On Sep 2, 2015 10:43 AM, "Mark Janes" <<a href="mailto:mark.a.janes@intel.com">mark.a.janes@intel.com</a>> wrote: > > Kenneth Graunke <<a href="mailto:kenneth@whitecape.org">kenneth@whitecape.org</a>> writes: > > > On Wednesday, September 02, 2015 12:03:12 AM Matt Turner wrote: > >> The lowered code reads from the destination, which isn't possible from > >> message registers. > >> > >> Fixes the dEQP functional.shaders.precision.int.highp_mul_fragment test > >> on SNB. > >> --- > >> src/mesa/drivers/dri/i965/brw_fs.cpp | 8 ++++---- > >> 1 file changed, 4 insertions(+), 4 deletions(-) > >> > >> diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp > >> index 269914d..e28eb5d 100644 > >> --- a/src/mesa/drivers/dri/i965/brw_fs.cpp > >> +++ b/src/mesa/drivers/dri/i965/brw_fs.cpp > >> @@ -3192,7 +3192,8 @@ fs_visitor::lower_integer_multiplication() > >> * schedule multi-component multiplications much better. > >> */ > >> > >> - if (inst->conditional_mod && inst->dst.is_null()) { > >> + fs_reg orig_dst = inst->dst; > >> + if (orig_dst.is_null() || orig_dst.file == MRF) { > >> inst->dst = fs_reg(GRF, alloc.allocate(dispatch_width / 8), > >> inst->dst.type); > >> } > >> @@ -3258,10 +3259,9 @@ fs_visitor::lower_integer_multiplication() > >> > >> ibld.ADD(dst, low, high); > >> > >> - if (inst->conditional_mod) { > >> - fs_reg null(retype(ibld.null_reg_f(), inst->dst.type)); > >> + if (inst->conditional_mod || orig_dst.file == MRF) { > >> set_condmod(inst->conditional_mod, > >> - ibld.MOV(null, inst->dst)); > >> + ibld.MOV(orig_dst, inst->dst)); > >> } > >> } > >> > >> > > > > Cc: "10.6 11.0" <<a href="mailto:mesa-stable@lists.freedesktop.org">mesa-stable@lists.freedesktop.org</a>> > > Reviewed-by: Kenneth Graunke <<a href="mailto:kenneth@whitecape.org">kenneth@whitecape.org</a>> > > The second hunk doesn't apply to 10.6. That's because this patch uses fs_builder which didn't exist in 10.6. It should be an easy back-port.