[llvm] 5931be6 - [DAGCombine][PowerPC] Convert negated abs to trivial arithmetic ops

[Kai Luo via llvm-commits]

Author: Kai Luo
Date: 2020-11-24T09:43:35Z
New Revision: 5931be60b5238e5e134fcde75eb2d8121f3dca82

URL: https://github.com/llvm/llvm-project/commit/5931be60b5238e5e134fcde75eb2d8121f3dca82
DIFF: https://github.com/llvm/llvm-project/commit/5931be60b5238e5e134fcde75eb2d8121f3dca82.diff

LOG: [DAGCombine][PowerPC] Convert negated abs to trivial arithmetic ops

This patch converts `0 - abs(x)` to `Y = sra (X, size(X)-1); sub (Y, xor (X, Y))` for better codegen.

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D91120

Added: 
    

Modified: 
    llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
    llvm/test/CodeGen/AArch64/neg-abs.ll
    llvm/test/CodeGen/PowerPC/neg-abs.ll
    llvm/test/CodeGen/RISCV/neg-abs.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index d18d37eea41a..cae602d166d1 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -3209,6 +3209,19 @@ SDValue DAGCombiner::visitSUB(SDNode *N) {
       // 0 - X --> X if X is 0 or the minimum signed value.
       return N1;
     }
+
+    // Convert 0 - abs(x) -> Y = sra (X, size(X)-1); sub (Y, xor (X, Y)).
+    if (N1->getOpcode() == ISD::ABS &&
+        !TLI.isOperationLegalOrCustom(ISD::ABS, VT)) {
+      SDValue X = N1->getOperand(0);
+      SDValue Shift =
+          DAG.getNode(ISD::SRA, DL, VT, X,
+                      DAG.getConstant(BitWidth - 1, DL, getShiftAmountTy(VT)));
+      SDValue Xor = DAG.getNode(ISD::XOR, DL, VT, X, Shift);
+      AddToWorklist(Shift.getNode());
+      AddToWorklist(Xor.getNode());
+      return DAG.getNode(ISD::SUB, DL, VT, Shift, Xor);
+    }
   }
 
   // Canonicalize (sub -1, x) -> ~x, i.e. (xor x, -1)

diff  --git a/llvm/test/CodeGen/AArch64/neg-abs.ll b/llvm/test/CodeGen/AArch64/neg-abs.ll
index 3dcb04a8e35f..0ee39f516f76 100644
--- a/llvm/test/CodeGen/AArch64/neg-abs.ll
+++ b/llvm/test/CodeGen/AArch64/neg-abs.ll
@@ -7,9 +7,9 @@ declare i64 @llvm.abs.i64(i64, i1 immarg)
 define i64 at neg_abs(i64 %x) {
 ; CHECK-LABEL: neg_abs:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    cmp x0, #0 // =0
-; CHECK-NEXT:    cneg x8, x0, mi
-; CHECK-NEXT:    neg x0, x8
+; CHECK-NEXT:    asr x8, x0, #63
+; CHECK-NEXT:    eor x9, x0, x8
+; CHECK-NEXT:    sub x0, x8, x9
 ; CHECK-NEXT:    ret
   %abs = tail call i64 @llvm.abs.i64(i64 %x, i1 true)
   %neg = sub nsw i64 0, %abs

diff  --git a/llvm/test/CodeGen/PowerPC/neg-abs.ll b/llvm/test/CodeGen/PowerPC/neg-abs.ll
index b870bd3ce195..bbe27fdd057c 100644
--- a/llvm/test/CodeGen/PowerPC/neg-abs.ll
+++ b/llvm/test/CodeGen/PowerPC/neg-abs.ll
@@ -9,9 +9,8 @@ define i64 at neg_abs(i64 %x) {
 ; CHECK-LE-LABEL: neg_abs:
 ; CHECK-LE:       # %bb.0:
 ; CHECK-LE-NEXT:    sradi r4, r3, 63
-; CHECK-LE-NEXT:    add r3, r3, r4
 ; CHECK-LE-NEXT:    xor r3, r3, r4
-; CHECK-LE-NEXT:    neg r3, r3
+; CHECK-LE-NEXT:    sub r3, r4, r3
 ; CHECK-LE-NEXT:    blr
   %abs = tail call i64 @llvm.abs.i64(i64 %x, i1 true)
   %neg = sub nsw i64 0, %abs

diff  --git a/llvm/test/CodeGen/RISCV/neg-abs.ll b/llvm/test/CodeGen/RISCV/neg-abs.ll
index 9f56a2e77767..2171a1d24a28 100644
--- a/llvm/test/CodeGen/RISCV/neg-abs.ll
+++ b/llvm/test/CodeGen/RISCV/neg-abs.ll
@@ -9,18 +9,15 @@ define i32 @neg_abs32(i32 %x) {
 ; RV32-LABEL: neg_abs32:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    srai a1, a0, 31
-; RV32-NEXT:    add a0, a0, a1
 ; RV32-NEXT:    xor a0, a0, a1
-; RV32-NEXT:    neg a0, a0
+; RV32-NEXT:    sub a0, a1, a0
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: neg_abs32:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    sext.w a1, a0
-; RV64-NEXT:    srai a1, a1, 63
-; RV64-NEXT:    add a0, a0, a1
+; RV64-NEXT:    sraiw a1, a0, 31
 ; RV64-NEXT:    xor a0, a0, a1
-; RV64-NEXT:    negw a0, a0
+; RV64-NEXT:    subw a0, a1, a0
 ; RV64-NEXT:    ret
   %abs = tail call i32 @llvm.abs.i32(i32 %x, i1 true)
   %neg = sub nsw i32 0, %abs
@@ -30,25 +27,20 @@ define i32 @neg_abs32(i32 %x) {
 define i64 @neg_abs64(i64 %x) {
 ; RV32-LABEL: neg_abs64:
 ; RV32:       # %bb.0:
-; RV32-NEXT:    bgez a1, .LBB1_2
-; RV32-NEXT:  # %bb.1:
-; RV32-NEXT:    snez a2, a0
-; RV32-NEXT:    add a1, a1, a2
-; RV32-NEXT:    neg a1, a1
-; RV32-NEXT:    neg a0, a0
-; RV32-NEXT:  .LBB1_2:
-; RV32-NEXT:    snez a2, a0
-; RV32-NEXT:    add a1, a1, a2
-; RV32-NEXT:    neg a1, a1
-; RV32-NEXT:    neg a0, a0
+; RV32-NEXT:    srai a2, a1, 31
+; RV32-NEXT:    xor a0, a0, a2
+; RV32-NEXT:    sltu a3, a2, a0
+; RV32-NEXT:    xor a1, a1, a2
+; RV32-NEXT:    sub a1, a2, a1
+; RV32-NEXT:    sub a1, a1, a3
+; RV32-NEXT:    sub a0, a2, a0
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: neg_abs64:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    srai a1, a0, 63
-; RV64-NEXT:    add a0, a0, a1
 ; RV64-NEXT:    xor a0, a0, a1
-; RV64-NEXT:    neg a0, a0
+; RV64-NEXT:    sub a0, a1, a0
 ; RV64-NEXT:    ret
   %abs = tail call i64 @llvm.abs.i64(i64 %x, i1 true)
   %neg = sub nsw i64 0, %abs