[llvm] 2f7ccaf - [SCEV] Add predicate in SolveLinEq to ensure B is a multiple of A. (#108777)
via llvm-commits
llvm-commits at lists.llvm.org
Sat Sep 28 06:20:01 PDT 2024
Author: Florian Hahn
Date: 2024-09-28T14:19:57+01:00
New Revision: 2f7ccaf4a8565628a4c7d2b5a49bb45478940be6
URL: https://github.com/llvm/llvm-project/commit/2f7ccaf4a8565628a4c7d2b5a49bb45478940be6
DIFF: https://github.com/llvm/llvm-project/commit/2f7ccaf4a8565628a4c7d2b5a49bb45478940be6.diff
LOG: [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
Added:
Modified:
llvm/lib/Analysis/ScalarEvolution.cpp
llvm/test/Analysis/ScalarEvolution/ne-overflow.ll
llvm/test/Analysis/ScalarEvolution/predicated-max-backedge-taken-count-guard-info.ll
llvm/test/Analysis/ScalarEvolution/trip-count-urem.ll
llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
llvm/test/Transforms/LoopVectorize/opaque-ptr.ll
Removed:
################################################################################
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 09e5c080c19cf9..d5db3263294a6d 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -10129,8 +10129,11 @@ const SCEV *ScalarEvolution::stripInjectiveFunctions(const SCEV *S) const {
/// A and B isn't important.
///
/// If the equation does not have a solution, SCEVCouldNotCompute is returned.
-static const SCEV *SolveLinEquationWithOverflow(const APInt &A, const SCEV *B,
- ScalarEvolution &SE) {
+static const SCEV *
+SolveLinEquationWithOverflow(const APInt &A, const SCEV *B,
+ SmallPtrSetImpl<const SCEVPredicate *> *Predicates,
+
+ ScalarEvolution &SE) {
uint32_t BW = A.getBitWidth();
assert(BW == SE.getTypeSizeInBits(B->getType()));
assert(A != 0 && "A must be non-zero.");
@@ -10146,8 +10149,22 @@ static const SCEV *SolveLinEquationWithOverflow(const APInt &A, const SCEV *B,
//
// B is divisible by D if and only if the multiplicity of prime factor 2 for B
// is not less than multiplicity of this prime factor for D.
- if (SE.getMinTrailingZeros(B) < Mult2)
- return SE.getCouldNotCompute();
+ if (SE.getMinTrailingZeros(B) < Mult2) {
+ // Check if we can prove there's no remainder using URem.
+ const SCEV *URem =
+ SE.getURemExpr(B, SE.getConstant(APInt::getOneBitSet(BW, Mult2)));
+ const SCEV *Zero = SE.getZero(B->getType());
+ if (!SE.isKnownPredicate(CmpInst::ICMP_EQ, URem, Zero)) {
+ // Try to add a predicate ensuring B is a multiple of 1 << Mult2.
+ if (!Predicates)
+ return SE.getCouldNotCompute();
+
+ // Avoid adding a predicate that is known to be false.
+ if (SE.isKnownPredicate(CmpInst::ICMP_NE, URem, Zero))
+ return SE.getCouldNotCompute();
+ Predicates->insert(SE.getEqualPredicate(URem, Zero));
+ }
+ }
// 3. Compute I: the multiplicative inverse of (A / D) in arithmetic
// modulo (N / D).
@@ -10577,8 +10594,9 @@ ScalarEvolution::ExitLimit ScalarEvolution::howFarToZero(const SCEV *V,
// Solve the general equation.
if (!StepC || StepC->getValue()->isZero())
return getCouldNotCompute();
- const SCEV *E = SolveLinEquationWithOverflow(StepC->getAPInt(),
- getNegativeSCEV(Start), *this);
+ const SCEV *E = SolveLinEquationWithOverflow(
+ StepC->getAPInt(), getNegativeSCEV(Start),
+ AllowPredicates ? &Predicates : nullptr, *this);
const SCEV *M = E;
if (E != getCouldNotCompute()) {
diff --git a/llvm/test/Analysis/ScalarEvolution/ne-overflow.ll b/llvm/test/Analysis/ScalarEvolution/ne-overflow.ll
index 3022281658a75f..bb97005e8faf40 100644
--- a/llvm/test/Analysis/ScalarEvolution/ne-overflow.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ne-overflow.ll
@@ -58,6 +58,15 @@ define void @test_well_defined_infinite_st(i32 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i32 2147483647
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
;
entry:
br label %for.body
@@ -79,6 +88,15 @@ define void @test_well_defined_infinite_ld(i32 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i32 2147483647
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
;
entry:
br label %for.body
@@ -100,6 +118,15 @@ define void @test_no_mustprogress(i32 %N) {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i32 2147483647
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
;
entry:
br label %for.body
@@ -187,6 +214,15 @@ define void @test_abnormal_exit(i32 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i32 2147483647
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
;
entry:
br label %for.body
@@ -209,10 +245,24 @@ define void @test_other_exit(i32 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: <multiple exits> Unpredictable backedge-taken count.
; CHECK-NEXT: exit count for for.body: i32 9
; CHECK-NEXT: exit count for for.latch: ***COULDNOTCOMPUTE***
+; CHECK-NEXT: predicated exit count for for.latch: ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-EMPTY:
; CHECK-NEXT: Loop %for.body: constant max backedge-taken count is i32 9
; CHECK-NEXT: Loop %for.body: symbolic max backedge-taken count is i32 9
; CHECK-NEXT: symbolic max exit count for for.body: i32 9
; CHECK-NEXT: symbolic max exit count for for.latch: ***COULDNOTCOMPUTE***
+; CHECK-NEXT: predicated symbolic max exit count for for.latch: ((-2 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-EMPTY:
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is (9 umin ((-2 + %N) /u 2))
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is (9 umin ((-2 + %N) /u 2))
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i32 %N to i1) to i32) == 0
;
entry:
br label %for.body
@@ -267,6 +317,18 @@ define void @test_sext(i64 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is (%N /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 %N to i1) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i64 9223372036854775807
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 %N to i1) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is (%N /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 %N to i1) to i64) == 0
;
entry:
br label %for.body
@@ -288,6 +350,21 @@ define void @test_zext_of_sext(i64 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is (%N /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nusw>
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 %N to i1) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i64 9223372036854775807
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nusw>
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 %N to i1) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is (%N /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nusw>
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 %N to i1) to i64) == 0
;
entry:
br label %for.body
@@ -310,6 +387,18 @@ define void @test_zext_offset(i64 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-21 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nusw>
+; CHECK-NEXT: Equal predicate: (zext i1 (true + (trunc i64 %N to i1)) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i64 9223372036854775807
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nusw>
+; CHECK-NEXT: Equal predicate: (zext i1 (true + (trunc i64 %N to i1)) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is ((-21 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nusw>
+; CHECK-NEXT: Equal predicate: (zext i1 (true + (trunc i64 %N to i1)) to i64) == 0
;
entry:
br label %for.body
@@ -332,6 +421,18 @@ define void @test_sext_offset(i64 %N) mustprogress {
; CHECK-NEXT: Loop %for.body: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %for.body: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-21 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: Equal predicate: (zext i1 (true + (trunc i64 %N to i1)) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated constant max backedge-taken count is i64 9223372036854775807
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: Equal predicate: (zext i1 (true + (trunc i64 %N to i1)) to i64) == 0
+; CHECK-NEXT: Loop %for.body: Predicated symbolic max backedge-taken count is ((-21 + %N) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: {0,+,2}<%for.body> Added Flags: <nssw>
+; CHECK-NEXT: Equal predicate: (zext i1 (true + (trunc i64 %N to i1)) to i64) == 0
;
entry:
br label %for.body
diff --git a/llvm/test/Analysis/ScalarEvolution/predicated-max-backedge-taken-count-guard-info.ll b/llvm/test/Analysis/ScalarEvolution/predicated-max-backedge-taken-count-guard-info.ll
index ba3a5b4cfb3ae8..1805b983c8e2e4 100644
--- a/llvm/test/Analysis/ScalarEvolution/predicated-max-backedge-taken-count-guard-info.ll
+++ b/llvm/test/Analysis/ScalarEvolution/predicated-max-backedge-taken-count-guard-info.ll
@@ -7,6 +7,15 @@ define i32 @ptr_induction_ult(ptr %a, ptr %b) {
; CHECK-NEXT: Loop %loop: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %loop: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %loop: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %loop: Predicated backedge-taken count is (((-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) /u 4)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %b to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i2))) to i64) == 0
+; CHECK-NEXT: Loop %loop: Predicated constant max backedge-taken count is i64 4611686018427387903
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %b to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i2))) to i64) == 0
+; CHECK-NEXT: Loop %loop: Predicated symbolic max backedge-taken count is (((-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) /u 4)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 (ptrtoint ptr %b to i64) to i2) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i2))) to i64) == 0
;
entry:
%cmp.6 = icmp ult ptr %a, %b
@@ -28,6 +37,15 @@ define i32 @ptr_induction_ult_3_step_6(ptr %a, ptr %b) {
; CHECK-NEXT: Loop %loop: Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %loop: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %loop: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %loop: Predicated backedge-taken count is (((3074457345618258603 * (ptrtoint ptr %b to i64)) + (-3074457345618258603 * (ptrtoint ptr %a to i64))) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 ((-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) to i1) to i64) == 0
+; CHECK-NEXT: Loop %loop: Predicated constant max backedge-taken count is i64 9223372036854775807
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 ((-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) to i1) to i64) == 0
+; CHECK-NEXT: Loop %loop: Predicated symbolic max backedge-taken count is (((3074457345618258603 * (ptrtoint ptr %b to i64)) + (-3074457345618258603 * (ptrtoint ptr %a to i64))) /u 2)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i1 (trunc i64 ((-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) to i1) to i64) == 0
;
entry:
%cmp.6 = icmp ult ptr %a, %b
@@ -74,10 +92,24 @@ define void @ptr_induction_early_exit_eq_1(ptr %a, ptr %b, ptr %c) {
; CHECK-NEXT: Loop %loop: <multiple exits> Unpredictable backedge-taken count.
; CHECK-NEXT: exit count for loop: ***COULDNOTCOMPUTE***
; CHECK-NEXT: exit count for loop.inc: ***COULDNOTCOMPUTE***
+; CHECK-NEXT: predicated exit count for loop.inc: ((-8 + (-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) /u 8)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i3 ((trunc i64 (ptrtoint ptr %b to i64) to i3) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i3))) to i64) == 0
+; CHECK-EMPTY:
; CHECK-NEXT: Loop %loop: Unpredictable constant max backedge-taken count.
; CHECK-NEXT: Loop %loop: Unpredictable symbolic max backedge-taken count.
; CHECK-NEXT: symbolic max exit count for loop: ***COULDNOTCOMPUTE***
; CHECK-NEXT: symbolic max exit count for loop.inc: ***COULDNOTCOMPUTE***
+; CHECK-NEXT: predicated symbolic max exit count for loop.inc: ((-8 + (-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) /u 8)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i3 ((trunc i64 (ptrtoint ptr %b to i64) to i3) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i3))) to i64) == 0
+; CHECK-EMPTY:
+; CHECK-NEXT: Loop %loop: Predicated constant max backedge-taken count is i64 2305843009213693951
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i3 ((trunc i64 (ptrtoint ptr %b to i64) to i3) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i3))) to i64) == 0
+; CHECK-NEXT: Loop %loop: Predicated symbolic max backedge-taken count is ((-8 + (-1 * (ptrtoint ptr %a to i64)) + (ptrtoint ptr %b to i64)) /u 8)
+; CHECK-NEXT: Predicates:
+; CHECK-NEXT: Equal predicate: (zext i3 ((trunc i64 (ptrtoint ptr %b to i64) to i3) + (-1 * (trunc i64 (ptrtoint ptr %a to i64) to i3))) to i64) == 0
;
entry:
%cmp = icmp eq ptr %a, %b
diff --git a/llvm/test/Analysis/ScalarEvolution/trip-count-urem.ll b/llvm/test/Analysis/ScalarEvolution/trip-count-urem.ll
index 928d9accf35e7d..d24655f6ae5c18 100644
--- a/llvm/test/Analysis/ScalarEvolution/trip-count-urem.ll
+++ b/llvm/test/Analysis/ScalarEvolution/trip-count-urem.ll
@@ -6,9 +6,10 @@ declare void @foo()
define void @test_trip_count_expr_contains_urem(i32 %N) {
; CHECK-LABEL: 'test_trip_count_expr_contains_urem'
; CHECK-NEXT: Determining loop execution counts for: @test_trip_count_expr_contains_urem
-; CHECK-NEXT: Loop %loop: Unpredictable backedge-taken count.
-; CHECK-NEXT: Loop %loop: Unpredictable constant max backedge-taken count.
-; CHECK-NEXT: Loop %loop: Unpredictable symbolic max backedge-taken count.
+; CHECK-NEXT: Loop %loop: backedge-taken count is ((1 + (-1 * (zext i4 (1 + (trunc i32 %N to i4)) to i32))<nsw> + %N) /u 16)
+; CHECK-NEXT: Loop %loop: constant max backedge-taken count is i32 268435455
+; CHECK-NEXT: Loop %loop: symbolic max backedge-taken count is ((1 + (-1 * (zext i4 (1 + (trunc i32 %N to i4)) to i32))<nsw> + %N) /u 16)
+; CHECK-NEXT: Loop %loop: Trip multiple is 1
;
entry:
%n.rnd.up = add i32 %N, 1
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
index 8b71987246ee55..c0bc34c2b06efc 100644
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
@@ -4,11 +4,10 @@
define arm_aapcs_vfpcc void @float_float_mul(ptr nocapture readonly %a, ptr nocapture readonly %b, ptr nocapture %c, i32 %N) {
; CHECK-LABEL: float_float_mul:
; CHECK: @ %bb.0: @ %entry
-; CHECK-NEXT: cmp r3, #0
-; CHECK-NEXT: it eq
-; CHECK-NEXT: bxeq lr
-; CHECK-NEXT: .LBB0_1: @ %for.body.preheader
; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT: cmp r3, #0
+; CHECK-NEXT: beq .LBB0_10
+; CHECK-NEXT: @ %bb.1: @ %for.body.preheader
; CHECK-NEXT: cmp r3, #3
; CHECK-NEXT: bhi .LBB0_3
; CHECK-NEXT: @ %bb.2:
@@ -33,39 +32,42 @@ define arm_aapcs_vfpcc void @float_float_mul(ptr nocapture readonly %a, ptr noca
; CHECK-NEXT: beq .LBB0_11
; CHECK-NEXT: .LBB0_4: @ %for.body.preheader22
; CHECK-NEXT: mvn.w r7, r12
-; CHECK-NEXT: add.w r8, r7, r3
-; CHECK-NEXT: and r5, r3, #3
-; CHECK-NEXT: wls lr, r5, .LBB0_7
+; CHECK-NEXT: adds r4, r7, r3
+; CHECK-NEXT: and r7, r3, #3
+; CHECK-NEXT: add.w r8, r12, r7
+; CHECK-NEXT: wls lr, r7, .LBB0_7
; CHECK-NEXT: @ %bb.5: @ %for.body.prol.preheader
-; CHECK-NEXT: add.w r4, r12, r5
-; CHECK-NEXT: add.w r5, r0, r12, lsl #2
-; CHECK-NEXT: add.w r6, r1, r12, lsl #2
-; CHECK-NEXT: add.w r7, r2, r12, lsl #2
-; CHECK-NEXT: mov r12, r4
+; CHECK-NEXT: add.w r6, r0, r12, lsl #2
+; CHECK-NEXT: add.w r7, r1, r12, lsl #2
+; CHECK-NEXT: add.w r5, r2, r12, lsl #2
+; CHECK-NEXT: mov r12, r8
; CHECK-NEXT: .LBB0_6: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldmia r6!, {s0}
-; CHECK-NEXT: vldmia r5!, {s2}
+; CHECK-NEXT: vldmia r7!, {s0}
+; CHECK-NEXT: vldmia r6!, {s2}
; CHECK-NEXT: vmul.f32 s0, s2, s0
-; CHECK-NEXT: vstmia r7!, {s0}
+; CHECK-NEXT: vstmia r5!, {s0}
; CHECK-NEXT: le lr, .LBB0_6
; CHECK-NEXT: .LBB0_7: @ %for.body.prol.loopexit
-; CHECK-NEXT: cmp.w r8, #3
+; CHECK-NEXT: cmp r4, #3
; CHECK-NEXT: blo .LBB0_10
; CHECK-NEXT: @ %bb.8: @ %for.body.preheader1
-; CHECK-NEXT: sub.w r3, r3, r12
-; CHECK-NEXT: lsl.w r12, r12, #2
+; CHECK-NEXT: sub.w r3, r8, r3
+; CHECK-NEXT: movs r7, #1
+; CHECK-NEXT: rsb r3, r3, r3, lsl #30
+; CHECK-NEXT: subs r3, #4
+; CHECK-NEXT: add.w lr, r7, r3, lsr #2
+; CHECK-NEXT: lsl.w r3, r12, #2
; CHECK-NEXT: .LBB0_9: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: add.w r7, r1, r12
-; CHECK-NEXT: add.w r6, r0, r12
-; CHECK-NEXT: add.w r5, r2, r12
+; CHECK-NEXT: adds r7, r1, r3
+; CHECK-NEXT: adds r6, r0, r3
+; CHECK-NEXT: adds r5, r2, r3
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: vldr s0, [r7]
; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: vldr s2, [r6]
; CHECK-NEXT: adds r2, #16
-; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: vmul.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r5]
; CHECK-NEXT: vldr s0, [r7, #4]
@@ -80,10 +82,9 @@ define arm_aapcs_vfpcc void @float_float_mul(ptr nocapture readonly %a, ptr noca
; CHECK-NEXT: vldr s2, [r6, #12]
; CHECK-NEXT: vmul.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r5, #12]
-; CHECK-NEXT: bne .LBB0_9
-; CHECK-NEXT: .LBB0_10:
-; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, lr}
-; CHECK-NEXT: bx lr
+; CHECK-NEXT: le lr, .LBB0_9
+; CHECK-NEXT: .LBB0_10: @ %for.cond.cleanup
+; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, pc}
; CHECK-NEXT: .LBB0_11: @ %vector.ph
; CHECK-NEXT: bic r12, r3, #3
; CHECK-NEXT: movs r6, #1
@@ -217,11 +218,10 @@ for.body: ; preds = %for.body.prol.loope
define arm_aapcs_vfpcc void @float_float_add(ptr nocapture readonly %a, ptr nocapture readonly %b, ptr nocapture %c, i32 %N) {
; CHECK-LABEL: float_float_add:
; CHECK: @ %bb.0: @ %entry
-; CHECK-NEXT: cmp r3, #0
-; CHECK-NEXT: it eq
-; CHECK-NEXT: bxeq lr
-; CHECK-NEXT: .LBB1_1: @ %for.body.preheader
; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT: cmp r3, #0
+; CHECK-NEXT: beq .LBB1_10
+; CHECK-NEXT: @ %bb.1: @ %for.body.preheader
; CHECK-NEXT: cmp r3, #3
; CHECK-NEXT: bhi .LBB1_3
; CHECK-NEXT: @ %bb.2:
@@ -246,39 +246,42 @@ define arm_aapcs_vfpcc void @float_float_add(ptr nocapture readonly %a, ptr noca
; CHECK-NEXT: beq .LBB1_11
; CHECK-NEXT: .LBB1_4: @ %for.body.preheader22
; CHECK-NEXT: mvn.w r7, r12
-; CHECK-NEXT: add.w r8, r7, r3
-; CHECK-NEXT: and r5, r3, #3
-; CHECK-NEXT: wls lr, r5, .LBB1_7
+; CHECK-NEXT: adds r4, r7, r3
+; CHECK-NEXT: and r7, r3, #3
+; CHECK-NEXT: add.w r8, r12, r7
+; CHECK-NEXT: wls lr, r7, .LBB1_7
; CHECK-NEXT: @ %bb.5: @ %for.body.prol.preheader
-; CHECK-NEXT: add.w r4, r12, r5
-; CHECK-NEXT: add.w r5, r0, r12, lsl #2
-; CHECK-NEXT: add.w r6, r1, r12, lsl #2
-; CHECK-NEXT: add.w r7, r2, r12, lsl #2
-; CHECK-NEXT: mov r12, r4
+; CHECK-NEXT: add.w r6, r0, r12, lsl #2
+; CHECK-NEXT: add.w r7, r1, r12, lsl #2
+; CHECK-NEXT: add.w r5, r2, r12, lsl #2
+; CHECK-NEXT: mov r12, r8
; CHECK-NEXT: .LBB1_6: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldmia r6!, {s0}
-; CHECK-NEXT: vldmia r5!, {s2}
+; CHECK-NEXT: vldmia r7!, {s0}
+; CHECK-NEXT: vldmia r6!, {s2}
; CHECK-NEXT: vadd.f32 s0, s2, s0
-; CHECK-NEXT: vstmia r7!, {s0}
+; CHECK-NEXT: vstmia r5!, {s0}
; CHECK-NEXT: le lr, .LBB1_6
; CHECK-NEXT: .LBB1_7: @ %for.body.prol.loopexit
-; CHECK-NEXT: cmp.w r8, #3
+; CHECK-NEXT: cmp r4, #3
; CHECK-NEXT: blo .LBB1_10
; CHECK-NEXT: @ %bb.8: @ %for.body.preheader1
-; CHECK-NEXT: sub.w r3, r3, r12
-; CHECK-NEXT: lsl.w r12, r12, #2
+; CHECK-NEXT: sub.w r3, r8, r3
+; CHECK-NEXT: movs r7, #1
+; CHECK-NEXT: rsb r3, r3, r3, lsl #30
+; CHECK-NEXT: subs r3, #4
+; CHECK-NEXT: add.w lr, r7, r3, lsr #2
+; CHECK-NEXT: lsl.w r3, r12, #2
; CHECK-NEXT: .LBB1_9: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: add.w r7, r1, r12
-; CHECK-NEXT: add.w r6, r0, r12
-; CHECK-NEXT: add.w r5, r2, r12
+; CHECK-NEXT: adds r7, r1, r3
+; CHECK-NEXT: adds r6, r0, r3
+; CHECK-NEXT: adds r5, r2, r3
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: vldr s0, [r7]
; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: vldr s2, [r6]
; CHECK-NEXT: adds r2, #16
-; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: vadd.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r5]
; CHECK-NEXT: vldr s0, [r7, #4]
@@ -293,10 +296,9 @@ define arm_aapcs_vfpcc void @float_float_add(ptr nocapture readonly %a, ptr noca
; CHECK-NEXT: vldr s2, [r6, #12]
; CHECK-NEXT: vadd.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r5, #12]
-; CHECK-NEXT: bne .LBB1_9
-; CHECK-NEXT: .LBB1_10:
-; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, lr}
-; CHECK-NEXT: bx lr
+; CHECK-NEXT: le lr, .LBB1_9
+; CHECK-NEXT: .LBB1_10: @ %for.cond.cleanup
+; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, pc}
; CHECK-NEXT: .LBB1_11: @ %vector.ph
; CHECK-NEXT: bic r12, r3, #3
; CHECK-NEXT: movs r6, #1
@@ -430,11 +432,10 @@ for.body: ; preds = %for.body.prol.loope
define arm_aapcs_vfpcc void @float_float_sub(ptr nocapture readonly %a, ptr nocapture readonly %b, ptr nocapture %c, i32 %N) {
; CHECK-LABEL: float_float_sub:
; CHECK: @ %bb.0: @ %entry
-; CHECK-NEXT: cmp r3, #0
-; CHECK-NEXT: it eq
-; CHECK-NEXT: bxeq lr
-; CHECK-NEXT: .LBB2_1: @ %for.body.preheader
; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT: cmp r3, #0
+; CHECK-NEXT: beq .LBB2_10
+; CHECK-NEXT: @ %bb.1: @ %for.body.preheader
; CHECK-NEXT: cmp r3, #3
; CHECK-NEXT: bhi .LBB2_3
; CHECK-NEXT: @ %bb.2:
@@ -459,39 +460,42 @@ define arm_aapcs_vfpcc void @float_float_sub(ptr nocapture readonly %a, ptr noca
; CHECK-NEXT: beq .LBB2_11
; CHECK-NEXT: .LBB2_4: @ %for.body.preheader22
; CHECK-NEXT: mvn.w r7, r12
-; CHECK-NEXT: add.w r8, r7, r3
-; CHECK-NEXT: and r5, r3, #3
-; CHECK-NEXT: wls lr, r5, .LBB2_7
+; CHECK-NEXT: adds r4, r7, r3
+; CHECK-NEXT: and r7, r3, #3
+; CHECK-NEXT: add.w r8, r12, r7
+; CHECK-NEXT: wls lr, r7, .LBB2_7
; CHECK-NEXT: @ %bb.5: @ %for.body.prol.preheader
-; CHECK-NEXT: add.w r4, r12, r5
-; CHECK-NEXT: add.w r5, r0, r12, lsl #2
-; CHECK-NEXT: add.w r6, r1, r12, lsl #2
-; CHECK-NEXT: add.w r7, r2, r12, lsl #2
-; CHECK-NEXT: mov r12, r4
+; CHECK-NEXT: add.w r6, r0, r12, lsl #2
+; CHECK-NEXT: add.w r7, r1, r12, lsl #2
+; CHECK-NEXT: add.w r5, r2, r12, lsl #2
+; CHECK-NEXT: mov r12, r8
; CHECK-NEXT: .LBB2_6: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldmia r6!, {s0}
-; CHECK-NEXT: vldmia r5!, {s2}
+; CHECK-NEXT: vldmia r7!, {s0}
+; CHECK-NEXT: vldmia r6!, {s2}
; CHECK-NEXT: vsub.f32 s0, s2, s0
-; CHECK-NEXT: vstmia r7!, {s0}
+; CHECK-NEXT: vstmia r5!, {s0}
; CHECK-NEXT: le lr, .LBB2_6
; CHECK-NEXT: .LBB2_7: @ %for.body.prol.loopexit
-; CHECK-NEXT: cmp.w r8, #3
+; CHECK-NEXT: cmp r4, #3
; CHECK-NEXT: blo .LBB2_10
; CHECK-NEXT: @ %bb.8: @ %for.body.preheader1
-; CHECK-NEXT: sub.w r3, r3, r12
-; CHECK-NEXT: lsl.w r12, r12, #2
+; CHECK-NEXT: sub.w r3, r8, r3
+; CHECK-NEXT: movs r7, #1
+; CHECK-NEXT: rsb r3, r3, r3, lsl #30
+; CHECK-NEXT: subs r3, #4
+; CHECK-NEXT: add.w lr, r7, r3, lsr #2
+; CHECK-NEXT: lsl.w r3, r12, #2
; CHECK-NEXT: .LBB2_9: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: add.w r7, r1, r12
-; CHECK-NEXT: add.w r6, r0, r12
-; CHECK-NEXT: add.w r5, r2, r12
+; CHECK-NEXT: adds r7, r1, r3
+; CHECK-NEXT: adds r6, r0, r3
+; CHECK-NEXT: adds r5, r2, r3
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: vldr s0, [r7]
; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: vldr s2, [r6]
; CHECK-NEXT: adds r2, #16
-; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: vsub.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r5]
; CHECK-NEXT: vldr s0, [r7, #4]
@@ -506,10 +510,9 @@ define arm_aapcs_vfpcc void @float_float_sub(ptr nocapture readonly %a, ptr noca
; CHECK-NEXT: vldr s2, [r6, #12]
; CHECK-NEXT: vsub.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r5, #12]
-; CHECK-NEXT: bne .LBB2_9
-; CHECK-NEXT: .LBB2_10:
-; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, lr}
-; CHECK-NEXT: bx lr
+; CHECK-NEXT: le lr, .LBB2_9
+; CHECK-NEXT: .LBB2_10: @ %for.cond.cleanup
+; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, pc}
; CHECK-NEXT: .LBB2_11: @ %vector.ph
; CHECK-NEXT: bic r12, r3, #3
; CHECK-NEXT: movs r6, #1
@@ -643,11 +646,10 @@ for.body: ; preds = %for.body.prol.loope
define arm_aapcs_vfpcc void @float_int_mul(ptr nocapture readonly %a, ptr nocapture readonly %b, ptr nocapture %c, i32 %N) {
; CHECK-LABEL: float_int_mul:
; CHECK: @ %bb.0: @ %entry
+; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, r9, lr}
; CHECK-NEXT: cmp r3, #0
-; CHECK-NEXT: it eq
-; CHECK-NEXT: bxeq lr
-; CHECK-NEXT: .LBB3_1: @ %for.body.preheader
-; CHECK-NEXT: push.w {r4, r5, r6, r7, r8, lr}
+; CHECK-NEXT: beq.w .LBB3_13
+; CHECK-NEXT: @ %bb.1: @ %for.body.preheader
; CHECK-NEXT: cmp r3, #3
; CHECK-NEXT: bls .LBB3_6
; CHECK-NEXT: @ %bb.2: @ %vector.memcheck
@@ -681,42 +683,45 @@ define arm_aapcs_vfpcc void @float_int_mul(ptr nocapture readonly %a, ptr nocapt
; CHECK-NEXT: mov.w r12, #0
; CHECK-NEXT: .LBB3_7: @ %for.body.preheader16
; CHECK-NEXT: mvn.w r7, r12
-; CHECK-NEXT: add.w r8, r7, r3
-; CHECK-NEXT: and r5, r3, #3
-; CHECK-NEXT: wls lr, r5, .LBB3_10
+; CHECK-NEXT: add.w r9, r7, r3
+; CHECK-NEXT: and r7, r3, #3
+; CHECK-NEXT: add.w r8, r12, r7
+; CHECK-NEXT: wls lr, r7, .LBB3_10
; CHECK-NEXT: @ %bb.8: @ %for.body.prol.preheader
-; CHECK-NEXT: add.w r4, r12, r5
-; CHECK-NEXT: add.w r5, r0, r12, lsl #2
-; CHECK-NEXT: add.w r6, r1, r12, lsl #2
-; CHECK-NEXT: add.w r7, r2, r12, lsl #2
-; CHECK-NEXT: mov r12, r4
+; CHECK-NEXT: add.w r6, r0, r12, lsl #2
+; CHECK-NEXT: add.w r7, r1, r12, lsl #2
+; CHECK-NEXT: add.w r5, r2, r12, lsl #2
+; CHECK-NEXT: mov r12, r8
; CHECK-NEXT: .LBB3_9: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: ldr r4, [r6], #4
-; CHECK-NEXT: vldmia r5!, {s2}
+; CHECK-NEXT: ldr r4, [r7], #4
+; CHECK-NEXT: vldmia r6!, {s2}
; CHECK-NEXT: vmov s0, r4
; CHECK-NEXT: vcvt.f32.s32 s0, s0
; CHECK-NEXT: vmul.f32 s0, s2, s0
-; CHECK-NEXT: vstmia r7!, {s0}
+; CHECK-NEXT: vstmia r5!, {s0}
; CHECK-NEXT: le lr, .LBB3_9
; CHECK-NEXT: .LBB3_10: @ %for.body.prol.loopexit
-; CHECK-NEXT: cmp.w r8, #3
+; CHECK-NEXT: cmp.w r9, #3
; CHECK-NEXT: blo .LBB3_13
; CHECK-NEXT: @ %bb.11: @ %for.body.preheader1
+; CHECK-NEXT: sub.w r3, r8, r3
; CHECK-NEXT: add.w r1, r1, r12, lsl #2
-; CHECK-NEXT: sub.w r3, r3, r12
+; CHECK-NEXT: movs r7, #1
; CHECK-NEXT: adds r1, #8
-; CHECK-NEXT: lsl.w r12, r12, #2
+; CHECK-NEXT: rsb r3, r3, r3, lsl #30
+; CHECK-NEXT: subs r3, #4
+; CHECK-NEXT: add.w lr, r7, r3, lsr #2
+; CHECK-NEXT: lsl.w r3, r12, #2
; CHECK-NEXT: .LBB3_12: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldr s0, [r1, #-8]
-; CHECK-NEXT: add.w r7, r0, r12
-; CHECK-NEXT: add.w r6, r2, r12
+; CHECK-NEXT: adds r7, r0, r3
+; CHECK-NEXT: adds r6, r2, r3
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: vcvt.f32.s32 s0, s0
; CHECK-NEXT: vldr s2, [r7]
; CHECK-NEXT: adds r2, #16
-; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: vmul.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r6]
; CHECK-NEXT: vldr s0, [r1, #-4]
@@ -730,15 +735,14 @@ define arm_aapcs_vfpcc void @float_int_mul(ptr nocapture readonly %a, ptr nocapt
; CHECK-NEXT: vmul.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r6, #8]
; CHECK-NEXT: vldr s0, [r1, #4]
-; CHECK-NEXT: add.w r1, r1, #16
+; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: vldr s2, [r7, #12]
; CHECK-NEXT: vcvt.f32.s32 s0, s0
; CHECK-NEXT: vmul.f32 s0, s2, s0
; CHECK-NEXT: vstr s0, [r6, #12]
-; CHECK-NEXT: bne .LBB3_12
-; CHECK-NEXT: .LBB3_13:
-; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, lr}
-; CHECK-NEXT: bx lr
+; CHECK-NEXT: le lr, .LBB3_12
+; CHECK-NEXT: .LBB3_13: @ %for.cond.cleanup
+; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, pc}
entry:
%cmp8 = icmp eq i32 %N, 0
br i1 %cmp8, label %for.cond.cleanup, label %for.body.preheader
diff --git a/llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll b/llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
index 272e47b3ee1e73..5eebf133135556 100644
--- a/llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
+++ b/llvm/test/Transforms/LoopUnroll/runtime-loop-multiple-exits.ll
@@ -4514,7 +4514,7 @@ define void @test8() {
; EPILOG-NEXT: %i4.7 = add nuw nsw i64 %i3, 8
; EPILOG-NEXT: br i1 false, label %outerloop.loopexit.loopexit, label %latch.7
; EPILOG: latch.7:
-; EPILOG-NEXT: %niter.next.7 = add i64 %niter, 8
+; EPILOG-NEXT: %niter.next.7 = add nuw nsw i64 %niter, 8
; EPILOG-NEXT: %niter.ncmp.7 = icmp ne i64 %niter.next.7, %unroll_iter
; EPILOG-NEXT: br i1 %niter.ncmp.7, label %innerH, label %exit.unr-lcssa.loopexit
; EPILOG: exit.unr-lcssa.loopexit:
diff --git a/llvm/test/Transforms/LoopVectorize/opaque-ptr.ll b/llvm/test/Transforms/LoopVectorize/opaque-ptr.ll
index 13e79a4a47b39c..f62c3c7f42ec4e 100644
--- a/llvm/test/Transforms/LoopVectorize/opaque-ptr.ll
+++ b/llvm/test/Transforms/LoopVectorize/opaque-ptr.ll
@@ -4,18 +4,80 @@
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 [ [[P1_START:%.*]], [[ENTRY:%.*]] ], [ [[P1_NEXT:%.*]], [[LOOP]] ]
-; CHECK-NEXT: [[P2:%.*]] = phi ptr [ [[P2_START:%.*]], [[ENTRY]] ], [ [[P2_NEXT:%.*]], [[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:%.*]]
+; 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
;
@@ -80,14 +142,14 @@ define void @test_ptr_iv_with_inbounds(ptr %p1.start, ptr %p2.start, ptr %p1.end
; 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 [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
+; 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 [[META3]]
+; 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 [[META0]], !noalias [[META3]]
+; 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 [[LOOP5:![0-9]+]]
+; 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]]
@@ -105,7 +167,7 @@ define void @test_ptr_iv_with_inbounds(ptr %p1.start, ptr %p2.start, ptr %p1.end
; 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 [[LOOP8:![0-9]+]]
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP15:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
@@ -155,7 +217,7 @@ define void @store_pointer_induction(ptr %start, ptr %end) {
; 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 [[LOOP9:![0-9]+]]
+; 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]]
@@ -167,7 +229,7 @@ define void @store_pointer_induction(ptr %start, ptr %end) {
; 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 [[LOOP10:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
More information about the llvm-commits
mailing list