i965/fs: Add byte scattered read message and fs support

v2: Fix alignment style (Topi Pohjolainen)
    (Jason Ekstrand)
    - Enable bit_size parameter to scattered messages to enable different
      bitsizes byte/word/dword.
    - Remove use of brw_send_indirect_scattered_message in favor of
      brw_send_indirect_surface_message.
    - Move scattered messages to surface messages namespace.
    - Assert align1 for scattered messages and assume Gen8+.
    - Inline brw_set_dp_byte_scattered_read.

v3: (Jason Ekstrand)
    - Use renamed brw_byte_scattered_data_element_from_bit_size method
    - Assert scattered read for Gen8+ and Haswell.
    - Use conditional expresion at components_read.
    - Include comment about params for scattered opcodes.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

src/intel/compiler/brw_eu.h

@@ -485,6 +485,14 @@ brw_typed_surface_write(struct brw_codegen *p,
                         unsigned msg_length,
                         unsigned num_channels);
 
+void
+brw_byte_scattered_read(struct brw_codegen *p,
+                        struct brw_reg dst,
+                        struct brw_reg payload,
+                        struct brw_reg surface,
+                        unsigned msg_length,
+                        unsigned bit_size);
+
 void
 brw_byte_scattered_write(struct brw_codegen *p,
                          struct brw_reg payload,

src/intel/compiler/brw_eu_defines.h

@@ -409,6 +409,8 @@ enum opcode {
     * opcode, but instead of taking a single payload blog they expect their
     * arguments separately as individual sources, like untyped write/read.
     */
+   SHADER_OPCODE_BYTE_SCATTERED_READ,
+   SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL,
    SHADER_OPCODE_BYTE_SCATTERED_WRITE,
    SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL,
 

src/intel/compiler/brw_eu_emit.c

@@ -2998,6 +2998,38 @@ brw_byte_scattered_data_element_from_bit_size(unsigned bit_size)
    }
 }
 
+
+void
+brw_byte_scattered_read(struct brw_codegen *p,
+                        struct brw_reg dst,
+                        struct brw_reg payload,
+                        struct brw_reg surface,
+                        unsigned msg_length,
+                        unsigned bit_size)
+{
+   const struct gen_device_info *devinfo = p->devinfo;
+   assert(devinfo->gen > 7 || devinfo->is_haswell);
+   assert(brw_inst_access_mode(devinfo, p->current) == BRW_ALIGN_1);
+   const unsigned sfid =  GEN7_SFID_DATAPORT_DATA_CACHE;
+
+   struct brw_inst *insn = brw_send_indirect_surface_message(
+      p, sfid, dst, payload, surface, msg_length,
+      brw_surface_payload_size(p, 1, true, true),
+      false);
+
+   unsigned msg_control =
+      brw_byte_scattered_data_element_from_bit_size(bit_size) << 2;
+
+   if (brw_inst_exec_size(devinfo, p->current) == BRW_EXECUTE_16)
+      msg_control |= 1; /* SIMD16 mode */
+   else
+      msg_control |= 0; /* SIMD8 mode */
+
+   brw_inst_set_dp_msg_type(devinfo, insn,
+                            HSW_DATAPORT_DC_PORT0_BYTE_SCATTERED_READ);
+   brw_inst_set_dp_msg_control(devinfo, insn, msg_control);
+}
+
 void
 brw_byte_scattered_write(struct brw_codegen *p,
                          struct brw_reg payload,

src/intel/compiler/brw_fs.cpp

@@ -251,6 +251,7 @@ fs_inst::is_send_from_grf() const
    case SHADER_OPCODE_UNTYPED_SURFACE_READ:
    case SHADER_OPCODE_UNTYPED_SURFACE_WRITE:
    case SHADER_OPCODE_BYTE_SCATTERED_WRITE:
+   case SHADER_OPCODE_BYTE_SCATTERED_READ:
    case SHADER_OPCODE_TYPED_ATOMIC:
    case SHADER_OPCODE_TYPED_SURFACE_READ:
    case SHADER_OPCODE_TYPED_SURFACE_WRITE:
@@ -750,6 +751,18 @@ fs_inst::components_read(unsigned i) const
       else
          return 1;
 
+   case SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL:
+      /* Scattered logical opcodes use the following params:
+       * src[0] Surface coordinates
+       * src[1] Surface operation source (ignored for reads)
+       * src[2] Surface
+       * src[3] IMM with always 1 dimension.
+       * src[4] IMM with arg bitsize for scattered read/write 8, 16, 32
+       */
+      assert(src[3].file == IMM &&
+             src[4].file == IMM);
+      return i == 1 ? 0 : 1;
+
    case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL:
       assert(src[3].file == IMM &&
              src[4].file == IMM);
@@ -798,6 +811,7 @@ fs_inst::size_read(int arg) const
    case SHADER_OPCODE_TYPED_SURFACE_WRITE:
    case FS_OPCODE_INTERPOLATE_AT_PER_SLOT_OFFSET:
    case SHADER_OPCODE_BYTE_SCATTERED_WRITE:
+   case SHADER_OPCODE_BYTE_SCATTERED_READ:
       if (arg == 0)
          return mlen * REG_SIZE;
       break;
@@ -4545,6 +4559,12 @@ fs_visitor::lower_logical_sends()
                                     ibld.sample_mask_reg());
          break;
 
+      case SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL:
+         lower_surface_logical_send(ibld, inst,
+                                    SHADER_OPCODE_BYTE_SCATTERED_READ,
+                                    fs_reg());
+         break;
+
       case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL:
          lower_surface_logical_send(ibld, inst,
                                     SHADER_OPCODE_BYTE_SCATTERED_WRITE,
@@ -5036,6 +5056,7 @@ get_lowered_simd_width(const struct gen_device_info *devinfo,
    case SHADER_OPCODE_UNTYPED_SURFACE_READ_LOGICAL:
    case SHADER_OPCODE_UNTYPED_SURFACE_WRITE_LOGICAL:
    case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL:
+   case SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL:
       return MIN2(16, inst->exec_size);
 
    case SHADER_OPCODE_URB_READ_SIMD8:

src/intel/compiler/brw_fs_copy_propagation.cpp

@@ -656,6 +656,7 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry)
       case SHADER_OPCODE_TYPED_SURFACE_READ:
       case SHADER_OPCODE_TYPED_SURFACE_WRITE:
       case SHADER_OPCODE_BYTE_SCATTERED_WRITE:
+      case SHADER_OPCODE_BYTE_SCATTERED_READ:
          /* We only propagate into the surface argument of the
           * instruction. Everything else goes through LOAD_PAYLOAD.
           */
@@ -696,6 +697,7 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry)
       case SHADER_OPCODE_TYPED_SURFACE_READ_LOGICAL:
       case SHADER_OPCODE_TYPED_SURFACE_WRITE_LOGICAL:
       case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL:
+      case SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL:
          inst->src[i] = val;
          progress = true;
          break;

src/intel/compiler/brw_fs_generator.cpp

@@ -2086,6 +2086,12 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width)
                                    inst->mlen, src[2].ud);
          break;
 
+      case SHADER_OPCODE_BYTE_SCATTERED_READ:
+         assert(src[2].file == BRW_IMMEDIATE_VALUE);
+         brw_byte_scattered_read(p, dst, src[0], src[1],
+                                 inst->mlen, src[2].ud);
+         break;
+
       case SHADER_OPCODE_BYTE_SCATTERED_WRITE:
          assert(src[2].file == BRW_IMMEDIATE_VALUE);
          brw_byte_scattered_write(p, src[0], src[1],

src/intel/compiler/brw_fs_surface_builder.cpp

@@ -161,6 +161,16 @@ namespace brw {
                           addr, tmp, surface, dims, op, rsize);
       }
 
+      fs_reg
+      emit_byte_scattered_read(const fs_builder &bld,
+                               const fs_reg &surface, const fs_reg &addr,
+                               unsigned dims, unsigned size,
+                               unsigned bit_size, brw_predicate pred)
+      {
+         return emit_send(bld, SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL,
+                          addr, fs_reg(), surface, dims, bit_size, size, pred);
+      }
+
       void
       emit_byte_scattered_write(const fs_builder &bld, const fs_reg &surface,
                                 const fs_reg &addr, const fs_reg &src,
@@ -1202,4 +1212,3 @@ namespace brw {
       }
    }
 }
-

src/intel/compiler/brw_fs_surface_builder.h

@@ -64,6 +64,13 @@ namespace brw {
                         unsigned dims, unsigned rsize, unsigned op,
                         brw_predicate pred = BRW_PREDICATE_NONE);
 
+      fs_reg
+      emit_byte_scattered_read(const fs_builder &bld,
+                               const fs_reg &surface, const fs_reg &addr,
+                               unsigned dims, unsigned size,
+                               unsigned bit_size,
+                               brw_predicate pred = BRW_PREDICATE_NONE);
+
       void
       emit_byte_scattered_write(const fs_builder &bld, const fs_reg &surface,
                                 const fs_reg &addr, const fs_reg &src,

src/intel/compiler/brw_shader.cpp

@@ -293,6 +293,10 @@ brw_instruction_name(const struct gen_device_info *devinfo, enum opcode op)
    case SHADER_OPCODE_MEMORY_FENCE:
       return "memory_fence";
 
+   case SHADER_OPCODE_BYTE_SCATTERED_READ:
+      return "byte_scattered_read";
+   case SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL:
+      return "byte_scattered_read_logical";
    case SHADER_OPCODE_BYTE_SCATTERED_WRITE:
       return "byte_scattered_write";
    case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL:
@@ -999,6 +1003,8 @@ backend_instruction::is_volatile() const
    case SHADER_OPCODE_UNTYPED_SURFACE_READ_LOGICAL:
    case SHADER_OPCODE_TYPED_SURFACE_READ:
    case SHADER_OPCODE_TYPED_SURFACE_READ_LOGICAL:
+   case SHADER_OPCODE_BYTE_SCATTERED_READ:
+   case SHADER_OPCODE_BYTE_SCATTERED_READ_LOGICAL:
    case SHADER_OPCODE_URB_READ_SIMD8:
    case SHADER_OPCODE_URB_READ_SIMD8_PER_SLOT:
    case VEC4_OPCODE_URB_READ: