[ARM] Implement target hook function to decide folding (mul (add x, c1), c2)

Prevent the folding in DAGCombine if it leads to worse code.

Reviewed By: dmgreen

Differential Revision: https://reviews.llvm.org/D109124

Author: benshi001

llvm/lib/Target/ARM/ARMISelLowering.cpp

@@ -18793,6 +18793,31 @@ bool ARMTargetLowering::isLegalAddImmediate(int64_t Imm) const {
   return AbsImm >= 0 && AbsImm <= 255;
 }
 
+// Return false to prevent folding
+// (mul (add r, c0), c1) -> (add (mul r, c1), c0*c1) in DAGCombine,
+// if the folding leads to worse code.
+bool ARMTargetLowering::isMulAddWithConstProfitable(
+    const SDValue &AddNode, const SDValue &ConstNode) const {
+  // Let the DAGCombiner decide for vector types and large types.
+  const EVT VT = AddNode.getValueType();
+  if (VT.isVector() || VT.getScalarSizeInBits() > 32)
+    return true;
+
+  // It is worse if c0 is legal add immediate, while c1*c0 is not
+  // and has to be composed by at least two instructions.
+  const ConstantSDNode *C0Node = cast<ConstantSDNode>(AddNode.getOperand(1));
+  const ConstantSDNode *C1Node = cast<ConstantSDNode>(ConstNode);
+  const int64_t C0 = C0Node->getSExtValue();
+  APInt CA = C0Node->getAPIntValue() * C1Node->getAPIntValue();
+  if (!isLegalAddImmediate(C0) || isLegalAddImmediate(CA.getSExtValue()))
+    return true;
+  if (ConstantMaterializationCost((unsigned)CA.getZExtValue(), Subtarget) > 1)
+    return false;
+
+  // Default to true and let the DAGCombiner decide.
+  return true;
+}
+
 static bool getARMIndexedAddressParts(SDNode *Ptr, EVT VT,
                                       bool isSEXTLoad, SDValue &Base,
                                       SDValue &Offset, bool &isInc,

llvm/lib/Target/ARM/ARMISelLowering.h

@@ -712,6 +712,9 @@ class VectorType;
                                       Align Alignment,
                                       const DataLayout &DL) const;
 
+    bool isMulAddWithConstProfitable(const SDValue &AddNode,
+                                     const SDValue &ConstNode) const override;
+
     bool alignLoopsWithOptSize() const override;
 
     /// Returns the number of interleaved accesses that will be generated when

llvm/test/CodeGen/ARM/addimm-mulimm.ll

@@ -243,10 +243,9 @@ define i16 @fold_sub301_mul19_i16(i16 %a) {
 define i32 @fold_add251_mul253_i32(i32 %a) {
 ; CHECK-ARMV6-LABEL: fold_add251_mul253_i32:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mov r1, #15
-; CHECK-ARMV6-NEXT:    mov r2, #253
-; CHECK-ARMV6-NEXT:    orr r1, r1, #63488
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    add r0, r0, #251
+; CHECK-ARMV6-NEXT:    mov r1, #253
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
 ;
 ; CHECK-ARMV7-LABEL: fold_add251_mul253_i32:
@@ -258,15 +257,10 @@ define i32 @fold_add251_mul253_i32(i32 %a) {
 ;
 ; CHECK-THUMBV6M-LABEL: fold_add251_mul253_i32:
 ; CHECK-THUMBV6M:       @ %bb.0:
+; CHECK-THUMBV6M-NEXT:    adds r0, #251
 ; CHECK-THUMBV6M-NEXT:    movs r1, #253
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI8_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI8_0:
-; CHECK-THUMBV6M-NEXT:    .long 63503 @ 0xf80f
 ;
 ; CHECK-THUMBV7M-LABEL: fold_add251_mul253_i32:
 ; CHECK-THUMBV7M:       @ %bb.0:
@@ -282,9 +276,9 @@ define i32 @fold_add251_mul253_i32(i32 %a) {
 define i16 @fold_add251_mul253_i16(i16 %a) {
 ; CHECK-ARMV6-LABEL: fold_add251_mul253_i16:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mvn r1, #2032
-; CHECK-ARMV6-NEXT:    mov r2, #253
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    add r0, r0, #251
+; CHECK-ARMV6-NEXT:    mov r1, #253
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
 ;
 ; CHECK-ARMV7-LABEL: fold_add251_mul253_i16:
@@ -297,15 +291,10 @@ define i16 @fold_add251_mul253_i16(i16 %a) {
 ;
 ; CHECK-THUMBV6M-LABEL: fold_add251_mul253_i16:
 ; CHECK-THUMBV6M:       @ %bb.0:
+; CHECK-THUMBV6M-NEXT:    adds r0, #251
 ; CHECK-THUMBV6M-NEXT:    movs r1, #253
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI9_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI9_0:
-; CHECK-THUMBV6M-NEXT:    .long 4294965263 @ 0xfffff80f
 ;
 ; CHECK-THUMBV7M-LABEL: fold_add251_mul253_i16:
 ; CHECK-THUMBV7M:       @ %bb.0:
@@ -319,41 +308,19 @@ define i16 @fold_add251_mul253_i16(i16 %a) {
 }
 
 define i32 @fold_sub251_mul253_i32(i32 %a) {
-; CHECK-ARMV6-LABEL: fold_sub251_mul253_i32:
-; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mvn r1, #14
-; CHECK-ARMV6-NEXT:    mov r2, #253
-; CHECK-ARMV6-NEXT:    sub r1, r1, #63488
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
-; CHECK-ARMV6-NEXT:    bx lr
-;
-; CHECK-ARMV7-LABEL: fold_sub251_mul253_i32:
-; CHECK-ARMV7:       @ %bb.0:
-; CHECK-ARMV7-NEXT:    mov r1, #253
-; CHECK-ARMV7-NEXT:    mul r0, r0, r1
-; CHECK-ARMV7-NEXT:    movw r1, #63503
-; CHECK-ARMV7-NEXT:    sub r0, r0, r1
-; CHECK-ARMV7-NEXT:    bx lr
-;
-; CHECK-THUMBV6M-LABEL: fold_sub251_mul253_i32:
-; CHECK-THUMBV6M:       @ %bb.0:
-; CHECK-THUMBV6M-NEXT:    movs r1, #253
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI10_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
-; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI10_0:
-; CHECK-THUMBV6M-NEXT:    .long 4294903793 @ 0xffff07f1
+; CHECK-ARM-LABEL: fold_sub251_mul253_i32:
+; CHECK-ARM:       @ %bb.0:
+; CHECK-ARM-NEXT:    sub r0, r0, #251
+; CHECK-ARM-NEXT:    mov r1, #253
+; CHECK-ARM-NEXT:    mul r0, r0, r1
+; CHECK-ARM-NEXT:    bx lr
 ;
-; CHECK-THUMBV7M-LABEL: fold_sub251_mul253_i32:
-; CHECK-THUMBV7M:       @ %bb.0:
-; CHECK-THUMBV7M-NEXT:    movs r1, #253
-; CHECK-THUMBV7M-NEXT:    muls r0, r1, r0
-; CHECK-THUMBV7M-NEXT:    movw r1, #63503
-; CHECK-THUMBV7M-NEXT:    subs r0, r0, r1
-; CHECK-THUMBV7M-NEXT:    bx lr
+; CHECK-THUMB-LABEL: fold_sub251_mul253_i32:
+; CHECK-THUMB:       @ %bb.0:
+; CHECK-THUMB-NEXT:    subs r0, #251
+; CHECK-THUMB-NEXT:    movs r1, #253
+; CHECK-THUMB-NEXT:    muls r0, r1, r0
+; CHECK-THUMB-NEXT:    bx lr
   %b = add i32 %a, -251
   %c = mul i32 %b, 253
   ret i32 %c
@@ -362,10 +329,9 @@ define i32 @fold_sub251_mul253_i32(i32 %a) {
 define i16 @fold_sub251_mul253_i16(i16 %a) {
 ; CHECK-ARMV6-LABEL: fold_sub251_mul253_i16:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mov r1, #241
-; CHECK-ARMV6-NEXT:    mov r2, #253
-; CHECK-ARMV6-NEXT:    orr r1, r1, #1792
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    sub r0, r0, #251
+; CHECK-ARMV6-NEXT:    mov r1, #253
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
 ;
 ; CHECK-ARMV7-LABEL: fold_sub251_mul253_i16:
@@ -377,15 +343,10 @@ define i16 @fold_sub251_mul253_i16(i16 %a) {
 ;
 ; CHECK-THUMBV6M-LABEL: fold_sub251_mul253_i16:
 ; CHECK-THUMBV6M:       @ %bb.0:
+; CHECK-THUMBV6M-NEXT:    subs r0, #251
 ; CHECK-THUMBV6M-NEXT:    movs r1, #253
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI11_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI11_0:
-; CHECK-THUMBV6M-NEXT:    .long 2033 @ 0x7f1
 ;
 ; CHECK-THUMBV7M-LABEL: fold_sub251_mul253_i16:
 ; CHECK-THUMBV7M:       @ %bb.0:
@@ -401,43 +362,32 @@ define i16 @fold_sub251_mul253_i16(i16 %a) {
 define i32 @fold_add251_mul353_i32(i32 %a) {
 ; CHECK-ARMV6-LABEL: fold_add251_mul353_i32:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mov r2, #97
-; CHECK-ARMV6-NEXT:    ldr r1, .LCPI12_0
-; CHECK-ARMV6-NEXT:    orr r2, r2, #256
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    mov r1, #97
+; CHECK-ARMV6-NEXT:    add r0, r0, #251
+; CHECK-ARMV6-NEXT:    orr r1, r1, #256
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
-; CHECK-ARMV6-NEXT:    .p2align 2
-; CHECK-ARMV6-NEXT:  @ %bb.1:
-; CHECK-ARMV6-NEXT:  .LCPI12_0:
-; CHECK-ARMV6-NEXT:    .long 88603 @ 0x15a1b
 ;
 ; CHECK-ARMV7-LABEL: fold_add251_mul353_i32:
 ; CHECK-ARMV7:       @ %bb.0:
-; CHECK-ARMV7-NEXT:    movw r1, #23067
-; CHECK-ARMV7-NEXT:    movw r2, #353
-; CHECK-ARMV7-NEXT:    movt r1, #1
-; CHECK-ARMV7-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV7-NEXT:    add r0, r0, #251
+; CHECK-ARMV7-NEXT:    movw r1, #353
+; CHECK-ARMV7-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV7-NEXT:    bx lr
 ;
 ; CHECK-THUMBV6M-LABEL: fold_add251_mul353_i32:
 ; CHECK-THUMBV6M:       @ %bb.0:
 ; CHECK-THUMBV6M-NEXT:    movs r1, #255
 ; CHECK-THUMBV6M-NEXT:    adds r1, #98
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI12_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    adds r0, #251
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI12_0:
-; CHECK-THUMBV6M-NEXT:    .long 88603 @ 0x15a1b
 ;
 ; CHECK-THUMBV7M-LABEL: fold_add251_mul353_i32:
 ; CHECK-THUMBV7M:       @ %bb.0:
-; CHECK-THUMBV7M-NEXT:    movw r1, #23067
-; CHECK-THUMBV7M-NEXT:    movw r2, #353
-; CHECK-THUMBV7M-NEXT:    movt r1, #1
-; CHECK-THUMBV7M-NEXT:    mla r0, r0, r2, r1
+; CHECK-THUMBV7M-NEXT:    adds r0, #251
+; CHECK-THUMBV7M-NEXT:    movw r1, #353
+; CHECK-THUMBV7M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV7M-NEXT:    bx lr
   %b = add i32 %a, 251
   %c = mul i32 %b, 353
@@ -447,11 +397,10 @@ define i32 @fold_add251_mul353_i32(i32 %a) {
 define i16 @fold_add251_mul353_i16(i16 %a) {
 ; CHECK-ARMV6-LABEL: fold_add251_mul353_i16:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mov r2, #97
-; CHECK-ARMV6-NEXT:    mov r1, #27
-; CHECK-ARMV6-NEXT:    orr r2, r2, #256
-; CHECK-ARMV6-NEXT:    orr r1, r1, #23040
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    mov r1, #97
+; CHECK-ARMV6-NEXT:    add r0, r0, #251
+; CHECK-ARMV6-NEXT:    orr r1, r1, #256
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
 ;
 ; CHECK-ARMV7-LABEL: fold_add251_mul353_i16:
@@ -465,14 +414,9 @@ define i16 @fold_add251_mul353_i16(i16 %a) {
 ; CHECK-THUMBV6M:       @ %bb.0:
 ; CHECK-THUMBV6M-NEXT:    movs r1, #255
 ; CHECK-THUMBV6M-NEXT:    adds r1, #98
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI13_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    adds r0, #251
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI13_0:
-; CHECK-THUMBV6M-NEXT:    .long 23067 @ 0x5a1b
 ;
 ; CHECK-THUMBV7M-LABEL: fold_add251_mul353_i16:
 ; CHECK-THUMBV7M:       @ %bb.0:
@@ -488,43 +432,32 @@ define i16 @fold_add251_mul353_i16(i16 %a) {
 define i32 @fold_sub251_mul353_i32(i32 %a) {
 ; CHECK-ARMV6-LABEL: fold_sub251_mul353_i32:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mov r2, #97
-; CHECK-ARMV6-NEXT:    ldr r1, .LCPI14_0
-; CHECK-ARMV6-NEXT:    orr r2, r2, #256
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    mov r1, #97
+; CHECK-ARMV6-NEXT:    sub r0, r0, #251
+; CHECK-ARMV6-NEXT:    orr r1, r1, #256
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
-; CHECK-ARMV6-NEXT:    .p2align 2
-; CHECK-ARMV6-NEXT:  @ %bb.1:
-; CHECK-ARMV6-NEXT:  .LCPI14_0:
-; CHECK-ARMV6-NEXT:    .long 4294878693 @ 0xfffea5e5
 ;
 ; CHECK-ARMV7-LABEL: fold_sub251_mul353_i32:
 ; CHECK-ARMV7:       @ %bb.0:
-; CHECK-ARMV7-NEXT:    movw r1, #42469
-; CHECK-ARMV7-NEXT:    movw r2, #353
-; CHECK-ARMV7-NEXT:    movt r1, #65534
-; CHECK-ARMV7-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV7-NEXT:    sub r0, r0, #251
+; CHECK-ARMV7-NEXT:    movw r1, #353
+; CHECK-ARMV7-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV7-NEXT:    bx lr
 ;
 ; CHECK-THUMBV6M-LABEL: fold_sub251_mul353_i32:
 ; CHECK-THUMBV6M:       @ %bb.0:
 ; CHECK-THUMBV6M-NEXT:    movs r1, #255
 ; CHECK-THUMBV6M-NEXT:    adds r1, #98
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI14_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    subs r0, #251
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI14_0:
-; CHECK-THUMBV6M-NEXT:    .long 4294878693 @ 0xfffea5e5
 ;
 ; CHECK-THUMBV7M-LABEL: fold_sub251_mul353_i32:
 ; CHECK-THUMBV7M:       @ %bb.0:
-; CHECK-THUMBV7M-NEXT:    movw r1, #42469
-; CHECK-THUMBV7M-NEXT:    movw r2, #353
-; CHECK-THUMBV7M-NEXT:    movt r1, #65534
-; CHECK-THUMBV7M-NEXT:    mla r0, r0, r2, r1
+; CHECK-THUMBV7M-NEXT:    subs r0, #251
+; CHECK-THUMBV7M-NEXT:    movw r1, #353
+; CHECK-THUMBV7M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV7M-NEXT:    bx lr
   %b = add i32 %a, -251
   %c = mul i32 %b, 353
@@ -534,11 +467,10 @@ define i32 @fold_sub251_mul353_i32(i32 %a) {
 define i16 @fold_sub251_mul353_i16(i16 %a) {
 ; CHECK-ARMV6-LABEL: fold_sub251_mul353_i16:
 ; CHECK-ARMV6:       @ %bb.0:
-; CHECK-ARMV6-NEXT:    mov r2, #97
-; CHECK-ARMV6-NEXT:    mvn r1, #26
-; CHECK-ARMV6-NEXT:    orr r2, r2, #256
-; CHECK-ARMV6-NEXT:    sub r1, r1, #23040
-; CHECK-ARMV6-NEXT:    mla r0, r0, r2, r1
+; CHECK-ARMV6-NEXT:    mov r1, #97
+; CHECK-ARMV6-NEXT:    sub r0, r0, #251
+; CHECK-ARMV6-NEXT:    orr r1, r1, #256
+; CHECK-ARMV6-NEXT:    mul r0, r0, r1
 ; CHECK-ARMV6-NEXT:    bx lr
 ;
 ; CHECK-ARMV7-LABEL: fold_sub251_mul353_i16:
@@ -553,14 +485,9 @@ define i16 @fold_sub251_mul353_i16(i16 %a) {
 ; CHECK-THUMBV6M:       @ %bb.0:
 ; CHECK-THUMBV6M-NEXT:    movs r1, #255
 ; CHECK-THUMBV6M-NEXT:    adds r1, #98
-; CHECK-THUMBV6M-NEXT:    muls r1, r0, r1
-; CHECK-THUMBV6M-NEXT:    ldr r0, .LCPI15_0
-; CHECK-THUMBV6M-NEXT:    adds r0, r1, r0
+; CHECK-THUMBV6M-NEXT:    subs r0, #251
+; CHECK-THUMBV6M-NEXT:    muls r0, r1, r0
 ; CHECK-THUMBV6M-NEXT:    bx lr
-; CHECK-THUMBV6M-NEXT:    .p2align 2
-; CHECK-THUMBV6M-NEXT:  @ %bb.1:
-; CHECK-THUMBV6M-NEXT:  .LCPI15_0:
-; CHECK-THUMBV6M-NEXT:    .long 4294944229 @ 0xffffa5e5
 ;
 ; CHECK-THUMBV7M-LABEL: fold_sub251_mul353_i16:
 ; CHECK-THUMBV7M:       @ %bb.0: