[PowerPC] Fix vector equality comparison for v2i64 pre-Power8

[nemanjai]

Summary

The current code makes the assumption that equality comparison can be performed with a word comparison instruction. While this is true if the entire 64-bit results are used, it does not generally work. It is possible that the low order words and high order words produce different results and a user of only one will get the wrong result.

This patch adds an and of the result words so that each word has the result of the comparison of the entire doubleword that contains it.

[bmahjour]

Shall we also add a test for -mcpu=pwr8 to make sure vcmpequd is used?

LGTM otherwise.

[nemanjai]

In D115678#3193324, @bmahjour wrote:

Shall we also add a test for -mcpu=pwr8 to make sure vcmpequd is used?

LGTM otherwise.

That's a good idea. I'll add it on the commit. Thank you.

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

SDValue PPCTargetLowering::LowerSETCC(SDValue Op, SelectionDAG &DAG) const {
   assert(!IsStrict && "Don't know how to handle STRICT_FSETCC!");
 
   if (Op.getValueType() == MVT::v2i64) {
     // When the operands themselves are v2i64 values, we need to do something
     // special because VSX has no underlying comparison operations for these.
     if (LHS.getValueType() == MVT::v2i64) {
       // Equality can be handled by casting to the legal type for Altivec
       // comparisons, everything else needs to be expanded.
-      if (CC == ISD::SETEQ || CC == ISD::SETNE) {
-        return DAG.getNode(
-            ISD::BITCAST, dl, MVT::v2i64,
-            DAG.getSetCC(dl, MVT::v4i32,
-                         DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, LHS),
-                         DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, RHS), CC));
-      }
-
+      if (CC != ISD::SETEQ && CC != ISD::SETNE)
         return SDValue();
+      SDValue SetCC32 = DAG.getSetCC(
+          dl, MVT::v4i32, DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, LHS),
+          DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, RHS), CC);
+      int ShuffV[] = {1, 0, 3, 2};
+      SDValue Shuff =
+          DAG.getVectorShuffle(MVT::v4i32, dl, SetCC32, SetCC32, ShuffV);
+      return DAG.getBitcast(
+          MVT::v2i64, DAG.getNode(ISD::AND, dl, MVT::v4i32, Shuff, SetCC32));
     }
 
     // We handle most of these in the usual way.
     return Op;
   }
 
   // If we're comparing for equality to zero, expose the fact that this is
   // implemented as a ctlz/srl pair on ppc, so that the dag combiner can

llvm/test/CodeGen/PowerPC/vec-icmpeq-v2i64-p7.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mtriple=powerpc-aix- < %s | \
+; RUN:   FileCheck %s
+; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mtriple=powerpc64le-- < %s | \
+; RUN:   FileCheck %s --check-prefix=CHECK_LE
+; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-- < %s | \
+; RUN:   FileCheck %s --check-prefix=CHECK_P8LE
+define i1 @foo(<2 x i64> %a) #0 {
+; CHECK-LABEL: foo:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xxswapd 35, 34
+; CHECK-NEXT:    lwz 3, L..C0(2) # %const.0
+; CHECK-NEXT:    vcmpequw 2, 2, 3
+; CHECK-NEXT:    lxvw4x 35, 0, 3
+; CHECK-NEXT:    addi 3, 1, -16
+; CHECK-NEXT:    vperm 3, 2, 2, 3
+; CHECK-NEXT:    xxland 0, 35, 34
+; CHECK-NEXT:    stxvw4x 0, 0, 3
+; CHECK-NEXT:    lwz 3, -12(1)
+; CHECK-NEXT:    blr
+;
+; CHECK_LE-LABEL: foo:
+; CHECK_LE:       # %bb.0: # %entry
+; CHECK_LE-NEXT:    xxswapd 35, 34
+; CHECK_LE-NEXT:    addis 3, 2, .LCPI0_0@toc@ha
+; CHECK_LE-NEXT:    addi 3, 3, .LCPI0_0@toc@l
+; CHECK_LE-NEXT:    vcmpequw 2, 2, 3
+; CHECK_LE-NEXT:    lvx 3, 0, 3
+; CHECK_LE-NEXT:    addi 3, 1, -16
+; CHECK_LE-NEXT:    vperm 3, 2, 2, 3
+; CHECK_LE-NEXT:    xxland 34, 35, 34
+; CHECK_LE-NEXT:    stvx 2, 0, 3
+; CHECK_LE-NEXT:    ld 3, -16(1)
+; CHECK_LE-NEXT:    blr
+;
+; CHECK_P8LE-LABEL: foo:
+; CHECK_P8LE:       # %bb.0: # %entry
+; CHECK_P8LE-NEXT:    xxswapd 35, 34
+; CHECK_P8LE-NEXT:    vcmpequd 2, 2, 3
+; CHECK_P8LE-NEXT:    xxswapd 0, 34
+; CHECK_P8LE-NEXT:    mffprd 3, 0
+; CHECK_P8LE-NEXT:    blr
+entry:
+  %0 = shufflevector <2 x i64> %a, <2 x i64> poison, <2 x i32> <i32 1, i32 undef>
+  %1 = icmp eq <2 x i64> %a, %0
+  %2 = extractelement <2 x i1> %1, i32 0
+  ret i1 %2
+}