nak/sm70: allow first parameter of hfma2 to be non-reg
Either Rb or Rc can be the non-register, so the copy if both not reg should be sufficient. Totals: CodeSize: 14025216 -> 14022144 (-0.02%) Static cycle count: 5313517 -> 5312651 (-0.02%) Totals from 4 (0.30% of 1332) affected shaders: CodeSize: 119168 -> 116096 (-2.58%) Static cycle count: 33920 -> 33054 (-2.55%) Only affects: q2rtx/q2rtx-rt-pipeline 42 -0.48% -0.45% This also helps with the coop matrix shaders. Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36104>
This commit is contained in:
@@ -1086,7 +1086,6 @@ impl SM70Op for OpHFma2 {
|
||||
let [src0, src1, src2] = &mut self.srcs;
|
||||
swap_srcs_if_not_reg(src0, src1, gpr);
|
||||
b.copy_alu_src_if_not_reg(src0, gpr, SrcType::F16v2);
|
||||
b.copy_alu_src_if_not_reg(src1, gpr, SrcType::F16v2);
|
||||
b.copy_alu_src_if_both_not_reg(src1, src2, gpr, SrcType::F16v2);
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user