llvm-project/llvm/test/Transforms/LoopStrengthReduce/X86/2008-08-14-ShadowIV.ll

100 lines
2.9 KiB
LLVM
Raw Normal View History

Switch the SCEV expander and LoopStrengthReduce to use TargetTransformInfo rather than TargetLowering, removing one of the primary instances of the layering violation of Transforms depending directly on Target. This is a really big deal because LSR used to be a "special" pass that could only be tested fully using llc and by looking at the full output of it. It also couldn't run with any other loop passes because it had to be created by the backend. No longer is this true. LSR is now just a normal pass and we should probably lift the creation of LSR out of lib/CodeGen/Passes.cpp and into the PassManagerBuilder. =] I've not done this, or updated all of the tests to use opt and a triple, because I suspect someone more familiar with LSR would do a better job. This change should be essentially without functional impact for normal compilations, and only change behvaior of targetless compilations. The conversion required changing all of the LSR code to refer to the TTI interfaces, which fortunately are very similar to TargetLowering's interfaces. However, it also allowed us to *always* expect to have some implementation around. I've pushed that simplification through the pass, and leveraged it to simplify code somewhat. It required some test updates for one of two things: either we used to skip some checks altogether but now we get the default "no" answer for them, or we used to have no information about the target and now we do have some. I've also started the process of removing AddrMode, as the TTI interface doesn't use it any longer. In some cases this simplifies code, and in others it adds some complexity, but I think it's not a bad tradeoff even there. Subsequent patches will try to clean this up even further and use other (more appropriate) abstractions. Yet again, almost all of the formatting changes brought to you by clang-format. =] llvm-svn: 171735
2013-01-07 22:41:08 +08:00
; RUN: opt < %s -loop-reduce -S -mtriple=x86_64-unknown-unknown | grep "phi double" | count 1
define void @foobar(i32 %n) nounwind {
entry:
icmp eq i32 %n, 0 ; <i1>:0 [#uses=2]
br i1 %0, label %return, label %bb.nph
bb.nph: ; preds = %entry
%umax = select i1 %0, i32 1, i32 %n ; <i32> [#uses=1]
br label %bb
bb: ; preds = %bb, %bb.nph
%i.03 = phi i32 [ 0, %bb.nph ], [ %indvar.next, %bb ] ; <i32> [#uses=3]
tail call void @bar( i32 %i.03 ) nounwind
uitofp i32 %i.03 to double ; <double>:1 [#uses=1]
tail call void @foo( double %1 ) nounwind
%indvar.next = add i32 %i.03, 1 ; <i32> [#uses=2]
%exitcond = icmp eq i32 %indvar.next, %umax ; <i1> [#uses=1]
br i1 %exitcond, label %return, label %bb
return: ; preds = %bb, %entry
ret void
}
; Unable to eliminate cast because the mantissa bits for double are not enough
; to hold all of i64 IV bits.
define void @foobar2(i64 %n) nounwind {
entry:
icmp eq i64 %n, 0 ; <i1>:0 [#uses=2]
br i1 %0, label %return, label %bb.nph
bb.nph: ; preds = %entry
%umax = select i1 %0, i64 1, i64 %n ; <i64> [#uses=1]
br label %bb
bb: ; preds = %bb, %bb.nph
%i.03 = phi i64 [ 0, %bb.nph ], [ %indvar.next, %bb ] ; <i64> [#uses=3]
trunc i64 %i.03 to i32 ; <i32>:1 [#uses=1]
tail call void @bar( i32 %1 ) nounwind
uitofp i64 %i.03 to double ; <double>:2 [#uses=1]
tail call void @foo( double %2 ) nounwind
%indvar.next = add i64 %i.03, 1 ; <i64> [#uses=2]
%exitcond = icmp eq i64 %indvar.next, %umax ; <i1> [#uses=1]
br i1 %exitcond, label %return, label %bb
return: ; preds = %bb, %entry
ret void
}
; Unable to eliminate cast due to potentional overflow.
define void @foobar3() nounwind {
entry:
tail call i32 (...)* @nn( ) nounwind ; <i32>:0 [#uses=1]
icmp eq i32 %0, 0 ; <i1>:1 [#uses=1]
br i1 %1, label %return, label %bb
bb: ; preds = %bb, %entry
%i.03 = phi i32 [ 0, %entry ], [ %3, %bb ] ; <i32> [#uses=3]
tail call void @bar( i32 %i.03 ) nounwind
uitofp i32 %i.03 to double ; <double>:2 [#uses=1]
tail call void @foo( double %2 ) nounwind
add i32 %i.03, 1 ; <i32>:3 [#uses=2]
tail call i32 (...)* @nn( ) nounwind ; <i32>:4 [#uses=1]
icmp ugt i32 %4, %3 ; <i1>:5 [#uses=1]
br i1 %5, label %bb, label %return
return: ; preds = %bb, %entry
ret void
}
; Unable to eliminate cast due to overflow.
define void @foobar4() nounwind {
entry:
br label %bb.nph
bb.nph: ; preds = %entry
br label %bb
bb: ; preds = %bb, %bb.nph
%i.03 = phi i8 [ 0, %bb.nph ], [ %indvar.next, %bb ] ; <i32> [#uses=3]
%tmp2 = sext i8 %i.03 to i32 ; <i32>:0 [#uses=1]
tail call void @bar( i32 %tmp2 ) nounwind
%tmp3 = uitofp i8 %i.03 to double ; <double>:1 [#uses=1]
tail call void @foo( double %tmp3 ) nounwind
%indvar.next = add i8 %i.03, 1 ; <i32> [#uses=2]
%tmp = sext i8 %indvar.next to i32
%exitcond = icmp eq i32 %tmp, 32767 ; <i1> [#uses=1]
br i1 %exitcond, label %return, label %bb
return: ; preds = %bb, %entry
ret void
}
declare void @bar(i32)
declare void @foo(double)
declare i32 @nn(...)