[llvm] [IndVarSimplify] Remove sinkunusedInvariants (PR #169250)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Nov 23 14:36:03 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Vigneshwar Jayakumar (VigneshwarJ)
<details>
<summary>Changes</summary>
This sinkunused invariants from preheader to exit does not sink the invariant memory instructions. Hence the liveness range of the memory instructions is extended till the exit block creating a lot of register spills.
This performance regression was not very visible before because the sinkunused invariants code had a bug which double iterated skipping a lot of potential instructions that could be sunk.
Tried sinking the invariant memory instructions, but that causes performance regression in small cases (#<!-- -->157559). This effort is to see if removing this code has a big performance impact.
---
Patch is 40.74 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/169250.diff
23 Files Affected:
- (modified) llvm/lib/Transforms/Scalar/IndVarSimplify.cpp (-83)
- (modified) llvm/test/Transforms/IndVarSimplify/AMDGPU/addrspace-7-doesnt-crash.ll (+1-1)
- (modified) llvm/test/Transforms/IndVarSimplify/ARM/code-size.ll (+10-12)
- (modified) llvm/test/Transforms/IndVarSimplify/ARM/indvar-unroll-imm-cost.ll (+2-2)
- (modified) llvm/test/Transforms/IndVarSimplify/X86/inner-loop-by-latch-cond.ll (+1-1)
- (modified) llvm/test/Transforms/IndVarSimplify/exit-count-select.ll (+12-12)
- (modified) llvm/test/Transforms/IndVarSimplify/finite-exit-comparisons.ll (+3-3)
- (modified) llvm/test/Transforms/IndVarSimplify/pr116483.ll (+4-4)
- (modified) llvm/test/Transforms/IndVarSimplify/pr24783.ll (+1-1)
- (modified) llvm/test/Transforms/IndVarSimplify/pr39673.ll (+1-1)
- (modified) llvm/test/Transforms/IndVarSimplify/pr63763.ll (+3-3)
- (modified) llvm/test/Transforms/IndVarSimplify/replace-loop-exit-folds.ll (+10-11)
- (modified) llvm/test/Transforms/IndVarSimplify/rewrite-loop-exit-values-phi.ll (+4-4)
- (modified) llvm/test/Transforms/IndVarSimplify/scev-expander-preserve-lcssa.ll (+7-7)
- (modified) llvm/test/Transforms/IndVarSimplify/scev-invalidation.ll (+2-2)
- (modified) llvm/test/Transforms/IndVarSimplify/sentinel.ll (+7-7)
- (removed) llvm/test/Transforms/IndVarSimplify/sink-from-preheader.ll (-32)
- (removed) llvm/test/Transforms/IndVarSimplify/sink-trapping.ll (-19)
- (modified) llvm/test/Transforms/IndVarSimplify/zext-nuw.ll (+1-1)
- (modified) llvm/test/Transforms/LoopDeletion/invalidate-scev-after-hoisting.ll (+1-1)
- (modified) llvm/test/Transforms/LoopDistribute/laa-invalidation.ll (+1-1)
- (modified) llvm/test/Transforms/LoopUnroll/unroll-cleanup.ll (+7-7)
- (modified) llvm/test/Transforms/PhaseOrdering/ARM/arm_mean_q7.ll (+6-8)
``````````diff
diff --git a/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp b/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
index b46527eb1057b..e22591f9298b4 100644
--- a/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
+++ b/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
@@ -162,7 +162,6 @@ class IndVarSimplify {
const SCEV *ExitCount,
PHINode *IndVar, SCEVExpander &Rewriter);
- bool sinkUnusedInvariants(Loop *L);
public:
IndVarSimplify(LoopInfo *LI, ScalarEvolution *SE, DominatorTree *DT,
@@ -1093,85 +1092,6 @@ linearFunctionTestReplace(Loop *L, BasicBlock *ExitingBB,
return true;
}
-//===----------------------------------------------------------------------===//
-// sinkUnusedInvariants. A late subpass to cleanup loop preheaders.
-//===----------------------------------------------------------------------===//
-
-/// If there's a single exit block, sink any loop-invariant values that
-/// were defined in the preheader but not used inside the loop into the
-/// exit block to reduce register pressure in the loop.
-bool IndVarSimplify::sinkUnusedInvariants(Loop *L) {
- BasicBlock *ExitBlock = L->getExitBlock();
- if (!ExitBlock) return false;
-
- BasicBlock *Preheader = L->getLoopPreheader();
- if (!Preheader) return false;
-
- bool MadeAnyChanges = false;
- for (Instruction &I : llvm::make_early_inc_range(llvm::reverse(*Preheader))) {
-
- // Skip BB Terminator.
- if (Preheader->getTerminator() == &I)
- continue;
-
- // New instructions were inserted at the end of the preheader.
- if (isa<PHINode>(I))
- break;
-
- // Don't move instructions which might have side effects, since the side
- // effects need to complete before instructions inside the loop. Also don't
- // move instructions which might read memory, since the loop may modify
- // memory. Note that it's okay if the instruction might have undefined
- // behavior: LoopSimplify guarantees that the preheader dominates the exit
- // block.
- if (I.mayHaveSideEffects() || I.mayReadFromMemory())
- continue;
-
- // Skip debug or pseudo instructions.
- if (I.isDebugOrPseudoInst())
- continue;
-
- // Skip eh pad instructions.
- if (I.isEHPad())
- continue;
-
- // Don't sink alloca: we never want to sink static alloca's out of the
- // entry block, and correctly sinking dynamic alloca's requires
- // checks for stacksave/stackrestore intrinsics.
- // FIXME: Refactor this check somehow?
- if (isa<AllocaInst>(&I))
- continue;
-
- // Determine if there is a use in or before the loop (direct or
- // otherwise).
- bool UsedInLoop = false;
- for (Use &U : I.uses()) {
- Instruction *User = cast<Instruction>(U.getUser());
- BasicBlock *UseBB = User->getParent();
- if (PHINode *P = dyn_cast<PHINode>(User)) {
- unsigned i =
- PHINode::getIncomingValueNumForOperand(U.getOperandNo());
- UseBB = P->getIncomingBlock(i);
- }
- if (UseBB == Preheader || L->contains(UseBB)) {
- UsedInLoop = true;
- break;
- }
- }
-
- // If there is, the def must remain in the preheader.
- if (UsedInLoop)
- continue;
-
- // Otherwise, sink it to the exit block.
- I.moveBefore(ExitBlock->getFirstInsertionPt());
- SE->forgetValue(&I);
- MadeAnyChanges = true;
- }
-
- return MadeAnyChanges;
-}
-
static void replaceExitCond(BranchInst *BI, Value *NewCond,
SmallVectorImpl<WeakTrackingVH> &DeadInsts) {
auto *OldCond = BI->getCondition();
@@ -2079,9 +1999,6 @@ bool IndVarSimplify::run(Loop *L) {
// The Rewriter may not be used from this point on.
- // Loop-invariant instructions in the preheader that aren't used in the
- // loop may be sunk below the loop to reduce register pressure.
- Changed |= sinkUnusedInvariants(L);
// rewriteFirstIterationLoopExitValues does not rely on the computation of
// trip count and therefore can further simplify exit values in addition to
diff --git a/llvm/test/Transforms/IndVarSimplify/AMDGPU/addrspace-7-doesnt-crash.ll b/llvm/test/Transforms/IndVarSimplify/AMDGPU/addrspace-7-doesnt-crash.ll
index 08dcf1d7a0091..8e932e0c00d4f 100644
--- a/llvm/test/Transforms/IndVarSimplify/AMDGPU/addrspace-7-doesnt-crash.ll
+++ b/llvm/test/Transforms/IndVarSimplify/AMDGPU/addrspace-7-doesnt-crash.ll
@@ -7,11 +7,11 @@ define void @f(ptr addrspace(7) %arg) {
; CHECK-LABEL: define void @f
; CHECK-SAME: (ptr addrspace(7) [[ARG:%.*]]) {
; CHECK-NEXT: bb:
+; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr addrspace(7) [[ARG]], i32 8
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 false, label [[BB2:%.*]], label [[BB1]]
; CHECK: bb2:
-; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr addrspace(7) [[ARG]], i32 8
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb3:
; CHECK-NEXT: [[I4:%.*]] = load i32, ptr addrspace(7) [[SCEVGEP]], align 4
diff --git a/llvm/test/Transforms/IndVarSimplify/ARM/code-size.ll b/llvm/test/Transforms/IndVarSimplify/ARM/code-size.ll
index 2003b1a72206d..3c6535da486aa 100644
--- a/llvm/test/Transforms/IndVarSimplify/ARM/code-size.ll
+++ b/llvm/test/Transforms/IndVarSimplify/ARM/code-size.ll
@@ -4,33 +4,31 @@
define i32 @remove_loop(i32 %size) #0 {
; CHECK-V8M-LABEL: @remove_loop(
-; CHECK-V8M-SAME: i32 [[SIZE:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-V8M-NEXT: entry:
-; CHECK-V8M-NEXT: br label %[[WHILE_COND:.*]]
-; CHECK-V8M: while.cond:
-; CHECK-V8M-NEXT: br i1 false, label %[[WHILE_COND]], label %[[WHILE_END:.*]]
-; CHECK-V8M: while.end:
-; CHECK-V8M-NEXT: [[TMP0:%.*]] = add i32 [[SIZE]], 31
+; CHECK-V8M-NEXT: [[TMP0:%.*]] = add i32 [[SIZE:%.*]], 31
; CHECK-V8M-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[SIZE]], i32 31)
; CHECK-V8M-NEXT: [[TMP1:%.*]] = sub i32 [[TMP0]], [[UMIN]]
; CHECK-V8M-NEXT: [[TMP2:%.*]] = lshr i32 [[TMP1]], 5
; CHECK-V8M-NEXT: [[TMP3:%.*]] = shl nuw i32 [[TMP2]], 5
; CHECK-V8M-NEXT: [[TMP4:%.*]] = sub i32 [[SIZE]], [[TMP3]]
+; CHECK-V8M-NEXT: br label [[WHILE_COND:%.*]]
+; CHECK-V8M: while.cond:
+; CHECK-V8M-NEXT: br i1 false, label [[WHILE_COND]], label [[WHILE_END:%.*]]
+; CHECK-V8M: while.end:
; CHECK-V8M-NEXT: ret i32 [[TMP4]]
;
; CHECK-V8A-LABEL: @remove_loop(
-; CHECK-V8A-SAME: i32 [[SIZE:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-V8A-NEXT: entry:
-; CHECK-V8A-NEXT: br label %[[WHILE_COND:.*]]
-; CHECK-V8A: while.cond:
-; CHECK-V8A-NEXT: br i1 false, label %[[WHILE_COND]], label %[[WHILE_END:.*]]
-; CHECK-V8A: while.end:
-; CHECK-V8A-NEXT: [[TMP0:%.*]] = add i32 [[SIZE]], 31
+; CHECK-V8A-NEXT: [[TMP0:%.*]] = add i32 [[SIZE:%.*]], 31
; CHECK-V8A-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[SIZE]], i32 31)
; CHECK-V8A-NEXT: [[TMP1:%.*]] = sub i32 [[TMP0]], [[UMIN]]
; CHECK-V8A-NEXT: [[TMP2:%.*]] = lshr i32 [[TMP1]], 5
; CHECK-V8A-NEXT: [[TMP3:%.*]] = shl nuw i32 [[TMP2]], 5
; CHECK-V8A-NEXT: [[TMP4:%.*]] = sub i32 [[SIZE]], [[TMP3]]
+; CHECK-V8A-NEXT: br label [[WHILE_COND:%.*]]
+; CHECK-V8A: while.cond:
+; CHECK-V8A-NEXT: br i1 false, label [[WHILE_COND]], label [[WHILE_END:%.*]]
+; CHECK-V8A: while.end:
; CHECK-V8A-NEXT: ret i32 [[TMP4]]
;
entry:
diff --git a/llvm/test/Transforms/IndVarSimplify/ARM/indvar-unroll-imm-cost.ll b/llvm/test/Transforms/IndVarSimplify/ARM/indvar-unroll-imm-cost.ll
index 2261423766792..382f026e7de6a 100644
--- a/llvm/test/Transforms/IndVarSimplify/ARM/indvar-unroll-imm-cost.ll
+++ b/llvm/test/Transforms/IndVarSimplify/ARM/indvar-unroll-imm-cost.ll
@@ -77,6 +77,8 @@ define dso_local arm_aapcscc void @test(ptr nocapture %pDest, ptr nocapture read
; CHECK-NEXT: [[CMP2780:%.*]] = icmp ugt i32 [[ADD25]], [[J_0_LCSSA]]
; CHECK-NEXT: br i1 [[CMP2780]], label [[FOR_BODY29_PREHEADER:%.*]], label [[FOR_END40]]
; CHECK: for.body29.preheader:
+; CHECK-NEXT: [[TMP10:%.*]] = sub nsw i32 [[ADD25]], [[J_0_LCSSA]]
+; CHECK-NEXT: [[SCEVGEP93:%.*]] = getelementptr i16, ptr [[PSRCB_ADDR_1_LCSSA]], i32 [[TMP10]]
; CHECK-NEXT: br label [[FOR_BODY29:%.*]]
; CHECK: for.body29:
; CHECK-NEXT: [[J_184:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY29]] ], [ [[J_0_LCSSA]], [[FOR_BODY29_PREHEADER]] ]
@@ -100,8 +102,6 @@ define dso_local arm_aapcscc void @test(ptr nocapture %pDest, ptr nocapture read
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[ADD25]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END40_LOOPEXIT:%.*]], label [[FOR_BODY29]]
; CHECK: for.end40.loopexit:
-; CHECK-NEXT: [[TMP10:%.*]] = sub nsw i32 [[ADD25]], [[J_0_LCSSA]]
-; CHECK-NEXT: [[SCEVGEP93:%.*]] = getelementptr i16, ptr [[PSRCB_ADDR_1_LCSSA]], i32 [[TMP10]]
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, ptr [[PSRCA_ADDR_1_LCSSA]], i32 [[TMP10]]
; CHECK-NEXT: [[SCEVGEP94:%.*]] = getelementptr i32, ptr [[PDEST_ADDR_1_LCSSA]], i32 [[TMP10]]
; CHECK-NEXT: br label [[FOR_END40]]
diff --git a/llvm/test/Transforms/IndVarSimplify/X86/inner-loop-by-latch-cond.ll b/llvm/test/Transforms/IndVarSimplify/X86/inner-loop-by-latch-cond.ll
index 0fa6e34cf186e..0eb9debce8177 100644
--- a/llvm/test/Transforms/IndVarSimplify/X86/inner-loop-by-latch-cond.ll
+++ b/llvm/test/Transforms/IndVarSimplify/X86/inner-loop-by-latch-cond.ll
@@ -14,6 +14,7 @@ define void @test(i64 %a) {
; CHECK: outer_header:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[OUTER_LATCH:%.*]] ], [ 21, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[I:%.*]] = phi i64 [ 20, [[ENTRY]] ], [ [[I_NEXT:%.*]], [[OUTER_LATCH]] ]
+; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: br label [[INNER_HEADER:%.*]]
; CHECK: inner_header:
; CHECK-NEXT: [[J:%.*]] = phi i64 [ 1, [[OUTER_HEADER]] ], [ [[J_NEXT:%.*]], [[INNER_HEADER]] ]
@@ -22,7 +23,6 @@ define void @test(i64 %a) {
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[J_NEXT]], [[INDVARS_IV]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[INNER_HEADER]], label [[OUTER_LATCH]]
; CHECK: outer_latch:
-; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: [[COND2:%.*]] = icmp ne i64 [[I_NEXT]], 40
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: br i1 [[COND2]], label [[OUTER_HEADER]], label [[RETURN:%.*]]
diff --git a/llvm/test/Transforms/IndVarSimplify/exit-count-select.ll b/llvm/test/Transforms/IndVarSimplify/exit-count-select.ll
index 1592b84480e3f..50c8e0fb7aabf 100644
--- a/llvm/test/Transforms/IndVarSimplify/exit-count-select.ll
+++ b/llvm/test/Transforms/IndVarSimplify/exit-count-select.ll
@@ -4,12 +4,12 @@
define i32 @logical_and_2ops(i32 %n, i32 %m) {
; CHECK-LABEL: @logical_and_2ops(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[M:%.*]]
+; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 [[N:%.*]])
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: br i1 false, label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
-; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[M:%.*]]
-; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 [[N:%.*]])
; CHECK-NEXT: ret i32 [[UMIN]]
;
entry:
@@ -28,12 +28,12 @@ exit:
define i32 @logical_or_2ops(i32 %n, i32 %m) {
; CHECK-LABEL: @logical_or_2ops(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[M:%.*]]
+; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 [[N:%.*]])
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[LOOP]]
; CHECK: exit:
-; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[M:%.*]]
-; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 [[N:%.*]])
; CHECK-NEXT: ret i32 [[UMIN]]
;
entry:
@@ -52,14 +52,14 @@ exit:
define i32 @logical_and_3ops(i32 %n, i32 %m, i32 %k) {
; CHECK-LABEL: @logical_and_3ops(
; CHECK-NEXT: entry:
-; CHECK-NEXT: br label [[LOOP:%.*]]
-; CHECK: loop:
-; CHECK-NEXT: br i1 false, label [[LOOP]], label [[EXIT:%.*]]
-; CHECK: exit:
; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[K:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = freeze i32 [[M:%.*]]
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 [[TMP1]])
; CHECK-NEXT: [[UMIN1:%.*]] = call i32 @llvm.umin.i32(i32 [[UMIN]], i32 [[N:%.*]])
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: br i1 false, label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
; CHECK-NEXT: ret i32 [[UMIN1]]
;
entry:
@@ -80,14 +80,14 @@ exit:
define i32 @logical_or_3ops(i32 %n, i32 %m, i32 %k) {
; CHECK-LABEL: @logical_or_3ops(
; CHECK-NEXT: entry:
-; CHECK-NEXT: br label [[LOOP:%.*]]
-; CHECK: loop:
-; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[LOOP]]
-; CHECK: exit:
; CHECK-NEXT: [[TMP0:%.*]] = freeze i32 [[K:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = freeze i32 [[M:%.*]]
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 [[TMP1]])
; CHECK-NEXT: [[UMIN1:%.*]] = call i32 @llvm.umin.i32(i32 [[UMIN]], i32 [[N:%.*]])
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[LOOP]]
+; CHECK: exit:
; CHECK-NEXT: ret i32 [[UMIN1]]
;
entry:
diff --git a/llvm/test/Transforms/IndVarSimplify/finite-exit-comparisons.ll b/llvm/test/Transforms/IndVarSimplify/finite-exit-comparisons.ll
index e006d9f6696ca..f798eb281f51a 100644
--- a/llvm/test/Transforms/IndVarSimplify/finite-exit-comparisons.ll
+++ b/llvm/test/Transforms/IndVarSimplify/finite-exit-comparisons.ll
@@ -932,6 +932,9 @@ for.end: ; preds = %for.body, %entry
define i16 @ult_multiuse_profit(i16 %n.raw, i8 %start) mustprogress {
; CHECK-LABEL: @ult_multiuse_profit(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[START:%.*]], 1
+; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP2]] to i16
+; CHECK-NEXT: [[UMAX:%.*]] = call i16 @llvm.umax.i16(i16 [[TMP1]], i16 254)
; CHECK-NEXT: [[TMP0:%.*]] = trunc i16 254 to i8
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
@@ -940,9 +943,6 @@ define i16 @ult_multiuse_profit(i16 %n.raw, i8 %start) mustprogress {
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i8 [[IV_NEXT]], [[TMP0]]
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
; CHECK: for.end:
-; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[START:%.*]], 1
-; CHECK-NEXT: [[TMP2:%.*]] = zext i8 [[TMP1]] to i16
-; CHECK-NEXT: [[UMAX:%.*]] = call i16 @llvm.umax.i16(i16 [[TMP2]], i16 254)
; CHECK-NEXT: ret i16 [[UMAX]]
;
entry:
diff --git a/llvm/test/Transforms/IndVarSimplify/pr116483.ll b/llvm/test/Transforms/IndVarSimplify/pr116483.ll
index 093e25a3caa81..e9e0d22bf960a 100644
--- a/llvm/test/Transforms/IndVarSimplify/pr116483.ll
+++ b/llvm/test/Transforms/IndVarSimplify/pr116483.ll
@@ -4,16 +4,16 @@
define i32 @test() {
; CHECK-LABEL: define i32 @test() {
; CHECK-NEXT: [[ENTRY:.*:]]
-; CHECK-NEXT: br label %[[LOOP_BODY:.*]]
-; CHECK: [[LOOP_BODY]]:
-; CHECK-NEXT: br i1 true, label %[[EXIT:.*]], label %[[LOOP_BODY]]
-; CHECK: [[EXIT]]:
; CHECK-NEXT: [[XOR:%.*]] = xor i32 0, 3
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[XOR]], 329
; CHECK-NEXT: [[CONV:%.*]] = trunc i32 [[MUL]] to i16
; CHECK-NEXT: [[SEXT:%.*]] = shl i16 [[CONV]], 8
; CHECK-NEXT: [[CONV1:%.*]] = ashr i16 [[SEXT]], 8
; CHECK-NEXT: [[CONV3:%.*]] = zext i16 [[CONV1]] to i32
+; CHECK-NEXT: br label %[[LOOP_BODY:.*]]
+; CHECK: [[LOOP_BODY]]:
+; CHECK-NEXT: br i1 true, label %[[EXIT:.*]], label %[[LOOP_BODY]]
+; CHECK: [[EXIT]]:
; CHECK-NEXT: ret i32 [[CONV3]]
;
entry:
diff --git a/llvm/test/Transforms/IndVarSimplify/pr24783.ll b/llvm/test/Transforms/IndVarSimplify/pr24783.ll
index c521bcaf59d49..37ecf42ea0fd3 100644
--- a/llvm/test/Transforms/IndVarSimplify/pr24783.ll
+++ b/llvm/test/Transforms/IndVarSimplify/pr24783.ll
@@ -7,11 +7,11 @@ target triple = "powerpc64-unknown-linux-gnu"
define void @f(ptr %end.s, ptr %loc, i32 %p) {
; CHECK-LABEL: @f(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds i32, ptr [[END_S:%.*]], i32 [[P:%.*]]
; CHECK-NEXT: br label [[WHILE_BODY_I:%.*]]
; CHECK: while.body.i:
; CHECK-NEXT: br i1 true, label [[LOOP_EXIT:%.*]], label [[WHILE_BODY_I]]
; CHECK: loop.exit:
-; CHECK-NEXT: [[END:%.*]] = getelementptr inbounds i32, ptr [[END_S:%.*]], i32 [[P:%.*]]
; CHECK-NEXT: store ptr [[END]], ptr [[LOC:%.*]], align 8
; CHECK-NEXT: ret void
;
diff --git a/llvm/test/Transforms/IndVarSimplify/pr39673.ll b/llvm/test/Transforms/IndVarSimplify/pr39673.ll
index 7b093b34b91ad..3cee1ab7be881 100644
--- a/llvm/test/Transforms/IndVarSimplify/pr39673.ll
+++ b/llvm/test/Transforms/IndVarSimplify/pr39673.ll
@@ -148,6 +148,7 @@ loop2.end: ; preds = %loop2
define i16 @neg_loop_carried(i16 %arg) {
; CHECK-LABEL: @neg_loop_carried(
; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP0:%.*]] = add i16 [[ARG:%.*]], 2
; CHECK-NEXT: br label [[LOOP1:%.*]]
; CHECK: loop1:
; CHECK-NEXT: [[L1:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[L1_ADD:%.*]], [[LOOP1]] ]
@@ -155,7 +156,6 @@ define i16 @neg_loop_carried(i16 %arg) {
; CHECK-NEXT: [[CMP1:%.*]] = icmp ult i16 [[L1_ADD]], 2
; CHECK-NEXT: br i1 [[CMP1]], label [[LOOP1]], label [[LOOP2_PREHEADER:%.*]]
; CHECK: loop2.preheader:
-; CHECK-NEXT: [[TMP0:%.*]] = add i16 [[ARG:%.*]], 2
; CHECK-NEXT: br label [[LOOP2:%.*]]
; CHECK: loop2:
; CHECK-NEXT: [[K2:%.*]] = phi i16 [ [[K2_ADD:%.*]], [[LOOP2]] ], [ [[TMP0]], [[LOOP2_PREHEADER]] ]
diff --git a/llvm/test/Transforms/IndVarSimplify/pr63763.ll b/llvm/test/Transforms/IndVarSimplify/pr63763.ll
index 427db1e67410a..a5fde67d6140a 100644
--- a/llvm/test/Transforms/IndVarSimplify/pr63763.ll
+++ b/llvm/test/Transforms/IndVarSimplify/pr63763.ll
@@ -16,13 +16,13 @@ define i32 @test(i1 %c) {
; CHECK-NEXT: [[CONV2:%.*]] = ashr exact i32 [[SEXT]], 24
; CHECK-NEXT: [[INVARIANT_OP:%.*]] = sub nsw i32 7, [[CONV2]]
; CHECK-NEXT: call void @use(i32 [[INVARIANT_OP]])
+; CHECK-NEXT: [[SEXT_US:%.*]] = shl i32 [[SEL]], 24
+; CHECK-NEXT: [[CONV2_US:%.*]] = ashr exact i32 [[SEXT_US]], 24
+; CHECK-NEXT: [[INVARIANT_OP_US:%.*]] = sub nsw i32 7, [[CONV2_US]]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[LOOP]]
; CHECK: exit:
-; CHECK-NEXT: [[SEXT_US:%.*]] = shl i32 [[SEL]], 24
-; CHECK-NEXT: [[CONV2_US:%.*]] = ashr exact i32 [[SEXT_US]], 24
-; CHECK-NEXT: [[INVARIANT_OP_US:%.*]] = sub nsw i32 7, [[CONV2_US]]
; CHECK-NEXT: ret i32 [[INVARIANT_OP_US]]
;
entry:
diff --git a/llvm/test/Transforms/IndVarSimplify/replace-loop-exit-folds.ll b/llvm/test/Transforms/IndVarSimplify/replace-loop-exit-folds.ll
index b3162de0f2245..7cdc98a6c4f7c 100644
--- a/llvm/test/Transforms/IndVarSimplify/replace-loop-exit-folds.ll
+++ b/llvm/test/Transforms/IndVarSimplify/replace-loop-exit-folds.ll
@@ -4,22 +4,21 @@
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
define i32 @remove_loop(i32 %size) {
-; CHECK-LABEL: define i32 @remove_loop(
-; CHECK-SAME: i32 [[SIZE:%.*]]) {
-; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: br label %[[WHILE_COND:.*]]
-; CHECK: [[WHILE_COND]]:
-; CHECK-NEXT: [[SIZE_ADDR_0:%.*]] = phi i32 [ [[SIZE]], %[[ENTRY]] ], [ [[SUB:%.*]], %[[WHILE_COND]] ]
-; CHECK-NEXT: [[CMP:%.*]] = icmp ugt i32 [[SIZE_ADDR_0]], 31
-; CHECK-NEXT: [[SUB]] = add i32 [[SIZE_ADDR_0]], -32
-; CHECK-NEXT: br i1 [[CMP]], label %[[WHILE_COND]], label %[[WHILE_END:.*]]
-; CHECK: [[WHILE_END]]:
-; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[SIZE]], 31
+; CHECK-LABEL: @remove_loop(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[SIZE:%.*]], 31
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[SIZE]], i32 31)
; CHECK-NEXT: [[TMP1:%.*]] = sub i32 [[TMP0]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = lshr i32 [[TMP1]], 5
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw i32 [[TMP2]], 5
; CHECK-NEXT: [[TMP4:%.*]] = sub i32 [[SIZE]], [[TMP3]]
+; CHECK-NEXT: br label [...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/169250
More information about the llvm-commits
mailing list