[LLVM][CodeGen][SVE] ASRD cannot represent sdiv-by-one. (#162708)

We lower signed divides by a power-of-two to ASRD. However, ASRD's
immediate is log2(shift_amount) in the range 1 to elt-bitwidth, which
means it cannot represent sdiv-by-one.

Fixes #162616

Author: paulwalker-arm

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -16249,7 +16249,9 @@ SDValue AArch64TargetLowering::LowerDIV(SDValue Op, SelectionDAG &DAG) const {
 
   bool Negated;
   uint64_t SplatVal;
-  if (Signed && isPow2Splat(Op.getOperand(1), SplatVal, Negated)) {
+  // NOTE: SRAD cannot be used to represent sdiv-by-one.
+  if (Signed && isPow2Splat(Op.getOperand(1), SplatVal, Negated) &&
+      SplatVal > 1) {
     SDValue Pg = getPredicateForScalableVector(DAG, DL, VT);
     SDValue Res =
         DAG.getNode(AArch64ISD::SRAD_MERGE_OP1, DL, VT, Pg, Op->getOperand(0),
@@ -30034,7 +30036,9 @@ SDValue AArch64TargetLowering::LowerFixedLengthVectorIntDivideToSVE(
 
   bool Negated;
   uint64_t SplatVal;
-  if (Signed && isPow2Splat(Op.getOperand(1), SplatVal, Negated)) {
+  // NOTE: SRAD cannot be used to represent sdiv-by-one.
+  if (Signed && isPow2Splat(Op.getOperand(1), SplatVal, Negated) &&
+      SplatVal > 1) {
     EVT ContainerVT = getContainerForFixedLengthVector(DAG, VT);
     SDValue Op1 = convertToScalableVector(DAG, ContainerVT, Op.getOperand(0));
     SDValue Op2 = DAG.getTargetConstant(Log2_64(SplatVal), DL, MVT::i32);

llvm/test/CodeGen/AArch64/sve-asrd.ll

@@ -0,0 +1,53 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc -mattr=+sve -combiner-disabled < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+; Ensure we don't try to represent sdiv-by-one using ARSD.
+define <16 x i16> @sdiv_by_one_v16i16(<16 x i16> %a) vscale_range(2,2) {
+; CHECK-LABEL: sdiv_by_one_v16i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    adrp x8, .LCPI0_0
+; CHECK-NEXT:    add x8, x8, :lo12:.LCPI0_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 def $z1
+; CHECK-NEXT:    // kill: def $q0 killed $q0 def $z0
+; CHECK-NEXT:    ld1h { z2.h }, p0/z, [x8]
+; CHECK-NEXT:    sunpklo z0.s, z0.h
+; CHECK-NEXT:    sunpklo z1.s, z1.h
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    sunpklo z3.s, z2.h
+; CHECK-NEXT:    ext z2.b, z2.b, z2.b, #16
+; CHECK-NEXT:    sunpklo z2.s, z2.h
+; CHECK-NEXT:    sdiv z0.s, p0/m, z0.s, z3.s
+; CHECK-NEXT:    sdiv z1.s, p0/m, z1.s, z2.s
+; CHECK-NEXT:    ptrue p0.h, vl8
+; CHECK-NEXT:    uzp1 z0.h, z0.h, z0.h
+; CHECK-NEXT:    uzp1 z1.h, z1.h, z1.h
+; CHECK-NEXT:    splice z0.h, p0, z0.h, z1.h
+; CHECK-NEXT:    movprfx z1, z0
+; CHECK-NEXT:    ext z1.b, z1.b, z0.b, #16
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $z0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $z1
+; CHECK-NEXT:    ret
+  %res = sdiv <16 x i16> %a, splat(i16 1)
+  ret <16 x i16> %res
+}
+
+; Ensure we don't try to represent sdiv-by-one using ARSD.
+define <vscale x 8 x i16> @sdiv_by_one_nxv8i16(<vscale x 8 x i16> %a) {
+; CHECK-LABEL: sdiv_by_one_nxv8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z1.h, #1 // =0x1
+; CHECK-NEXT:    sunpkhi z2.s, z0.h
+; CHECK-NEXT:    sunpklo z0.s, z0.h
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    sunpkhi z3.s, z1.h
+; CHECK-NEXT:    sunpklo z1.s, z1.h
+; CHECK-NEXT:    sdiv z2.s, p0/m, z2.s, z3.s
+; CHECK-NEXT:    sdiv z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT:    uzp1 z0.h, z0.h, z2.h
+; CHECK-NEXT:    ret
+  %res = sdiv <vscale x 8 x i16> %a, splat(i16 1)
+  ret <vscale x 8 x i16> %res
+}