[X86] Prevent constant hoisting for a couple compare immediates that the selection DAG knows how to optimize into a shift.

This allows "icmp ugt %a, 4294967295" and "icmp uge %a, 4294967296" to be optimized into right shifts by 32 which can fold the immediate into the shift instruction. These patterns show up with some regularity in real code.

Unfortunately, since getImmCost can't see the icmp predicate we can't be tell if we're only catching these specific cases.

llvm-svn: 256126
This commit is contained in:
Craig Topper 2015-12-20 18:41:54 +00:00
parent 30e2307f61
commit 074e845260
2 changed files with 38 additions and 1 deletions

View File

@ -1199,6 +1199,19 @@ int X86TTIImpl::getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
case Instruction::Store:
ImmIdx = 0;
break;
case Instruction::ICmp:
// This is an imperfect hack to prevent constant hoisting of
// compares that might be trying to check if a 64-bit value fits in
// 32-bits. The backend can optimize these cases using a right shift by 32.
// Ideally we would check the compare predicate here. There also other
// similar immediates the backend can use shifts for.
if (Idx == 1 && Imm.getBitWidth() == 64) {
uint64_t ImmVal = Imm.getZExtValue();
if (ImmVal == 0x100000000ULL || ImmVal == 0xffffffff)
return TTI::TCC_Free;
}
ImmIdx = 1;
break;
case Instruction::And:
// We support 64-bit ANDs with immediates with 32-bits of leading zeroes
// by using a 32-bit operation with implicit zero extension. Detect such
@ -1215,7 +1228,6 @@ int X86TTIImpl::getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
case Instruction::SRem:
case Instruction::Or:
case Instruction::Xor:
case Instruction::ICmp:
ImmIdx = 1;
break;
// Always return TCC_Free for the shift value of a shift instruction.

View File

@ -0,0 +1,25 @@
; RUN: llc < %s -O3 -march=x86-64 |FileCheck %s
define i64 @foo(i64 %data1, i64 %data2, i64 %data3)
{
; If constant 4294967295 is hoisted to a variable, then we won't be able to
; use a shift right by 32 to optimize the compare.
entry:
%val1 = add i64 %data3, 1
%x = icmp ugt i64 %data1, 4294967295
br i1 %x, label %End, label %L_val2
; CHECK: shrq $32, {{.*}}
; CHECK: shrq $32, {{.*}}
L_val2:
%val2 = add i64 %data3, 2
%y = icmp ugt i64 %data2, 4294967295
br i1 %y, label %End, label %L_val3
L_val3:
%val3 = add i64 %data3, 3
br label %End
End:
%p1 = phi i64 [%val1,%entry], [%val2,%L_val2], [%val3,%L_val3]
ret i64 %p1
}