[AArch64][SDAG] Detect non-zeroes in truncating buildvectors in fshl lowering (#123597)
A BUILD_VECTOR can implicity shrink the bits of the operands if the
operand types are not legal. For example a v8i16 constant BUILD_VECTOR
might be represented as v8i16 BUILDVECTOR(i32 1, i32 2, ...).
Unfortunately this means that the constants are not accepted by
matchUnaryPredicateImpl, preventing in this case funnel shifts detecting
that all the operands are non-zero. Add a flag to help it match.
diff --git a/llvm/include/llvm/CodeGen/SelectionDAGNodes.h b/llvm/include/llvm/CodeGen/SelectionDAGNodes.h
index 49467ce0..8c1e2fa 100644
--- a/llvm/include/llvm/CodeGen/SelectionDAGNodes.h
+++ b/llvm/include/llvm/CodeGen/SelectionDAGNodes.h
@@ -3261,13 +3261,16 @@
template <typename ConstNodeType>
bool matchUnaryPredicateImpl(SDValue Op,
std::function<bool(ConstNodeType *)> Match,
- bool AllowUndefs = false);
+ bool AllowUndefs = false,
+ bool AllowTruncation = false);
/// Hook for matching ConstantSDNode predicate
inline bool matchUnaryPredicate(SDValue Op,
std::function<bool(ConstantSDNode *)> Match,
- bool AllowUndefs = false) {
- return matchUnaryPredicateImpl<ConstantSDNode>(Op, Match, AllowUndefs);
+ bool AllowUndefs = false,
+ bool AllowTruncation = false) {
+ return matchUnaryPredicateImpl<ConstantSDNode>(Op, Match, AllowUndefs,
+ AllowTruncation);
}
/// Hook for matching ConstantFPSDNode predicate
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index b416c0e..8f50a14 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -363,7 +363,7 @@
template <typename ConstNodeType>
bool ISD::matchUnaryPredicateImpl(SDValue Op,
std::function<bool(ConstNodeType *)> Match,
- bool AllowUndefs) {
+ bool AllowUndefs, bool AllowTruncation) {
// FIXME: Add support for scalar UNDEF cases?
if (auto *C = dyn_cast<ConstNodeType>(Op))
return Match(C);
@@ -382,16 +382,17 @@
}
auto *Cst = dyn_cast<ConstNodeType>(Op.getOperand(i));
- if (!Cst || Cst->getValueType(0) != SVT || !Match(Cst))
+ if (!Cst || (!AllowTruncation && Cst->getValueType(0) != SVT) ||
+ !Match(Cst))
return false;
}
return true;
}
// Build used template types.
template bool ISD::matchUnaryPredicateImpl<ConstantSDNode>(
- SDValue, std::function<bool(ConstantSDNode *)>, bool);
+ SDValue, std::function<bool(ConstantSDNode *)>, bool, bool);
template bool ISD::matchUnaryPredicateImpl<ConstantFPSDNode>(
- SDValue, std::function<bool(ConstantFPSDNode *)>, bool);
+ SDValue, std::function<bool(ConstantFPSDNode *)>, bool, bool);
bool ISD::matchBinaryPredicate(
SDValue LHS, SDValue RHS,
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index 49ec47f..98206b7 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -7971,7 +7971,7 @@
return ISD::matchUnaryPredicate(
Z,
[=](ConstantSDNode *C) { return !C || C->getAPIntValue().urem(BW) != 0; },
- true);
+ /*AllowUndef=*/true, /*AllowTruncation=*/true);
}
static SDValue expandVPFunnelShift(SDNode *Node, SelectionDAG &DAG) {
diff --git a/llvm/test/CodeGen/AArch64/fsh.ll b/llvm/test/CodeGen/AArch64/fsh.ll
index bc311f6..9196d51 100644
--- a/llvm/test/CodeGen/AArch64/fsh.ll
+++ b/llvm/test/CodeGen/AArch64/fsh.ll
@@ -3909,9 +3909,8 @@
define <8 x i8> @fshl_v8i8_c(<8 x i8> %a, <8 x i8> %b) {
; CHECK-SD-LABEL: fshl_v8i8_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: ushr v1.8b, v1.8b, #1
; CHECK-SD-NEXT: shl v0.8b, v0.8b, #3
-; CHECK-SD-NEXT: usra v0.8b, v1.8b, #4
+; CHECK-SD-NEXT: usra v0.8b, v1.8b, #5
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fshl_v8i8_c:
@@ -3927,8 +3926,7 @@
define <8 x i8> @fshr_v8i8_c(<8 x i8> %a, <8 x i8> %b) {
; CHECK-SD-LABEL: fshr_v8i8_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: add v0.8b, v0.8b, v0.8b
-; CHECK-SD-NEXT: shl v0.8b, v0.8b, #4
+; CHECK-SD-NEXT: shl v0.8b, v0.8b, #5
; CHECK-SD-NEXT: usra v0.8b, v1.8b, #3
; CHECK-SD-NEXT: ret
;
@@ -3945,9 +3943,8 @@
define <16 x i8> @fshl_v16i8_c(<16 x i8> %a, <16 x i8> %b) {
; CHECK-SD-LABEL: fshl_v16i8_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: ushr v1.16b, v1.16b, #1
; CHECK-SD-NEXT: shl v0.16b, v0.16b, #3
-; CHECK-SD-NEXT: usra v0.16b, v1.16b, #4
+; CHECK-SD-NEXT: usra v0.16b, v1.16b, #5
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fshl_v16i8_c:
@@ -3963,8 +3960,7 @@
define <16 x i8> @fshr_v16i8_c(<16 x i8> %a, <16 x i8> %b) {
; CHECK-SD-LABEL: fshr_v16i8_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: add v0.16b, v0.16b, v0.16b
-; CHECK-SD-NEXT: shl v0.16b, v0.16b, #4
+; CHECK-SD-NEXT: shl v0.16b, v0.16b, #5
; CHECK-SD-NEXT: usra v0.16b, v1.16b, #3
; CHECK-SD-NEXT: ret
;
@@ -3981,9 +3977,8 @@
define <4 x i16> @fshl_v4i16_c(<4 x i16> %a, <4 x i16> %b) {
; CHECK-SD-LABEL: fshl_v4i16_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: ushr v1.4h, v1.4h, #1
; CHECK-SD-NEXT: shl v0.4h, v0.4h, #3
-; CHECK-SD-NEXT: usra v0.4h, v1.4h, #12
+; CHECK-SD-NEXT: usra v0.4h, v1.4h, #13
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fshl_v4i16_c:
@@ -3999,8 +3994,7 @@
define <4 x i16> @fshr_v4i16_c(<4 x i16> %a, <4 x i16> %b) {
; CHECK-SD-LABEL: fshr_v4i16_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: add v0.4h, v0.4h, v0.4h
-; CHECK-SD-NEXT: shl v0.4h, v0.4h, #12
+; CHECK-SD-NEXT: shl v0.4h, v0.4h, #13
; CHECK-SD-NEXT: usra v0.4h, v1.4h, #3
; CHECK-SD-NEXT: ret
;
@@ -4018,7 +4012,6 @@
; CHECK-SD-LABEL: fshl_v7i16_c:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: adrp x8, .LCPI124_0
-; CHECK-SD-NEXT: ushr v1.8h, v1.8h, #1
; CHECK-SD-NEXT: adrp x9, .LCPI124_1
; CHECK-SD-NEXT: ldr q2, [x8, :lo12:.LCPI124_0]
; CHECK-SD-NEXT: ldr q3, [x9, :lo12:.LCPI124_1]
@@ -4060,7 +4053,6 @@
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: adrp x8, .LCPI125_0
; CHECK-SD-NEXT: adrp x9, .LCPI125_1
-; CHECK-SD-NEXT: add v0.8h, v0.8h, v0.8h
; CHECK-SD-NEXT: ldr q2, [x8, :lo12:.LCPI125_0]
; CHECK-SD-NEXT: ldr q3, [x9, :lo12:.LCPI125_1]
; CHECK-SD-NEXT: ushl v1.8h, v1.8h, v2.8h
@@ -4099,9 +4091,8 @@
define <8 x i16> @fshl_v8i16_c(<8 x i16> %a, <8 x i16> %b) {
; CHECK-SD-LABEL: fshl_v8i16_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: ushr v1.8h, v1.8h, #1
; CHECK-SD-NEXT: shl v0.8h, v0.8h, #3
-; CHECK-SD-NEXT: usra v0.8h, v1.8h, #12
+; CHECK-SD-NEXT: usra v0.8h, v1.8h, #13
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fshl_v8i16_c:
@@ -4117,8 +4108,7 @@
define <8 x i16> @fshr_v8i16_c(<8 x i16> %a, <8 x i16> %b) {
; CHECK-SD-LABEL: fshr_v8i16_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: add v0.8h, v0.8h, v0.8h
-; CHECK-SD-NEXT: shl v0.8h, v0.8h, #12
+; CHECK-SD-NEXT: shl v0.8h, v0.8h, #13
; CHECK-SD-NEXT: usra v0.8h, v1.8h, #3
; CHECK-SD-NEXT: ret
;
@@ -4135,12 +4125,10 @@
define <16 x i16> @fshl_v16i16_c(<16 x i16> %a, <16 x i16> %b) {
; CHECK-SD-LABEL: fshl_v16i16_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: ushr v2.8h, v2.8h, #1
-; CHECK-SD-NEXT: shl v0.8h, v0.8h, #3
-; CHECK-SD-NEXT: ushr v3.8h, v3.8h, #1
; CHECK-SD-NEXT: shl v1.8h, v1.8h, #3
-; CHECK-SD-NEXT: usra v0.8h, v2.8h, #12
-; CHECK-SD-NEXT: usra v1.8h, v3.8h, #12
+; CHECK-SD-NEXT: shl v0.8h, v0.8h, #3
+; CHECK-SD-NEXT: usra v1.8h, v3.8h, #13
+; CHECK-SD-NEXT: usra v0.8h, v2.8h, #13
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: fshl_v16i16_c:
@@ -4158,10 +4146,8 @@
define <16 x i16> @fshr_v16i16_c(<16 x i16> %a, <16 x i16> %b) {
; CHECK-SD-LABEL: fshr_v16i16_c:
; CHECK-SD: // %bb.0: // %entry
-; CHECK-SD-NEXT: add v1.8h, v1.8h, v1.8h
-; CHECK-SD-NEXT: add v0.8h, v0.8h, v0.8h
-; CHECK-SD-NEXT: shl v1.8h, v1.8h, #12
-; CHECK-SD-NEXT: shl v0.8h, v0.8h, #12
+; CHECK-SD-NEXT: shl v1.8h, v1.8h, #13
+; CHECK-SD-NEXT: shl v0.8h, v0.8h, #13
; CHECK-SD-NEXT: usra v1.8h, v3.8h, #3
; CHECK-SD-NEXT: usra v0.8h, v2.8h, #3
; CHECK-SD-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/smul_fix.ll b/llvm/test/CodeGen/AArch64/smul_fix.ll
index 50a189d..dacce72 100644
--- a/llvm/test/CodeGen/AArch64/smul_fix.ll
+++ b/llvm/test/CodeGen/AArch64/smul_fix.ll
@@ -144,8 +144,7 @@
; CHECK-NEXT: smull v0.4s, v0.4h, v1.4h
; CHECK-NEXT: shrn v1.4h, v0.4s, #16
; CHECK-NEXT: xtn v2.4h, v0.4s
-; CHECK-NEXT: add v1.4h, v1.4h, v1.4h
-; CHECK-NEXT: shl v0.4h, v1.4h, #13
+; CHECK-NEXT: shl v0.4h, v1.4h, #14
; CHECK-NEXT: usra v0.4h, v2.4h, #2
; CHECK-NEXT: ret
%tmp = call <4 x i16> @llvm.smul.fix.v4i16(<4 x i16> %x, <4 x i16> %y, i32 2)
diff --git a/llvm/test/CodeGen/AArch64/umul_fix.ll b/llvm/test/CodeGen/AArch64/umul_fix.ll
index 9f4da82..823f4bd 100644
--- a/llvm/test/CodeGen/AArch64/umul_fix.ll
+++ b/llvm/test/CodeGen/AArch64/umul_fix.ll
@@ -152,8 +152,7 @@
; CHECK-NEXT: umull v0.4s, v0.4h, v1.4h
; CHECK-NEXT: shrn v1.4h, v0.4s, #16
; CHECK-NEXT: xtn v2.4h, v0.4s
-; CHECK-NEXT: add v1.4h, v1.4h, v1.4h
-; CHECK-NEXT: shl v0.4h, v1.4h, #11
+; CHECK-NEXT: shl v0.4h, v1.4h, #12
; CHECK-NEXT: usra v0.4h, v2.4h, #4
; CHECK-NEXT: ret
%tmp = call <4 x i16> @llvm.umul.fix.v4i16(<4 x i16> %x, <4 x i16> %y, i32 4)
