OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

intel/fs: Lower dword integer multiplies on XeHP.

Browse Source 
From the BSpec:

 "When multiplying DW X DW, resulting dst can only be QW precision. If
 DW precision is required at output than MUL/MACH macro must be used."

So for now simply lower it. We might want to revisit it later.

Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10000>
This commit is contained in:
Rafael Antognolli
2019-01-29 16:34:30 -08:00
committed by Marge Bot
parent 3f50dde8b3
commit 49b2d9f428
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/intel/compiler/brw_fs.cpp
View File

@@ -4231,7 +4231,8 @@ fs_visitor::lower_integer_multiplication()
} else if (!inst->dst.is_accumulator() && } else if (!inst->dst.is_accumulator() &&
(inst->dst.type == BRW_REGISTER_TYPE_D || (inst->dst.type == BRW_REGISTER_TYPE_D ||
inst->dst.type == BRW_REGISTER_TYPE_UD) && inst->dst.type == BRW_REGISTER_TYPE_UD) &&
!devinfo->has_integer_dword_mul) { (!devinfo->has_integer_dword_mul ||
devinfo->verx10 >= 125)) {
lower_mul_dword_inst(inst, block); lower_mul_dword_inst(inst, block);
inst->remove(block); inst->remove(block);
progress = true; progress = true;