[llvm] [AArch64] Enable RT and partial unrolling with reductions for Apple CPUs. (PR #149699)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Jul 20 04:33:31 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
@llvm/pr-subscribers-llvm-transforms
Author: Florian Hahn (fhahn)
<details>
<summary>Changes</summary>
Update unrolling preferences for Apple Silicon CPUs to enable partial
unrolling and runtime unrolling for small loops with reductions.
This builds on top of unroller changes to introduce parallel reduction
phis, if possible: https://github.com/llvm/llvm-project/pull/149470.
---
Patch is 62.29 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/149699.diff
10 Files Affected:
- (modified) llvm/include/llvm/Transforms/Utils/UnrollLoop.h (+3)
- (modified) llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (+19)
- (modified) llvm/lib/Transforms/Utils/LoopUnroll.cpp (+130)
- (modified) llvm/test/Transforms/LoopUnroll/AArch64/apple-unrolling.ll (+148-40)
- (modified) llvm/test/Transforms/LoopUnroll/ARM/instr-size-costs.ll (+10-6)
- (modified) llvm/test/Transforms/LoopUnroll/partial-unroll-reductions.ll (+24-12)
- (modified) llvm/test/Transforms/LoopUnroll/runtime-loop5.ll (+13-7)
- (modified) llvm/test/Transforms/LoopUnroll/runtime-unroll-reductions.ll (+7-5)
- (modified) llvm/test/Transforms/LoopUnroll/runtime-unroll-remainder.ll (+20-14)
- (modified) llvm/test/Transforms/PhaseOrdering/SystemZ/sub-xor.ll (+16-16)
``````````diff
diff --git a/llvm/include/llvm/Transforms/Utils/UnrollLoop.h b/llvm/include/llvm/Transforms/Utils/UnrollLoop.h
index 765c613b04a44..86eb78dc70372 100644
--- a/llvm/include/llvm/Transforms/Utils/UnrollLoop.h
+++ b/llvm/include/llvm/Transforms/Utils/UnrollLoop.h
@@ -163,6 +163,9 @@ LLVM_ABI bool computeUnrollCount(
TargetTransformInfo::UnrollingPreferences &UP,
TargetTransformInfo::PeelingPreferences &PP, bool &UseUpperBound);
+LLVM_ABI std::optional<RecurrenceDescriptor>
+canParallelizeReductionWhenUnrolling(PHINode &Phi, Loop *L,
+ ScalarEvolution *SE);
} // end namespace llvm
#endif // LLVM_TRANSFORMS_UTILS_UNROLLLOOP_H
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 90d3d92d6bbf5..d4fb60d9c65e5 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -25,6 +25,7 @@
#include "llvm/Support/Debug.h"
#include "llvm/TargetParser/AArch64TargetParser.h"
#include "llvm/Transforms/InstCombine/InstCombiner.h"
+#include "llvm/Transforms/Utils/UnrollLoop.h"
#include "llvm/Transforms/Vectorize/LoopVectorizationLegality.h"
#include <algorithm>
#include <optional>
@@ -4787,6 +4788,19 @@ getAppleRuntimeUnrollPreferences(Loop *L, ScalarEvolution &SE,
if (!L->getExitBlock())
return;
+ // Check if the loop contains any reductions that could be parallelized when unrolling.
+ // If so, enable partial unrolling, if the trip count is know to be a multiple of 2.
+ bool HasParellelizableReductions =
+ L->getNumBlocks() == 1 &&
+ any_of(L->getHeader()->phis(), [&SE, L](PHINode &Phi) {
+ return canParallelizeReductionWhenUnrolling(Phi, L, &SE);
+ }) && isLoopSizeWithinBudget(L, TTI, 12, nullptr);
+ if (HasParellelizableReductions &&
+ SE.getSmallConstantTripMultiple(L, L->getExitingBlock()) % 2 == 0) {
+ UP.Partial = true;
+ UP.MaxCount = 4;
+ }
+
const SCEV *BTC = SE.getSymbolicMaxBackedgeTakenCount(L);
if (isa<SCEVConstant>(BTC) || isa<SCEVCouldNotCompute>(BTC) ||
(SE.getSmallConstantMaxTripCount(L) > 0 &&
@@ -4802,6 +4816,11 @@ getAppleRuntimeUnrollPreferences(Loop *L, ScalarEvolution &SE,
// Limit to loops with trip counts that are cheap to expand.
UP.SCEVExpansionBudget = 1;
+ if (HasParellelizableReductions) {
+ UP.Runtime = true;
+ UP.DefaultUnrollRuntimeCount = 4;
+ }
+
// Try to unroll small, single block loops, if they have load/store
// dependencies, to expose more parallel memory access streams.
BasicBlock *Header = L->getHeader();
diff --git a/llvm/lib/Transforms/Utils/LoopUnroll.cpp b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
index 86b268de43cf6..63b311a7b1580 100644
--- a/llvm/lib/Transforms/Utils/LoopUnroll.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
@@ -41,6 +41,7 @@
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
@@ -660,6 +661,38 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
OrigPHINode.push_back(cast<PHINode>(I));
}
+ // Collect phi nodes for reductions for which we can introduce multiple
+ // parallel reduction phis and compute the final reduction result after the
+ // loop. This requires a single exit block after unrolling. This is ensured by
+ // restricting to single-block loops where the unrolled iterations are known
+ // to not exit.
+ DenseMap<PHINode *, RecurrenceDescriptor> Reductions;
+ bool CanAddAdditionalAccumulators =
+ !CompletelyUnroll && L->getNumBlocks() == 1 &&
+ (ULO.Runtime ||
+ (ExitInfos.contains(Header) && ((ExitInfos[Header].TripCount != 0 &&
+ ExitInfos[Header].BreakoutTrip == 0))));
+
+ // Limit parallelizing reductions to unroll counts of 4 or less for now.
+ // TODO: The number of parallel reductions should depend on the number of
+ // execution units. We also don't have to add a parallel reduction phi per
+ // unrolled iteration, but could for example add a parallel phi for every 2
+ // unrolled iterations.
+ if (CanAddAdditionalAccumulators && ULO.Count <= 4) {
+ for (PHINode &Phi : Header->phis()) {
+ auto RdxDesc = canParallelizeReductionWhenUnrolling(Phi, L, SE);
+ if (!RdxDesc)
+ continue;
+
+ // Only handle duplicate phis for a single reduction for now.
+ // TODO: Handle any number of reductions
+ if (!Reductions.empty())
+ continue;
+
+ Reductions[&Phi] = *RdxDesc;
+ }
+ }
+
std::vector<BasicBlock *> Headers;
std::vector<BasicBlock *> Latches;
Headers.push_back(Header);
@@ -710,6 +743,7 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
// latch. This is a reasonable default placement if we don't have block
// frequencies, and if we do, well the layout will be adjusted later.
auto BlockInsertPt = std::next(LatchBlock->getIterator());
+ SmallVector<Instruction *> PartialReductions;
for (unsigned It = 1; It != ULO.Count; ++It) {
SmallVector<BasicBlock *, 8> NewBlocks;
SmallDenseMap<const Loop *, Loop *, 4> NewLoops;
@@ -733,6 +767,31 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
for (PHINode *OrigPHI : OrigPHINode) {
PHINode *NewPHI = cast<PHINode>(VMap[OrigPHI]);
Value *InVal = NewPHI->getIncomingValueForBlock(LatchBlock);
+
+ // Use cloned phis as parallel phis for partial reductions, which will
+ // get combined to the final reduction result after the loop.
+ if (Reductions.contains(OrigPHI)) {
+ // Collect partial reduction results.
+ if (PartialReductions.empty())
+ PartialReductions.push_back(cast<Instruction>(InVal));
+ PartialReductions.push_back(cast<Instruction>(VMap[InVal]));
+
+ // Update the start value for the cloned phis to use the identity
+ // value for the reduction.
+ const RecurrenceDescriptor &RdxDesc = Reductions[OrigPHI];
+ NewPHI->setIncomingValueForBlock(
+ L->getLoopPreheader(),
+ getRecurrenceIdentity(RdxDesc.getRecurrenceKind(),
+ OrigPHI->getType(),
+ RdxDesc.getFastMathFlags()));
+
+ // Update NewPHI to use the cloned value for the iteration and move
+ // to header.
+ NewPHI->replaceUsesOfWith(InVal, VMap[InVal]);
+ NewPHI->moveBefore(OrigPHI->getIterator());
+ continue;
+ }
+
if (Instruction *InValI = dyn_cast<Instruction>(InVal))
if (It > 1 && L->contains(InValI))
InVal = LastValueMap[InValI];
@@ -832,7 +891,11 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
PN->replaceAllUsesWith(PN->getIncomingValueForBlock(Preheader));
PN->eraseFromParent();
} else if (ULO.Count > 1) {
+ if (Reductions.contains(PN))
+ continue;
+
Value *InVal = PN->removeIncomingValue(LatchBlock, false);
+
// If this value was defined in the loop, take the value defined by the
// last iteration of the loop.
if (Instruction *InValI = dyn_cast<Instruction>(InVal)) {
@@ -1010,6 +1073,38 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
}
}
+ // If there are partial reductions, create code in the exit block to compute
+ // the final result and update users of the final result.
+ if (!PartialReductions.empty()) {
+ BasicBlock *ExitBlock = L->getExitBlock();
+ assert(ExitBlock &&
+ "Can only introduce parallel reduction phis with single exit block");
+ assert(Reductions.size() == 1 &&
+ "currently only a single reduction is supported");
+ Value *FinalRdxValue = PartialReductions.back();
+ Value *RdxResult = nullptr;
+ for (PHINode &Phi : ExitBlock->phis()) {
+ if (Phi.getIncomingValueForBlock(L->getLoopLatch()) != FinalRdxValue)
+ continue;
+ if (!RdxResult) {
+ RdxResult = PartialReductions.front();
+ IRBuilder Builder(ExitBlock, ExitBlock->getFirstNonPHIIt());
+ RecurKind RK = Reductions.begin()->second.getRecurrenceKind();
+ for (Instruction *RdxPart : drop_begin(PartialReductions)) {
+ RdxResult = Builder.CreateBinOp(
+ (Instruction::BinaryOps)RecurrenceDescriptor::getOpcode(RK),
+ RdxPart, RdxResult, "bin.rdx");
+ }
+ NeedToFixLCSSA = true;
+ for (Instruction *RdxPart : PartialReductions)
+ RdxPart->dropPoisonGeneratingFlags();
+ }
+
+ Phi.replaceAllUsesWith(RdxResult);
+ continue;
+ }
+ }
+
if (DTUToUse) {
// Apply updates to the DomTree.
DT = &DTU.getDomTree();
@@ -1111,3 +1206,38 @@ MDNode *llvm::GetUnrollMetadata(MDNode *LoopID, StringRef Name) {
}
return nullptr;
}
+
+std::optional<RecurrenceDescriptor>
+llvm::canParallelizeReductionWhenUnrolling(PHINode &Phi, Loop *L,
+ ScalarEvolution *SE) {
+ RecurrenceDescriptor RedDes;
+ if (!RecurrenceDescriptor::isReductionPHI(&Phi, L, RedDes,
+ /*DemandedBits=*/nullptr,
+ /*AC=*/nullptr, /*DT=*/nullptr, SE))
+ return std::nullopt;
+ RecurKind RK = RedDes.getRecurrenceKind();
+ // Skip unsupported reductions.
+ // TODO: Handle additional reductions, including FP and min-max
+ // reductions.
+ if (!RecurrenceDescriptor::isIntegerRecurrenceKind(RK) ||
+ RecurrenceDescriptor::isAnyOfRecurrenceKind(RK) ||
+ RecurrenceDescriptor::isFindIVRecurrenceKind(RK) ||
+ RecurrenceDescriptor::isMinMaxRecurrenceKind(RK))
+ return std::nullopt;
+
+ // Don't unroll reductions with constant ops; those can be folded to a
+ // single induction update.
+ if (any_of(cast<Instruction>(Phi.getIncomingValueForBlock(L->getLoopLatch()))
+ ->operands(),
+ IsaPred<Constant>))
+ return std::nullopt;
+
+ BasicBlock *Latch = L->getLoopLatch();
+ if (!Latch ||
+ !is_contained(
+ cast<Instruction>(Phi.getIncomingValueForBlock(Latch))->operands(),
+ &Phi))
+ return std::nullopt;
+
+ return RedDes;
+}
diff --git a/llvm/test/Transforms/LoopUnroll/AArch64/apple-unrolling.ll b/llvm/test/Transforms/LoopUnroll/AArch64/apple-unrolling.ll
index 0b78beea54aa9..e219e2720b5db 100644
--- a/llvm/test/Transforms/LoopUnroll/AArch64/apple-unrolling.ll
+++ b/llvm/test/Transforms/LoopUnroll/AArch64/apple-unrolling.ll
@@ -585,16 +585,34 @@ define i32 @test_add_reduction_unroll_partial(ptr %a, i64 noundef %n) {
; APPLE-NEXT: [[ENTRY:.*]]:
; APPLE-NEXT: br label %[[LOOP:.*]]
; APPLE: [[LOOP]]:
-; APPLE-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT_3:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_1:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_1:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_2:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_2:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_3:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_3:%.*]], %[[LOOP]] ]
; APPLE-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT:%.*]], %[[LOOP]] ]
; APPLE-NEXT: [[GEP_A:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV]]
; APPLE-NEXT: [[TMP0:%.*]] = load i32, ptr [[GEP_A]], align 2
-; APPLE-NEXT: [[RDX_NEXT]] = add nuw nsw i32 [[RDX]], [[TMP0]]
-; APPLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; APPLE-NEXT: [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
-; APPLE-NEXT: br i1 [[EC]], label %[[EXIT:.*]], label %[[LOOP]]
+; APPLE-NEXT: [[RDX_NEXT]] = add i32 [[RDX]], [[TMP0]]
+; APPLE-NEXT: [[IV_NEXT:%.*]] = add nuw nsw i64 [[IV]], 1
+; APPLE-NEXT: [[GEP_A_1:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT]]
+; APPLE-NEXT: [[TMP1:%.*]] = load i32, ptr [[GEP_A_1]], align 2
+; APPLE-NEXT: [[RDX_NEXT_1]] = add i32 [[RDX_1]], [[TMP1]]
+; APPLE-NEXT: [[IV_NEXT_1:%.*]] = add nuw nsw i64 [[IV]], 2
+; APPLE-NEXT: [[GEP_A_2:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT_1]]
+; APPLE-NEXT: [[TMP2:%.*]] = load i32, ptr [[GEP_A_2]], align 2
+; APPLE-NEXT: [[RDX_NEXT_2]] = add i32 [[RDX_2]], [[TMP2]]
+; APPLE-NEXT: [[IV_NEXT_2:%.*]] = add nuw nsw i64 [[IV]], 3
+; APPLE-NEXT: [[GEP_A_3:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT_2]]
+; APPLE-NEXT: [[TMP3:%.*]] = load i32, ptr [[GEP_A_3]], align 2
+; APPLE-NEXT: [[RDX_NEXT_3]] = add i32 [[RDX_3]], [[TMP3]]
+; APPLE-NEXT: [[IV_NEXT_3]] = add nuw nsw i64 [[IV]], 4
+; APPLE-NEXT: [[EC_3:%.*]] = icmp eq i64 [[IV_NEXT_3]], 1024
+; APPLE-NEXT: br i1 [[EC_3]], label %[[EXIT:.*]], label %[[LOOP]]
; APPLE: [[EXIT]]:
-; APPLE-NEXT: [[BIN_RDX2:%.*]] = phi i32 [ [[RDX_NEXT]], %[[LOOP]] ]
+; APPLE-NEXT: [[RES:%.*]] = phi i32 [ [[RDX_NEXT_3]], %[[LOOP]] ]
+; APPLE-NEXT: [[BIN_RDX:%.*]] = add i32 [[RDX_NEXT_1]], [[RDX_NEXT]]
+; APPLE-NEXT: [[BIN_RDX1:%.*]] = add i32 [[RDX_NEXT_2]], [[BIN_RDX]]
+; APPLE-NEXT: [[BIN_RDX2:%.*]] = add i32 [[RDX_NEXT_3]], [[BIN_RDX1]]
; APPLE-NEXT: ret i32 [[BIN_RDX2]]
;
; OTHER-LABEL: define i32 @test_add_reduction_unroll_partial(
@@ -603,27 +621,33 @@ define i32 @test_add_reduction_unroll_partial(ptr %a, i64 noundef %n) {
; OTHER-NEXT: br label %[[LOOP:.*]]
; OTHER: [[LOOP]]:
; OTHER-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT_3:%.*]], %[[LOOP]] ]
-; OTHER-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_3:%.*]], %[[LOOP]] ]
+; OTHER-NEXT: [[RDX_1:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_1:%.*]], %[[LOOP]] ]
+; OTHER-NEXT: [[RDX_2:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_2:%.*]], %[[LOOP]] ]
+; OTHER-NEXT: [[RDX_3:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_3:%.*]], %[[LOOP]] ]
+; OTHER-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT:%.*]], %[[LOOP]] ]
; OTHER-NEXT: [[GEP_A:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV]]
; OTHER-NEXT: [[TMP0:%.*]] = load i32, ptr [[GEP_A]], align 2
-; OTHER-NEXT: [[RDX_NEXT:%.*]] = add nuw nsw i32 [[RDX]], [[TMP0]]
+; OTHER-NEXT: [[RDX_NEXT]] = add i32 [[RDX]], [[TMP0]]
; OTHER-NEXT: [[IV_NEXT:%.*]] = add nuw nsw i64 [[IV]], 1
; OTHER-NEXT: [[GEP_A_1:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT]]
; OTHER-NEXT: [[TMP1:%.*]] = load i32, ptr [[GEP_A_1]], align 2
-; OTHER-NEXT: [[RDX_2:%.*]] = add nuw nsw i32 [[RDX_NEXT]], [[TMP1]]
+; OTHER-NEXT: [[RDX_NEXT_1]] = add i32 [[RDX_1]], [[TMP1]]
; OTHER-NEXT: [[IV_NEXT_1:%.*]] = add nuw nsw i64 [[IV]], 2
; OTHER-NEXT: [[GEP_A_2:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT_1]]
; OTHER-NEXT: [[TMP2:%.*]] = load i32, ptr [[GEP_A_2]], align 2
-; OTHER-NEXT: [[RDX_NEXT_2:%.*]] = add nuw nsw i32 [[RDX_2]], [[TMP2]]
+; OTHER-NEXT: [[RDX_NEXT_2]] = add i32 [[RDX_2]], [[TMP2]]
; OTHER-NEXT: [[IV_NEXT_2:%.*]] = add nuw nsw i64 [[IV]], 3
; OTHER-NEXT: [[GEP_A_3:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT_2]]
; OTHER-NEXT: [[TMP3:%.*]] = load i32, ptr [[GEP_A_3]], align 2
-; OTHER-NEXT: [[RDX_NEXT_3]] = add nuw nsw i32 [[RDX_NEXT_2]], [[TMP3]]
+; OTHER-NEXT: [[RDX_NEXT_3]] = add i32 [[RDX_3]], [[TMP3]]
; OTHER-NEXT: [[IV_NEXT_3]] = add nuw nsw i64 [[IV]], 4
; OTHER-NEXT: [[EC_3:%.*]] = icmp eq i64 [[IV_NEXT_3]], 1024
; OTHER-NEXT: br i1 [[EC_3]], label %[[EXIT:.*]], label %[[LOOP]]
; OTHER: [[EXIT]]:
-; OTHER-NEXT: [[BIN_RDX2:%.*]] = phi i32 [ [[RDX_NEXT_3]], %[[LOOP]] ]
+; OTHER-NEXT: [[RES:%.*]] = phi i32 [ [[RDX_NEXT_3]], %[[LOOP]] ]
+; OTHER-NEXT: [[BIN_RDX:%.*]] = add i32 [[RDX_NEXT_1]], [[RDX_NEXT]]
+; OTHER-NEXT: [[BIN_RDX1:%.*]] = add i32 [[RDX_NEXT_2]], [[BIN_RDX]]
+; OTHER-NEXT: [[BIN_RDX2:%.*]] = add i32 [[RDX_NEXT_3]], [[BIN_RDX1]]
; OTHER-NEXT: ret i32 [[BIN_RDX2]]
;
entry:
@@ -725,21 +749,42 @@ define i32 @test_add_and_mul_reduction_unroll_partial(ptr %a, i64 noundef %n) {
; APPLE-NEXT: [[ENTRY:.*]]:
; APPLE-NEXT: br label %[[LOOP:.*]]
; APPLE: [[LOOP]]:
-; APPLE-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
-; APPLE-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT:%.*]], %[[LOOP]] ]
-; APPLE-NEXT: [[RDX_2:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_2_NEXT:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT_3:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_1:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[BIN_RDX3:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_21:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_2:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_3:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_3:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RES_2:%.*]], %[[LOOP]] ]
+; APPLE-NEXT: [[RDX_2:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_2_NEXT_3:%.*]], %[[LOOP]] ]
; APPLE-NEXT: [[GEP_A:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV]]
; APPLE-NEXT: [[TMP0:%.*]] = load i32, ptr [[GEP_A]], align 2
-; APPLE-NEXT: [[RDX_NEXT]] = add nuw nsw i32 [[RDX]], [[TMP0]]
-; APPLE-NEXT: [[RDX_2_NEXT]] = mul i32 [[RDX_2]], [[TMP0]]
-; APPLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; APPLE-NEXT: [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
-; APPLE-NEXT: br i1 [[EC]], label %[[EXIT:.*]], label %[[LOOP]]
+; APPLE-NEXT: [[RES_2]] = add i32 [[RDX]], [[TMP0]]
+; APPLE-NEXT: [[RDX_2_NEXT:%.*]] = mul i32 [[RDX_2]], [[TMP0]]
+; APPLE-NEXT: [[IV_NEXT:%.*]] = add nuw nsw i64 [[IV]], 1
+; APPLE-NEXT: [[GEP_A_1:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT]]
+; APPLE-NEXT: [[TMP1:%.*]] = load i32, ptr [[GEP_A_1]], align 2
+; APPLE-NEXT: [[BIN_RDX3]] = add i32 [[RDX_1]], [[TMP1]]
+; APPLE-NEXT: [[RDX_2_NEXT_1:%.*]] = mul i32 [[RDX_2_NEXT]], [[TMP1]]
+; APPLE-NEXT: [[IV_NEXT_1:%.*]] = add nuw nsw i64 [[IV]], 2
+; APPLE-NEXT: [[GEP_A_2:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT_1]]
+; APPLE-NEXT: [[TMP2:%.*]] = load i32, ptr [[GEP_A_2]], align 2
+; APPLE-NEXT: [[RDX_NEXT_2]] = add i32 [[RDX_21]], [[TMP2]]
+; APPLE-NEXT: [[RDX_2_NEXT_2:%.*]] = mul i32 [[RDX_2_NEXT_1]], [[TMP2]]
+; APPLE-NEXT: [[IV_NEXT_2:%.*]] = add nuw nsw i64 [[IV]], 3
+; APPLE-NEXT: [[GEP_A_3:%.*]] = getelementptr inbounds nuw i32, ptr [[A]], i64 [[IV_NEXT_2]]
+; APPLE-NEXT: [[TMP3:%.*]] = load i32, ptr [[GEP_A_3]], align 2
+; APPLE-NEXT: [[RDX_NEXT_3]] = add i32 [[RDX_3]], [[TMP3]]
+; APPLE-NEXT: [[RDX_2_NEXT_3]] = mul i32 [[RDX_2_NEXT_2]], [[TMP3]]
+; APPLE-NEXT: [[IV_NEXT_3]] = add nuw nsw i64 [[IV]], 4
+; APPLE-NEXT: [[EC_3:%.*]] = icmp eq i64 [[IV_NEXT_3]], 1024
+; APPLE-NEXT: br i1 [[EC_3]], label %[[EXIT:.*]], label %[[LOOP]]
; APPLE: [[EXIT]]:
-; APPLE-NEXT: [[BIN_RDX3:%.*]] = phi i32 [ [[RDX_NEXT]], %[[LOOP]] ]
-; APPLE-NEXT: [[RES_2:%.*]] = phi i32 [ [[RDX_2_NEXT]], %[[LOOP]] ]
+; APPLE-NEXT: [[RES_1:%.*]] = phi i32 [ [[RDX_NEXT_3]], %[[LOOP]] ]
+; APPLE-NEXT: [[RES_3:%.*]] = phi i32 [ [[RDX_2_NEXT_3]], %[[LOOP]] ]
; APPLE-NEXT: [[SUM:%.*]] = add i32 [[BIN_RDX3]], [[RES_2]]
-; APPLE-NEXT: ret i32 [[SUM]]
+; APPLE-NEXT: [[BIN_RDX2:%.*]] = add i32 [[RDX_NEXT_2]], [[SUM]]
+; APPLE-NEXT: [[BIN_RDX4:%.*]] = add i32 [[RDX_NEXT_3]], [[BIN_RDX2]]
+; APPLE-NEXT: [[SUM1:%.*]] = add i32 [[BIN_RDX4]], [[RES_3]]
+; APPLE-NEXT: ret i32 [[SUM1]]
;
; OTHER-LABEL: define i32 @test_add_and_mul_reduction_unroll_partial(
; OTHER-SAME: ptr [[A:%.*]], i64 noundef [[N:%.*]]) #[[ATTR0]] {
@@ -747,23 +792,25 @@ define i32 @test_add_and_mul_reduction_unroll_partial(ptr %a, i64 noundef %n) {
; OTHER-NEXT: br label %[[LOOP:.*]]
; OTHER: [[LOOP]]:
; OTHER-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT_1:%.*]], %[[LOOP]] ]
-; OTHER-NEXT: [[RDX:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_1:%.*]], %[[LOOP]] ]
+; OTHER-NEXT: [[RDX_1:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[RDX_NEXT_1:%.*]], %[[LOOP]] ]
+; OTHER-NEX...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/149699
More information about the llvm-commits
mailing list