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

[SDAG] SimplifyDemandedBits - generalize fold for 2 LSB of X*X 

This is translated from recent changes to the IR version of this function:
D119060
D119139
This commit is contained in:
Sanjay Patel 2022-02-07 15:22:08 -05:00
parent e4e671c54f
commit fc6bee1c11
2 changed files with 10 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
View File

@ -2265,9 +2265,14 @@ bool TargetLowering::SimplifyDemandedBits(
break;
}
case ISD::MUL:
// 'Quadratic Reciprocity': mul(x,x) -> 0 if we're only demanding bit[1]
if (DemandedBits == 2 && Op.getOperand(0) == Op.getOperand(1))
return TLO.CombineTo(Op, TLO.DAG.getConstant(0, dl, VT));
// For a squared value "X * X", the bottom 2 bits are 0 and X[0] because:
// X * X is odd iff X is odd.
// 'Quadratic Reciprocity': X * X -> 0 for bit[1]
if (Op.getOperand(0) == Op.getOperand(1) && DemandedBits.ult(4)) {
SDValue One = TLO.DAG.getConstant(1, dl, VT);
SDValue And1 = TLO.DAG.getNode(ISD::AND, dl, VT, Op.getOperand(0), One);
return TLO.CombineTo(Op, And1);
}
LLVM_FALLTHROUGH;
case ISD::ADD:
case ISD::SUB: {

13
llvm/test/CodeGen/AArch64/combine-mul.ll
View File

@ -108,8 +108,7 @@ define i32 @one_demanded_low_bit(i32 %x) {
define i16 @squared_one_demanded_low_bit(i16 %x) {
; CHECK-LABEL: squared_one_demanded_low_bit:
; CHECK: // %bb.0:
; CHECK-NEXT: mul w8, w0, w0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: and w0, w0, #0x1
; CHECK-NEXT: ret
%mul = mul i16 %x, %x
%and = and i16 %mul, 1
@ -120,7 +119,6 @@ define <4 x i32> @squared_one_demanded_low_bit_splat(<4 x i32> %x) {
; CHECK-LABEL: squared_one_demanded_low_bit_splat:
; CHECK: // %bb.0:
; CHECK-NEXT: mvni v1.4s, #1
; CHECK-NEXT: mul v0.4s, v0.4s, v0.4s
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%mul = mul <4 x i32> %x, %x
@ -131,8 +129,7 @@ define <4 x i32> @squared_one_demanded_low_bit_splat(<4 x i32> %x) {
define i32 @squared_demanded_2_low_bits(i32 %x) {
; CHECK-LABEL: squared_demanded_2_low_bits:
; CHECK: // %bb.0:
; CHECK-NEXT: mul w8, w0, w0
; CHECK-NEXT: and w0, w8, #0x3
; CHECK-NEXT: and w0, w0, #0x1
; CHECK-NEXT: ret
%mul = mul i32 %x, %x
%and = and i32 %mul, 3
@ -142,13 +139,7 @@ define i32 @squared_demanded_2_low_bits(i32 %x) {
define <2 x i64> @squared_demanded_2_low_bits_splat(<2 x i64> %x) {
; CHECK-LABEL: squared_demanded_2_low_bits_splat:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: mov x9, v0.d[1]
; CHECK-NEXT: mul x8, x8, x8
; CHECK-NEXT: mul x9, x9, x9
; CHECK-NEXT: fmov d0, x8
; CHECK-NEXT: mov x8, #-2
; CHECK-NEXT: mov v0.d[1], x9
; CHECK-NEXT: dup v1.2d, x8
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret