[llvm] [GISel][AArch64] Added more efficient lowering of Bitreverse (PR #139233)

[David Green via llvm-commits]

================
@@ -8985,49 +8985,62 @@ static MachineInstrBuilder SwapN(unsigned N, DstOp Dst, MachineIRBuilder &B,
 LegalizerHelper::LegalizeResult
 LegalizerHelper::lowerBitreverse(MachineInstr &MI) {
   auto [Dst, Src] = MI.getFirst2Regs();
-  const LLT Ty = MRI.getType(Src);
-  unsigned Size = Ty.getScalarSizeInBits();
+  const LLT SrcTy = MRI.getType(Src);
+  unsigned Size = SrcTy.getScalarSizeInBits();
+  unsigned VSize = SrcTy.getSizeInBits();
 
   if (Size >= 8) {
-    MachineInstrBuilder BSWAP =
-        MIRBuilder.buildInstr(TargetOpcode::G_BSWAP, {Ty}, {Src});
-
-    // swap high and low 4 bits in 8 bit blocks 7654|3210 -> 3210|7654
-    //    [(val & 0xF0F0F0F0) >> 4] | [(val & 0x0F0F0F0F) << 4]
-    // -> [(val & 0xF0F0F0F0) >> 4] | [(val << 4) & 0xF0F0F0F0]
-    MachineInstrBuilder Swap4 =
-        SwapN(4, Ty, MIRBuilder, BSWAP, APInt::getSplat(Size, APInt(8, 0xF0)));
-
-    // swap high and low 2 bits in 4 bit blocks 32|10 76|54 -> 10|32 54|76
-    //    [(val & 0xCCCCCCCC) >> 2] & [(val & 0x33333333) << 2]
-    // -> [(val & 0xCCCCCCCC) >> 2] & [(val << 2) & 0xCCCCCCCC]
-    MachineInstrBuilder Swap2 =
-        SwapN(2, Ty, MIRBuilder, Swap4, APInt::getSplat(Size, APInt(8, 0xCC)));
-
-    // swap high and low 1 bit in 2 bit blocks 1|0 3|2 5|4 7|6 -> 0|1 2|3 4|5
-    // 6|7
-    //    [(val & 0xAAAAAAAA) >> 1] & [(val & 0x55555555) << 1]
-    // -> [(val & 0xAAAAAAAA) >> 1] & [(val << 1) & 0xAAAAAAAA]
-    SwapN(1, Dst, MIRBuilder, Swap2, APInt::getSplat(Size, APInt(8, 0xAA)));
+    LLT VTy = LLT::fixed_vector(VSize / 8, 8);
+
+    if (LI.isLegal({TargetOpcode::G_BITREVERSE, {VTy, VTy}})) {
----------------
davemgreen wrote:

Is it worth checking that `[Elt]Size % 8 == 0` too?

https://github.com/llvm/llvm-project/pull/139233