e56a6a2683
Relative to the previous attempt this includes two fixes:
* Adjust callCapturesBefore() to not skip captures(ret: address,
provenance) arguments, as these will not count as a capture
at the call-site.
* When visiting uses during stack slot optimization, don't skip
the ModRef check for passthru captures. Calls can both modref
and be passthru for captures.
------
This extends CaptureTracking to support inferring non-trivial
CaptureInfos. The focus of this patch is to only support FunctionAttrs,
other users of CaptureTracking will be updated in followups.
The key API changes here are:
* DetermineUseCaptureKind() now returns a UseCaptureInfo where the UseCC
component specifies what is captured at that Use and the ResultCC
component specifies what may be captured via the return value of the
User. Usually only one or the other will be used (corresponding to
previous MAY_CAPTURE or PASSTHROUGH results), but both may be set for
call captures.
* The CaptureTracking::captures() extension point is passed this
UseCaptureInfo as well and then can decide what to do with it by
returning an Action, which is one of: Stop: stop traversal.
ContinueIgnoringReturn: continue traversal but don't follow the
instruction return value. Continue: continue traversal and follow the
instruction return value if it has additional CaptureComponents.
For now, this patch retains the (unsound) special logic for comparison
of null with a dereferenceable pointer. I'd like to switch key code to
take advantage of address/address_is_null before dropping it.
This PR mainly intends to introduce necessary API changes and basic
inference support, there are various possible improvements marked with
TODOs.
58 lines
2.7 KiB
LLVM
58 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
|
|
|
|
;; Check that -enable-loop-header-duplication at Oz enables certain types of
|
|
;; optimizations, for example replacing the loop body w/ a call to memset. If
|
|
;; loop idiom recognition begins to recognize unrotated loops, this test will
|
|
;; need to be updated.
|
|
|
|
; RUN: opt -passes='default<Oz>' -S < %s | FileCheck %s --check-prefix=NOROTATION
|
|
; RUN: opt -passes='default<Oz>' -S -enable-loop-header-duplication < %s | FileCheck %s --check-prefix=ROTATION
|
|
; RUN: opt -passes='default<O2>' -S < %s | FileCheck %s --check-prefix=ROTATION
|
|
|
|
define void @test(i8* noalias nonnull align 1 %start, i8* %end) unnamed_addr {
|
|
; NOROTATION-LABEL: define void @test(
|
|
; NOROTATION-SAME: ptr noalias nonnull writeonly align 1 captures(address) [[START:%.*]], ptr readnone captures(address) [[END:%.*]]) unnamed_addr #[[ATTR0:[0-9]+]] {
|
|
; NOROTATION-NEXT: entry:
|
|
; NOROTATION-NEXT: br label [[LOOP_HEADER:%.*]]
|
|
; NOROTATION: loop.header:
|
|
; NOROTATION-NEXT: [[PTR_IV:%.*]] = phi ptr [ [[START]], [[ENTRY:%.*]] ], [ [[PTR_IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
|
|
; NOROTATION-NEXT: [[_12_I:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
|
|
; NOROTATION-NEXT: br i1 [[_12_I]], label [[EXIT:%.*]], label [[LOOP_LATCH]]
|
|
; NOROTATION: loop.latch:
|
|
; NOROTATION-NEXT: [[PTR_IV_NEXT]] = getelementptr inbounds nuw i8, ptr [[PTR_IV]], i64 1
|
|
; NOROTATION-NEXT: store i8 1, ptr [[PTR_IV]], align 1
|
|
; NOROTATION-NEXT: br label [[LOOP_HEADER]]
|
|
; NOROTATION: exit:
|
|
; NOROTATION-NEXT: ret void
|
|
;
|
|
; ROTATION-LABEL: define void @test(
|
|
; ROTATION-SAME: ptr noalias nonnull writeonly align 1 captures(address) [[START:%.*]], ptr readnone captures(address) [[END:%.*]]) unnamed_addr #[[ATTR0:[0-9]+]] {
|
|
; ROTATION-NEXT: entry:
|
|
; ROTATION-NEXT: [[_12_I1:%.*]] = icmp eq ptr [[START]], [[END]]
|
|
; ROTATION-NEXT: br i1 [[_12_I1]], label [[EXIT:%.*]], label [[LOOP_LATCH_PREHEADER:%.*]]
|
|
; ROTATION: loop.latch.preheader:
|
|
; ROTATION-NEXT: [[END3:%.*]] = ptrtoint ptr [[END]] to i64
|
|
; ROTATION-NEXT: [[START4:%.*]] = ptrtoint ptr [[START]] to i64
|
|
; ROTATION-NEXT: [[TMP0:%.*]] = sub i64 [[END3]], [[START4]]
|
|
; ROTATION-NEXT: tail call void @llvm.memset.p0.i64(ptr nonnull align 1 [[START]], i8 1, i64 [[TMP0]], i1 false)
|
|
; ROTATION-NEXT: br label [[EXIT]]
|
|
; ROTATION: exit:
|
|
; ROTATION-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %loop.header
|
|
|
|
loop.header:
|
|
%ptr.iv = phi i8* [ %start, %entry ], [ %ptr.iv.next, %loop.latch ]
|
|
%_12.i = icmp eq i8* %ptr.iv, %end
|
|
br i1 %_12.i, label %exit, label %loop.latch
|
|
|
|
loop.latch:
|
|
%ptr.iv.next = getelementptr inbounds i8, i8* %ptr.iv, i64 1
|
|
store i8 1, i8* %ptr.iv, align 1
|
|
br label %loop.header
|
|
|
|
exit:
|
|
ret void
|
|
}
|