[llvm] [LoopAccessAnalysis] Keep pointer checks on partial analysis (PR #139719)
John Brawn via llvm-commits
llvm-commits at lists.llvm.org
Tue May 13 05:35:43 PDT 2025
https://github.com/john-brawn-arm created https://github.com/llvm/llvm-project/pull/139719
Currently if there's any memory access that AccessAnalysis couldn't analyze then all of the runtime pointer check results are discarded. This patch changes that so they're not, and we generate the runtime check information for those pointers that we could analyze, as transformations may still be able to make use of the partial information.
Of the transformations that use LoopAccessAnalysis, only LoopVersioningLICM changes behaviour as a result of this change. This is because the others either:
* Check canVectorizeMemory, which will return false when we have partial pointer information as analyzeLoop() will return false.
* Examine the dependencies returned by getDepChecker(), which will be empty as we exit analyzeLoop if we have partial pointer information before calling areDepsSafe(), which is what fills in the dependency information.
>From babdff19cc33a5843de761b8f09ab3b65d89bcf4 Mon Sep 17 00:00:00 2001
From: John Brawn <john.brawn at arm.com>
Date: Wed, 26 Mar 2025 10:34:27 +0000
Subject: [PATCH] [LoopAccessAnalysis] Keep pointer checks on partial analysis
Currently if there's any memory access that AccessAnalysis couldn't
analyze then all of the runtime pointer check results are discarded.
This patch changes that so they're not, and we generate the runtime
check information for those pointers that we could analyze, as
transformations may still be able to make use of the partial
information.
Of the transformations that use LoopAccessAnalysis, only
LoopVersioningLICM changes behaviour as a result of this change. This
is because the others either:
* Check canVectorizeMemory, which will return false when we have
partial pointer information as analyzeLoop() will return false.
* Examine the dependencies returned by getDepChecker(), which will be
empty as we exit analyzeLoop if we have partial pointer information
before calling areDepsSafe(), which is what fills in the dependency
information.
---
.../llvm/Analysis/LoopAccessAnalysis.h | 9 +-
llvm/lib/Analysis/LoopAccessAnalysis.cpp | 19 +-
.../LoopAccessAnalysis/forked-pointers.ll | 307 +++++++++++++++---
.../non-constant-strides-backward.ll | 12 +
.../non-constant-strides-forward.ll | 9 +
.../LoopAccessAnalysis/pointer-phis.ll | 21 +-
...ter-dependence-analysis-forked-pointers.ll | 14 +
.../underlying-object-loop-varying-phi.ll | 14 +
.../load-from-unknown-address.ll | 168 ++++++++--
9 files changed, 471 insertions(+), 102 deletions(-)
diff --git a/llvm/include/llvm/Analysis/LoopAccessAnalysis.h b/llvm/include/llvm/Analysis/LoopAccessAnalysis.h
index f715e0ec8dbb4..0abd7f1182108 100644
--- a/llvm/include/llvm/Analysis/LoopAccessAnalysis.h
+++ b/llvm/include/llvm/Analysis/LoopAccessAnalysis.h
@@ -192,7 +192,8 @@ class MemoryDepChecker {
/// of a write access.
void addAccess(LoadInst *LI);
- /// Check whether the dependencies between the accesses are safe.
+ /// Check whether the dependencies between the accesses are safe, and records
+ /// the dependence information in Dependences if so.
///
/// Only checks sets with elements in \p CheckDeps.
bool areDepsSafe(const DepCandidates &AccessSets,
@@ -779,10 +780,14 @@ class LoopAccessInfo {
/// We need to check that all of the pointers in this list are disjoint
/// at runtime. Using std::unique_ptr to make using move ctor simpler.
+ /// This list may contain only partial information when we've failed to
+ /// analyze all the memory accesses in the loop (i.e. CanVecMem is false).
std::unique_ptr<RuntimePointerChecking> PtrRtChecking;
- /// the Memory Dependence Checker which can determine the
+ /// The Memory Dependence Checker which can determine the
/// loop-independent and loop-carried dependences between memory accesses.
+ /// This will be empty if we've failed to analyze all the memory access in the
+ /// loop (i.e. CanVecMem is false).
std::unique_ptr<MemoryDepChecker> DepChecker;
Loop *TheLoop;
diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index af1a3c593c514..4d912abdf59a8 100644
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -529,8 +529,10 @@ void RuntimePointerChecking::groupChecks(
// equivalence class, the iteration order is deterministic.
for (auto M : DepCands.members(Access)) {
auto PointerI = PositionMap.find(M.getPointer());
- assert(PointerI != PositionMap.end() &&
- "pointer in equivalence class not found in PositionMap");
+ // If we can't find the pointer in PositionMap that means we can't
+ // generate a memcheck for it.
+ if (PointerI == PositionMap.end())
+ continue;
for (unsigned Pointer : PointerI->second) {
bool Merged = false;
// Mark this pointer as seen.
@@ -682,7 +684,9 @@ class AccessAnalysis {
/// non-intersection.
///
/// Returns true if we need no check or if we do and we can generate them
- /// (i.e. the pointers have computable bounds).
+ /// (i.e. the pointers have computable bounds). A return value of false means
+ /// we couldn't analyze and generate runtime checks for all pointers in the
+ /// loop, but we will have checks for those pointers we could analyze.
bool canCheckPtrAtRT(RuntimePointerChecking &RtCheck, ScalarEvolution *SE,
Loop *TheLoop,
const DenseMap<Value *, const SCEV *> &Strides,
@@ -1273,7 +1277,6 @@ bool AccessAnalysis::canCheckPtrAtRT(
/*Assume=*/true)) {
CanDoAliasSetRT = false;
UncomputablePtr = Access.getPointer();
- break;
}
}
}
@@ -1313,7 +1316,7 @@ bool AccessAnalysis::canCheckPtrAtRT(
}
}
- if (MayNeedRTCheck && CanDoRT)
+ if (MayNeedRTCheck)
RtCheck.generateChecks(DepCands, IsDepCheckNeeded);
LLVM_DEBUG(dbgs() << "LAA: We need to do " << RtCheck.getNumberOfChecks()
@@ -1323,11 +1326,7 @@ bool AccessAnalysis::canCheckPtrAtRT(
// are needed. This can happen when all pointers point to the same underlying
// object for example.
RtCheck.Need = CanDoRT ? RtCheck.getNumberOfChecks() != 0 : MayNeedRTCheck;
-
- bool CanDoRTIfNeeded = !RtCheck.Need || CanDoRT;
- if (!CanDoRTIfNeeded)
- RtCheck.reset();
- return CanDoRTIfNeeded;
+ return !RtCheck.Need || CanDoRT;
}
void AccessAnalysis::processMemAccesses() {
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/forked-pointers.ll b/llvm/test/Analysis/LoopAccessAnalysis/forked-pointers.ll
index cd388b4ee87f2..f0885cf0a6043 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/forked-pointers.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/forked-pointers.ll
@@ -633,7 +633,18 @@ define dso_local void @forked_ptrs_same_base_different_offset(ptr nocapture read
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP47:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP48:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP47]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP48]]:
+; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -645,7 +656,18 @@ define dso_local void @forked_ptrs_same_base_different_offset(ptr nocapture read
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP49:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP50:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP49]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP50]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -684,24 +706,24 @@ define dso_local void @forked_ptrs_add_to_offset(ptr nocapture readonly %Base, p
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
-; CHECK-NEXT: Comparing group ([[GRP47:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP51:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP48:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP52:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Check 1:
-; CHECK-NEXT: Comparing group ([[GRP47]]):
+; CHECK-NEXT: Comparing group ([[GRP51]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP49:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP53:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, ptr %Base, i64 %offset
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, ptr %Base, i64 %offset
; CHECK-NEXT: Grouped accesses:
-; CHECK-NEXT: Group [[GRP47]]:
+; CHECK-NEXT: Group [[GRP51]]:
; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP48]]:
+; CHECK-NEXT: Group [[GRP52]]:
; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP49]]:
+; CHECK-NEXT: Group [[GRP53]]:
; CHECK-NEXT: (Low: ((4 * %extra_offset) + %Base) High: (404 + (4 * %extra_offset) + %Base))
; CHECK-NEXT: Member: {(4 + (4 * %extra_offset) + %Base),+,4}<%for.body>
; CHECK-NEXT: Member: {((4 * %extra_offset) + %Base),+,4}<%for.body>
@@ -716,7 +738,18 @@ define dso_local void @forked_ptrs_add_to_offset(ptr nocapture readonly %Base, p
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP54:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP55:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP54]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP55]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -752,24 +785,24 @@ define dso_local void @forked_ptrs_sub_from_offset(ptr nocapture readonly %Base,
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
-; CHECK-NEXT: Comparing group ([[GRP50:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP56:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP51:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP57:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Check 1:
-; CHECK-NEXT: Comparing group ([[GRP50]]):
+; CHECK-NEXT: Comparing group ([[GRP56]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP52:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP58:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, ptr %Base, i64 %offset
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, ptr %Base, i64 %offset
; CHECK-NEXT: Grouped accesses:
-; CHECK-NEXT: Group [[GRP50]]:
+; CHECK-NEXT: Group [[GRP56]]:
; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP51]]:
+; CHECK-NEXT: Group [[GRP57]]:
; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP52]]:
+; CHECK-NEXT: Group [[GRP58]]:
; CHECK-NEXT: (Low: ((-4 * %extra_offset) + %Base) High: (404 + (-4 * %extra_offset) + %Base))
; CHECK-NEXT: Member: {(4 + (-4 * %extra_offset) + %Base),+,4}<%for.body>
; CHECK-NEXT: Member: {((-4 * %extra_offset) + %Base),+,4}<%for.body>
@@ -784,7 +817,18 @@ define dso_local void @forked_ptrs_sub_from_offset(ptr nocapture readonly %Base,
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP59:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP60:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP59]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP60]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -820,24 +864,24 @@ define dso_local void @forked_ptrs_add_sub_offset(ptr nocapture readonly %Base,
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
-; CHECK-NEXT: Comparing group ([[GRP53:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP61:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP54:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP62:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Check 1:
-; CHECK-NEXT: Comparing group ([[GRP53]]):
+; CHECK-NEXT: Comparing group ([[GRP61]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP55:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP63:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, ptr %Base, i64 %offset
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, ptr %Base, i64 %offset
; CHECK-NEXT: Grouped accesses:
-; CHECK-NEXT: Group [[GRP53]]:
+; CHECK-NEXT: Group [[GRP61]]:
; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP54]]:
+; CHECK-NEXT: Group [[GRP62]]:
; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP55]]:
+; CHECK-NEXT: Group [[GRP63]]:
; CHECK-NEXT: (Low: ((4 * %to_add) + (-4 * %to_sub) + %Base) High: (404 + (4 * %to_add) + (-4 * %to_sub) + %Base))
; CHECK-NEXT: Member: {(4 + (4 * %to_add) + (-4 * %to_sub) + %Base),+,4}<%for.body>
; CHECK-NEXT: Member: {((4 * %to_add) + (-4 * %to_sub) + %Base),+,4}<%for.body>
@@ -852,7 +896,18 @@ define dso_local void @forked_ptrs_add_sub_offset(ptr nocapture readonly %Base,
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP64:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP65:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP64]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP65]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -890,7 +945,18 @@ define dso_local void @forked_ptrs_mul_by_offset(ptr nocapture readonly %Base, p
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP66:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP67:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP66]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP67]]:
+; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -902,7 +968,18 @@ define dso_local void @forked_ptrs_mul_by_offset(ptr nocapture readonly %Base, p
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP68:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP69:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP68]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP69]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -940,7 +1017,18 @@ define dso_local void @forked_ptrs_uniform_and_strided_forks(ptr nocapture reado
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP70:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP71:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP70]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP71]]:
+; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -952,7 +1040,18 @@ define dso_local void @forked_ptrs_uniform_and_strided_forks(ptr nocapture reado
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP72:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP73:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP72]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP73]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -995,7 +1094,18 @@ define dso_local void @forked_ptrs_gather_and_contiguous_forks(ptr nocapture rea
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP74:0x[0-9a-f]+]]):
+; CHECK-NEXT: %1 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP75:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP74]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP75]]:
+; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -1007,7 +1117,18 @@ define dso_local void @forked_ptrs_gather_and_contiguous_forks(ptr nocapture rea
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP76:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %1 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP77:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP76]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP77]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -1046,7 +1167,18 @@ define dso_local void @forked_ptrs_two_forks_gep(ptr nocapture readonly %Base1,
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP78:0x[0-9a-f]+]]):
+; CHECK-NEXT: %1 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP79:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP78]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP79]]:
+; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -1058,7 +1190,18 @@ define dso_local void @forked_ptrs_two_forks_gep(ptr nocapture readonly %Base1,
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP80:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %1 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP81:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP80]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP81]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -1096,6 +1239,10 @@ define void @forked_ptrs_two_select(ptr nocapture readonly %Base1, ptr nocapture
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP82:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%loop>
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -1108,6 +1255,10 @@ define void @forked_ptrs_two_select(ptr nocapture readonly %Base1, ptr nocapture
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP83:0x[0-9a-f]+]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%loop>
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%loop>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -1146,7 +1297,18 @@ define void @forked_ptrs_too_many_gep_ops(ptr nocapture readonly %Base1, ptr noc
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP84:0x[0-9a-f]+]]):
+; CHECK-NEXT: %1 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP85:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP84]]:
+; CHECK-NEXT: (Low: %Dest High: (400 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP85]]:
+; CHECK-NEXT: (Low: %Preds High: (400 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -1158,7 +1320,18 @@ define void @forked_ptrs_too_many_gep_ops(ptr nocapture readonly %Base1, ptr noc
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP86:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %1 = getelementptr inbounds float, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP87:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP86]]:
+; RECURSE-NEXT: (Low: %Dest High: (400 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,4}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP87]]:
+; RECURSE-NEXT: (Low: %Preds High: (400 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -1194,7 +1367,18 @@ define void @forked_ptrs_vector_gep(ptr nocapture readonly %Base1, ptr nocapture
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP88:0x[0-9a-f]+]]):
+; CHECK-NEXT: %1 = getelementptr inbounds <4 x float>, ptr %Dest, i64 %indvars.iv
+; CHECK-NEXT: Against group ([[GRP89:0x[0-9a-f]+]]):
+; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP88]]:
+; CHECK-NEXT: (Low: %Dest High: (1552 + %Dest))
+; CHECK-NEXT: Member: {%Dest,+,64}<nuw><%for.body>
+; CHECK-NEXT: Group [[GRP89]]:
+; CHECK-NEXT: (Low: %Preds High: (388 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,16}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -1206,7 +1390,18 @@ define void @forked_ptrs_vector_gep(ptr nocapture readonly %Base1, ptr nocapture
; RECURSE-NEXT: Report: cannot identify array bounds
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
+; RECURSE-NEXT: Check 0:
+; RECURSE-NEXT: Comparing group ([[GRP90:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %1 = getelementptr inbounds <4 x float>, ptr %Dest, i64 %indvars.iv
+; RECURSE-NEXT: Against group ([[GRP91:0x[0-9a-f]+]]):
+; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP90]]:
+; RECURSE-NEXT: (Low: %Dest High: (1552 + %Dest))
+; RECURSE-NEXT: Member: {%Dest,+,64}<nuw><%for.body>
+; RECURSE-NEXT: Group [[GRP91]]:
+; RECURSE-NEXT: (Low: %Preds High: (388 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,16}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
@@ -1250,15 +1445,15 @@ define void @sc_add_expr_ice(ptr %Base1, ptr %Base2, i64 %N) {
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
-; CHECK-NEXT: Comparing group ([[GRP56:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP92:0x[0-9a-f]+]]):
; CHECK-NEXT: ptr %Base1
-; CHECK-NEXT: Against group ([[GRP57:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP93:0x[0-9a-f]+]]):
; CHECK-NEXT: %fptr = getelementptr inbounds double, ptr %Base2, i64 %sel
; CHECK-NEXT: Grouped accesses:
-; CHECK-NEXT: Group [[GRP56]]:
+; CHECK-NEXT: Group [[GRP92]]:
; CHECK-NEXT: (Low: %Base1 High: (8 + %Base1))
; CHECK-NEXT: Member: %Base1
-; CHECK-NEXT: Group [[GRP57]]:
+; CHECK-NEXT: Group [[GRP93]]:
; CHECK-NEXT: (Low: %Base2 High: ((8 * %N) + %Base2))
; CHECK-NEXT: Member: {%Base2,+,8}<%for.body>
; CHECK-EMPTY:
@@ -1277,15 +1472,15 @@ define void @sc_add_expr_ice(ptr %Base1, ptr %Base2, i64 %N) {
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
; RECURSE-NEXT: Check 0:
-; RECURSE-NEXT: Comparing group ([[GRP58:0x[0-9a-f]+]]):
+; RECURSE-NEXT: Comparing group ([[GRP94:0x[0-9a-f]+]]):
; RECURSE-NEXT: ptr %Base1
-; RECURSE-NEXT: Against group ([[GRP59:0x[0-9a-f]+]]):
+; RECURSE-NEXT: Against group ([[GRP95:0x[0-9a-f]+]]):
; RECURSE-NEXT: %fptr = getelementptr inbounds double, ptr %Base2, i64 %sel
; RECURSE-NEXT: Grouped accesses:
-; RECURSE-NEXT: Group [[GRP58]]:
+; RECURSE-NEXT: Group [[GRP94]]:
; RECURSE-NEXT: (Low: %Base1 High: (8 + %Base1))
; RECURSE-NEXT: Member: %Base1
-; RECURSE-NEXT: Group [[GRP59]]:
+; RECURSE-NEXT: Group [[GRP95]]:
; RECURSE-NEXT: (Low: %Base2 High: ((8 * %N) + %Base2))
; RECURSE-NEXT: Member: {%Base2,+,8}<%for.body>
; RECURSE-EMPTY:
@@ -1324,36 +1519,36 @@ define void @forked_ptrs_with_different_base(ptr nocapture readonly %Preds, ptr
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
-; CHECK-NEXT: Comparing group ([[GRP60:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP96:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP61:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP97:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Check 1:
-; CHECK-NEXT: Comparing group ([[GRP60]]):
+; CHECK-NEXT: Comparing group ([[GRP96]]):
; CHECK-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP62:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP98:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds double, ptr %0, i64 %indvars.iv
; CHECK-NEXT: Check 2:
-; CHECK-NEXT: Comparing group ([[GRP63:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP99:0x[0-9a-f]+]]):
; CHECK-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP61]]):
+; CHECK-NEXT: Against group ([[GRP97]]):
; CHECK-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; CHECK-NEXT: Check 3:
-; CHECK-NEXT: Comparing group ([[GRP63]]):
+; CHECK-NEXT: Comparing group ([[GRP99]]):
; CHECK-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; CHECK-NEXT: Against group ([[GRP62]]):
+; CHECK-NEXT: Against group ([[GRP98]]):
; CHECK-NEXT: %arrayidx5 = getelementptr inbounds double, ptr %0, i64 %indvars.iv
; CHECK-NEXT: Grouped accesses:
-; CHECK-NEXT: Group [[GRP60]]:
+; CHECK-NEXT: Group [[GRP96]]:
; CHECK-NEXT: (Low: %1 High: (63992 + %1))
; CHECK-NEXT: Member: {%1,+,8}<nw><%for.body>
-; CHECK-NEXT: Group [[GRP63]]:
+; CHECK-NEXT: Group [[GRP99]]:
; CHECK-NEXT: (Low: %2 High: (63992 + %2))
; CHECK-NEXT: Member: {%2,+,8}<nw><%for.body>
-; CHECK-NEXT: Group [[GRP61]]:
+; CHECK-NEXT: Group [[GRP97]]:
; CHECK-NEXT: (Low: %Preds High: (31996 + %Preds))
; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
-; CHECK-NEXT: Group [[GRP62]]:
+; CHECK-NEXT: Group [[GRP98]]:
; CHECK-NEXT: (Low: %0 High: (63992 + %0))
; CHECK-NEXT: Member: {%0,+,8}<nw><%for.body>
; CHECK-EMPTY:
@@ -1368,36 +1563,36 @@ define void @forked_ptrs_with_different_base(ptr nocapture readonly %Preds, ptr
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
; RECURSE-NEXT: Check 0:
-; RECURSE-NEXT: Comparing group ([[GRP64:0x[0-9a-f]+]]):
+; RECURSE-NEXT: Comparing group ([[GRP100:0x[0-9a-f]+]]):
; RECURSE-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; RECURSE-NEXT: Against group ([[GRP65:0x[0-9a-f]+]]):
+; RECURSE-NEXT: Against group ([[GRP101:0x[0-9a-f]+]]):
; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Check 1:
-; RECURSE-NEXT: Comparing group ([[GRP64]]):
+; RECURSE-NEXT: Comparing group ([[GRP100]]):
; RECURSE-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; RECURSE-NEXT: Against group ([[GRP66:0x[0-9a-f]+]]):
+; RECURSE-NEXT: Against group ([[GRP102:0x[0-9a-f]+]]):
; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds double, ptr %0, i64 %indvars.iv
; RECURSE-NEXT: Check 2:
-; RECURSE-NEXT: Comparing group ([[GRP67:0x[0-9a-f]+]]):
+; RECURSE-NEXT: Comparing group ([[GRP103:0x[0-9a-f]+]]):
; RECURSE-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; RECURSE-NEXT: Against group ([[GRP65]]):
+; RECURSE-NEXT: Against group ([[GRP101]]):
; RECURSE-NEXT: %arrayidx = getelementptr inbounds i32, ptr %Preds, i64 %indvars.iv
; RECURSE-NEXT: Check 3:
-; RECURSE-NEXT: Comparing group ([[GRP67]]):
+; RECURSE-NEXT: Comparing group ([[GRP103]]):
; RECURSE-NEXT: %arrayidx7 = getelementptr inbounds double, ptr %.sink, i64 %indvars.iv
-; RECURSE-NEXT: Against group ([[GRP66]]):
+; RECURSE-NEXT: Against group ([[GRP102]]):
; RECURSE-NEXT: %arrayidx5 = getelementptr inbounds double, ptr %0, i64 %indvars.iv
; RECURSE-NEXT: Grouped accesses:
-; RECURSE-NEXT: Group [[GRP64]]:
+; RECURSE-NEXT: Group [[GRP100]]:
; RECURSE-NEXT: (Low: %1 High: (63992 + %1))
; RECURSE-NEXT: Member: {%1,+,8}<nw><%for.body>
-; RECURSE-NEXT: Group [[GRP67]]:
+; RECURSE-NEXT: Group [[GRP103]]:
; RECURSE-NEXT: (Low: %2 High: (63992 + %2))
; RECURSE-NEXT: Member: {%2,+,8}<nw><%for.body>
-; RECURSE-NEXT: Group [[GRP65]]:
+; RECURSE-NEXT: Group [[GRP101]]:
; RECURSE-NEXT: (Low: %Preds High: (31996 + %Preds))
; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
-; RECURSE-NEXT: Group [[GRP66]]:
+; RECURSE-NEXT: Group [[GRP102]]:
; RECURSE-NEXT: (Low: %0 High: (63992 + %0))
; RECURSE-NEXT: Member: {%0,+,8}<nw><%for.body>
; RECURSE-EMPTY:
@@ -1452,6 +1647,9 @@ define void @forked_ptrs_with_different_base3(ptr nocapture readonly %Preds, ptr
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP104:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %Preds High: (31996 + %Preds))
+; CHECK-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -1464,6 +1662,9 @@ define void @forked_ptrs_with_different_base3(ptr nocapture readonly %Preds, ptr
; RECURSE-NEXT: Dependences:
; RECURSE-NEXT: Run-time memory checks:
; RECURSE-NEXT: Grouped accesses:
+; RECURSE-NEXT: Group [[GRP105:0x[0-9a-f]+]]:
+; RECURSE-NEXT: (Low: %Preds High: (31996 + %Preds))
+; RECURSE-NEXT: Member: {%Preds,+,4}<nuw><%for.body>
; RECURSE-EMPTY:
; RECURSE-NEXT: Non vectorizable stores to invariant address were not found in loop.
; RECURSE-NEXT: SCEV assumptions:
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-backward.ll b/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-backward.ll
index d263749ea1f46..1e696af9e2e4b 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-backward.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-backward.ll
@@ -237,6 +237,9 @@ define void @different_non_constant_strides_known_backward_via_assume(ptr %A, i6
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP1:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A))
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -271,6 +274,9 @@ define void @different_non_constant_strides_known_backward_via_assume_distance_l
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP2:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A)<nuw>)
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -306,6 +312,9 @@ define void @different_non_constant_strides_known_backward_via_assume_min_distan
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP3:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A))
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -341,6 +350,9 @@ define void @different_non_constant_strides_not_known_backward(ptr %A, i64 %scal
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP4:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A))
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-forward.ll b/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-forward.ll
index 5f4c732dc19df..e33d20e795646 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-forward.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/non-constant-strides-forward.ll
@@ -85,6 +85,9 @@ define void @different_non_constant_strides_known_forward_via_assume(ptr %A, i64
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP1:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A))
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -119,6 +122,9 @@ define void @different_non_constant_strides_known_forward_via_assume_min_distanc
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP2:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A))
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -154,6 +160,9 @@ define void @different_non_constant_strides_not_known_forward(ptr %A, i64 %scale
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP3:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (1024 + %A))
+; CHECK-NEXT: Member: {%A,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/pointer-phis.ll b/llvm/test/Analysis/LoopAccessAnalysis/pointer-phis.ll
index 48586ee9d9ed9..0f0635913c891 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/pointer-phis.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/pointer-phis.ll
@@ -462,6 +462,9 @@ define i32 @store_with_pointer_phi_in_same_bb_use_other_phi(ptr %A, ptr %B, ptr
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP10:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %A High: (256000 + %A))
+; CHECK-NEXT: Member: {%A,+,8}<nuw><%loop.header>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -503,36 +506,36 @@ define void @phi_load_store_memdep_check(i1 %c, ptr %A, ptr %B, ptr %C) {
; CHECK-EMPTY:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
-; CHECK-NEXT: Comparing group ([[GRP10:0x[0-9a-f]+]]):
+; CHECK-NEXT: Comparing group ([[GRP11:0x[0-9a-f]+]]):
; CHECK-NEXT: ptr %A
; CHECK-NEXT: ptr %A
-; CHECK-NEXT: Against group ([[GRP11:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP12:0x[0-9a-f]+]]):
; CHECK-NEXT: ptr %C
; CHECK-NEXT: ptr %C
; CHECK-NEXT: Check 1:
-; CHECK-NEXT: Comparing group ([[GRP10]]):
+; CHECK-NEXT: Comparing group ([[GRP11]]):
; CHECK-NEXT: ptr %A
; CHECK-NEXT: ptr %A
-; CHECK-NEXT: Against group ([[GRP12:0x[0-9a-f]+]]):
+; CHECK-NEXT: Against group ([[GRP13:0x[0-9a-f]+]]):
; CHECK-NEXT: ptr %B
; CHECK-NEXT: ptr %B
; CHECK-NEXT: Check 2:
-; CHECK-NEXT: Comparing group ([[GRP11]]):
+; CHECK-NEXT: Comparing group ([[GRP12]]):
; CHECK-NEXT: ptr %C
; CHECK-NEXT: ptr %C
-; CHECK-NEXT: Against group ([[GRP12]]):
+; CHECK-NEXT: Against group ([[GRP13]]):
; CHECK-NEXT: ptr %B
; CHECK-NEXT: ptr %B
; CHECK-NEXT: Grouped accesses:
-; CHECK-NEXT: Group [[GRP10]]:
+; CHECK-NEXT: Group [[GRP11]]:
; CHECK-NEXT: (Low: %A High: (2 + %A))
; CHECK-NEXT: Member: %A
; CHECK-NEXT: Member: %A
-; CHECK-NEXT: Group [[GRP11]]:
+; CHECK-NEXT: Group [[GRP12]]:
; CHECK-NEXT: (Low: %C High: (2 + %C))
; CHECK-NEXT: Member: %C
; CHECK-NEXT: Member: %C
-; CHECK-NEXT: Group [[GRP12]]:
+; CHECK-NEXT: Group [[GRP13]]:
; CHECK-NEXT: (Low: %B High: (2 + %B))
; CHECK-NEXT: Member: %B
; CHECK-NEXT: Member: %B
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/retry-runtime-checks-after-dependence-analysis-forked-pointers.ll b/llvm/test/Analysis/LoopAccessAnalysis/retry-runtime-checks-after-dependence-analysis-forked-pointers.ll
index 021447d53f943..35233de1cce73 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/retry-runtime-checks-after-dependence-analysis-forked-pointers.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/retry-runtime-checks-after-dependence-analysis-forked-pointers.ll
@@ -167,6 +167,13 @@ define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_m
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP9:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
+; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
+; CHECK-NEXT: Group [[GRP10:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
+; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
+; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -208,6 +215,13 @@ define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_m
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP11:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
+; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
+; CHECK-NEXT: Group [[GRP12:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
+; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
+; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/underlying-object-loop-varying-phi.ll b/llvm/test/Analysis/LoopAccessAnalysis/underlying-object-loop-varying-phi.ll
index 402081fb939f0..9e25baf31107d 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/underlying-object-loop-varying-phi.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/underlying-object-loop-varying-phi.ll
@@ -80,6 +80,9 @@ define void @indirect_ptr_recurrences_read_write_may_alias_no_tbaa(ptr %A, ptr %
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP1:0x[0-9a-f]+]]:
+; CHECK-NEXT: (Low: (8 + %B)<nuw> High: (40 + %B))
+; CHECK-NEXT: Member: {(8 + %B)<nuw>,+,8}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
@@ -111,7 +114,18 @@ define void @indirect_ptr_recurrences_read_write_may_alias_different_obj(ptr %A,
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT: Comparing group ([[GRP2:0x[0-9a-f]+]]):
+; CHECK-NEXT: %gep.C = getelementptr inbounds ptr, ptr %C, i64 %iv
+; CHECK-NEXT: Against group ([[GRP3:0x[0-9a-f]+]]):
+; CHECK-NEXT: %gep.B = getelementptr inbounds ptr, ptr %B, i64 %iv
; CHECK-NEXT: Grouped accesses:
+; CHECK-NEXT: Group [[GRP2]]:
+; CHECK-NEXT: (Low: (8 + %C)<nuw> High: (36 + %C))
+; CHECK-NEXT: Member: {(8 + %C)<nuw>,+,8}<nuw><%loop>
+; CHECK-NEXT: Group [[GRP3]]:
+; CHECK-NEXT: (Low: (8 + %B)<nuw> High: (40 + %B))
+; CHECK-NEXT: Member: {(8 + %B)<nuw>,+,8}<nuw><%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
diff --git a/llvm/test/Transforms/LoopVersioningLICM/load-from-unknown-address.ll b/llvm/test/Transforms/LoopVersioningLICM/load-from-unknown-address.ll
index e9b2954039198..89576f1684c3d 100644
--- a/llvm/test/Transforms/LoopVersioningLICM/load-from-unknown-address.ll
+++ b/llvm/test/Transforms/LoopVersioningLICM/load-from-unknown-address.ll
@@ -7,15 +7,25 @@ target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i8:8:32-i16:16:32-i6
; accesses but not others.
; Load from a gep whose bounds can't be calculated as the offset is loaded from memory
-; FIXME: Not knowing the bounds of the gep shouldn't stop us from hoisting the load of rval
define void @gep_loaded_offset(ptr %p, ptr %q, ptr %r, i32 %n) {
; CHECK-LABEL: define void @gep_loaded_offset(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], ptr [[R:%.*]], i32 [[N:%.*]]) {
-; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
-; CHECK: [[WHILE_BODY]]:
-; CHECK-NEXT: [[N_ADDR:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[ENTRY]] ]
-; CHECK-NEXT: [[P_ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], %[[WHILE_BODY]] ], [ [[P]], %[[ENTRY]] ]
+; CHECK-NEXT: [[WHILE_BODY_LVER_CHECK:.*:]]
+; CHECK-NEXT: [[TMP0:%.*]] = add nsw i32 [[N]], -1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
+; CHECK-NEXT: [[TMP2:%.*]] = shl nuw nsw i64 [[TMP1]], 2
+; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 4
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP3]]
+; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[R]], i64 8
+; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[P]], [[SCEVGEP1]]
+; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[R]], [[SCEVGEP]]
+; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label %[[WHILE_BODY_PH_LVER_ORIG:.*]], label %[[WHILE_BODY_PH:.*]]
+; CHECK: [[WHILE_BODY_PH_LVER_ORIG]]:
+; CHECK-NEXT: br label %[[WHILE_BODY_LVER_ORIG:.*]]
+; CHECK: [[WHILE_BODY_LVER_ORIG]]:
+; CHECK-NEXT: [[N_ADDR:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[N]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
+; CHECK-NEXT: [[P_ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[P]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
; CHECK-NEXT: [[DEC]] = add nsw i32 [[N_ADDR]], -1
; CHECK-NEXT: [[RVAL:%.*]] = load i64, ptr [[R]], align 4
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[Q]], i64 [[RVAL]]
@@ -23,7 +33,24 @@ define void @gep_loaded_offset(ptr %p, ptr %q, ptr %r, i32 %n) {
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds nuw i8, ptr [[P_ADDR]], i64 4
; CHECK-NEXT: store i32 [[VAL]], ptr [[P_ADDR]], align 4
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[DEC]], 0
-; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END:.*]], label %[[WHILE_BODY]]
+; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END_LOOPEXIT:.*]], label %[[WHILE_BODY_LVER_ORIG]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[WHILE_BODY_PH]]:
+; CHECK-NEXT: [[RVAL1:%.*]] = load i64, ptr [[R]], align 4, !alias.scope [[META2:![0-9]+]]
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[Q]], i64 [[RVAL1]]
+; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
+; CHECK: [[WHILE_BODY]]:
+; CHECK-NEXT: [[N_ADDR1:%.*]] = phi i32 [ [[DEC1:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[P_ADDR1:%.*]] = phi ptr [ [[INCDEC_PTR1:%.*]], %[[WHILE_BODY]] ], [ [[P]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[DEC1]] = add nsw i32 [[N_ADDR1]], -1
+; CHECK-NEXT: [[VAL1:%.*]] = load i32, ptr [[ARRAYIDX1]], align 4
+; CHECK-NEXT: [[INCDEC_PTR1]] = getelementptr inbounds nuw i8, ptr [[P_ADDR1]], i64 4
+; CHECK-NEXT: store i32 [[VAL1]], ptr [[P_ADDR1]], align 4, !alias.scope [[META5:![0-9]+]], !noalias [[META2]]
+; CHECK-NEXT: [[TOBOOL_NOT1:%.*]] = icmp eq i32 [[DEC1]], 0
+; CHECK-NEXT: br i1 [[TOBOOL_NOT1]], label %[[WHILE_END_LOOPEXIT2:.*]], label %[[WHILE_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK: [[WHILE_END_LOOPEXIT]]:
+; CHECK-NEXT: br label %[[WHILE_END:.*]]
+; CHECK: [[WHILE_END_LOOPEXIT2]]:
+; CHECK-NEXT: br label %[[WHILE_END]]
; CHECK: [[WHILE_END]]:
; CHECK-NEXT: ret void
;
@@ -89,15 +116,25 @@ while.end:
}
; Load from a gep whose bounds can't be calculated as the pointer is loaded from memory
-; FIXME: Not knowing the bounds of the gep shouldn't stop us from hoisting the load of rval
define void @gep_loaded_base(ptr %p, ptr %q, ptr %r, i32 %n) {
; CHECK-LABEL: define void @gep_loaded_base(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], ptr [[R:%.*]], i32 [[N:%.*]]) {
-; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
-; CHECK: [[WHILE_BODY]]:
-; CHECK-NEXT: [[N_ADDR:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[ENTRY]] ]
-; CHECK-NEXT: [[P_ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], %[[WHILE_BODY]] ], [ [[P]], %[[ENTRY]] ]
+; CHECK-NEXT: [[WHILE_BODY_LVER_CHECK:.*:]]
+; CHECK-NEXT: [[TMP0:%.*]] = add nsw i32 [[N]], -1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
+; CHECK-NEXT: [[TMP2:%.*]] = shl nuw nsw i64 [[TMP1]], 2
+; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 4
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP3]]
+; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[R]], i64 8
+; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[P]], [[SCEVGEP1]]
+; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[R]], [[SCEVGEP]]
+; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label %[[WHILE_BODY_PH_LVER_ORIG:.*]], label %[[WHILE_BODY_PH:.*]]
+; CHECK: [[WHILE_BODY_PH_LVER_ORIG]]:
+; CHECK-NEXT: br label %[[WHILE_BODY_LVER_ORIG:.*]]
+; CHECK: [[WHILE_BODY_LVER_ORIG]]:
+; CHECK-NEXT: [[N_ADDR:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[N]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
+; CHECK-NEXT: [[P_ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[P]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
; CHECK-NEXT: [[DEC]] = add nsw i32 [[N_ADDR]], -1
; CHECK-NEXT: [[RVAL:%.*]] = load ptr, ptr [[R]], align 4
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[RVAL]], i64 0
@@ -105,7 +142,24 @@ define void @gep_loaded_base(ptr %p, ptr %q, ptr %r, i32 %n) {
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds nuw i8, ptr [[P_ADDR]], i64 4
; CHECK-NEXT: store i32 [[VAL]], ptr [[P_ADDR]], align 4
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[DEC]], 0
-; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END:.*]], label %[[WHILE_BODY]]
+; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END_LOOPEXIT:.*]], label %[[WHILE_BODY_LVER_ORIG]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK: [[WHILE_BODY_PH]]:
+; CHECK-NEXT: [[RVAL1:%.*]] = load ptr, ptr [[R]], align 4, !alias.scope [[META10:![0-9]+]]
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[RVAL1]], i64 0
+; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
+; CHECK: [[WHILE_BODY]]:
+; CHECK-NEXT: [[N_ADDR1:%.*]] = phi i32 [ [[DEC1:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[P_ADDR1:%.*]] = phi ptr [ [[INCDEC_PTR1:%.*]], %[[WHILE_BODY]] ], [ [[P]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[DEC1]] = add nsw i32 [[N_ADDR1]], -1
+; CHECK-NEXT: [[VAL1:%.*]] = load i32, ptr [[ARRAYIDX1]], align 4
+; CHECK-NEXT: [[INCDEC_PTR1]] = getelementptr inbounds nuw i8, ptr [[P_ADDR1]], i64 4
+; CHECK-NEXT: store i32 [[VAL1]], ptr [[P_ADDR1]], align 4, !alias.scope [[META13:![0-9]+]], !noalias [[META10]]
+; CHECK-NEXT: [[TOBOOL_NOT1:%.*]] = icmp eq i32 [[DEC1]], 0
+; CHECK-NEXT: br i1 [[TOBOOL_NOT1]], label %[[WHILE_END_LOOPEXIT2:.*]], label %[[WHILE_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
+; CHECK: [[WHILE_END_LOOPEXIT]]:
+; CHECK-NEXT: br label %[[WHILE_END:.*]]
+; CHECK: [[WHILE_END_LOOPEXIT2]]:
+; CHECK-NEXT: br label %[[WHILE_END]]
; CHECK: [[WHILE_END]]:
; CHECK-NEXT: ret void
;
@@ -129,15 +183,25 @@ while.end:
}
; Load from a gep with an offset that scalar evolution can't describe
-; FIXME: Not knowing the bounds of the gep shouldn't stop us from hoisting the load of qval
define void @gep_strange_offset(ptr %p, ptr %q, ptr %r, i32 %n) {
; CHECK-LABEL: define void @gep_strange_offset(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], ptr [[R:%.*]], i32 [[N:%.*]]) {
-; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
-; CHECK: [[WHILE_BODY]]:
-; CHECK-NEXT: [[N_ADDR:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[ENTRY]] ]
-; CHECK-NEXT: [[P_ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], %[[WHILE_BODY]] ], [ [[P]], %[[ENTRY]] ]
+; CHECK-NEXT: [[WHILE_BODY_LVER_CHECK:.*:]]
+; CHECK-NEXT: [[TMP0:%.*]] = add nsw i32 [[N]], -1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
+; CHECK-NEXT: [[TMP2:%.*]] = shl nuw nsw i64 [[TMP1]], 2
+; CHECK-NEXT: [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 4
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP3]]
+; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[Q]], i64 4
+; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[P]], [[SCEVGEP1]]
+; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[Q]], [[SCEVGEP]]
+; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label %[[WHILE_BODY_PH_LVER_ORIG:.*]], label %[[WHILE_BODY_PH:.*]]
+; CHECK: [[WHILE_BODY_PH_LVER_ORIG]]:
+; CHECK-NEXT: br label %[[WHILE_BODY_LVER_ORIG:.*]]
+; CHECK: [[WHILE_BODY_LVER_ORIG]]:
+; CHECK-NEXT: [[N_ADDR:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[N]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
+; CHECK-NEXT: [[P_ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[P]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
; CHECK-NEXT: [[DEC]] = add nsw i32 [[N_ADDR]], -1
; CHECK-NEXT: [[QVAL:%.*]] = load i32, ptr [[Q]], align 4
; CHECK-NEXT: [[REM:%.*]] = srem i32 [[DEC]], 2
@@ -148,7 +212,27 @@ define void @gep_strange_offset(ptr %p, ptr %q, ptr %r, i32 %n) {
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds nuw i8, ptr [[P_ADDR]], i64 4
; CHECK-NEXT: store i32 [[ADD]], ptr [[P_ADDR]], align 4
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[DEC]], 0
-; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END:.*]], label %[[WHILE_BODY]]
+; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END_LOOPEXIT:.*]], label %[[WHILE_BODY_LVER_ORIG]], !llvm.loop [[LOOP16:![0-9]+]]
+; CHECK: [[WHILE_BODY_PH]]:
+; CHECK-NEXT: [[QVAL1:%.*]] = load i32, ptr [[Q]], align 4, !alias.scope [[META17:![0-9]+]]
+; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
+; CHECK: [[WHILE_BODY]]:
+; CHECK-NEXT: [[N_ADDR1:%.*]] = phi i32 [ [[DEC1:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[P_ADDR1:%.*]] = phi ptr [ [[INCDEC_PTR1:%.*]], %[[WHILE_BODY]] ], [ [[P]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[DEC1]] = add nsw i32 [[N_ADDR1]], -1
+; CHECK-NEXT: [[REM1:%.*]] = srem i32 [[DEC1]], 2
+; CHECK-NEXT: [[IDXPROM1:%.*]] = sext i32 [[REM1]] to i64
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[R]], i64 [[IDXPROM1]]
+; CHECK-NEXT: [[VAL1:%.*]] = load i32, ptr [[ARRAYIDX1]], align 4
+; CHECK-NEXT: [[ADD1:%.*]] = add nsw i32 [[VAL1]], [[QVAL1]]
+; CHECK-NEXT: [[INCDEC_PTR1]] = getelementptr inbounds nuw i8, ptr [[P_ADDR1]], i64 4
+; CHECK-NEXT: store i32 [[ADD1]], ptr [[P_ADDR1]], align 4, !alias.scope [[META20:![0-9]+]], !noalias [[META17]]
+; CHECK-NEXT: [[TOBOOL_NOT1:%.*]] = icmp eq i32 [[DEC1]], 0
+; CHECK-NEXT: br i1 [[TOBOOL_NOT1]], label %[[WHILE_END_LOOPEXIT2:.*]], label %[[WHILE_BODY]], !llvm.loop [[LOOP22:![0-9]+]]
+; CHECK: [[WHILE_END_LOOPEXIT]]:
+; CHECK-NEXT: br label %[[WHILE_END:.*]]
+; CHECK: [[WHILE_END_LOOPEXIT2]]:
+; CHECK-NEXT: br label %[[WHILE_END]]
; CHECK: [[WHILE_END]]:
; CHECK-NEXT: ret void
;
@@ -175,15 +259,24 @@ while.end:
}
; A memcpy-like loop where the source address is loaded from a pointer
-; FIXME: We should be able to hoist the load of the source address pointer
define void @memcpy_load_src(ptr %dst, ptr %src, i32 %n) {
; CHECK-LABEL: define void @memcpy_load_src(
; CHECK-SAME: ptr [[DST:%.*]], ptr [[SRC:%.*]], i32 [[N:%.*]]) {
-; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
-; CHECK: [[WHILE_BODY]]:
-; CHECK-NEXT: [[N_VAL:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[ENTRY]] ]
-; CHECK-NEXT: [[DST_VAL:%.*]] = phi ptr [ [[DST_VAL_NEXT:%.*]], %[[WHILE_BODY]] ], [ [[DST]], %[[ENTRY]] ]
+; CHECK-NEXT: [[WHILE_BODY_LVER_CHECK:.*:]]
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[SRC]], i64 8
+; CHECK-NEXT: [[TMP0:%.*]] = add nsw i32 [[N]], -1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
+; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
+; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP2]]
+; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[SRC]], [[SCEVGEP1]]
+; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[DST]], [[SCEVGEP]]
+; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label %[[WHILE_BODY_PH_LVER_ORIG:.*]], label %[[WHILE_BODY_PH:.*]]
+; CHECK: [[WHILE_BODY_PH_LVER_ORIG]]:
+; CHECK-NEXT: br label %[[WHILE_BODY_LVER_ORIG:.*]]
+; CHECK: [[WHILE_BODY_LVER_ORIG]]:
+; CHECK-NEXT: [[N_VAL:%.*]] = phi i32 [ [[DEC:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[N]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
+; CHECK-NEXT: [[DST_VAL:%.*]] = phi ptr [ [[DST_VAL_NEXT:%.*]], %[[WHILE_BODY_LVER_ORIG]] ], [ [[DST]], %[[WHILE_BODY_PH_LVER_ORIG]] ]
; CHECK-NEXT: [[DEC]] = add nsw i32 [[N_VAL]], -1
; CHECK-NEXT: [[SRC_VAL:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT: [[SRC_VAL_NEXT:%.*]] = getelementptr inbounds nuw i8, ptr [[SRC_VAL]], i64 1
@@ -192,7 +285,26 @@ define void @memcpy_load_src(ptr %dst, ptr %src, i32 %n) {
; CHECK-NEXT: [[VAL:%.*]] = load i8, ptr [[SRC_VAL]], align 1
; CHECK-NEXT: store i8 [[VAL]], ptr [[DST_VAL]], align 1
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[DEC]], 0
-; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END:.*]], label %[[WHILE_BODY]]
+; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label %[[WHILE_END_LOOPEXIT:.*]], label %[[WHILE_BODY_LVER_ORIG]], !llvm.loop [[LOOP23:![0-9]+]]
+; CHECK: [[WHILE_BODY_PH]]:
+; CHECK-NEXT: [[SRC_PROMOTED:%.*]] = load ptr, ptr [[SRC]], align 8, !alias.scope [[META24:![0-9]+]], !noalias [[META27:![0-9]+]]
+; CHECK-NEXT: br label %[[WHILE_BODY:.*]]
+; CHECK: [[WHILE_BODY]]:
+; CHECK-NEXT: [[SRC_VAL_NEXT3:%.*]] = phi ptr [ [[SRC_VAL_NEXT1:%.*]], %[[WHILE_BODY]] ], [ [[SRC_PROMOTED]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[N_VAL1:%.*]] = phi i32 [ [[DEC1:%.*]], %[[WHILE_BODY]] ], [ [[N]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[DST_VAL1:%.*]] = phi ptr [ [[DST_VAL_NEXT1:%.*]], %[[WHILE_BODY]] ], [ [[DST]], %[[WHILE_BODY_PH]] ]
+; CHECK-NEXT: [[DEC1]] = add nsw i32 [[N_VAL1]], -1
+; CHECK-NEXT: [[SRC_VAL_NEXT1]] = getelementptr inbounds nuw i8, ptr [[SRC_VAL_NEXT3]], i64 1
+; CHECK-NEXT: [[DST_VAL_NEXT1]] = getelementptr inbounds nuw i8, ptr [[DST_VAL1]], i64 1
+; CHECK-NEXT: store ptr [[SRC_VAL_NEXT1]], ptr [[SRC]], align 8, !alias.scope [[META24]], !noalias [[META27]]
+; CHECK-NEXT: [[VAL1:%.*]] = load i8, ptr [[SRC_VAL_NEXT3]], align 1
+; CHECK-NEXT: store i8 [[VAL1]], ptr [[DST_VAL1]], align 1, !alias.scope [[META27]]
+; CHECK-NEXT: [[TOBOOL_NOT1:%.*]] = icmp eq i32 [[DEC1]], 0
+; CHECK-NEXT: br i1 [[TOBOOL_NOT1]], label %[[WHILE_END_LOOPEXIT2:.*]], label %[[WHILE_BODY]], !llvm.loop [[LOOP29:![0-9]+]]
+; CHECK: [[WHILE_END_LOOPEXIT]]:
+; CHECK-NEXT: br label %[[WHILE_END:.*]]
+; CHECK: [[WHILE_END_LOOPEXIT2]]:
+; CHECK-NEXT: br label %[[WHILE_END]]
; CHECK: [[WHILE_END]]:
; CHECK-NEXT: ret void
;
More information about the llvm-commits
mailing list