| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6 |
| ; RUN: opt -passes=loop-distribute -enable-loop-distribute -S < %s | FileCheck %s |
| |
| ; When emitting the memchecks for: |
| ; |
| ; for (i = 0; i < n; i++) { |
| ; A[i + 1] = A[i] * B[i]; |
| ; ======================= |
| ; C[i] = D[i] * E[i]; |
| ; } |
| ; |
| ; we had a bug when expanding the bounds for A and C. These are expanded |
| ; multiple times and rely on the caching in SCEV expansion to avoid any |
| ; redundancy. However, due to logic in SCEVExpander::ReuseOrCreateCast, we |
| ; can get earlier expanded values invalidated when casts are used. This test |
| ; ensure that we are not using the invalidated values. |
| |
| define void @f(ptr %a1, ptr %a2, ptr %b, ptr %c1, ptr %c2, ptr %d, ptr %e) { |
| ; CHECK-LABEL: define void @f( |
| ; CHECK-SAME: ptr [[A1:%.*]], ptr [[A2:%.*]], ptr [[B:%.*]], ptr [[C1:%.*]], ptr [[C2:%.*]], ptr [[D:%.*]], ptr [[E:%.*]]) { |
| ; CHECK-NEXT: [[ENTRY:.*:]] |
| ; CHECK-NEXT: [[COND:%.*]] = icmp eq ptr [[E]], null |
| ; CHECK-NEXT: br i1 [[COND]], label %[[ONE:.*]], label %[[TWO:.*]] |
| ; CHECK: [[ONE]]: |
| ; CHECK-NEXT: br label %[[JOIN:.*]] |
| ; CHECK: [[TWO]]: |
| ; CHECK-NEXT: br label %[[JOIN]] |
| ; CHECK: [[JOIN]]: |
| ; CHECK-NEXT: [[A:%.*]] = phi ptr [ [[A1]], %[[ONE]] ], [ [[A2]], %[[TWO]] ] |
| ; CHECK-NEXT: [[C:%.*]] = phi ptr [ [[C1]], %[[ONE]] ], [ [[C2]], %[[TWO]] ] |
| ; CHECK-NEXT: br label %[[FOR_BODY_LVER_CHECK:.*]] |
| ; CHECK: [[FOR_BODY_LVER_CHECK]]: |
| ; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[A]], i64 84 |
| ; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[C]], i64 80 |
| ; CHECK-NEXT: [[SCEVGEP2:%.*]] = getelementptr i8, ptr [[D]], i64 80 |
| ; CHECK-NEXT: [[SCEVGEP3:%.*]] = getelementptr i8, ptr [[E]], i64 80 |
| ; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i8, ptr [[B]], i64 80 |
| ; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[A]], [[SCEVGEP1]] |
| ; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[C]], [[SCEVGEP]] |
| ; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]] |
| ; CHECK-NEXT: [[BOUND05:%.*]] = icmp ult ptr [[A]], [[SCEVGEP2]] |
| ; CHECK-NEXT: [[BOUND16:%.*]] = icmp ult ptr [[D]], [[SCEVGEP]] |
| ; CHECK-NEXT: [[FOUND_CONFLICT7:%.*]] = and i1 [[BOUND05]], [[BOUND16]] |
| ; CHECK-NEXT: [[CONFLICT_RDX:%.*]] = or i1 [[FOUND_CONFLICT]], [[FOUND_CONFLICT7]] |
| ; CHECK-NEXT: [[BOUND08:%.*]] = icmp ult ptr [[A]], [[SCEVGEP3]] |
| ; CHECK-NEXT: [[BOUND19:%.*]] = icmp ult ptr [[E]], [[SCEVGEP]] |
| ; CHECK-NEXT: [[FOUND_CONFLICT10:%.*]] = and i1 [[BOUND08]], [[BOUND19]] |
| ; CHECK-NEXT: [[CONFLICT_RDX11:%.*]] = or i1 [[CONFLICT_RDX]], [[FOUND_CONFLICT10]] |
| ; CHECK-NEXT: [[BOUND012:%.*]] = icmp ult ptr [[C]], [[SCEVGEP4]] |
| ; CHECK-NEXT: [[BOUND113:%.*]] = icmp ult ptr [[B]], [[SCEVGEP1]] |
| ; CHECK-NEXT: [[FOUND_CONFLICT14:%.*]] = and i1 [[BOUND012]], [[BOUND113]] |
| ; CHECK-NEXT: [[CONFLICT_RDX15:%.*]] = or i1 [[CONFLICT_RDX11]], [[FOUND_CONFLICT14]] |
| ; CHECK-NEXT: br i1 [[CONFLICT_RDX15]], label %[[FOR_BODY_PH_LVER_ORIG:.*]], label %[[FOR_BODY_PH_LDIST1:.*]] |
| ; CHECK: [[FOR_BODY_PH_LVER_ORIG]]: |
| ; CHECK-NEXT: br label %[[FOR_BODY_LVER_ORIG:.*]] |
| ; CHECK: [[FOR_BODY_LVER_ORIG]]: |
| ; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, %[[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], %[[FOR_BODY_LVER_ORIG]] ] |
| ; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IND_LVER_ORIG]] |
| ; CHECK-NEXT: [[LOADA_LVER_ORIG:%.*]] = load i32, ptr [[ARRAYIDXA_LVER_ORIG]], align 4 |
| ; CHECK-NEXT: [[ARRAYIDXB_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[IND_LVER_ORIG]] |
| ; CHECK-NEXT: [[LOADB_LVER_ORIG:%.*]] = load i32, ptr [[ARRAYIDXB_LVER_ORIG]], align 4 |
| ; CHECK-NEXT: [[MULA_LVER_ORIG:%.*]] = mul i32 [[LOADB_LVER_ORIG]], [[LOADA_LVER_ORIG]] |
| ; CHECK-NEXT: [[ADD_LVER_ORIG]] = add nuw nsw i64 [[IND_LVER_ORIG]], 1 |
| ; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[ADD_LVER_ORIG]] |
| ; CHECK-NEXT: store i32 [[MULA_LVER_ORIG]], ptr [[ARRAYIDXA_PLUS_4_LVER_ORIG]], align 4 |
| ; CHECK-NEXT: [[ARRAYIDXD_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[IND_LVER_ORIG]] |
| ; CHECK-NEXT: [[LOADD_LVER_ORIG:%.*]] = load i32, ptr [[ARRAYIDXD_LVER_ORIG]], align 4 |
| ; CHECK-NEXT: [[ARRAYIDXE_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[E]], i64 [[IND_LVER_ORIG]] |
| ; CHECK-NEXT: [[LOADE_LVER_ORIG:%.*]] = load i32, ptr [[ARRAYIDXE_LVER_ORIG]], align 4 |
| ; CHECK-NEXT: [[MULC_LVER_ORIG:%.*]] = mul i32 [[LOADD_LVER_ORIG]], [[LOADE_LVER_ORIG]] |
| ; CHECK-NEXT: [[ARRAYIDXC_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[IND_LVER_ORIG]] |
| ; CHECK-NEXT: store i32 [[MULC_LVER_ORIG]], ptr [[ARRAYIDXC_LVER_ORIG]], align 4 |
| ; CHECK-NEXT: [[EXITCOND_LVER_ORIG:%.*]] = icmp eq i64 [[ADD_LVER_ORIG]], 20 |
| ; CHECK-NEXT: br i1 [[EXITCOND_LVER_ORIG]], label %[[FOR_END_LOOPEXIT:.*]], label %[[FOR_BODY_LVER_ORIG]], !llvm.loop [[LOOP0:![0-9]+]] |
| ; CHECK: [[FOR_BODY_PH_LDIST1]]: |
| ; CHECK-NEXT: br label %[[FOR_BODY_LDIST1:.*]] |
| ; CHECK: [[FOR_BODY_LDIST1]]: |
| ; CHECK-NEXT: [[IND_LDIST1:%.*]] = phi i64 [ 0, %[[FOR_BODY_PH_LDIST1]] ], [ [[ADD_LDIST1:%.*]], %[[FOR_BODY_LDIST1]] ] |
| ; CHECK-NEXT: [[ARRAYIDXA_LDIST1:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IND_LDIST1]] |
| ; CHECK-NEXT: [[LOADA_LDIST1:%.*]] = load i32, ptr [[ARRAYIDXA_LDIST1]], align 4, !alias.scope [[META2:![0-9]+]], !noalias [[META5:![0-9]+]] |
| ; CHECK-NEXT: [[ARRAYIDXB_LDIST1:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[IND_LDIST1]] |
| ; CHECK-NEXT: [[LOADB_LDIST1:%.*]] = load i32, ptr [[ARRAYIDXB_LDIST1]], align 4, !alias.scope [[META9:![0-9]+]] |
| ; CHECK-NEXT: [[MULA_LDIST1:%.*]] = mul i32 [[LOADB_LDIST1]], [[LOADA_LDIST1]] |
| ; CHECK-NEXT: [[ADD_LDIST1]] = add nuw nsw i64 [[IND_LDIST1]], 1 |
| ; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LDIST1:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[ADD_LDIST1]] |
| ; CHECK-NEXT: store i32 [[MULA_LDIST1]], ptr [[ARRAYIDXA_PLUS_4_LDIST1]], align 4, !alias.scope [[META2]], !noalias [[META5]] |
| ; CHECK-NEXT: [[EXITCOND_LDIST1:%.*]] = icmp eq i64 [[ADD_LDIST1]], 20 |
| ; CHECK-NEXT: br i1 [[EXITCOND_LDIST1]], label %[[FOR_BODY_PH:.*]], label %[[FOR_BODY_LDIST1]] |
| ; CHECK: [[FOR_BODY_PH]]: |
| ; CHECK-NEXT: br label %[[FOR_BODY:.*]] |
| ; CHECK: [[FOR_BODY]]: |
| ; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, %[[FOR_BODY_PH]] ], [ [[ADD:%.*]], %[[FOR_BODY]] ] |
| ; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1 |
| ; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[IND]] |
| ; CHECK-NEXT: [[LOADD:%.*]] = load i32, ptr [[ARRAYIDXD]], align 4, !alias.scope [[META11:![0-9]+]] |
| ; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, ptr [[E]], i64 [[IND]] |
| ; CHECK-NEXT: [[LOADE:%.*]] = load i32, ptr [[ARRAYIDXE]], align 4, !alias.scope [[META12:![0-9]+]] |
| ; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]] |
| ; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[IND]] |
| ; CHECK-NEXT: store i32 [[MULC]], ptr [[ARRAYIDXC]], align 4, !alias.scope [[META13:![0-9]+]], !noalias [[META9]] |
| ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], 20 |
| ; CHECK-NEXT: br i1 [[EXITCOND]], label %[[FOR_END_LOOPEXIT16:.*]], label %[[FOR_BODY]] |
| ; CHECK: [[FOR_END_LOOPEXIT]]: |
| ; CHECK-NEXT: br label %[[FOR_END:.*]] |
| ; CHECK: [[FOR_END_LOOPEXIT16]]: |
| ; CHECK-NEXT: br label %[[FOR_END]] |
| ; CHECK: [[FOR_END]]: |
| ; CHECK-NEXT: ret void |
| ; |
| entry: |
| |
| %cond = icmp eq ptr %e, null |
| br i1 %cond, label %one, label %two |
| one: |
| br label %join |
| two: |
| br label %join |
| join: |
| |
| ; The pointers need to be defined by PHIs in order for the bug to trigger. |
| ; Because of the PHIs the existing casts won't be at the desired location so a |
| ; new cast will be emitted and the old cast will get invalidated. |
| ; These are the steps: |
| ; 1. After the bounds for A and C are first expanded: |
| ; join: |
| ; %a = phi i32* [ %a1, %one ], [ %a2, %two ] |
| ; %c = phi i32* [ %c1, %one ], [ %c2, %two ] |
| ; %c5 = bitcast i32* %c to i8* |
| ; %a3 = bitcast i32* %a to i8* |
| ; 2. After A is expanded again: |
| ; join: ; preds = %two, %one |
| ; %a = phi i32* [ %a1, %one ], [ %a2, %two ] |
| ; %c = phi i32* [ %c1, %one ], [ %c2, %two ] |
| ; %a3 = bitcast i32* %a to i8* <--- new |
| ; %c5 = bitcast i32* %c to i8* |
| ; %0 = bitcast i32* %a to i8* <--- old, invalidated |
| ; 3. Finally, when C is expanded again: |
| ; join: ; preds = %two, %one |
| ; %a = phi i32* [ %a1, %one ], [ %a2, %two ] |
| ; %c = phi i32* [ %c1, %one ], [ %c2, %two ] |
| ; %c5 = bitcast i32* %c to i8* <--- new |
| ; %a3 = bitcast i32* %a to i8* |
| ; %0 = bitcast i32* %c to i8* <--- old, invalidated |
| ; %1 = bitcast i32* %a to i8* |
| |
| %a = phi ptr [%a1, %one], [%a2, %two] |
| %c = phi ptr [%c1, %one], [%c2, %two] |
| br label %for.body |
| |
| |
| for.body: ; preds = %for.body, %entry |
| %ind = phi i64 [ 0, %join ], [ %add, %for.body ] |
| |
| %arrayidxA = getelementptr inbounds i32, ptr %a, i64 %ind |
| %loadA = load i32, ptr %arrayidxA, align 4 |
| |
| %arrayidxB = getelementptr inbounds i32, ptr %b, i64 %ind |
| %loadB = load i32, ptr %arrayidxB, align 4 |
| |
| %mulA = mul i32 %loadB, %loadA |
| |
| %add = add nuw nsw i64 %ind, 1 |
| %arrayidxA_plus_4 = getelementptr inbounds i32, ptr %a, i64 %add |
| store i32 %mulA, ptr %arrayidxA_plus_4, align 4 |
| |
| %arrayidxD = getelementptr inbounds i32, ptr %d, i64 %ind |
| %loadD = load i32, ptr %arrayidxD, align 4 |
| |
| %arrayidxE = getelementptr inbounds i32, ptr %e, i64 %ind |
| %loadE = load i32, ptr %arrayidxE, align 4 |
| |
| %mulC = mul i32 %loadD, %loadE |
| |
| %arrayidxC = getelementptr inbounds i32, ptr %c, i64 %ind |
| store i32 %mulC, ptr %arrayidxC, align 4 |
| |
| %exitcond = icmp eq i64 %add, 20 |
| br i1 %exitcond, label %for.end, label %for.body |
| |
| for.end: ; preds = %for.body |
| ret void |
| } |
| ;. |
| ; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]]} |
| ; CHECK: [[META1]] = !{!"llvm.loop.isdistributed", i32 1} |
| ; CHECK: [[META2]] = !{[[META3:![0-9]+]]} |
| ; CHECK: [[META3]] = distinct !{[[META3]], [[META4:![0-9]+]]} |
| ; CHECK: [[META4]] = distinct !{[[META4]], !"LVerDomain"} |
| ; CHECK: [[META5]] = !{[[META6:![0-9]+]], [[META7:![0-9]+]], [[META8:![0-9]+]]} |
| ; CHECK: [[META6]] = distinct !{[[META6]], [[META4]]} |
| ; CHECK: [[META7]] = distinct !{[[META7]], [[META4]]} |
| ; CHECK: [[META8]] = distinct !{[[META8]], [[META4]]} |
| ; CHECK: [[META9]] = !{[[META10:![0-9]+]]} |
| ; CHECK: [[META10]] = distinct !{[[META10]], [[META4]]} |
| ; CHECK: [[META11]] = !{[[META7]]} |
| ; CHECK: [[META12]] = !{[[META8]]} |
| ; CHECK: [[META13]] = !{[[META6]]} |
| ;. |
