Mesa (master): i965/fs: add generator support for pixel interpolator query

[Chris Forbes]

Module: Mesa
Branch: master
Commit: 6e91f2df958c835a1973e32d71578fa295ef00a8
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=6e91f2df958c835a1973e32d71578fa295ef00a8

Author: Chris Forbes <chrisf at ijw.co.nz>
Date:   Mon Nov 18 21:13:13 2013 +1300

i965/fs: add generator support for pixel interpolator query

V5: - Split into separate opcodes
    - Pass message data in src1 immediate
    - Put noperspective bit in fs_inst rather than adding any junk to
      backend_instruction

Signed-off-by: Chris Forbes <chrisf at ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>

---

 src/mesa/drivers/dri/i965/brw_defines.h        |    4 +++
 src/mesa/drivers/dri/i965/brw_fs.cpp           |    8 +++++
 src/mesa/drivers/dri/i965/brw_fs.h             |    7 +++++
 src/mesa/drivers/dri/i965/brw_fs_generator.cpp |   40 ++++++++++++++++++++++++
 4 files changed, 59 insertions(+)

diff --git a/src/mesa/drivers/dri/i965/brw_defines.h b/src/mesa/drivers/dri/i965/brw_defines.h
index e528232..8b73c5c 100644
--- a/src/mesa/drivers/dri/i965/brw_defines.h
+++ b/src/mesa/drivers/dri/i965/brw_defines.h
@@ -853,6 +853,10 @@ enum opcode {
    FS_OPCODE_UNPACK_HALF_2x16_SPLIT_X,
    FS_OPCODE_UNPACK_HALF_2x16_SPLIT_Y,
    FS_OPCODE_PLACEHOLDER_HALT,
+   FS_OPCODE_INTERPOLATE_AT_CENTROID,
+   FS_OPCODE_INTERPOLATE_AT_SAMPLE,
+   FS_OPCODE_INTERPOLATE_AT_SHARED_OFFSET,
+   FS_OPCODE_INTERPOLATE_AT_PER_SLOT_OFFSET,
 
    VS_OPCODE_URB_WRITE,
    VS_OPCODE_PULL_CONSTANT_LOAD,
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index a3ad375..951d69f 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -370,6 +370,10 @@ fs_inst::is_send_from_grf() const
 {
    return (opcode == FS_OPCODE_VARYING_PULL_CONSTANT_LOAD_GEN7 ||
            opcode == SHADER_OPCODE_SHADER_TIME_ADD ||
+           opcode == FS_OPCODE_INTERPOLATE_AT_CENTROID ||
+           opcode == FS_OPCODE_INTERPOLATE_AT_SAMPLE ||
+           opcode == FS_OPCODE_INTERPOLATE_AT_SHARED_OFFSET ||
+           opcode == FS_OPCODE_INTERPOLATE_AT_PER_SLOT_OFFSET ||
            (opcode == FS_OPCODE_UNIFORM_PULL_CONSTANT_LOAD &&
             src[1].file == GRF) ||
            (is_tex() && src[0].file == GRF));
@@ -837,6 +841,10 @@ fs_visitor::implied_mrf_writes(fs_inst *inst)
       return 2;
    case SHADER_OPCODE_UNTYPED_ATOMIC:
    case SHADER_OPCODE_UNTYPED_SURFACE_READ:
+   case FS_OPCODE_INTERPOLATE_AT_CENTROID:
+   case FS_OPCODE_INTERPOLATE_AT_SAMPLE:
+   case FS_OPCODE_INTERPOLATE_AT_SHARED_OFFSET:
+   case FS_OPCODE_INTERPOLATE_AT_PER_SLOT_OFFSET:
       return 0;
    default:
       unreachable("not reached");
diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 537f10e..1d3f9d0 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -196,6 +196,7 @@ public:
    bool shadow_compare:1;
    bool force_uncompressed:1;
    bool force_sechalf:1;
+   bool pi_noperspective:1;   /**< Pixel interpolator noperspective flag */
 };
 
 /**
@@ -623,6 +624,12 @@ private:
                                                  struct brw_reg offset);
    void generate_mov_dispatch_to_flags(fs_inst *inst);
 
+   void generate_pixel_interpolator_query(fs_inst *inst,
+                                          struct brw_reg dst,
+                                          struct brw_reg src,
+                                          struct brw_reg msg_data,
+                                          unsigned msg_type);
+
    void generate_set_omask(fs_inst *inst,
                            struct brw_reg dst,
                            struct brw_reg sample_mask);
diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index eae55f0..8e4a31d 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -995,6 +995,26 @@ fs_generator::generate_mov_dispatch_to_flags(fs_inst *inst)
    brw_pop_insn_state(p);
 }
 
+void
+fs_generator::generate_pixel_interpolator_query(fs_inst *inst,
+                                                struct brw_reg dst,
+                                                struct brw_reg src,
+                                                struct brw_reg msg_data,
+                                                unsigned msg_type)
+{
+   assert(msg_data.file == BRW_IMMEDIATE_VALUE &&
+          msg_data.type == BRW_REGISTER_TYPE_UD);
+
+   brw_pixel_interpolator_query(p,
+         retype(dst, BRW_REGISTER_TYPE_UW),
+         src,
+         inst->pi_noperspective,
+         msg_type,
+         msg_data.dw1.ud,
+         inst->mlen,
+         inst->regs_written);
+}
+
 
 static uint32_t brw_file_from_reg(fs_reg *reg)
 {
@@ -1730,6 +1750,26 @@ fs_generator::generate_code(exec_list *instructions)
          }
          break;
 
+      case FS_OPCODE_INTERPOLATE_AT_CENTROID:
+         generate_pixel_interpolator_query(inst, dst, src[0], src[1],
+                                           GEN7_PIXEL_INTERPOLATOR_LOC_CENTROID);
+         break;
+
+      case FS_OPCODE_INTERPOLATE_AT_SAMPLE:
+         generate_pixel_interpolator_query(inst, dst, src[0], src[1],
+                                           GEN7_PIXEL_INTERPOLATOR_LOC_SAMPLE);
+         break;
+
+      case FS_OPCODE_INTERPOLATE_AT_SHARED_OFFSET:
+         generate_pixel_interpolator_query(inst, dst, src[0], src[1],
+                                           GEN7_PIXEL_INTERPOLATOR_LOC_SHARED_OFFSET);
+         break;
+
+      case FS_OPCODE_INTERPOLATE_AT_PER_SLOT_OFFSET:
+         generate_pixel_interpolator_query(inst, dst, src[0], src[1],
+                                           GEN7_PIXEL_INTERPOLATOR_LOC_PER_SLOT_OFFSET);
+         break;
+
       default:
 	 if (inst->opcode < (int) ARRAY_SIZE(opcode_descs)) {
 	    _mesa_problem(ctx, "Unsupported opcode `%s' in FS",