maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[ISEL] Canonicalize STEP_VECTOR to LHS if RHS is a splat. 

This helps recognise patterns where we're trying to match STEP_VECTOR
patterns to INDEX instructions that take a GPR for the Start/Step.

The reason for canonicalising this operation to the LHS is
because it will already be canonicalised to the LHS if the RHS
is a constant splat vector.

Reviewed By: paulwalker-arm

Differential Revision: https://reviews.llvm.org/D118459
This commit is contained in:
Sander de Smalen 2022-02-03 08:59:49 +00:00
parent 78bf2e0a3f
commit 01bfe9729a
4 changed files with 60 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/include/llvm/CodeGen/SelectionDAG.h
View File

@ -1412,6 +1412,11 @@ public:
/// Return an AssertAlignSDNode.
SDValue getAssertAlign(const SDLoc &DL, SDValue V, Align A);
/// Swap N1 and N2 if Opcode is a commutative binary opcode
/// and the canonical form expects the opposite order.
void canonicalizeCommutativeBinop(unsigned Opcode, SDValue &N1,
SDValue &N2) const;
/// Return the specified value casted to
/// the target's desired shift amount type.
SDValue getShiftAmountOperand(EVT LHSTy, SDValue Op);

32
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -5629,20 +5629,34 @@ SDValue SelectionDAG::getNode(unsigned Opcode, const SDLoc &DL, EVT VT,
return getNode(Opcode, DL, VT, N1, N2, Flags);
}
void SelectionDAG::canonicalizeCommutativeBinop(unsigned Opcode, SDValue &N1,
SDValue &N2) const {
if (!TLI->isCommutativeBinOp(Opcode))
return;
// Canonicalize:
// binop(const, nonconst) -> binop(nonconst, const)
bool IsN1C = isConstantIntBuildVectorOrConstantInt(N1);
bool IsN2C = isConstantIntBuildVectorOrConstantInt(N2);
bool IsN1CFP = isConstantFPBuildVectorOrConstantFP(N1);
bool IsN2CFP = isConstantFPBuildVectorOrConstantFP(N2);
if ((IsN1C && !IsN2C) || (IsN1CFP && !IsN2CFP))
std::swap(N1, N2);
// Canonicalize:
// binop(splat(x), step_vector) -> binop(step_vector, splat(x))
else if (N1.getOpcode() == ISD::SPLAT_VECTOR &&
N2.getOpcode() == ISD::STEP_VECTOR)
std::swap(N1, N2);
}
SDValue SelectionDAG::getNode(unsigned Opcode, const SDLoc &DL, EVT VT,
SDValue N1, SDValue N2, const SDNodeFlags Flags) {
assert(N1.getOpcode() != ISD::DELETED_NODE &&
N2.getOpcode() != ISD::DELETED_NODE &&
"Operand is DELETED_NODE!");
// Canonicalize constant to RHS if commutative.
if (TLI->isCommutativeBinOp(Opcode)) {
bool IsN1C = isConstantIntBuildVectorOrConstantInt(N1);
bool IsN2C = isConstantIntBuildVectorOrConstantInt(N2);
bool IsN1CFP = isConstantFPBuildVectorOrConstantFP(N1);
bool IsN2CFP = isConstantFPBuildVectorOrConstantFP(N2);
if ((IsN1C && !IsN2C) || (IsN1CFP && !IsN2CFP))
std::swap(N1, N2);
}
canonicalizeCommutativeBinop(Opcode, N1, N2);
auto *N1C = dyn_cast<ConstantSDNode>(N1);
auto *N2C = dyn_cast<ConstantSDNode>(N2);

60
llvm/test/CodeGen/AArch64/active_lane_mask.ll
View File

@ -80,7 +80,7 @@ define <vscale x 16 x i1> @lane_mask_nxv16i1_i8(i8 %index, i8 %TC) {
; CHECK: // %bb.0:
; CHECK-NEXT: index z0.b, #0, #1
; CHECK-NEXT: mov z1.b, w0
; CHECK-NEXT: uqadd z0.b, z1.b, z0.b
; CHECK-NEXT: uqadd z0.b, z0.b, z1.b
; CHECK-NEXT: mov z1.b, w1
; CHECK-NEXT: ptrue p0.b
; CHECK-NEXT: cmphi p0.b, p0/z, z1.b, z0.b
@ -96,7 +96,7 @@ define <vscale x 8 x i1> @lane_mask_nxv8i1_i8(i8 %index, i8 %TC) {
; CHECK-NEXT: mov z1.h, w0
; CHECK-NEXT: and z0.h, z0.h, #0xff
; CHECK-NEXT: and z1.h, z1.h, #0xff
; CHECK-NEXT: add z0.h, z1.h, z0.h
; CHECK-NEXT: add z0.h, z0.h, z1.h
; CHECK-NEXT: mov z1.h, w1
; CHECK-NEXT: umin z0.h, z0.h, #255
; CHECK-NEXT: and z1.h, z1.h, #0xff
@ -115,7 +115,7 @@ define <vscale x 4 x i1> @lane_mask_nxv4i1_i8(i8 %index, i8 %TC) {
; CHECK-NEXT: mov z1.s, w0
; CHECK-NEXT: and z0.s, z0.s, #0xff
; CHECK-NEXT: and z1.s, z1.s, #0xff
; CHECK-NEXT: add z0.s, z1.s, z0.s
; CHECK-NEXT: add z0.s, z0.s, z1.s
; CHECK-NEXT: mov z1.s, w1
; CHECK-NEXT: umin z0.s, z0.s, #255
; CHECK-NEXT: and z1.s, z1.s, #0xff
@ -135,7 +135,7 @@ define <vscale x 2 x i1> @lane_mask_nxv2i1_i8(i8 %index, i8 %TC) {
; CHECK-NEXT: mov z1.d, x0
; CHECK-NEXT: and z0.d, z0.d, #0xff
; CHECK-NEXT: and z1.d, z1.d, #0xff
; CHECK-NEXT: add z0.d, z1.d, z0.d
; CHECK-NEXT: add z0.d, z0.d, z1.d
; CHECK-NEXT: // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT: mov z2.d, x1
; CHECK-NEXT: umin z0.d, z0.d, #255
@ -167,29 +167,29 @@ define <vscale x 32 x i1> @lane_mask_nxv32i1_i32(i32 %index, i32 %TC) {
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: mov z4.s, w1
; CHECK-NEXT: incw z1.s
; CHECK-NEXT: uqadd z5.s, z3.s, z0.s
; CHECK-NEXT: uqadd z5.s, z0.s, z3.s
; CHECK-NEXT: incw z2.s, all, mul #2
; CHECK-NEXT: mov z6.d, z1.d
; CHECK-NEXT: cmphi p1.s, p0/z, z4.s, z5.s
; CHECK-NEXT: uqadd z5.s, z3.s, z1.s
; CHECK-NEXT: uqadd z5.s, z1.s, z3.s
; CHECK-NEXT: cmphi p2.s, p0/z, z4.s, z5.s
; CHECK-NEXT: uqadd z5.s, z3.s, z2.s
; CHECK-NEXT: uqadd z5.s, z2.s, z3.s
; CHECK-NEXT: incw z6.s, all, mul #2
; CHECK-NEXT: incw z0.s, all, mul #4
; CHECK-NEXT: cmphi p3.s, p0/z, z4.s, z5.s
; CHECK-NEXT: uqadd z5.s, z3.s, z6.s
; CHECK-NEXT: uqadd z5.s, z6.s, z3.s
; CHECK-NEXT: incw z1.s, all, mul #4
; CHECK-NEXT: cmphi p4.s, p0/z, z4.s, z5.s
; CHECK-NEXT: uqadd z0.s, z3.s, z0.s
; CHECK-NEXT: uqadd z1.s, z3.s, z1.s
; CHECK-NEXT: uqadd z0.s, z0.s, z3.s
; CHECK-NEXT: uqadd z1.s, z1.s, z3.s
; CHECK-NEXT: incw z2.s, all, mul #4
; CHECK-NEXT: incw z6.s, all, mul #4
; CHECK-NEXT: uzp1 p1.h, p1.h, p2.h
; CHECK-NEXT: uzp1 p2.h, p3.h, p4.h
; CHECK-NEXT: cmphi p3.s, p0/z, z4.s, z0.s
; CHECK-NEXT: cmphi p4.s, p0/z, z4.s, z1.s
; CHECK-NEXT: uqadd z0.s, z3.s, z2.s
; CHECK-NEXT: uqadd z1.s, z3.s, z6.s
; CHECK-NEXT: uqadd z0.s, z2.s, z3.s
; CHECK-NEXT: uqadd z1.s, z6.s, z3.s
; CHECK-NEXT: cmphi p5.s, p0/z, z4.s, z0.s
; CHECK-NEXT: cmphi p0.s, p0/z, z4.s, z1.s
; CHECK-NEXT: uzp1 p3.h, p3.h, p4.h
@ -223,63 +223,63 @@ define <vscale x 32 x i1> @lane_mask_nxv32i1_i64(i64 %index, i64 %TC) {
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: mov z4.d, x1
; CHECK-NEXT: incd z1.d
; CHECK-NEXT: uqadd z5.d, z3.d, z0.d
; CHECK-NEXT: uqadd z6.d, z3.d, z1.d
; CHECK-NEXT: uqadd z5.d, z0.d, z3.d
; CHECK-NEXT: uqadd z6.d, z1.d, z3.d
; CHECK-NEXT: cmphi p1.d, p0/z, z4.d, z5.d
; CHECK-NEXT: mov z5.d, z1.d
; CHECK-NEXT: incd z2.d, all, mul #2
; CHECK-NEXT: cmphi p2.d, p0/z, z4.d, z6.d
; CHECK-NEXT: uqadd z6.d, z3.d, z2.d
; CHECK-NEXT: uqadd z6.d, z2.d, z3.d
; CHECK-NEXT: mov z7.d, z0.d
; CHECK-NEXT: incd z5.d, all, mul #2
; CHECK-NEXT: uzp1 p1.s, p1.s, p2.s
; CHECK-NEXT: cmphi p2.d, p0/z, z4.d, z6.d
; CHECK-NEXT: uqadd z6.d, z3.d, z5.d
; CHECK-NEXT: uqadd z6.d, z5.d, z3.d
; CHECK-NEXT: mov z24.d, z1.d
; CHECK-NEXT: incd z7.d, all, mul #4
; CHECK-NEXT: cmphi p3.d, p0/z, z4.d, z6.d
; CHECK-NEXT: uqadd z6.d, z3.d, z7.d
; CHECK-NEXT: uqadd z6.d, z7.d, z3.d
; CHECK-NEXT: mov z25.d, z2.d
; CHECK-NEXT: incd z24.d, all, mul #4
; CHECK-NEXT: mov z26.d, z5.d
; CHECK-NEXT: cmphi p4.d, p0/z, z4.d, z6.d
; CHECK-NEXT: uqadd z6.d, z3.d, z24.d
; CHECK-NEXT: uqadd z6.d, z24.d, z3.d
; CHECK-NEXT: incd z25.d, all, mul #4
; CHECK-NEXT: cmphi p5.d, p0/z, z4.d, z6.d
; CHECK-NEXT: uqadd z6.d, z3.d, z25.d
; CHECK-NEXT: uqadd z6.d, z25.d, z3.d
; CHECK-NEXT: incd z26.d, all, mul #4
; CHECK-NEXT: cmphi p6.d, p0/z, z4.d, z6.d
; CHECK-NEXT: uqadd z6.d, z3.d, z26.d
; CHECK-NEXT: uqadd z6.d, z26.d, z3.d
; CHECK-NEXT: uzp1 p2.s, p2.s, p3.s
; CHECK-NEXT: cmphi p3.d, p0/z, z4.d, z6.d
; CHECK-NEXT: incd z0.d, all, mul #8
; CHECK-NEXT: incd z1.d, all, mul #8
; CHECK-NEXT: uzp1 p4.s, p4.s, p5.s
; CHECK-NEXT: uzp1 p3.s, p6.s, p3.s
; CHECK-NEXT: uqadd z0.d, z3.d, z0.d
; CHECK-NEXT: uqadd z1.d, z3.d, z1.d
; CHECK-NEXT: uqadd z0.d, z0.d, z3.d
; CHECK-NEXT: uqadd z1.d, z1.d, z3.d
; CHECK-NEXT: incd z2.d, all, mul #8
; CHECK-NEXT: incd z5.d, all, mul #8
; CHECK-NEXT: uzp1 p1.h, p1.h, p2.h
; CHECK-NEXT: uzp1 p2.h, p4.h, p3.h
; CHECK-NEXT: cmphi p3.d, p0/z, z4.d, z0.d
; CHECK-NEXT: cmphi p4.d, p0/z, z4.d, z1.d
; CHECK-NEXT: uqadd z0.d, z3.d, z2.d
; CHECK-NEXT: uqadd z1.d, z3.d, z5.d
; CHECK-NEXT: uqadd z0.d, z2.d, z3.d
; CHECK-NEXT: uqadd z1.d, z5.d, z3.d
; CHECK-NEXT: incd z7.d, all, mul #8
; CHECK-NEXT: incd z24.d, all, mul #8
; CHECK-NEXT: cmphi p5.d, p0/z, z4.d, z0.d
; CHECK-NEXT: cmphi p6.d, p0/z, z4.d, z1.d
; CHECK-NEXT: uqadd z0.d, z3.d, z7.d
; CHECK-NEXT: uqadd z1.d, z3.d, z24.d
; CHECK-NEXT: uqadd z0.d, z7.d, z3.d
; CHECK-NEXT: uqadd z1.d, z24.d, z3.d
; CHECK-NEXT: incd z25.d, all, mul #8
; CHECK-NEXT: incd z26.d, all, mul #8
; CHECK-NEXT: uzp1 p3.s, p3.s, p4.s
; CHECK-NEXT: uzp1 p4.s, p5.s, p6.s
; CHECK-NEXT: cmphi p5.d, p0/z, z4.d, z0.d
; CHECK-NEXT: cmphi p6.d, p0/z, z4.d, z1.d
; CHECK-NEXT: uqadd z0.d, z3.d, z25.d
; CHECK-NEXT: uqadd z1.d, z3.d, z26.d
; CHECK-NEXT: uqadd z0.d, z25.d, z3.d
; CHECK-NEXT: uqadd z1.d, z26.d, z3.d
; CHECK-NEXT: cmphi p7.d, p0/z, z4.d, z0.d
; CHECK-NEXT: cmphi p0.d, p0/z, z4.d, z1.d
; CHECK-NEXT: uzp1 p5.s, p5.s, p6.s
@ -308,9 +308,9 @@ define <vscale x 32 x i1> @lane_mask_nxv32i1_i8(i8 %index, i8 %TC) {
; CHECK-NEXT: mov z2.b, w0
; CHECK-NEXT: add z1.b, z0.b, z1.b
; CHECK-NEXT: mov z3.b, w1
; CHECK-NEXT: uqadd z0.b, z2.b, z0.b
; CHECK-NEXT: uqadd z0.b, z0.b, z2.b
; CHECK-NEXT: ptrue p1.b
; CHECK-NEXT: uqadd z1.b, z2.b, z1.b
; CHECK-NEXT: uqadd z1.b, z1.b, z2.b
; CHECK-NEXT: cmphi p0.b, p1/z, z3.b, z0.b
; CHECK-NEXT: cmphi p1.b, p1/z, z3.b, z1.b
; CHECK-NEXT: ret

8
llvm/test/CodeGen/AArch64/sve-stepvector.ll
View File

@ -218,7 +218,7 @@ define <vscale x 2 x i64> @multiple_use_stepvector_nxv2i64_1(i64 %data) {
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: index z0.d, #0, #1
; CHECK-NEXT: mov z1.d, x0
; CHECK-NEXT: add z1.d, z1.d, z0.d
; CHECK-NEXT: add z1.d, z0.d, z1.d
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mul z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
@ -292,11 +292,7 @@ entry:
define <vscale x 2 x i64> @mul_add_stepvector_nxv2i64_commutative(i64 %x, i64 %y) {
; CHECK-LABEL: mul_add_stepvector_nxv2i64_commutative:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: index z1.d, #0, #1
; CHECK-NEXT: mov z2.d, x1
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov z0.d, x0
; CHECK-NEXT: mla z0.d, p0/m, z2.d, z1.d
; CHECK-NEXT: index z0.d, x0, x1
; CHECK-NEXT: ret
entry:
%0 = insertelement <vscale x 2 x i64> poison, i64 %y, i32 0