diff options
author | Matt Turner <[email protected]> | 2017-10-23 10:44:39 -0700 |
---|---|---|
committer | Matt Turner <[email protected]> | 2018-02-28 11:15:47 -0800 |
commit | 3a584a15c0b1dd6c31a6520a0f749306f48d5782 (patch) | |
tree | 2d61172b60df79b1dd8c16422b65608652436ee4 /src/intel/compiler | |
parent | 432674ce93ceee2abd7e0cc4171bc36a499d4c1f (diff) |
intel/compiler/fs: Don't generate integer DWord multiply on Gen11
Like CHV et al., Gen11 does not support 32x32 -> 32/64-bit integer
multiplies.
Reviewed-by: Kenneth Graunke <[email protected]>
Diffstat (limited to 'src/intel/compiler')
-rw-r--r-- | src/intel/compiler/brw_fs.cpp | 6 |
1 files changed, 1 insertions, 5 deletions
diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp index bed632d21b9..113f62c46c7 100644 --- a/src/intel/compiler/brw_fs.cpp +++ b/src/intel/compiler/brw_fs.cpp @@ -3549,11 +3549,7 @@ fs_visitor::lower_integer_multiplication() inst->dst.type != BRW_REGISTER_TYPE_UD)) continue; - /* Gen8's MUL instruction can do a 32-bit x 32-bit -> 32-bit - * operation directly, but CHV/BXT cannot. - */ - if (devinfo->gen >= 8 && - !devinfo->is_cherryview && !gen_device_info_is_9lp(devinfo)) + if (devinfo->has_integer_dword_mul) continue; if (inst->src[1].file == IMM && |