i965/fs: Add emit_cs_terminate to emit CS_OPCODE_CS_TERMINATE

v2:
 * Do more work at the visitor level. g0 is loaded and sent to the
   generator now.

v3:
 * Use Ken's comment explaining g0 usage

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 6200deb72189585527bb6837441591383dc396fb..3d82adc1a2245d0b775dafdb5bf09ba35695df6a 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -388,6 +388,7 @@ public:
                                  bool use_2nd_half = false);
    void emit_fb_writes();
    void emit_urb_writes();
+   void emit_cs_terminate();
 
    void emit_shader_time_begin();
    void emit_shader_time_end();

diff --git a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
index f37fdea6978eddb9502851784874caa8c50426f9..01d4cbd1ac7ed7b92a7530f9af6a5876d7abf9fa 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_visitor.cpp
@@ -4156,6 +4156,28 @@ fs_visitor::resolve_ud_negate(fs_reg *reg)
    *reg = temp;
 }
 
+void
+fs_visitor::emit_cs_terminate()
+{
+   assert(brw->gen >= 7);
+
+   /* We are getting the thread ID from the compute shader header */
+   assert(stage == MESA_SHADER_COMPUTE);
+
+   /* We can't directly send from g0, since sends with EOT have to use
+    * g112-127. So, copy it to a virtual register, The register allocator will
+    * make sure it uses the appropriate register range.
+    */
+   struct brw_reg g0 = retype(brw_vec8_grf(0, 0), BRW_REGISTER_TYPE_UD);
+   fs_reg payload = fs_reg(GRF, alloc.allocate(1), BRW_REGISTER_TYPE_UD);
+   fs_inst *inst = emit(MOV(payload, g0));
+   inst->force_writemask_all = true;
+
+   /* Send a message to the thread spawner to terminate the thread. */
+   inst = emit(CS_OPCODE_CS_TERMINATE, reg_undef, payload);
+   inst->eot = true;
+}
+
 /**
  * Resolve the result of a Gen4-5 CMP instruction to a proper boolean.
  *