844c188c79
Update getDependenceDistanceStrideAndSize to reason about different combinations of strides directly and explicitly. Update getPtrStride to return 0 for invariant pointers. Then proceed by checking the strides. If either source or sink are not strided by a constant (i.e. not a non-wrapping AddRec) or invariant, the accesses may overlap with earlier or later iterations and we cannot generate runtime checks to disambiguate them. Otherwise they are either loop invariant or strided. In that case, we can generate a runtime check to disambiguate them. If both are strided by constants, we proceed as previously. This is an alternative to https://github.com/llvm/llvm-project/pull/99239 and also replaces additional checks if the underlying object is loop-invariant. Fixes https://github.com/llvm/llvm-project/issues/87189. PR: https://github.com/llvm/llvm-project/pull/99577
42 lines
1.6 KiB
LLVM
42 lines
1.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -passes='print<access-info>' -disable-output 2>&1 < %s | FileCheck %s
|
|
|
|
define void @test(ptr noalias %x, ptr noalias %y, ptr noalias %z) {
|
|
; CHECK-LABEL: 'test'
|
|
; CHECK-NEXT: loop:
|
|
; CHECK-NEXT: Report: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop
|
|
; CHECK-NEXT: Unsafe indirect dependence.
|
|
; CHECK-NEXT: Dependences:
|
|
; CHECK-NEXT: IndirectUnsafe:
|
|
; CHECK-NEXT: %load = load double, ptr %gep.sel, align 8 ->
|
|
; CHECK-NEXT: store double %load, ptr %gep.sel2, align 8
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Run-time memory checks:
|
|
; CHECK-NEXT: Grouped accesses:
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
|
|
; CHECK-NEXT: SCEV assumptions:
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Expressions re-written:
|
|
;
|
|
entry:
|
|
%gep.y = getelementptr double, ptr %y, i64 -32
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ %iv.next, %loop ], [ 0, %entry ]
|
|
%icmp = icmp ule i64 %iv, 32
|
|
%sel = select i1 %icmp, ptr %x, ptr %gep.y
|
|
%gep.sel = getelementptr inbounds double, ptr %sel, i64 %iv
|
|
%load = load double, ptr %gep.sel, align 8
|
|
%sel2 = select i1 %icmp, ptr %y, ptr %z
|
|
%gep.sel2 = getelementptr inbounds double, ptr %sel2, i64 %iv
|
|
store double %load, ptr %gep.sel2, align 8
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exit.cond = icmp eq i64 %iv, 94
|
|
br i1 %exit.cond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|