpp | 45 --------------------------
 src/mesa/drivers/dri/i965/brw_shader.cpp       |  2 --
 5 files changed, 2 insertions(+), 52 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_defines.h b/src/mesa/drivers/dri/i965/brw_defines.h
index 5476235..702eb5a 100644
--- a/src/mesa/drivers/dri/i965/brw_defines.h
+++ b/src/mesa/drivers/dri/i965/brw_defines.h
@@ -951,7 +951,6 @@ enum opcode {
    FS_OPCODE_FB_WRITE_LOGICAL,
 
    FS_OPCODE_REP_FB_WRITE,
-   FS_OPCODE_PACK_STENCIL_REF,
    SHADER_OPCODE_RCP,
    SHADER_OPCODE_RSQ,
    SHADER_OPCODE_SQRT,
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 9ab9d01..5cd7b34 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -3841,8 +3841,8 @@ lower_fb_write_logical_send(const fs_builder &bld, fs_inst *inst,
 
       sources[length] = bld.vgrf(BRW_REGISTER_TYPE_UD);
       bld.exec_all().annotate("FB write OS")
-         .emit(FS_OPCODE_PACK_STENCIL_REF, sources[length],
-               retype(src_stencil, BRW_REGISTER_TYPE_UB));
+         .MOV(retype(sources[length], BRW_REGISTER_TYPE_UB),
+              subscript(src_stencil, BRW_REGISTER_TYPE_UB, 0));
       length++;
    }
 
diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index e656487..02184b4 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -430,8 +430,6 @@ private:
    void generate_urb_read(fs_inst *inst, struct brw_reg dst, struct brw_reg payload);
    void generate_urb_write(fs_inst *inst, struct brw_reg payload);
    void generate_cs_terminate(fs_inst *inst, struct brw_reg payload);
-   void generate_stencil_ref_packing(fs_inst *inst, struct brw_reg dst,
-                                     struct brw_reg src);
    void generate_barrier(fs_inst *inst, struct brw_reg src);
    void generate_linterp(fs_inst *inst, struct brw_reg dst,
 			 struct brw_reg *src);
diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index 1c91212..25f46c5 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -510,47 +510,6 @@ fs_generator::generate_cs_terminate(fs_inst *inst, struct brw_reg payload)
 }
 
 void
-fs_generator::generate_stencil_ref_packing(fs_inst *inst,
-                                           struct brw_reg dst,
-                                           struct brw_reg src)
-{
-   assert(dispatch_width == 8);
-   assert(devinfo->gen >= 9);
-
-   /* Stencil value updates are provided in 8 slots of 1 byte per slot.
-    * Presumably, in order to save memory bandwidth, the stencil reference
-    * values written from the FS need to be packed into 2 dwords (this makes
-    * sense because the stencil values are limited to 1 byte each and a SIMD8
-    * send, so stencil slots 0-3 in dw0, and 4-7 in dw1.)
-    *
-    * The spec is confusing here because in the payload definition of MDP_RTW_S8
-    * (Message Data Payload for Render Target Writes with Stencil 8b) the
-    * stencil value seems to be dw4.0-dw4.7. However, if you look at the type of
-    * dw4 it is type MDPR_STENCIL (Message Data Payload Register) which is the
-    * packed values specified above and diagrammed below:
-    *
-    *     31                             0
-    *     --------------------------------
-    * DW  |                              |
-    * 2-7 |            IGNORED           |
-    *     |                              |
-    *     --------------------------------
-    * DW1 | STC   | STC   | STC   | STC  |
-    *     | slot7 | slot6 | slot5 | slot4|
-    *     --------------------------------
-    * DW0 | STC   | STC   | STC   | STC  |
-    *     | slot3 | slot2 | slot1 | slot0|
-    *     --------------------------------
-    */
-
-   src.vstride = BRW_VERTICAL_STRIDE_4;
-   src.width = BRW_WIDTH_1;
-   src.hstride = BRW_HORIZONTAL_STRIDE_0;
-   assert(src.type == BRW_REGISTER_TYPE_UB);
-   brw_MOV(p, retype(dst, BRW_REGISTER_TYPE_UB), src);
-}
-
-void
 fs_generator::generate_barrier(fs_inst *inst, struct brw_reg src)
 {
    brw_barrier(p, src);
@@ -2096,10 +2055,6 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width)
 	 generate_barrier(inst, src[0]);
 	 break;
 
-      case FS_OPCODE_PACK_STENCIL_REF:
-         generate_stencil_ref_packing(inst, dst, src[0]);
-         break;
-
       default:
          unreachable("Unsupported opcode");
 
diff --git a/src/mesa/drivers/dri/i965/brw_shader.cpp b/src/mesa/drivers/dri/i965/brw_shader.cpp
index f6f51bb..7863003 100644
--- a/src/mesa/drivers/dri/i965/brw_shader.cpp
+++ b/src/mesa/drivers/dri/i965/brw_shader.cpp
@@ -180,8 +180,6 @@ brw_instruction_name(const struct brw_device_info *devinfo, enum opcode op)
       return "fb_write";
    case FS_OPCODE_FB_WRITE_LOGICAL:
       return "fb_write_logical";
-   case FS_OPCODE_PACK_STENCIL_REF:
-      return "pack_stencil_ref";
    case FS_OPCODE_REP_FB_WRITE:
       return "rep_fb_write";
 
-- 
2.7.3