[AArch64] Generate BSP instead of TBL for select shuffles. (#121474)

In using BIF/BIT/BSL the constant mask has a larger chance of being
regular, being able to be materialized with a movi. On some cpus the
BIF/BIT/BSL is slightly quicker too.

Author: davemgreen

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -14004,6 +14004,23 @@ SDValue AArch64TargetLowering::LowerVECTOR_SHUFFLE(SDValue Op,
                                   dl);
   }
 
+  // Check for a "select shuffle", generating a BSL to pick between lanes in
+  // V1/V2.
+  if (ShuffleVectorInst::isSelectMask(ShuffleMask, NumElts)) {
+    assert(VT.getScalarSizeInBits() <= 32 &&
+           "Expected larger vector element sizes to be handled already");
+    SmallVector<SDValue> MaskElts;
+    for (int M : ShuffleMask)
+      MaskElts.push_back(DAG.getConstant(
+          M >= static_cast<int>(NumElts) ? 0 : 0xffffffff, dl, MVT::i32));
+    EVT IVT = VT.changeVectorElementTypeToInteger();
+    SDValue MaskConst = DAG.getBuildVector(IVT, dl, MaskElts);
+    return DAG.getBitcast(VT, DAG.getNode(AArch64ISD::BSP, dl, IVT, MaskConst,
+                                          DAG.getBitcast(IVT, V1),
+                                          DAG.getBitcast(IVT, V2)));
+  }
+
+  // Fall back to generating a TBL
   return GenerateTBL(Op, ShuffleMask, DAG);
 }
 

llvm/test/CodeGen/AArch64/arm64-neon-3vdiff.ll

@@ -2537,14 +2537,13 @@ entry:
 define <8 x i16> @cmplx_mul_combined_re_im(<8 x i16> noundef %a, i64 %scale.coerce) {
 ; CHECK-LABEL: cmplx_mul_combined_re_im:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    lsr x9, x0, #16
-; CHECK-NEXT:    adrp x8, .LCPI196_0
+; CHECK-NEXT:    lsr x8, x0, #16
+; CHECK-NEXT:    movi v1.2d, #0xffff0000ffff0000
 ; CHECK-NEXT:    fmov d5, x0
-; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI196_0]
 ; CHECK-NEXT:    rev32 v4.8h, v0.8h
-; CHECK-NEXT:    dup v1.8h, w9
-; CHECK-NEXT:    sqneg v2.8h, v1.8h
-; CHECK-NEXT:    tbl v1.16b, { v1.16b, v2.16b }, v3.16b
+; CHECK-NEXT:    dup v2.8h, w8
+; CHECK-NEXT:    sqneg v3.8h, v2.8h
+; CHECK-NEXT:    bsl v1.16b, v2.16b, v3.16b
 ; CHECK-NEXT:    sqdmull v2.4s, v0.4h, v5.h[0]
 ; CHECK-NEXT:    sqdmull2 v0.4s, v0.8h, v5.h[0]
 ; CHECK-NEXT:    sqdmlal v2.4s, v4.4h, v1.4h

llvm/test/CodeGen/AArch64/shuffle-select.ll

@@ -4,12 +4,8 @@
 define <8 x i8> @sel_v8i8(<8 x i8> %v0, <8 x i8> %v1) {
 ; CHECK-LABEL: sel_v8i8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
-; CHECK-NEXT:    adrp x8, .LCPI0_0
-; CHECK-NEXT:    mov v0.d[1], v1.d[0]
-; CHECK-NEXT:    ldr d1, [x8, :lo12:.LCPI0_0]
-; CHECK-NEXT:    tbl v0.8b, { v0.16b }, v1.8b
+; CHECK-NEXT:    movi d2, #0xff00ff00ff00ff
+; CHECK-NEXT:    bif v0.8b, v1.8b, v2.8b
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
   ret <8 x i8> %tmp0
@@ -18,11 +14,8 @@ define <8 x i8> @sel_v8i8(<8 x i8> %v0, <8 x i8> %v1) {
 define <16 x i8> @sel_v16i8(<16 x i8> %v0, <16 x i8> %v1) {
 ; CHECK-LABEL: sel_v16i8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    adrp x8, .LCPI1_0
-; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI1_0]
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    movi v2.2d, #0xff00ff00ff00ff
+; CHECK-NEXT:    bif v0.16b, v1.16b, v2.16b
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
   ret <16 x i8> %tmp0
@@ -32,10 +25,8 @@ define <16 x i8> @sel_v16i8_poison(<16 x i8> %v0, <16 x i8> %v1) {
 ; CHECK-LABEL: sel_v16i8_poison:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    adrp x8, .LCPI2_0
-; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
 ; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI2_0]
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    bif v0.16b, v1.16b, v2.16b
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 22, i32 23, i32 24, i32 25, i32 26, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
   ret <16 x i8> %tmp0
@@ -45,10 +36,8 @@ define <16 x i8> @sel_v16i8_unregular(<16 x i8> %v0, <16 x i8> %v1) {
 ; CHECK-LABEL: sel_v16i8_unregular:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    adrp x8, .LCPI3_0
-; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
 ; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI3_0]
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    bif v0.16b, v1.16b, v2.16b
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 27, i32 28, i32 29, i32 30, i32 31>
   ret <16 x i8> %tmp0
@@ -67,11 +56,8 @@ define <4 x i16> @sel_v4i16(<4 x i16> %v0, <4 x i16> %v1) {
 define <8 x i16> @sel_v8i16(<8 x i16> %v0, <8 x i16> %v1) {
 ; CHECK-LABEL: sel_v8i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    adrp x8, .LCPI5_0
-; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI5_0]
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    movi v2.2d, #0x00ffff0000ffff
+; CHECK-NEXT:    bif v0.16b, v1.16b, v2.16b
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
   ret <8 x i16> %tmp0
@@ -121,11 +107,8 @@ define <4 x half> @sel_v4f16(<4 x half> %v0, <4 x half> %v1) {
 define <8 x half> @sel_v8f16(<8 x half> %v0, <8 x half> %v1) {
 ; CHECK-LABEL: sel_v8f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    adrp x8, .LCPI10_0
-; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI10_0]
-; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
-; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    movi v2.2d, #0x00ffff0000ffff
+; CHECK-NEXT:    bif v0.16b, v1.16b, v2.16b
 ; CHECK-NEXT:    ret
   %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
   ret <8 x half> %tmp0