i965/cs: Add generator support for CS_OPCODE_CS_TERMINATE

v2:
 * Don't rely on brw_eu* to generate the send instruction. We now
   generate the send here, and drop the "i965/cs: Add support for the
   SEND message that terminates a CS thread" brw_eu* patch.

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 3d82adc1a2245d0b775dafdb5bf09ba35695df6a..4adde66b6fdade81406b04f39e64497bd7347c17 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -557,6 +557,7 @@ private:
                       GLuint nr);
    void generate_fb_write(fs_inst *inst, 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_blorp_fb_write(fs_inst *inst);
    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 3bfee7eb7decc2eb6f29af2c8654c87ac0884267..9ddba3a26dc2ad66a92af7ed8aae8bb5a43d930e 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -369,6 +369,37 @@ fs_generator::generate_urb_write(fs_inst *inst, struct brw_reg payload)
    brw_inst_set_urb_global_offset(p->devinfo, insn, inst->offset);
 }
 
+void
+fs_generator::generate_cs_terminate(fs_inst *inst, struct brw_reg payload)
+{
+   struct brw_inst *insn;
+
+   insn = brw_next_insn(p, BRW_OPCODE_SEND);
+
+   brw_set_dest(p, insn, brw_null_reg());
+   brw_set_src0(p, insn, payload);
+   brw_set_src1(p, insn, brw_imm_d(0));
+
+   /* Terminate a compute shader by sending a message to the thread spawner.
+    */
+   brw_inst_set_sfid(devinfo, insn, BRW_SFID_THREAD_SPAWNER);
+   brw_inst_set_mlen(devinfo, insn, 1);
+   brw_inst_set_rlen(devinfo, insn, 0);
+   brw_inst_set_eot(devinfo, insn, inst->eot);
+   brw_inst_set_header_present(devinfo, insn, false);
+
+   brw_inst_set_ts_opcode(devinfo, insn, 0); /* Dereference resource */
+   brw_inst_set_ts_request_type(devinfo, insn, 0); /* Root thread */
+
+   /* Note that even though the thread has a URB resource associated with it,
+    * we set the "do not dereference URB" bit, because the URB resource is
+    * managed by the fixed-function unit, so it will free it automatically.
+    */
+   brw_inst_set_ts_resource_select(devinfo, insn, 1); /* Do not dereference URB */
+
+   brw_inst_set_mask_control(devinfo, insn, BRW_MASK_DISABLE);
+}
+
 void
 fs_generator::generate_blorp_fb_write(fs_inst *inst)
 {
@@ -2074,6 +2105,10 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width)
                                            GEN7_PIXEL_INTERPOLATOR_LOC_PER_SLOT_OFFSET);
          break;
 
+      case CS_OPCODE_CS_TERMINATE:
+         generate_cs_terminate(inst, src[0]);
+         break;
+
       default:
          unreachable("Unsupported opcode");