diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 053046b..b7a9d14 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -588,6 +588,10 @@ public:
 
 private:
    void generate_code(exec_list *instructions, FILE *dump_file);
+   void fire_fb_write(fs_inst *inst,
+                      GLuint base_reg,
+                      struct brw_reg implied_header,
+                      GLuint nr);
    void generate_fb_write(fs_inst *inst);
    void generate_blorp_fb_write(fs_inst *inst);
    void generate_pixel_xy(struct brw_reg dst, bool is_x);
diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index ff85171..5dc630e 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -92,11 +92,47 @@ fs_generator::patch_discard_jumps_to_fb_writes()
 }
 
 void
+fs_generator::fire_fb_write(fs_inst *inst,
+                            GLuint base_reg,
+                            struct brw_reg implied_header,
+                            GLuint nr)
+{
+   uint32_t msg_control;
+
+   if (brw->gen < 6) {
+      brw_MOV(p,
+              brw_message_reg(base_reg + 1),
+              brw_vec8_grf(1, 0));
+   }
+
+   if (this->dual_source_output)
+      msg_control = BRW_DATAPORT_RENDER_TARGET_WRITE_SIMD8_DUAL_SOURCE_SUBSPAN01;
+   else if (dispatch_width == 16)
+      msg_control = BRW_DATAPORT_RENDER_TARGET_WRITE_SIMD16_SINGLE_SOURCE;
+   else
+      msg_control = BRW_DATAPORT_RENDER_TARGET_WRITE_SIMD8_SINGLE_SOURCE_SUBSPAN01;
+
+   uint32_t surf_index =
+      c->prog_data.binding_table.render_target_start + inst->target;
+
+   brw_fb_WRITE(p,
+                dispatch_width,
+                base_reg,
+                implied_header,
+                msg_control,
+                surf_index,
+                nr,
+                0,
+                inst->eot,
+                inst->header_present);
+
+   brw_mark_surface_used(&c->prog_data.base, surf_index);
+}
+
+void
 fs_generator::generate_fb_write(fs_inst *inst)
 {
-   bool eot = inst->eot;
    struct brw_reg implied_header;
-   uint32_t msg_control;
 
    /* Header is 2 regs, g0 and g1 are the contents. g0 will be implied
     * move, here's g1.
@@ -149,38 +185,66 @@ fs_generator::generate_fb_write(fs_inst *inst)
 	 implied_header = brw_null_reg();
       } else {
 	 implied_header = retype(brw_vec8_grf(0, 0), BRW_REGISTER_TYPE_UW);
-
-	 brw_MOV(p,
-		 brw_message_reg(inst->base_mrf + 1),
-		 brw_vec8_grf(1, 0));
       }
    } else {
       implied_header = brw_null_reg();
    }
 
-   if (this->dual_source_output)
-      msg_control = BRW_DATAPORT_RENDER_TARGET_WRITE_SIMD8_DUAL_SOURCE_SUBSPAN01;
-   else if (dispatch_width == 16)
-      msg_control = BRW_DATAPORT_RENDER_TARGET_WRITE_SIMD16_SINGLE_SOURCE;
-   else
-      msg_control = BRW_DATAPORT_RENDER_TARGET_WRITE_SIMD8_SINGLE_SOURCE_SUBSPAN01;
+   if (!c->runtime_check_aads_emit) {
+      fire_fb_write(inst, inst->base_mrf, implied_header, inst->mlen);
+   } else {
+      /* This can only happen in Gen < 6
+       */
+      bool tryJMPI = getenv("INTEL_AA_TRY_JMPI") != NULL;
+      if (tryJMPI) {
+         fprintf(stderr, "Using JMPI to do AA runtime checks...\n");
+         struct brw_reg v1_null_ud = vec1(retype(brw_null_reg(), BRW_REGISTER_TYPE_UD));
+         struct brw_reg ip = brw_ip_reg();
+         int jmp;
 
-   brw_pop_insn_state(p);
+         brw_set_compression_control(p, BRW_COMPRESSION_NONE);
+         brw_set_conditionalmod(p, BRW_CONDITIONAL_NZ);
+         brw_AND(p,
+                 v1_null_ud,
+                 get_element_ud(brw_vec8_grf(1,0), 6),
+                 brw_imm_ud(1<<26));
+         jmp = brw_JMPI(p, ip, ip, brw_imm_ud(0)) - p->store;
+         {
+            fire_fb_write(inst, inst->base_mrf+1, implied_header, inst->mlen-1);
+         }
+         brw_land_fwd_jump(p, jmp);
+         fire_fb_write(inst, inst->base_mrf, implied_header, inst->mlen);
+      } else {
+         fprintf(stderr, "Using IF/ELSE/ENDIF to do AA runtime checks...\n");
+         struct brw_reg v1_null_ud = vec1(retype(brw_null_reg(), BRW_REGISTER_TYPE_UD));
+         struct brw_reg tmp_reg_ud = brw_vec1_grf(BRW_MAX_GRF-1, 0);
 
-   uint32_t surf_index =
-      c->prog_data.binding_table.render_target_start + inst->target;
-   brw_fb_WRITE(p,
-		dispatch_width,
-		inst->base_mrf,
-		implied_header,
-		msg_control,
-		surf_index,
-		inst->mlen,
-		0,
-		eot,
-		inst->header_present);
+         brw_set_compression_control(p, BRW_COMPRESSION_NONE);
+         brw_AND(p,
+                 tmp_reg_ud,
+                 get_element_ud(brw_vec8_grf(1,0), 6),
+                 brw_imm_ud(1<<26));
+         brw_CMP(p,
+                 v1_null_ud,
+                 BRW_CONDITIONAL_Z,
+                 tmp_reg_ud,
+                 brw_imm_ud(0));
+         brw_IF(p, BRW_EXECUTE_1);
+         {
+            /* Shift message header one register since we are not sending
+             * AA data stored in inst->base_mrf+2
+             */
+            fire_fb_write(inst, inst->base_mrf+1, implied_header, inst->mlen-1);
+         }
+         brw_ELSE(p);
+         {
+            fire_fb_write(inst, inst->base_mrf, implied_header, inst->mlen);
+         }
+         brw_ENDIF(p);
+      }
+   }
 
-   brw_mark_surface_used(&c->prog_data.base, surf_index);
+   brw_pop_insn_state(p);
 }
 
 void