[CodeGenPrepare] Use isKnownNonZero

Author: dtcxzyw

llvm/lib/CodeGen/CodeGenPrepare.cpp

@@ -2114,22 +2114,17 @@ bool CodeGenPrepare::optimizeURem(Instruction *Rem) {
 /// Some targets have better codegen for `ctpop(X) u< 2` than `ctpop(X) == 1`.
 /// This function converts `ctpop(X) ==/!= 1` into `ctpop(X) u</u> 2/1` if the
 /// result cannot be zero.
-static bool adjustIsPower2Test(CmpInst *Cmp) {
+static bool adjustIsPower2Test(CmpInst *Cmp, const DataLayout &DL) {
   ICmpInst::Predicate Pred;
   if (!match(Cmp, m_ICmp(Pred, m_Intrinsic<Intrinsic::ctpop>(), m_One())))
     return false;
   if (!ICmpInst::isEquality(Pred))
     return false;
   auto *II = cast<IntrinsicInst>(Cmp->getOperand(0));
-  if (auto Range = II->getRange()) {
-    Type *Ty = II->getType();
-    unsigned BitWidth = Ty->getScalarSizeInBits();
-    if (Range->contains(APInt::getZero(BitWidth)))
-      return false;
-
+  if (isKnownNonZero(II, DL)) {
     if (Pred == ICmpInst::ICMP_EQ) {
       Cmp->setPredicate(ICmpInst::ICMP_ULT);
-      Cmp->setOperand(1, ConstantInt::get(Ty, 2));
+      Cmp->setOperand(1, ConstantInt::get(II->getType(), 2));
     } else
       Cmp->setPredicate(ICmpInst::ICMP_UGT);
     return true;
@@ -2156,7 +2151,7 @@ bool CodeGenPrepare::optimizeCmp(CmpInst *Cmp, ModifyDT &ModifiedDT) {
   if (foldFCmpToFPClassTest(Cmp, *TLI, *DL))
     return true;
 
-  if (adjustIsPower2Test(Cmp))
+  if (adjustIsPower2Test(Cmp, *DL))
     return true;
 
   return false;

llvm/test/CodeGen/X86/ispow2.ll

@@ -102,7 +102,7 @@ define <4 x i1> @is_pow2_non_zero_4xv64(<4 x i64> %xin) {
 ; CHECK-AVX512:       # %bb.0:
 ; CHECK-AVX512-NEXT:    vporq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm0, %ymm0
 ; CHECK-AVX512-NEXT:    vpopcntq %ymm0, %ymm0
-; CHECK-AVX512-NEXT:    vpcmpeqq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm0, %k1
+; CHECK-AVX512-NEXT:    vpcmpltq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm0, %k1
 ; CHECK-AVX512-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
 ; CHECK-AVX512-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
 ; CHECK-AVX512-NEXT:    vzeroupper
@@ -155,7 +155,7 @@ define <4 x i1> @neither_pow2_non_zero_4xv64(<4 x i64> %xin) {
 ; CHECK-AVX512:       # %bb.0:
 ; CHECK-AVX512-NEXT:    vporq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm0, %ymm0
 ; CHECK-AVX512-NEXT:    vpopcntq %ymm0, %ymm0
-; CHECK-AVX512-NEXT:    vpcmpneqq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm0, %k1
+; CHECK-AVX512-NEXT:    vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm0, %k1
 ; CHECK-AVX512-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
 ; CHECK-AVX512-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
 ; CHECK-AVX512-NEXT:    vzeroupper

llvm/test/CodeGen/X86/known-never-zero.ll

@@ -555,9 +555,9 @@ define <4 x i32> @smax_known_zero_vec(<4 x i32> %x, <4 x i32> %y) {
 ; X86-NEXT:    por %xmm2, %xmm0
 ; X86-NEXT:    pcmpeqd %xmm1, %xmm1
 ; X86-NEXT:    paddd %xmm0, %xmm1
-; X86-NEXT:    pxor {{\.?LCPI[0-9]+_[0-9]+}}, %xmm1
-; X86-NEXT:    pxor %xmm1, %xmm0
-; X86-NEXT:    pcmpgtd %xmm1, %xmm0
+; X86-NEXT:    pand %xmm1, %xmm0
+; X86-NEXT:    pxor %xmm1, %xmm1
+; X86-NEXT:    pcmpeqd %xmm1, %xmm0
 ; X86-NEXT:    psrld $31, %xmm0
 ; X86-NEXT:    retl
 ;
@@ -566,10 +566,10 @@ define <4 x i32> @smax_known_zero_vec(<4 x i32> %x, <4 x i32> %y) {
 ; X64-NEXT:    vpmaxsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
 ; X64-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
 ; X64-NEXT:    vpaddd %xmm1, %xmm0, %xmm1
-; X64-NEXT:    vpxor %xmm1, %xmm0, %xmm0
-; X64-NEXT:    vpminud %xmm1, %xmm0, %xmm1
+; X64-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; X64-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; X64-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
-; X64-NEXT:    vpandn {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
+; X64-NEXT:    vpsrld $31, %xmm0, %xmm0
 ; X64-NEXT:    retq
   %z = call <4 x i32> @llvm.smax.v4i32(<4 x i32> %x, <4 x i32> <i32 54, i32 23, i32 12, i32 1>)
   %r = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %z)