diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp @@ -1456,14 +1456,16 @@ if (ConstantSDNode *CIdx = dyn_cast(Idx)) { unsigned IdxVal = CIdx->getZExtValue(); - unsigned LoNumElts = Lo.getValueType().getVectorNumElements(); - if (IdxVal < LoNumElts) + unsigned LoNumElts = Lo.getValueType().getVectorMinNumElements(); + if (IdxVal < LoNumElts) { Lo = DAG.getNode(ISD::INSERT_VECTOR_ELT, dl, Lo.getValueType(), Lo, Elt, Idx); - else + return; + } else if (!Vec.getValueType().isScalableVector()) { Hi = DAG.getNode(ISD::INSERT_VECTOR_ELT, dl, Hi.getValueType(), Hi, Elt, DAG.getVectorIdxConstant(IdxVal - LoNumElts, dl)); - return; + return; + } } // See if the target wants to custom expand this node. @@ -1476,7 +1478,7 @@ if (VecVT.getScalarSizeInBits() < 8) { EltVT = MVT::i8; VecVT = EVT::getVectorVT(*DAG.getContext(), EltVT, - VecVT.getVectorNumElements()); + VecVT.getVectorElementCount()); Vec = DAG.getNode(ISD::ANY_EXTEND, dl, VecVT, Vec); // Extend the element type to match if needed. if (EltVT.bitsGT(Elt.getValueType())) @@ -1501,7 +1503,8 @@ SDValue EltPtr = TLI.getVectorElementPointer(DAG, StackPtr, VecVT, Idx); Store = DAG.getTruncStore( Store, dl, Elt, EltPtr, MachinePointerInfo::getUnknownStack(MF), EltVT, - commonAlignment(SmallestAlign, EltVT.getSizeInBits() / 8)); + commonAlignment(SmallestAlign, + EltVT.getSizeInBits().getFixedSize() / 8)); EVT LoVT, HiVT; std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(VecVT); @@ -1510,13 +1513,11 @@ Lo = DAG.getLoad(LoVT, dl, Store, StackPtr, PtrInfo, SmallestAlign); // Increment the pointer to the other part. - unsigned IncrementSize = LoVT.getSizeInBits() / 8; - StackPtr = - DAG.getMemBasePlusOffset(StackPtr, TypeSize::Fixed(IncrementSize), dl); + auto Load = cast(Lo); + MachinePointerInfo MPI = Load->getPointerInfo(); + IncrementPointer(Load, LoVT, MPI, StackPtr); - // Load the Hi part from the stack slot. - Hi = DAG.getLoad(HiVT, dl, Store, StackPtr, - PtrInfo.getWithOffset(IncrementSize), SmallestAlign); + Hi = DAG.getLoad(HiVT, dl, Store, StackPtr, MPI, SmallestAlign); // If we adjusted the original type, we need to truncate the results. std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(N->getValueType(0)); diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp @@ -2025,7 +2025,12 @@ SDValue SelectionDAG::CreateStackTemporary(TypeSize Bytes, Align Alignment) { MachineFrameInfo &MFI = MF->getFrameInfo(); - int FrameIdx = MFI.CreateStackObject(Bytes, Alignment, false); + const TargetFrameLowering *TFI = MF->getSubtarget().getFrameLowering(); + int StackID = 0; + if (Bytes.isScalable()) + StackID = TFI->getStackIDForScalableVectors(); + int FrameIdx = MFI.CreateStackObject(Bytes, Alignment, + false, nullptr, StackID); return getFrameIndex(FrameIdx, TLI->getFrameIndexTy(getDataLayout())); } @@ -5937,8 +5942,16 @@ const SDLoc &DL, const SDNodeFlags Flags) { EVT VT = Base.getValueType(); - return getMemBasePlusOffset(Base, getConstant(Offset.getFixedSize(), DL, VT), - DL, Flags); + SDValue Index; + + if (Offset.isScalable()) + Index = getVScale(DL, Base.getValueType(), + APInt(Base.getValueSizeInBits().getFixedSize(), + Offset.getKnownMinSize())); + else + Index = getConstant(Offset.getFixedSize(), DL, VT); + + return getMemBasePlusOffset(Base, Index, DL, Flags); } SDValue SelectionDAG::getMemBasePlusOffset(SDValue Ptr, SDValue Offset, diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp --- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp @@ -7197,16 +7197,26 @@ SDValue Idx, EVT VecVT, const SDLoc &dl) { - if (isa(Idx)) + if (!VecVT.isScalableVector() && isa(Idx)) return Idx; EVT IdxVT = Idx.getValueType(); - unsigned NElts = VecVT.getVectorNumElements(); - if (isPowerOf2_32(NElts)) { - APInt Imm = APInt::getLowBitsSet(IdxVT.getSizeInBits(), - Log2_32(NElts)); - return DAG.getNode(ISD::AND, dl, IdxVT, Idx, - DAG.getConstant(Imm, dl, IdxVT)); + unsigned NElts = VecVT.getVectorMinNumElements(); + if (VecVT.isScalableVector()) { + SDValue VS = DAG.getVScale(dl, IdxVT, + APInt(IdxVT.getSizeInBits().getFixedSize(), + NElts)); + SDValue Sub = DAG.getNode(ISD::SUB, dl, IdxVT, VS, + DAG.getConstant(1, dl, IdxVT)); + + return DAG.getNode(ISD::UMIN, dl, IdxVT, Idx, Sub); + } else { + if (isPowerOf2_32(NElts)) { + APInt Imm = APInt::getLowBitsSet(IdxVT.getSizeInBits(), + Log2_32(NElts)); + return DAG.getNode(ISD::AND, dl, IdxVT, Idx, + DAG.getConstant(Imm, dl, IdxVT)); + } } return DAG.getNode(ISD::UMIN, dl, IdxVT, Idx, @@ -7223,8 +7233,8 @@ EVT EltVT = VecVT.getVectorElementType(); // Calculate the element offset and add it to the pointer. - unsigned EltSize = EltVT.getSizeInBits() / 8; // FIXME: should be ABI size. - assert(EltSize * 8 == EltVT.getSizeInBits() && + unsigned EltSize = EltVT.getSizeInBits().getFixedSize() / 8; // FIXME: should be ABI size. + assert(EltSize * 8 == EltVT.getSizeInBits().getFixedSize() && "Converting bits to bytes lost precision"); Index = clampDynamicVectorIndex(DAG, Index, VecVT, dl); diff --git a/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll b/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll new file mode 100644 --- /dev/null +++ b/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll @@ -0,0 +1,186 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s + +; INSERT VECTOR ELT + +define @promote_insert_8i8( %a, i8 %elt, i64 %idx) { +; CHECK-LABEL: promote_insert_8i8: +; CHECK: // %bb.0: +; CHECK-NEXT: mov z1.h, w1 +; CHECK-NEXT: index z2.h, #0, #1 +; CHECK-NEXT: ptrue p0.h +; CHECK-NEXT: cmpeq p0.h, p0/z, z2.h, z1.h +; CHECK-NEXT: mov z0.h, p0/m, w0 +; CHECK-NEXT: ret + %ins = insertelement %a, i8 %elt, i64 %idx + ret %ins +} + +define @split_insert_32i8_idx( %a, i8 %elt, i64 %idx) { +; CHECK-LABEL: split_insert_32i8_idx: +; CHECK: // %bb.0: +; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: addvl sp, sp, #-2 +; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG +; CHECK-NEXT: .cfi_offset w29, -16 +; CHECK-NEXT: rdvl x8, #2 +; CHECK-NEXT: sub x8, x8, #1 // =1 +; CHECK-NEXT: cmp x1, x8 +; CHECK-NEXT: ptrue p0.b +; CHECK-NEXT: csel x8, x1, x8, lo +; CHECK-NEXT: mov x9, sp +; CHECK-NEXT: st1b { z1.b }, p0, [x9, #1, mul vl] +; CHECK-NEXT: st1b { z0.b }, p0, [sp] +; CHECK-NEXT: strb w0, [x9, x8] +; CHECK-NEXT: ld1b { z1.b }, p0/z, [x9, #1, mul vl] +; CHECK-NEXT: ld1b { z0.b }, p0/z, [sp] +; CHECK-NEXT: addvl sp, sp, #2 +; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret + %ins = insertelement %a, i8 %elt, i64 %idx + ret %ins +} + +define @split_insert_8f32_idx( %a, float %elt, i64 %idx) { +; CHECK-LABEL: split_insert_8f32_idx: +; CHECK: // %bb.0: +; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: addvl sp, sp, #-2 +; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG +; CHECK-NEXT: .cfi_offset w29, -16 +; CHECK-NEXT: cnth x8 +; CHECK-NEXT: sub x8, x8, #1 // =1 +; CHECK-NEXT: cmp x0, x8 +; CHECK-NEXT: ptrue p0.s +; CHECK-NEXT: csel x8, x0, x8, lo +; CHECK-NEXT: mov x9, sp +; CHECK-NEXT: st1w { z1.s }, p0, [x9, #1, mul vl] +; CHECK-NEXT: st1w { z0.s }, p0, [sp] +; CHECK-NEXT: str s2, [x9, x8, lsl #2] +; CHECK-NEXT: ld1w { z1.s }, p0/z, [x9, #1, mul vl] +; CHECK-NEXT: ld1w { z0.s }, p0/z, [sp] +; CHECK-NEXT: addvl sp, sp, #2 +; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret + %ins = insertelement %a, float %elt, i64 %idx + ret %ins +} + +define @split_insert_8i64_idx( %a, i64 %elt, i64 %idx) { +; CHECK-LABEL: split_insert_8i64_idx: +; CHECK: // %bb.0: +; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: addvl sp, sp, #-4 +; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG +; CHECK-NEXT: .cfi_offset w29, -16 +; CHECK-NEXT: cnth x8 +; CHECK-NEXT: sub x8, x8, #1 // =1 +; CHECK-NEXT: cmp x1, x8 +; CHECK-NEXT: ptrue p0.d +; CHECK-NEXT: csel x8, x1, x8, lo +; CHECK-NEXT: mov x9, sp +; CHECK-NEXT: st1d { z3.d }, p0, [x9, #3, mul vl] +; CHECK-NEXT: st1d { z2.d }, p0, [x9, #2, mul vl] +; CHECK-NEXT: st1d { z1.d }, p0, [x9, #1, mul vl] +; CHECK-NEXT: st1d { z0.d }, p0, [sp] +; CHECK-NEXT: str x0, [x9, x8, lsl #3] +; CHECK-NEXT: ld1d { z1.d }, p0/z, [x9, #1, mul vl] +; CHECK-NEXT: ld1d { z2.d }, p0/z, [x9, #2, mul vl] +; CHECK-NEXT: ld1d { z3.d }, p0/z, [x9, #3, mul vl] +; CHECK-NEXT: ld1d { z0.d }, p0/z, [sp] +; CHECK-NEXT: addvl sp, sp, #4 +; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret + %ins = insertelement %a, i64 %elt, i64 %idx + ret %ins +} + +; INSERT VECTOR ELT, CONSTANT IDX + +define @promote_insert_4i16( %a, i16 %elt) { +; CHECK-LABEL: promote_insert_4i16: +; CHECK: // %bb.0: +; CHECK-NEXT: mov w8, #5 +; CHECK-NEXT: index z1.s, #0, #1 +; CHECK-NEXT: mov z2.s, w8 +; CHECK-NEXT: ptrue p0.s +; CHECK-NEXT: cmpeq p0.s, p0/z, z1.s, z2.s +; CHECK-NEXT: mov z0.s, p0/m, w0 +; CHECK-NEXT: ret + %ins = insertelement %a, i16 %elt, i64 5 + ret %ins +} + +; In this test, the index is small enough that we know it will be in the +; low half of the vector and there is no need to go through the stack as +; done in the remaining tests +define @split_insert_32i8( %a, i8 %elt) { +; CHECK-LABEL: split_insert_32i8: +; CHECK: // %bb.0: +; CHECK-NEXT: mov w8, #3 +; CHECK-NEXT: index z2.b, #0, #1 +; CHECK-NEXT: mov z3.b, w8 +; CHECK-NEXT: ptrue p0.b +; CHECK-NEXT: cmpeq p0.b, p0/z, z2.b, z3.b +; CHECK-NEXT: mov z0.b, p0/m, w0 +; CHECK-NEXT: ret + %ins = insertelement %a, i8 %elt, i64 3 + ret %ins +} + +define @split_insert_32i16( %a, i16 %elt) { +; CHECK-LABEL: split_insert_32i16: +; CHECK: // %bb.0: +; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: addvl sp, sp, #-4 +; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG +; CHECK-NEXT: .cfi_offset w29, -16 +; CHECK-NEXT: rdvl x10, #2 +; CHECK-NEXT: sub x10, x10, #1 // =1 +; CHECK-NEXT: mov w9, #128 +; CHECK-NEXT: cmp x10, #128 // =128 +; CHECK-NEXT: ptrue p0.h +; CHECK-NEXT: mov x8, sp +; CHECK-NEXT: csel x9, x10, x9, lo +; CHECK-NEXT: st1h { z3.h }, p0, [x8, #3, mul vl] +; CHECK-NEXT: st1h { z2.h }, p0, [x8, #2, mul vl] +; CHECK-NEXT: st1h { z1.h }, p0, [x8, #1, mul vl] +; CHECK-NEXT: st1h { z0.h }, p0, [sp] +; CHECK-NEXT: strh w0, [x8, x9, lsl #1] +; CHECK-NEXT: ld1h { z1.h }, p0/z, [x8, #1, mul vl] +; CHECK-NEXT: ld1h { z2.h }, p0/z, [x8, #2, mul vl] +; CHECK-NEXT: ld1h { z3.h }, p0/z, [x8, #3, mul vl] +; CHECK-NEXT: ld1h { z0.h }, p0/z, [sp] +; CHECK-NEXT: addvl sp, sp, #4 +; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret + %ins = insertelement %a, i16 %elt, i64 128 + ret %ins +} + +define @split_insert_8i32( %a, i32 %elt) { +; CHECK-LABEL: split_insert_8i32: +; CHECK: // %bb.0: +; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: addvl sp, sp, #-2 +; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG +; CHECK-NEXT: .cfi_offset w29, -16 +; CHECK-NEXT: mov w9, #16960 +; CHECK-NEXT: cnth x10 +; CHECK-NEXT: movk w9, #15, lsl #16 +; CHECK-NEXT: sub x10, x10, #1 // =1 +; CHECK-NEXT: cmp x10, x9 +; CHECK-NEXT: ptrue p0.s +; CHECK-NEXT: mov x8, sp +; CHECK-NEXT: csel x9, x10, x9, lo +; CHECK-NEXT: st1w { z1.s }, p0, [x8, #1, mul vl] +; CHECK-NEXT: st1w { z0.s }, p0, [sp] +; CHECK-NEXT: str w0, [x8, x9, lsl #2] +; CHECK-NEXT: ld1w { z1.s }, p0/z, [x8, #1, mul vl] +; CHECK-NEXT: ld1w { z0.s }, p0/z, [sp] +; CHECK-NEXT: addvl sp, sp, #2 +; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret + %ins = insertelement %a, i32 %elt, i64 1000000 + ret %ins +}