2dcf858ba0
The checks created by LAA only compute a pointer difference and do not need to capture provenance. Use SCEVPtrToAddr instead of SCEVPtrToInt for computations. To avoid regressions while parts of SCEV are migrated to use PtrToAddr this adds logic to rewrite all PtrToInt to PtrToAddr if possible in the created expressions. This is needed to avoid regressions. Similarly, if in the original IR we have a PtrToInt, SCEVExpander tries to re-use it if possible when expanding PtrToAddr. Depends on https://github.com/llvm/llvm-project/pull/178727. Fixes https://github.com/llvm/llvm-project/issues/156978. PR: https://github.com/llvm/llvm-project/pull/178861
43 lines
1.9 KiB
LLVM
43 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "vector.ph\:" --version 5
|
|
; RUN: opt < %s -passes=loop-vectorize,dce,instcombine -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
define void @add_ints(ptr nocapture %A, ptr nocapture %B, ptr nocapture %C) {
|
|
; CHECK-LABEL: define void @add_ints(
|
|
; CHECK-SAME: ptr captures(none) [[A:%.*]], ptr captures(none) [[B:%.*]], ptr captures(none) [[C:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: br label %[[VECTOR_MEMCHECK:.*]]
|
|
; CHECK: [[VECTOR_MEMCHECK]]:
|
|
; CHECK-NEXT: [[A1:%.*]] = ptrtoaddr ptr [[A]] to i64
|
|
; CHECK-NEXT: [[B2:%.*]] = ptrtoaddr ptr [[B]] to i64
|
|
; CHECK-NEXT: [[C3:%.*]] = ptrtoaddr ptr [[C]] to i64
|
|
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 [[A1]], [[B2]]
|
|
; CHECK-NEXT: [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP0]], 16
|
|
; CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[A1]], [[C3]]
|
|
; CHECK-NEXT: [[DIFF_CHECK4:%.*]] = icmp ult i64 [[TMP1]], 16
|
|
; CHECK-NEXT: [[CONFLICT_RDX:%.*]] = or i1 [[DIFF_CHECK]], [[DIFF_CHECK4]]
|
|
; CHECK-NEXT: br i1 [[CONFLICT_RDX]], [[SCALAR_PH:label %.*]], label %[[VECTOR_PH:.*]]
|
|
; CHECK: [[VECTOR_PH]]:
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %B, i64 %iv
|
|
%0 = load i32, ptr %arrayidx, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, ptr %C, i64 %iv
|
|
%1 = load i32, ptr %arrayidx2, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%arrayidx4 = getelementptr inbounds i32, ptr %A, i64 %iv
|
|
store i32 %add, ptr %arrayidx4, align 4
|
|
%iv.next = add i64 %iv, 1
|
|
%iv.trunc = trunc i64 %iv.next to i32
|
|
%exitcond = icmp eq i32 %iv.trunc, 200
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|