diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp --- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp @@ -3024,6 +3024,18 @@ } } + // Given: + // icmp eq/ne (urem %x, %y), 0 + // Iff %x has 0 or 1 bits set, and %y has at least 2 bits set, omit 'urem': + // icmp eq/ne %x, 0 + if (N0.getOpcode() == ISD::UREM && N1C->isNullValue() && + (Cond == ISD::SETEQ || Cond == ISD::SETNE)) { + KnownBits XKnown = DAG.computeKnownBits(N0.getOperand(0)); + KnownBits YKnown = DAG.computeKnownBits(N0.getOperand(1)); + if (XKnown.countMaxPopulation() == 1 && YKnown.countMinPopulation() >= 2) + return DAG.getSetCC(dl, VT, N0.getOperand(0), N1, Cond); + } + if (SDValue V = optimizeSetCCOfSignedTruncationCheck(VT, N0, N1, Cond, DCI, dl)) return V; diff --git a/llvm/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll b/llvm/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll --- a/llvm/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll +++ b/llvm/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll @@ -14,14 +14,7 @@ define i1 @p0_scalar_urem_by_const(i32 %x, i32 %y) { ; CHECK-LABEL: p0_scalar_urem_by_const: ; CHECK: # %bb.0: -; CHECK-NEXT: # kill: def $edi killed $edi def $rdi -; CHECK-NEXT: andl $128, %edi -; CHECK-NEXT: movl $2863311531, %eax # imm = 0xAAAAAAAB -; CHECK-NEXT: imulq %rdi, %rax -; CHECK-NEXT: shrq $34, %rax -; CHECK-NEXT: addl %eax, %eax -; CHECK-NEXT: leal (%rax,%rax,2), %eax -; CHECK-NEXT: cmpl %eax, %edi +; CHECK-NEXT: testb $-128, %dil ; CHECK-NEXT: sete %al ; CHECK-NEXT: retq %t0 = and i32 %x, 128 ; clearly a power-of-two or zero @@ -33,12 +26,7 @@ define i1 @p1_scalar_urem_by_nonconst(i32 %x, i32 %y) { ; CHECK-LABEL: p1_scalar_urem_by_nonconst: ; CHECK: # %bb.0: -; CHECK-NEXT: movl %edi, %eax -; CHECK-NEXT: andl $128, %eax -; CHECK-NEXT: orl $6, %esi -; CHECK-NEXT: xorl %edx, %edx -; CHECK-NEXT: divl %esi -; CHECK-NEXT: testl %edx, %edx +; CHECK-NEXT: testb $-128, %dil ; CHECK-NEXT: sete %al ; CHECK-NEXT: retq %t0 = and i32 %x, 128 ; clearly a power-of-two or zero