[InstCombine] add folds for icmp+ctpop

https://alive2.llvm.org/ce/z/XjFPQJ

  define void @src(i64 %value) {
    %t0 = call i64 @llvm.ctpop.i64(i64 %value)
    %gt = icmp ugt i64 %t0, 63
    %lt = icmp ult i64 %t0, 64
    call void @use(i1 %gt, i1 %lt)
    ret void
  }

  define void @tgt(i64 %value) {
    %eq = icmp eq i64 %value, -1
    %ne = icmp ne i64 %value, -1
    call void @use(i1 %eq, i1 %ne)
    ret void
  }

  declare i64 @llvm.ctpop.i64(i64) #1
  declare void @use(i1, i1)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 24713d7..fe342dc 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -3174,6 +3174,18 @@ Instruction *InstCombinerImpl::foldICmpIntrinsicWithConstant(ICmpInst &Cmp,
   unsigned BitWidth = C.getBitWidth();
   ICmpInst::Predicate Pred = Cmp.getPredicate();
   switch (II->getIntrinsicID()) {
+  case Intrinsic::ctpop: {
+    // (ctpop X > BitWidth - 1) --> X == -1
+    Value *X = II->getArgOperand(0);
+    if (C == BitWidth - 1 && Pred == ICmpInst::ICMP_UGT)
+      return CmpInst::Create(Instruction::ICmp, ICmpInst::ICMP_EQ, X,
+                             ConstantInt::getAllOnesValue(Ty));
+    // (ctpop X < BitWidth) --> X != -1
+    if (C == BitWidth && Pred == ICmpInst::ICMP_ULT)
+      return CmpInst::Create(Instruction::ICmp, ICmpInst::ICMP_NE, X,
+                             ConstantInt::getAllOnesValue(Ty));
+    break;
+  }
   case Intrinsic::ctlz: {
     // ctlz(0bXXXXXXXX) > 3 -> 0bXXXXXXXX < 0b00010000
     if (Pred == ICmpInst::ICMP_UGT && C.ult(BitWidth)) {

diff --git a/llvm/test/Transforms/InstCombine/cmp-intrinsic.ll b/llvm/test/Transforms/InstCombine/cmp-intrinsic.ll
index 6519eda..599a749 100644 (file)
--- a/llvm/test/Transforms/InstCombine/cmp-intrinsic.ll
+++ b/llvm/test/Transforms/InstCombine/cmp-intrinsic.ll
@@ -495,7 +495,7 @@ define i1 @ctpop_ugt_bitwidth_minus_one_i8(i8 %x, i8* %p) {
 ; CHECK-LABEL: @ctpop_ugt_bitwidth_minus_one_i8(
 ; CHECK-NEXT:    [[POP:%.*]] = tail call i8 @llvm.ctpop.i8(i8 [[X:%.*]]), [[RNG2:!range !.*]]
 ; CHECK-NEXT:    store i8 [[POP]], i8* [[P:%.*]], align 1
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ugt i8 [[POP]], 7
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 [[X]], -1
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %pop = tail call i8 @llvm.ctpop.i8(i8 %x)
@@ -506,8 +506,7 @@ define i1 @ctpop_ugt_bitwidth_minus_one_i8(i8 %x, i8* %p) {
 
 define <2 x i1> @ctpop_ult_bitwidth_v2i32(<2 x i32> %x) {
 ; CHECK-LABEL: @ctpop_ult_bitwidth_v2i32(
-; CHECK-NEXT:    [[POP:%.*]] = tail call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> [[X:%.*]])
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ult <2 x i32> [[POP]], <i32 32, i32 32>
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ne <2 x i32> [[X:%.*]], <i32 -1, i32 -1>
 ; CHECK-NEXT:    ret <2 x i1> [[CMP]]
 ;
   %pop = tail call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> %x)