[PATCH] D134706: [AArch64] Lower multiplication by a constant int to shl+sub+shl

[Allen zhong via Phabricator via llvm-commits]

Allen created this revision.
Allen added reviewers: dmgreen, efriedma.
Herald added subscribers: hiraditya, kristof.beyls.
Herald added a project: All.
Allen requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

Decompose the const 14 can be separated from D132322 <https://reviews.llvm.org/D132322>
Change the costmodel to lower a = b * C where C = 2^n - 2^m to

  lsl     w8, w0, n
  sub     w0, w8, w0, lsl m


https://reviews.llvm.org/D134706

Files:
  llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
  llvm/test/CodeGen/AArch64/mul_pow2.ll


Index: llvm/test/CodeGen/AArch64/mul_pow2.ll
===================================================================
--- llvm/test/CodeGen/AArch64/mul_pow2.ll
+++ llvm/test/CodeGen/AArch64/mul_pow2.ll
@@ -408,8 +408,8 @@
 define i32 @test14(i32 %x) {
 ; CHECK-LABEL: test14:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov w8, #14
-; CHECK-NEXT:    mul w0, w0, w8
+; CHECK-NEXT:    lsl w8, w0, #4
+; CHECK-NEXT:    sub w0, w8, w0, lsl #1
 ; CHECK-NEXT:    ret
 ;
 ; GISEL-LABEL: test14:
Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -14799,7 +14799,7 @@
   // More aggressively, some multiplications N0 * C can be lowered to
   // shift+add+shift if the constant C = A * B where A = 2^N + 1 and B = 2^M,
   // e.g. 6=3*2=(2+1)*2.
-  // TODO: consider lowering more cases, e.g. C = 14, -6, -14 or even 45
+  // TODO: consider lowering more cases, e.g. C = -6, -14 or even 45
   // which equals to (1+2)*16-(1+2).
 
   // TrailingZeroes is used to test if the mul can be lowered to
@@ -14826,12 +14826,16 @@
   bool ShiftValUseIsN0 = true;
   // Do we need to negate the result?
   bool NegateResult = false;
+  // Is the sub has 2 shifted value operands?
+  bool Sub2Shift = false;
 
   if (ConstValue.isNonNegative()) {
     // (mul x, 2^N + 1) => (add (shl x, N), x)
     // (mul x, 2^N - 1) => (sub (shl x, N), x)
     // (mul x, (2^N + 1) * 2^M) => (shl (add (shl x, N), x), M)
+    // (mul x, (2^(N-M) - 1) * 2^M) => (sub (shl x, N), (shl x, M))
     APInt SCVMinus1 = ShiftedConstValue - 1;
+    APInt SCVPlus1 = ShiftedConstValue + 1;
     APInt CVPlus1 = ConstValue + 1;
     if (SCVMinus1.isPowerOf2()) {
       ShiftAmt = SCVMinus1.logBase2();
@@ -14839,6 +14843,10 @@
     } else if (CVPlus1.isPowerOf2()) {
       ShiftAmt = CVPlus1.logBase2();
       AddSubOpc = ISD::SUB;
+    } else if (SCVPlus1.isPowerOf2()) {
+      ShiftAmt = SCVPlus1.logBase2() + TrailingZeroes;
+      AddSubOpc = ISD::SUB;
+      Sub2Shift = true;
     } else
       return SDValue();
   } else {
@@ -14858,11 +14866,15 @@
       return SDValue();
   }
 
-  SDValue ShiftedVal = DAG.getNode(ISD::SHL, DL, VT, N0,
-                                   DAG.getConstant(ShiftAmt, DL, MVT::i64));
-
-  SDValue AddSubN0 = ShiftValUseIsN0 ? ShiftedVal : N0;
-  SDValue AddSubN1 = ShiftValUseIsN0 ? N0 : ShiftedVal;
+  SDValue ShiftedVal0 = DAG.getNode(ISD::SHL, DL, VT, N0,
+                                    DAG.getConstant(ShiftAmt, DL, MVT::i64));
+  if (Sub2Shift) {
+    SDValue ShiftedVal1 = DAG.getNode(
+        ISD::SHL, DL, VT, N0, DAG.getConstant(TrailingZeroes, DL, MVT::i64));
+    return DAG.getNode(ISD::SUB, DL, VT, ShiftedVal0, ShiftedVal1);
+  }
+  SDValue AddSubN0 = ShiftValUseIsN0 ? ShiftedVal0 : N0;
+  SDValue AddSubN1 = ShiftValUseIsN0 ? N0 : ShiftedVal0;
   SDValue Res = DAG.getNode(AddSubOpc, DL, VT, AddSubN0, AddSubN1);
   assert(!(NegateResult && TrailingZeroes) &&
          "NegateResult and TrailingZeroes cannot both be true for now.");


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D134706.463116.patch
Type: text/x-patch
Size: 3133 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220927/5d1eb0dd/attachment-0001.bin>