[X86] Remove and autoupgrade the scalar fma intrinsics with masking.

This converts them to what clang is now using for codegen. Unfortunately, there seem to be a few kinks to work out still. I'll try to address with follow up patches.

llvm-svn: 336871

2 files changed, 0 insertions, 47 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 29ae67af7b7..cdf5746bb97 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -2535,16 +2535,6 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
   case Intrinsic::x86_avx512_mask_min_ss_round:
   case Intrinsic::x86_avx512_mask_max_sd_round:
   case Intrinsic::x86_avx512_mask_min_sd_round:
-  case Intrinsic::x86_avx512_mask_vfmadd_ss:
-  case Intrinsic::x86_avx512_mask_vfmadd_sd:
-  case Intrinsic::x86_avx512_maskz_vfmadd_ss:
-  case Intrinsic::x86_avx512_maskz_vfmadd_sd:
-  case Intrinsic::x86_avx512_mask3_vfmadd_ss:
-  case Intrinsic::x86_avx512_mask3_vfmadd_sd:
-  case Intrinsic::x86_avx512_mask3_vfmsub_ss:
-  case Intrinsic::x86_avx512_mask3_vfmsub_sd:
-  case Intrinsic::x86_avx512_mask3_vfnmsub_ss:
-  case Intrinsic::x86_avx512_mask3_vfnmsub_sd:
   case Intrinsic::x86_sse_cmp_ss:
   case Intrinsic::x86_sse_min_ss:
   case Intrinsic::x86_sse_max_ss:
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
index 97d24019eb6..425f5ce384b 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
@@ -1497,10 +1497,6 @@ Value *InstCombiner::SimplifyDemandedVectorElts(Value *V, APInt DemandedElts,
     case Intrinsic::x86_avx512_mask_sub_sd_round:
     case Intrinsic::x86_avx512_mask_max_sd_round:
     case Intrinsic::x86_avx512_mask_min_sd_round:
-    case Intrinsic::x86_avx512_mask_vfmadd_ss:
-    case Intrinsic::x86_avx512_mask_vfmadd_sd:
-    case Intrinsic::x86_avx512_maskz_vfmadd_ss:
-    case Intrinsic::x86_avx512_maskz_vfmadd_sd:
       TmpV = SimplifyDemandedVectorElts(II->getArgOperand(0), DemandedElts,
                                         UndefElts, Depth + 1);
       if (TmpV) { II->setArgOperand(0, TmpV); MadeChange = true; }
@@ -1527,39 +1523,6 @@ Value *InstCombiner::SimplifyDemandedVectorElts(Value *V, APInt DemandedElts,
 
       break;
 
-    case Intrinsic::x86_avx512_mask3_vfmadd_ss:
-    case Intrinsic::x86_avx512_mask3_vfmadd_sd:
-    case Intrinsic::x86_avx512_mask3_vfmsub_ss:
-    case Intrinsic::x86_avx512_mask3_vfmsub_sd:
-    case Intrinsic::x86_avx512_mask3_vfnmsub_ss:
-    case Intrinsic::x86_avx512_mask3_vfnmsub_sd:
-      // These intrinsics get the passthru bits from operand 2.
-      TmpV = SimplifyDemandedVectorElts(II->getArgOperand(2), DemandedElts,
-                                        UndefElts, Depth + 1);
-      if (TmpV) { II->setArgOperand(2, TmpV); MadeChange = true; }
-
-      // If lowest element of a scalar op isn't used then use Arg2.
-      if (!DemandedElts[0]) {
-        Worklist.Add(II);
-        return II->getArgOperand(2);
-      }
-
-      // Only lower element is used for operand 0 and 1.
-      DemandedElts = 1;
-      TmpV = SimplifyDemandedVectorElts(II->getArgOperand(0), DemandedElts,
-                                        UndefElts2, Depth + 1);
-      if (TmpV) { II->setArgOperand(0, TmpV); MadeChange = true; }
-      TmpV = SimplifyDemandedVectorElts(II->getArgOperand(1), DemandedElts,
-                                        UndefElts3, Depth + 1);
-      if (TmpV) { II->setArgOperand(1, TmpV); MadeChange = true; }
-
-      // Lower element is undefined if all three lower elements are undefined.
-      // Consider things like undef&0.  The result is known zero, not undef.
-      if (!UndefElts2[0] || !UndefElts3[0])
-        UndefElts.clearBit(0);
-
-      break;
-
     case Intrinsic::x86_sse2_packssdw_128:
     case Intrinsic::x86_sse2_packsswb_128:
     case Intrinsic::x86_sse2_packuswb_128: