intel/fs: Rely on undocumented unrestricted regioning for 32x16-bit integer multiply.

Even though the hardware spec claims that any "integer DWord multiply"
operation is affected by the regioning restrictions of CHV/BXT/GLK,
this is inconsistent with the behavior of the simulator and with
empirical evidence -- Return false from has_dst_aligned_region_restriction()
for such instructions as a micro-optimization.

Tested-by: Anuj Phogat <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>

1 files changed, 11 insertions, 3 deletions

diff --git a/src/intel/compiler/brw_ir_fs.h b/src/intel/compiler/brw_ir_fs.h
index c4427a658b0..56a4bdc6e52 100644
--- a/src/intel/compiler/brw_ir_fs.h
+++ b/src/intel/compiler/brw_ir_fs.h
@@ -542,11 +542,19 @@ has_dst_aligned_region_restriction(const gen_device_info *devinfo,
                                    const fs_inst *inst)
 {
    const brw_reg_type exec_type = get_exec_type(inst);
-   const bool is_int_multiply = !brw_reg_type_is_floating_point(exec_type) &&
-         (inst->opcode == BRW_OPCODE_MUL || inst->opcode == BRW_OPCODE_MAD);
+   /* Even though the hardware spec claims that "integer DWord multiply"
+    * operations are restricted, empirical evidence and the behavior of the
+    * simulator suggest that only 32x32-bit integer multiplication is
+    * restricted.
+    */
+   const bool is_dword_multiply = !brw_reg_type_is_floating_point(exec_type) &&
+      ((inst->opcode == BRW_OPCODE_MUL &&
+        MIN2(type_sz(inst->src[0].type), type_sz(inst->src[1].type)) >= 4) ||
+       (inst->opcode == BRW_OPCODE_MAD &&
+        MIN2(type_sz(inst->src[1].type), type_sz(inst->src[2].type)) >= 4));
 
    if (type_sz(inst->dst.type) > 4 || type_sz(exec_type) > 4 ||
-       (type_sz(exec_type) == 4 && is_int_multiply))
+       (type_sz(exec_type) == 4 && is_dword_multiply))
       return devinfo->is_cherryview || gen_device_info_is_9lp(devinfo);
    else
       return false;