[PATCH] D59066: [TargetLowering] improve the default expansion of uaddsat/usubsat

[Sanjay Patel via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL356332: [TargetLowering] improve the default expansion of uaddsat/usubsat (authored by spatel, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D59066?vs=189871&id=191018#toc

Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59066/new/

https://reviews.llvm.org/D59066

Files:
  llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
  llvm/trunk/test/CodeGen/AArch64/uadd_sat_vec.ll


Index: llvm/trunk/test/CodeGen/AArch64/uadd_sat_vec.ll
===================================================================
--- llvm/trunk/test/CodeGen/AArch64/uadd_sat_vec.ll
+++ llvm/trunk/test/CodeGen/AArch64/uadd_sat_vec.ll
@@ -404,8 +404,7 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    add v1.2d, v0.2d, v1.2d
 ; CHECK-NEXT:    cmhi v0.2d, v0.2d, v1.2d
-; CHECK-NEXT:    bic v1.16b, v1.16b, v0.16b
-; CHECK-NEXT:    orr v0.16b, v0.16b, v1.16b
+; CHECK-NEXT:    orr v0.16b, v1.16b, v0.16b
 ; CHECK-NEXT:    ret
   %z = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> %x, <2 x i64> %y)
   ret <2 x i64> %z
@@ -418,10 +417,8 @@
 ; CHECK-NEXT:    add v3.2d, v1.2d, v3.2d
 ; CHECK-NEXT:    cmhi v0.2d, v0.2d, v2.2d
 ; CHECK-NEXT:    cmhi v1.2d, v1.2d, v3.2d
-; CHECK-NEXT:    bic v2.16b, v2.16b, v0.16b
-; CHECK-NEXT:    bic v3.16b, v3.16b, v1.16b
-; CHECK-NEXT:    orr v0.16b, v0.16b, v2.16b
-; CHECK-NEXT:    orr v1.16b, v1.16b, v3.16b
+; CHECK-NEXT:    orr v0.16b, v2.16b, v0.16b
+; CHECK-NEXT:    orr v1.16b, v3.16b, v1.16b
 ; CHECK-NEXT:    ret
   %z = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> %x, <4 x i64> %y)
   ret <4 x i64> %z
@@ -438,14 +435,10 @@
 ; CHECK-NEXT:    cmhi v1.2d, v1.2d, v5.2d
 ; CHECK-NEXT:    cmhi v2.2d, v2.2d, v6.2d
 ; CHECK-NEXT:    cmhi v3.2d, v3.2d, v7.2d
-; CHECK-NEXT:    bic v4.16b, v4.16b, v0.16b
-; CHECK-NEXT:    bic v5.16b, v5.16b, v1.16b
-; CHECK-NEXT:    bic v6.16b, v6.16b, v2.16b
-; CHECK-NEXT:    bic v7.16b, v7.16b, v3.16b
-; CHECK-NEXT:    orr v0.16b, v0.16b, v4.16b
-; CHECK-NEXT:    orr v1.16b, v1.16b, v5.16b
-; CHECK-NEXT:    orr v2.16b, v2.16b, v6.16b
-; CHECK-NEXT:    orr v3.16b, v3.16b, v7.16b
+; CHECK-NEXT:    orr v0.16b, v4.16b, v0.16b
+; CHECK-NEXT:    orr v1.16b, v5.16b, v1.16b
+; CHECK-NEXT:    orr v2.16b, v6.16b, v2.16b
+; CHECK-NEXT:    orr v3.16b, v7.16b, v3.16b
 ; CHECK-NEXT:    ret
   %z = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> %x, <8 x i64> %y)
   ret <8 x i64> %z
Index: llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -5426,9 +5426,20 @@
   SDValue AllOnes = DAG.getAllOnesConstant(dl, VT);
 
   if (Opcode == ISD::UADDSAT) {
+    if (getBooleanContents(VT) == ZeroOrNegativeOneBooleanContent) {
+      // (LHS + RHS) | OverflowMask
+      SDValue OverflowMask = DAG.getSExtOrTrunc(Overflow, dl, VT);
+      return DAG.getNode(ISD::OR, dl, VT, SumDiff, OverflowMask);
+    }
     // Overflow ? 0xffff.... : (LHS + RHS)
     return DAG.getSelect(dl, VT, Overflow, AllOnes, SumDiff);
   } else if (Opcode == ISD::USUBSAT) {
+    if (getBooleanContents(VT) == ZeroOrNegativeOneBooleanContent) {
+      // (LHS - RHS) & ~OverflowMask
+      SDValue OverflowMask = DAG.getSExtOrTrunc(Overflow, dl, VT);
+      SDValue Not = DAG.getNOT(dl, OverflowMask, VT);
+      return DAG.getNode(ISD::AND, dl, VT, SumDiff, Not);
+    }
     // Overflow ? 0 : (LHS - RHS)
     return DAG.getSelect(dl, VT, Overflow, Zero, SumDiff);
   } else {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D59066.191018.patch
Type: text/x-patch
Size: 3104 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190317/5816fccc/attachment-0001.bin>