Don't swap src operands if the swapping causes invalid datetype combination for mad instruction

Don't swap src0 and src1 of pseudo_mad instruction in HWConformity if the swapping
causes invalid datatype combination. For example:
pseudo_mad (32)  result1(0,0)<1>:d  x1(0,0)<2;0>:uw  r0.1<0;0>:d  z(0,0)<1;0>:d

In this case, we swap src0(actually src2) and src1 if src1 is scalar but src0 is
not, as src0(actually src2) has no regioning support:
pseudo_mad (32)  result1(0,0)<1>:d  r0.1<0;0>:d  x1(0,0)<2;0>:uw  z(0,0)<1;0>:d

After swapping, the datatype combination is invalid as it changes the datatype
combination from (W * D + D) to (D * W + D). If src2(actually src0) is D, HW only
supports (W * D + D).

Then we wouldn't generate mad, and we generate mul+add instead. But without this
swapping, actually we can generate mad as src0(actually src2) is aligned to dst.

Author: fangliu2020

visa/HWConformity.cpp

@@ -4220,7 +4220,10 @@ bool HWConformity::generateAlign1Mad(G4_BB *bb, INST_LIST_ITER iter) {
                src1->isSrcRegRegion() && src1->asSrcRegRegion()->isScalar()) {
       // Swap src0 and src1 if src1 is scalar but src0 is not, as src2 regioning
       // support is quite limited.
-      inst->swapSrc(0, 1);
+      // But don't swap if the swapping causes invalid datatype combination,
+      // e.g. src0(:w) * src1(:d) ->  src0(:d) * src1(:w)
+      if (IS_DTYPE(src0->getType()) || !IS_DTYPE(src1->getType()))
+        inst->swapSrc(0, 1);
     } else if (isLowPrecisionFloatTy(src0->getType()) &&
                src1->getType() == Type_F) {
       inst->swapSrc(0, 1);