[X86][CodeGen] Fix crash when commute operands of Instruction for code size

llvm/lib/Target/X86/X86InstrInfo.cpp

@@ -2326,33 +2326,26 @@ MachineInstr *X86InstrInfo::commuteInstructionImpl(MachineInstr &MI, bool NewMI,
   case X86::VBLENDPSrri:
     // If we're optimizing for size, try to use MOVSD/MOVSS.
     if (MI.getParent()->getParent()->getFunction().hasOptSize()) {
-      unsigned Mask;
-      switch (Opc) {
-      default:
-        llvm_unreachable("Unreachable!");
-      case X86::BLENDPDrri:
-        Opc = X86::MOVSDrr;
-        Mask = 0x03;
-        break;
-      case X86::BLENDPSrri:
-        Opc = X86::MOVSSrr;
-        Mask = 0x0F;
-        break;
-      case X86::VBLENDPDrri:
-        Opc = X86::VMOVSDrr;
-        Mask = 0x03;
-        break;
-      case X86::VBLENDPSrri:
-        Opc = X86::VMOVSSrr;
-        Mask = 0x0F;
-        break;
-      }
+      unsigned Mask = (Opc == X86::BLENDPDrri || Opc == X86::VBLENDPDrri) ? 0x03: 0x0F;
       if ((MI.getOperand(3).getImm() ^ Mask) == 1) {
+#define FROM_TO(FROM, TO)                                                      \
+  case X86::FROM:                                                              \
+    Opc = X86::TO;                                                             \
+    break;
+        switch (Opc) {
+        default:
+          llvm_unreachable("Unreachable!");
+        FROM_TO(BLENDPDrri, MOVSDrr)
+        FROM_TO(BLENDPSrri, MOVSSrr)
+        FROM_TO(VBLENDPDrri, VMOVSDrr)
+        FROM_TO(VBLENDPSrri, VMOVSSrr)
+        }
         WorkingMI = CloneIfNew(MI);
         WorkingMI->setDesc(get(Opc));
         WorkingMI->removeOperand(3);
         break;
       }
+#undef FROM_TO
     }
     [[fallthrough]];
   case X86::PBLENDWrri:

llvm/test/CodeGen/X86/commute-blend-avx2.ll

@@ -88,3 +88,12 @@ define <4 x double> @commute_fold_vblendpd_256(<4 x double> %a, ptr %b) #0 {
   ret <4 x double> %2
 }
 declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
+
+define <4 x float> @commute_vblendpd_128_for_code_size(<4 x float> %a, <4 x float> %b) optsize {
+; CHECK-LABEL: commute_vblendpd_128_for_code_size:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
+; CHECK-NEXT:    retq
+  %r = shufflevector <4 x float> %b, <4 x float> %a, <4 x i32> <i32 0, i32 5, i32 2, i32 3>
+  ret <4 x float> %r
+}