llvm/test/Transforms/InstCombine/all-bits-shift.ll
Matthias Braun e152c1527d InstCombine: Restrict computeKnownBits() on all Values to OptLevel > 2
As part of r251146 InstCombine was extended to call computeKnownBits on
every value in the function to determine whether it happens to be
constant. This increases typical compiletime by 1-3% (5% in irgen+opt
time) in my measurements. On the other hand this case did not trigger
once in the whole llvm-testsuite.

This patch introduces the notion of ExpensiveCombines which are only
enabled for OptLevel > 2. I removed the check in InstructionSimplify as
that is called from various places where the OptLevel is not known but
given the rarity of the situation I think a check in InstCombine is
enough.

Differential Revision: http://reviews.llvm.org/D16835

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@263047 91177308-0d34-0410-b5e6-96231b3b80d8
2016-03-09 18:47:11 +00:00

46 lines
1.3 KiB
LLVM

; RUN: opt -S -instcombine -expensive-combines < %s | FileCheck %s
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
@d = global i32 15, align 4
@b = global i32* @d, align 8
@a = common global i32 0, align 4
; Function Attrs: nounwind
define signext i32 @main() #1 {
entry:
%0 = load i32*, i32** @b, align 8
%1 = load i32, i32* @a, align 4
%lnot = icmp eq i32 %1, 0
%lnot.ext = zext i1 %lnot to i32
%shr.i = lshr i32 2072, %lnot.ext
%call.lobit = lshr i32 %shr.i, 7
%2 = and i32 %call.lobit, 1
%3 = load i32, i32* %0, align 4
%or = or i32 %2, %3
store i32 %or, i32* %0, align 4
%4 = load i32, i32* @a, align 4
%lnot.1 = icmp eq i32 %4, 0
%lnot.ext.1 = zext i1 %lnot.1 to i32
%shr.i.1 = lshr i32 2072, %lnot.ext.1
%call.lobit.1 = lshr i32 %shr.i.1, 7
%5 = and i32 %call.lobit.1, 1
%or.1 = or i32 %5, %or
store i32 %or.1, i32* %0, align 4
ret i32 %or.1
; Check that both InstCombine and InstSimplify can use computeKnownBits to
; realize that:
; ((2072 >> (L == 0)) >> 7) & 1
; is always zero.
; CHECK-LABEL: @main
; CHECK: %[[V1:[0-9]+]] = load i32*, i32** @b, align 8
; CHECK: %[[V2:[0-9]+]] = load i32, i32* %[[V1]], align 4
; CHECK: ret i32 %[[V2]]
}
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }