shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/opaque-ptr.ll
Florian Hahn 2f7ccaf4a8
[SCEV] Add predicate in SolveLinEq to ensure B is a multiple of A. (#108777) 
This can help in cases where pointer alignment info is missing, e.g.
https://github.com/llvm/llvm-project/pull/108210

The predicate is formed for the complex expression that's passed to
SolveLinEquationWithOverflow and the checks could probably be pushed
closer to the root nodes, which in some cases may be cheaper to check.


PR: https://github.com/llvm/llvm-project/pull/108777
2024-09-28 14:19:57 +01:00

249 lines
14 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes=loop-vectorize -force-vector-width=2 < %s | FileCheck %s
define void @test_ptr_iv_no_inbounds(ptr %p1.start, ptr %p2.start, ptr %p1.end) {
; CHECK-LABEL: @test_ptr_iv_no_inbounds(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[P1_START7:%.*]] = ptrtoint ptr [[P1_START:%.*]] to i64
; CHECK-NEXT: [[P1_END6:%.*]] = ptrtoint ptr [[P1_END:%.*]] to i64
; CHECK-NEXT: [[P1_START4:%.*]] = ptrtoint ptr [[P1_START]] to i64
; CHECK-NEXT: [[P1_END3:%.*]] = ptrtoint ptr [[P1_END]] to i64
; CHECK-NEXT: [[P1_START2:%.*]] = ptrtoint ptr [[P1_START]] to i64
; CHECK-NEXT: [[P1_END1:%.*]] = ptrtoint ptr [[P1_END]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[P1_END6]], -4
; CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[TMP0]], [[P1_START7]]
; CHECK-NEXT: [[TMP2:%.*]] = lshr i64 [[TMP1]], 2
; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 2
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[TMP4:%.*]] = trunc i64 [[P1_END1]] to i2
; CHECK-NEXT: [[TMP5:%.*]] = trunc i64 [[P1_START2]] to i2
; CHECK-NEXT: [[TMP6:%.*]] = sub i2 [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = zext i2 [[TMP6]] to i64
; CHECK-NEXT: [[IDENT_CHECK:%.*]] = icmp ne i64 [[TMP7]], 0
; CHECK-NEXT: br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[TMP8:%.*]] = add i64 [[P1_END3]], -4
; CHECK-NEXT: [[TMP9:%.*]] = sub i64 [[TMP8]], [[P1_START4]]
; CHECK-NEXT: [[TMP10:%.*]] = lshr i64 [[TMP9]], 2
; CHECK-NEXT: [[TMP11:%.*]] = shl nuw i64 [[TMP10]], 2
; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[TMP11]], 4
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P1_START]], i64 [[TMP12]]
; CHECK-NEXT: [[SCEVGEP5:%.*]] = getelementptr i8, ptr [[P2_START:%.*]], i64 [[TMP12]]
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[P1_START]], [[SCEVGEP5]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[P2_START]], [[SCEVGEP]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP3]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP3]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP13:%.*]] = mul i64 [[N_VEC]], 4
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[P1_START]], i64 [[TMP13]]
; CHECK-NEXT: [[TMP14:%.*]] = mul i64 [[N_VEC]], 4
; CHECK-NEXT: [[IND_END8:%.*]] = getelementptr i8, ptr [[P2_START]], i64 [[TMP14]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP15:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[P1_START]], i64 [[TMP15]]
; CHECK-NEXT: [[OFFSET_IDX10:%.*]] = mul i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP16:%.*]] = add i64 [[OFFSET_IDX10]], 0
; CHECK-NEXT: [[NEXT_GEP11:%.*]] = getelementptr i8, ptr [[P2_START]], i64 [[TMP16]]
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr float, ptr [[NEXT_GEP]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP17]], align 4, !alias.scope [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
; CHECK-NEXT: [[TMP18:%.*]] = getelementptr float, ptr [[NEXT_GEP11]], i32 0
; CHECK-NEXT: [[WIDE_LOAD12:%.*]] = load <2 x float>, ptr [[TMP18]], align 4, !alias.scope [[META3]]
; CHECK-NEXT: [[TMP19:%.*]] = fadd <2 x float> [[WIDE_LOAD]], [[WIDE_LOAD12]]
; CHECK-NEXT: store <2 x float> [[TMP19]], ptr [[TMP17]], align 4, !alias.scope [[META0]], !noalias [[META3]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP3]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P1_START]], [[ENTRY:%.*]] ], [ [[P1_START]], [[VECTOR_SCEVCHECK]] ], [ [[P1_START]], [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL9:%.*]] = phi ptr [ [[IND_END8]], [[MIDDLE_BLOCK]] ], [ [[P2_START]], [[ENTRY]] ], [ [[P2_START]], [[VECTOR_SCEVCHECK]] ], [ [[P2_START]], [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[P1:%.*]] = phi ptr [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[P1_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[P2:%.*]] = phi ptr [ [[BC_RESUME_VAL9]], [[SCALAR_PH]] ], [ [[P2_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[P1_VAL:%.*]] = load float, ptr [[P1]], align 4
; CHECK-NEXT: [[P2_VAL:%.*]] = load float, ptr [[P2]], align 4
; CHECK-NEXT: [[SUM:%.*]] = fadd float [[P1_VAL]], [[P2_VAL]]
; CHECK-NEXT: store float [[SUM]], ptr [[P1]], align 4
; CHECK-NEXT: [[P1_NEXT]] = getelementptr float, ptr [[P1]], i64 1
; CHECK-NEXT: [[P2_NEXT]] = getelementptr float, ptr [[P2]], i64 1
; CHECK-NEXT: [[C:%.*]] = icmp ne ptr [[P1_NEXT]], [[P1_END]]
; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%p1 = phi ptr [ %p1.start, %entry ], [ %p1.next, %loop ]
%p2 = phi ptr [ %p2.start, %entry ], [ %p2.next, %loop ]
%p1.val = load float, ptr %p1
%p2.val = load float, ptr %p2
%sum = fadd float %p1.val, %p2.val
store float %sum, ptr %p1
%p1.next = getelementptr float, ptr %p1, i64 1
%p2.next = getelementptr float, ptr %p2, i64 1
%c = icmp ne ptr %p1.next, %p1.end
br i1 %c, label %loop, label %exit
exit:
ret void
}
define void @test_ptr_iv_with_inbounds(ptr %p1.start, ptr %p2.start, ptr %p1.end) {
; CHECK-LABEL: @test_ptr_iv_with_inbounds(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[P1_START5:%.*]] = ptrtoint ptr [[P1_START:%.*]] to i64
; CHECK-NEXT: [[P1_END4:%.*]] = ptrtoint ptr [[P1_END:%.*]] to i64
; CHECK-NEXT: [[P1_START2:%.*]] = ptrtoint ptr [[P1_START]] to i64
; CHECK-NEXT: [[P1_END1:%.*]] = ptrtoint ptr [[P1_END]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[P1_END4]], -4
; CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[TMP0]], [[P1_START5]]
; CHECK-NEXT: [[TMP2:%.*]] = lshr i64 [[TMP1]], 2
; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 2
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[TMP4:%.*]] = add i64 [[P1_END1]], -4
; CHECK-NEXT: [[TMP5:%.*]] = sub i64 [[TMP4]], [[P1_START2]]
; CHECK-NEXT: [[TMP6:%.*]] = lshr i64 [[TMP5]], 2
; CHECK-NEXT: [[TMP7:%.*]] = shl nuw i64 [[TMP6]], 2
; CHECK-NEXT: [[TMP8:%.*]] = add i64 [[TMP7]], 4
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P1_START]], i64 [[TMP8]]
; CHECK-NEXT: [[SCEVGEP3:%.*]] = getelementptr i8, ptr [[P2_START:%.*]], i64 [[TMP8]]
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[P1_START]], [[SCEVGEP3]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[P2_START]], [[SCEVGEP]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP3]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP3]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP9:%.*]] = mul i64 [[N_VEC]], 4
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[P1_START]], i64 [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = mul i64 [[N_VEC]], 4
; CHECK-NEXT: [[IND_END6:%.*]] = getelementptr i8, ptr [[P2_START]], i64 [[TMP10]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP11:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[P1_START]], i64 [[TMP11]]
; CHECK-NEXT: [[OFFSET_IDX8:%.*]] = mul i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[OFFSET_IDX8]], 0
; CHECK-NEXT: [[NEXT_GEP9:%.*]] = getelementptr i8, ptr [[P2_START]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr float, ptr [[NEXT_GEP]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP13]], align 4, !alias.scope [[META9:![0-9]+]], !noalias [[META12:![0-9]+]]
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr float, ptr [[NEXT_GEP9]], i32 0
; CHECK-NEXT: [[WIDE_LOAD10:%.*]] = load <2 x float>, ptr [[TMP14]], align 4, !alias.scope [[META12]]
; CHECK-NEXT: [[TMP15:%.*]] = fadd <2 x float> [[WIDE_LOAD]], [[WIDE_LOAD10]]
; CHECK-NEXT: store <2 x float> [[TMP15]], ptr [[TMP13]], align 4, !alias.scope [[META9]], !noalias [[META12]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP3]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P1_START]], [[ENTRY:%.*]] ], [ [[P1_START]], [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: [[BC_RESUME_VAL7:%.*]] = phi ptr [ [[IND_END6]], [[MIDDLE_BLOCK]] ], [ [[P2_START]], [[ENTRY]] ], [ [[P2_START]], [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[P1:%.*]] = phi ptr [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[P1_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[P2:%.*]] = phi ptr [ [[BC_RESUME_VAL7]], [[SCALAR_PH]] ], [ [[P2_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[P1_VAL:%.*]] = load float, ptr [[P1]], align 4
; CHECK-NEXT: [[P2_VAL:%.*]] = load float, ptr [[P2]], align 4
; CHECK-NEXT: [[SUM:%.*]] = fadd float [[P1_VAL]], [[P2_VAL]]
; CHECK-NEXT: store float [[SUM]], ptr [[P1]], align 4
; CHECK-NEXT: [[P1_NEXT]] = getelementptr inbounds float, ptr [[P1]], i64 1
; CHECK-NEXT: [[P2_NEXT]] = getelementptr inbounds float, ptr [[P2]], i64 1
; CHECK-NEXT: [[C:%.*]] = icmp ne ptr [[P1_NEXT]], [[P1_END]]
; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP15:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%p1 = phi ptr [ %p1.start, %entry ], [ %p1.next, %loop ]
%p2 = phi ptr [ %p2.start, %entry ], [ %p2.next, %loop ]
%p1.val = load float, ptr %p1
%p2.val = load float, ptr %p2
%sum = fadd float %p1.val, %p2.val
store float %sum, ptr %p1
%p1.next = getelementptr inbounds float, ptr %p1, i64 1
%p2.next = getelementptr inbounds float, ptr %p2, i64 1
%c = icmp ne ptr %p1.next, %p1.end
br i1 %c, label %loop, label %exit
exit:
ret void
}
define void @store_pointer_induction(ptr %start, ptr %end) {
; CHECK-LABEL: @store_pointer_induction(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[START2:%.*]] = ptrtoint ptr [[START:%.*]] to i64
; CHECK-NEXT: [[END1:%.*]] = ptrtoint ptr [[END:%.*]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[END1]], -8
; CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
; CHECK-NEXT: [[TMP2:%.*]] = lshr i64 [[TMP1]], 3
; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 2
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP3]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP3]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[N_VEC]], 8
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 [[TMP4]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[POINTER_PHI:%.*]] = phi ptr [ [[START]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <2 x i64> <i64 0, i64 8>
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x ptr> [[TMP5]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr ptr, ptr [[TMP6]], i32 0
; CHECK-NEXT: store <2 x ptr> [[TMP5]], ptr [[TMP7]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 16
; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP3]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[START]], [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: store ptr [[IV]], ptr [[IV]], align 4
; CHECK-NEXT: [[IV_NEXT]] = getelementptr inbounds ptr, ptr [[IV]], i32 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq ptr [[IV_NEXT]], [[END]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi ptr [ %start, %entry ], [ %iv.next, %loop ]
store ptr %iv, ptr %iv, align 4
%iv.next = getelementptr inbounds ptr, ptr %iv, i32 1
%exitcond = icmp eq ptr %iv.next, %end
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
Reference in New Issue View Git Blame Copy Permalink