Add DAG combine for shl + add of constants.

Do
 (shl (add x, c1), c2) -> (add (shl x, c2), c1 << c2)

This is already done for multiplies, but since multiplies
by powers of two are turned into shifts, we also need
to handle it here.

This might want checks for isLegalAddImmediate to avoid
transforming an add of a legal immediate with one that isn't.

llvm-svn: 217610

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -1517,28 +1517,6 @@ SDValue DAGCombiner::visitMERGE_VALUES(SDNode *N) {
   return SDValue(N, 0);   // Return N so it doesn't get rechecked!
 }
 
-static
-SDValue combineShlAddConstant(SDLoc DL, SDValue N0, SDValue N1,
-                              SelectionDAG &DAG) {
-  EVT VT = N0.getValueType();
-  SDValue N00 = N0.getOperand(0);
-  SDValue N01 = N0.getOperand(1);
-  ConstantSDNode *N01C = dyn_cast<ConstantSDNode>(N01);
-
-  if (N01C && N00.getOpcode() == ISD::ADD && N00.getNode()->hasOneUse() &&
-      isa<ConstantSDNode>(N00.getOperand(1))) {
-    // fold (add (shl (add x, c1), c2), ) -> (add (add (shl x, c2), c1<<c2), )
-    N0 = DAG.getNode(ISD::ADD, SDLoc(N0), VT,
-                     DAG.getNode(ISD::SHL, SDLoc(N00), VT,
-                                 N00.getOperand(0), N01),
-                     DAG.getNode(ISD::SHL, SDLoc(N01), VT,
-                                 N00.getOperand(1), N01));
-    return DAG.getNode(ISD::ADD, DL, VT, N0, N1);
-  }
-
-  return SDValue();
-}
-
 SDValue DAGCombiner::visitADD(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   SDValue N1 = N->getOperand(1);
@@ -1655,16 +1633,6 @@ SDValue DAGCombiner::visitADD(SDNode *N) {
     }
   }
 
-  // fold (add (shl (add x, c1), c2), ) -> (add (add (shl x, c2), c1<<c2), )
-  if (N0.getOpcode() == ISD::SHL && N0.getNode()->hasOneUse()) {
-    SDValue Result = combineShlAddConstant(SDLoc(N), N0, N1, DAG);
-    if (Result.getNode()) return Result;
-  }
-  if (N1.getOpcode() == ISD::SHL && N1.getNode()->hasOneUse()) {
-    SDValue Result = combineShlAddConstant(SDLoc(N), N1, N0, DAG);
-    if (Result.getNode()) return Result;
-  }
-
   // fold (add x, shl(0 - y, n)) -> sub(x, shl(y, n))
   if (N1.getOpcode() == ISD::SHL &&
       N1.getOperand(0).getOpcode() == ISD::SUB)
@@ -4185,6 +4153,18 @@ SDValue DAGCombiner::visitSHL(SDNode *N) {
                        HiBitsMask);
   }
 
+  // fold (shl (add x, c1), c2) -> (add (shl x, c2), c1 << c2)
+  // Variant of version done on multiply, except mul by a power of 2 is turned
+  // into a shift.
+  APInt Val;
+  if (N1C && N0.getOpcode() == ISD::ADD && N0.getNode()->hasOneUse() &&
+      (isa<ConstantSDNode>(N0.getOperand(1)) ||
+       isConstantSplatVector(N0.getOperand(1).getNode(), Val))) {
+    SDValue Shl0 = DAG.getNode(ISD::SHL, SDLoc(N0), VT, N0.getOperand(0), N1);
+    SDValue Shl1 = DAG.getNode(ISD::SHL, SDLoc(N1), VT, N0.getOperand(1), N1);
+    return DAG.getNode(ISD::ADD, SDLoc(N), VT, Shl0, Shl1);
+  }
+
   if (N1C) {
     SDValue NewSHL = visitShiftByConstant(N, N1C);
     if (NewSHL.getNode())

llvm/test/CodeGen/AArch64/arm64-shifted-sext.ll

@@ -166,8 +166,8 @@ entry:
 define i32 @extendedLeftShiftshortTointBy16(i16 signext %a) nounwind readnone ssp {
 entry:
 ; CHECK-LABEL: extendedLeftShiftshortTointBy16:
-; CHECK: add [[REG:w[0-9]+]], w0, #1
+; CHECK: lsl [[REG:w[0-9]+]], w0, #16
-; CHECK: lsl w0, [[REG]], #16
+; CHECK: add w0, [[REG]], #16, lsl #12
   %inc = add i16 %a, 1
   %conv2 = zext i16 %inc to i32
   %shl = shl nuw i32 %conv2, 16

llvm/test/CodeGen/R600/shl_add_constant.ll

@@ -0,0 +1,90 @@
+; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
+
+declare i32 @llvm.r600.read.tidig.x() #1
+
+; Test with inline immediate
+
+; FUNC-LABEL: @shl_2_add_9_i32
+; SI: V_LSHLREV_B32_e32  [[REG:v[0-9]+]], 2, {{v[0-9]+}}
+; SI: V_ADD_I32_e32 [[RESULT:v[0-9]+]], 36, [[REG]]
+; SI: BUFFER_STORE_DWORD [[RESULT]]
+; SI: S_ENDPGM
+define void @shl_2_add_9_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
+  %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1
+  %ptr = getelementptr i32 addrspace(1)* %in, i32 %tid.x
+  %val = load i32 addrspace(1)* %ptr, align 4
+  %add = add i32 %val, 9
+  %result = shl i32 %add, 2
+  store i32 %result, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; FUNC-LABEL: @shl_2_add_9_i32_2_add_uses
+; SI-DAG: V_ADD_I32_e32 [[ADDREG:v[0-9]+]], 9, {{v[0-9]+}}
+; SI-DAG: V_LSHLREV_B32_e32 [[SHLREG:v[0-9]+]], 2, {{v[0-9]+}}
+; SI-DAG: BUFFER_STORE_DWORD [[ADDREG]]
+; SI-DAG: BUFFER_STORE_DWORD [[SHLREG]]
+; SI: S_ENDPGM
+define void @shl_2_add_9_i32_2_add_uses(i32 addrspace(1)* %out0, i32 addrspace(1)* %out1, i32 addrspace(1)* %in) #0 {
+  %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1
+  %ptr = getelementptr i32 addrspace(1)* %in, i32 %tid.x
+  %val = load i32 addrspace(1)* %ptr, align 4
+  %add = add i32 %val, 9
+  %result = shl i32 %add, 2
+  store i32 %result, i32 addrspace(1)* %out0, align 4
+  store i32 %add, i32 addrspace(1)* %out1, align 4
+  ret void
+}
+
+; Test with add literal constant
+
+; FUNC-LABEL: @shl_2_add_999_i32
+; SI: V_LSHLREV_B32_e32  [[REG:v[0-9]+]], 2, {{v[0-9]+}}
+; SI: V_ADD_I32_e32 [[RESULT:v[0-9]+]], 0xf9c, [[REG]]
+; SI: BUFFER_STORE_DWORD [[RESULT]]
+; SI: S_ENDPGM
+define void @shl_2_add_999_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
+  %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1
+  %ptr = getelementptr i32 addrspace(1)* %in, i32 %tid.x
+  %val = load i32 addrspace(1)* %ptr, align 4
+  %shl = add i32 %val, 999
+  %result = shl i32 %shl, 2
+  store i32 %result, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; FUNC-LABEL: @test_add_shl_add_constant
+; SI-DAG: S_LOAD_DWORD [[X:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
+; SI-DAG: S_LOAD_DWORD [[Y:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
+; SI: S_LSHL_B32 [[SHL3:s[0-9]+]], [[X]], 3
+; SI: S_ADD_I32 [[TMP:s[0-9]+]], [[SHL3]], [[Y]]
+; SI: S_ADD_I32 [[RESULT:s[0-9]+]], [[TMP]], 0x3d8
+; SI: V_MOV_B32_e32 [[VRESULT:v[0-9]+]], [[RESULT]]
+; SI: BUFFER_STORE_DWORD [[VRESULT]]
+define void @test_add_shl_add_constant(i32 addrspace(1)* %out, i32 %x, i32 %y) #0 {
+  %add.0 = add i32 %x, 123
+  %shl = shl i32 %add.0, 3
+  %add.1 = add i32 %shl, %y
+   store i32 %add.1, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; FUNC-LABEL: @test_add_shl_add_constant_inv
+; SI-DAG: S_LOAD_DWORD [[X:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
+; SI-DAG: S_LOAD_DWORD [[Y:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
+; SI: S_LSHL_B32 [[SHL3:s[0-9]+]], [[X]], 3
+; SI: S_ADD_I32 [[TMP:s[0-9]+]], [[SHL3]], [[Y]]
+; SI: S_ADD_I32 [[RESULT:s[0-9]+]], [[TMP]], 0x3d8
+; SI: V_MOV_B32_e32 [[VRESULT:v[0-9]+]], [[RESULT]]
+; SI: BUFFER_STORE_DWORD [[VRESULT]]
+
+define void @test_add_shl_add_constant_inv(i32 addrspace(1)* %out, i32 %x, i32 %y) #0 {
+  %add.0 = add i32 %x, 123
+  %shl = shl i32 %add.0, 3
+  %add.1 = add i32 %y, %shl
+  store i32 %add.1, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind readnone }

llvm/test/CodeGen/R600/shl_add_ptr.ll

@@ -1,7 +1,4 @@
-; XFAIL: *
+; RUN: llc -march=r600 -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
-; Enable when patch to perform shl + add constant generic DAG combiner patch is in.
-
-; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
 
 ; Test that doing a shift of a pointer with a constant add will be
 ; folded into the constant offset addressing mode even if the add has

llvm/test/CodeGen/R600/trunc.ll

@@ -31,10 +31,10 @@ define void @trunc_load_shl_i64(i32 addrspace(1)* %out, i64 %a) {
 
 ; SI-LABEL: @trunc_shl_i64:
 ; SI: S_LOAD_DWORDX2 s{{\[}}[[LO_SREG:[0-9]+]]:{{[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd
-; SI: S_ADD_U32 s[[LO_SREG2:[0-9]+]], s[[LO_SREG]],
+; SI: S_LSHL_B64 s{{\[}}[[LO_SHL:[0-9]+]]:{{[0-9]+\]}}, s{{\[}}[[LO_SREG]]:{{[0-9]+\]}}, 2
+; SI: S_ADD_U32 s[[LO_SREG2:[0-9]+]], s[[LO_SHL]],
 ; SI: S_ADDC_U32
-; SI: S_LSHL_B64 s{{\[}}[[LO_SHL:[0-9]+]]:{{[0-9]+\]}}, s{{\[}}[[LO_SREG2]]:{{[0-9]+\]}}, 2
+; SI: V_MOV_B32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG2]]
-; SI: V_MOV_B32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SHL]]
 ; SI: BUFFER_STORE_DWORD v[[LO_VREG]],
 define void @trunc_shl_i64(i64 addrspace(1)* %out2, i32 addrspace(1)* %out, i64 %a) {
   %aa = add i64 %a, 234 ; Prevent shrinking store.

llvm/test/CodeGen/X86/add_shl_constant.ll

@@ -0,0 +1,49 @@
+; RUN: llc -march=x86-64 < %s | FileCheck %s
+
+; CHECK-LABEL: add_shl_add_constant_1_i32
+; CHECK: leal 984(%rsi,%rdi,8), %eax
+; CHECK-NEXT: retq
+define i32 @add_shl_add_constant_1_i32(i32 %x, i32 %y) nounwind {
+  %add.0 = add i32 %x, 123
+  %shl = shl i32 %add.0, 3
+  %add.1 = add i32 %shl, %y
+  ret i32 %add.1
+}
+
+; CHECK-LABEL: add_shl_add_constant_2_i32
+; CHECK: leal 984(%rsi,%rdi,8), %eax
+; CHECK-NEXT: retq
+define i32 @add_shl_add_constant_2_i32(i32 %x, i32 %y) nounwind {
+  %add.0 = add i32 %x, 123
+  %shl = shl i32 %add.0, 3
+  %add.1 = add i32 %y, %shl
+  ret i32 %add.1
+}
+
+; CHECK: LCPI2_0:
+; CHECK: .long 984
+; CHECK: _add_shl_add_constant_1_v4i32
+; CHECK: pslld $3, %[[REG:xmm[0-9]+]]
+; CHECK: paddd %xmm1, %[[REG]]
+; CHECK: paddd LCPI2_0(%rip), %[[REG:xmm[0-9]+]]
+; CHECK: retq
+define <4 x i32> @add_shl_add_constant_1_v4i32(<4 x i32> %x, <4 x i32> %y) nounwind {
+  %add.0 = add <4 x i32> %x, <i32 123, i32 123, i32 123, i32 123>
+  %shl = shl <4 x i32> %add.0, <i32 3, i32 3, i32 3, i32 3>
+  %add.1 = add <4 x i32> %shl, %y
+  ret <4 x i32> %add.1
+}
+
+; CHECK: LCPI3_0:
+; CHECK: .long 984
+; CHECK: _add_shl_add_constant_2_v4i32
+; CHECK: pslld $3, %[[REG:xmm[0-9]+]]
+; CHECK: paddd %xmm1, %[[REG]]
+; CHECK: paddd LCPI3_0(%rip), %[[REG:xmm[0-9]+]]
+; CHECK: retq
+define <4 x i32> @add_shl_add_constant_2_v4i32(<4 x i32> %x, <4 x i32> %y) nounwind {
+  %add.0 = add <4 x i32> %x, <i32 123, i32 123, i32 123, i32 123>
+  %shl = shl <4 x i32> %add.0, <i32 3, i32 3, i32 3, i32 3>
+  %add.1 = add <4 x i32> %y, %shl
+  ret <4 x i32> %add.1
+}