[llvm] [VPlan] Sink vector loop region recipes in licm (PR #172343)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 15 10:06:45 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Luke Lau (lukel97)
<details>
<summary>Changes</summary>
If a recipe in the vector loop region doesn't have any users inside the region, it can be sunk to the nearest common denominator of its users.
This gives slightly more accurate cost modelling, and on RISC-V seems to cause some loops to be vectorized with a higher VF.
The underlying motivation for this is to simplify an upcoming patch by not worrying about having to manually sink a recipe to the middle block.
In RISCV/divrem.ll and X86/cost-conditional-branches.ll I added a store to the original loop to prevent them from being completely sunk, so it still tests the original intent.
---
Patch is 230.08 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/172343.diff
44 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp (+27)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll (+14-14)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/invariant-replicate-region.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product-neon.ll (+38-38)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product.ll (+52-52)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll (+37-25)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/pointer-induction.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/X86/cost-conditional-branches.ll (+54-260)
- (modified) llvm/test/Transforms/LoopVectorize/X86/drop-inbounds-flags-for-reverse-vector-pointer.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/X86/induction-costs.ll (+3-3)
- (modified) llvm/test/Transforms/LoopVectorize/X86/invariant-load-gather.ll (+4-4)
- (modified) llvm/test/Transforms/LoopVectorize/X86/pr141968-instsimplifyfolder.ll (+15-95)
- (modified) llvm/test/Transforms/LoopVectorize/X86/pr72969.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/X86/replicate-recipe-with-only-first-lane-used.ll (+3-3)
- (modified) llvm/test/Transforms/LoopVectorize/X86/replicating-load-store-costs.ll (+17-25)
- (modified) llvm/test/Transforms/LoopVectorize/X86/tail_loop_folding.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/first-order-recurrence-dead-instructions.ll (+6-6)
- (modified) llvm/test/Transforms/LoopVectorize/first-order-recurrence-scalable-vf1.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/first-order-recurrence-sink-replicate-region.ll (+3-3)
- (modified) llvm/test/Transforms/LoopVectorize/first-order-recurrence-with-uniform-ops.ll (+9-9)
- (modified) llvm/test/Transforms/LoopVectorize/first-order-recurrence.ll (+37-41)
- (modified) llvm/test/Transforms/LoopVectorize/instruction-only-used-outside-of-loop.ll (+5-5)
- (modified) llvm/test/Transforms/LoopVectorize/iv-select-cmp-decreasing.ll (+8-8)
- (modified) llvm/test/Transforms/LoopVectorize/iv_outside_user.ll (+17-19)
- (modified) llvm/test/Transforms/LoopVectorize/lcssa-crashes.ll (+8-8)
- (modified) llvm/test/Transforms/LoopVectorize/no_outside_user.ll (+45-45)
- (modified) llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-liveout.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/optsize.ll (+6-6)
- (modified) llvm/test/Transforms/LoopVectorize/pointer-induction.ll (+6-6)
- (modified) llvm/test/Transforms/LoopVectorize/pr36983-multiple-lcssa.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/pr43166-fold-tail-by-masking.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/pr51614-fold-tail-by-masking.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/pr55167-fold-tail-live-out.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/pr66616.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/reduction-minmax-users-and-predicated.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/reduction-order.ll (+6-6)
- (modified) llvm/test/Transforms/LoopVectorize/reduction-small-size.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/select-reduction.ll (+5-5)
- (modified) llvm/test/Transforms/LoopVectorize/store-reduction-results-in-tail-folded-loop.ll (+5-5)
- (modified) llvm/test/Transforms/LoopVectorize/tail-folding-vectorization-factor-1.ll (+4-4)
- (modified) llvm/test/Transforms/LoopVectorize/vplan-printing-reductions.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/vplan-printing.ll (+1-1)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 6627133878fdb..c757ba4aede5f 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -2467,6 +2467,33 @@ static void licm(VPlan &Plan) {
R.moveBefore(*Preheader, Preheader->end());
}
}
+
+ // Sink any recipes which don't have any users in the region to the nearest
+ // common dominator of its users.
+ VPDominatorTree VPDT(Plan);
+ for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
+ vp_post_order_shallow(LoopRegion->getEntry()))) {
+ for (VPRecipeBase &R : make_early_inc_range(reverse(*VPBB))) {
+ if (cannotHoistOrSinkRecipe(R))
+ continue;
+ SmallSetVector<VPRecipeBase *, 4> Users;
+ if (any_of(R.definedValues(), [&Users](VPValue *V) {
+ return any_of(V->users(), [&Users](VPUser *U) {
+ auto *UR = cast<VPRecipeBase>(U);
+ Users.insert(UR);
+ return UR->getParent()->getEnclosingLoopRegion();
+ });
+ }))
+ continue;
+ if (Users.empty())
+ continue;
+ VPBasicBlock *SinkVPBB = Users.front()->getParent();
+ for (auto *User : drop_begin(Users))
+ SinkVPBB = cast<VPBasicBlock>(
+ VPDT.findNearestCommonDominator(SinkVPBB, User->getParent()));
+ R.moveBefore(*SinkVPBB, SinkVPBB->begin());
+ }
+ }
}
void VPlanTransforms::truncateToMinimalBitwidths(
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll
index 40db6a53b49e4..46bb50dfd9799 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll
@@ -94,10 +94,10 @@ define i64 @pointer_induction_only(ptr %start, ptr %end) {
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 [[END1]], [[START2]]
; CHECK-NEXT: [[TMP1:%.*]] = lshr i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 8
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 16
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
-; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 4
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 8
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[N_VEC]], 4
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 [[TMP3]]
@@ -106,15 +106,15 @@ define i64 @pointer_induction_only(ptr %start, ptr %end) {
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 4
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[OFFSET_IDX]]
-; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i32, ptr [[NEXT_GEP]], i64 2
-; CHECK-NEXT: [[WIDE_LOAD4:%.*]] = load <2 x i32>, ptr [[TMP7]], align 1
-; CHECK-NEXT: [[TMP9:%.*]] = zext <2 x i32> [[WIDE_LOAD4]] to <2 x i64>
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; CHECK-NEXT: [[TMP5:%.*]] = getelementptr i32, ptr [[NEXT_GEP]], i64 4
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP5]], align 1
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
-; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <2 x i64> [[TMP9]], i32 1
-; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <2 x i64> [[TMP9]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = zext <4 x i32> [[WIDE_LOAD]] to <4 x i64>
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i64> [[TMP7]], i32 3
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i64> [[TMP7]], i32 2
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
@@ -163,11 +163,11 @@ define i64 @int_and_pointer_iv(ptr %start, i32 %N) {
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i32, ptr [[NEXT_GEP]], i64 4
; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x i32>, ptr [[TMP3]], align 4
-; CHECK-NEXT: [[TMP5:%.*]] = zext <4 x i32> [[WIDE_LOAD3]] to <4 x i64>
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1000
; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: middle.block:
+; CHECK-NEXT: [[TMP5:%.*]] = zext <4 x i32> [[WIDE_LOAD3]] to <4 x i64>
; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i64> [[TMP5]], i32 2
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: exit:
@@ -271,7 +271,7 @@ define i64 @test_ptr_ivs_and_widened_ivs(ptr %src, i32 %N) {
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[N]], -1
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 8
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 16
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 8
@@ -289,15 +289,15 @@ define i64 @test_ptr_ivs_and_widened_ivs(ptr %src, i32 %N) {
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i32, ptr [[NEXT_GEP]], i64 4
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP6]], align 4
-; CHECK-NEXT: [[TMP7:%.*]] = xor <4 x i32> [[WIDE_LOAD]], splat (i32 1)
-; CHECK-NEXT: [[TMP8:%.*]] = zext <4 x i32> [[TMP7]] to <4 x i64>
-; CHECK-NEXT: [[TMP9:%.*]] = zext <4 x i32> [[STEP_ADD]] to <4 x i64>
-; CHECK-NEXT: [[TMP10:%.*]] = shl <4 x i64> [[TMP8]], [[TMP9]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD]], splat (i32 4)
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: middle.block:
+; CHECK-NEXT: [[TMP9:%.*]] = xor <4 x i32> [[WIDE_LOAD]], splat (i32 1)
+; CHECK-NEXT: [[TMP12:%.*]] = zext <4 x i32> [[TMP9]] to <4 x i64>
+; CHECK-NEXT: [[TMP13:%.*]] = zext <4 x i32> [[STEP_ADD]] to <4 x i64>
+; CHECK-NEXT: [[TMP10:%.*]] = shl <4 x i64> [[TMP12]], [[TMP13]]
; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i64> [[TMP10]], i32 3
; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i64> [[TMP10]], i32 2
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/invariant-replicate-region.ll b/llvm/test/Transforms/LoopVectorize/AArch64/invariant-replicate-region.ll
index 9dfb987bd24a6..3951b88e41d55 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/invariant-replicate-region.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/invariant-replicate-region.ll
@@ -42,11 +42,11 @@ define i32 @test_invariant_replicate_region(i32 %x, i1 %c) {
; CHECK-NEXT: br label %[[PRED_UREM_CONTINUE6]]
; CHECK: [[PRED_UREM_CONTINUE6]]:
; CHECK-NEXT: [[TMP12:%.*]] = phi <4 x i32> [ [[TMP11]], %[[PRED_UREM_CONTINUE4]] ], [ [[TMP14]], %[[PRED_UREM_IF5]] ]
-; CHECK-NEXT: [[PREDPHI:%.*]] = select i1 [[C]], <4 x i32> [[TMP12]], <4 x i32> zeroinitializer
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP16:%.*]] = icmp eq i32 [[INDEX_NEXT]], 100
; CHECK-NEXT: br i1 [[TMP16]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[PREDPHI:%.*]] = select i1 [[C]], <4 x i32> [[TMP12]], <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP17:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 3
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product-neon.ll b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product-neon.ll
index b2be0e1d7a442..e80449432d29b 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product-neon.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product-neon.ll
@@ -493,12 +493,12 @@ define i32 @not_dotp_not_loop_carried(ptr %a, ptr %b) {
; CHECK-INTERLEAVE1-NEXT: [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP4]], align 1
; CHECK-INTERLEAVE1-NEXT: [[TMP6:%.*]] = zext <16 x i8> [[WIDE_LOAD1]] to <16 x i32>
; CHECK-INTERLEAVE1-NEXT: [[TMP7]] = mul <16 x i32> [[TMP6]], [[TMP3]]
-; CHECK-INTERLEAVE1-NEXT: [[TMP8:%.*]] = shufflevector <16 x i32> [[VECTOR_RECUR]], <16 x i32> [[TMP7]], <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
-; CHECK-INTERLEAVE1-NEXT: [[TMP9:%.*]] = add <16 x i32> [[TMP7]], [[TMP8]]
; CHECK-INTERLEAVE1-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-INTERLEAVE1-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; CHECK-INTERLEAVE1-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK-INTERLEAVE1: middle.block:
+; CHECK-INTERLEAVE1-NEXT: [[TMP8:%.*]] = shufflevector <16 x i32> [[VECTOR_RECUR]], <16 x i32> [[TMP7]], <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
+; CHECK-INTERLEAVE1-NEXT: [[TMP9:%.*]] = add <16 x i32> [[TMP7]], [[TMP8]]
; CHECK-INTERLEAVE1-NEXT: [[TMP11:%.*]] = extractelement <16 x i32> [[TMP9]], i32 15
; CHECK-INTERLEAVE1-NEXT: br label [[FOR_EXIT:%.*]]
; CHECK-INTERLEAVE1: for.exit:
@@ -526,12 +526,12 @@ define i32 @not_dotp_not_loop_carried(ptr %a, ptr %b) {
; CHECK-INTERLEAVED-NEXT: [[TMP12:%.*]] = zext <16 x i8> [[WIDE_LOAD3]] to <16 x i32>
; CHECK-INTERLEAVED-NEXT: [[TMP7:%.*]] = mul <16 x i32> [[TMP6]], [[TMP3]]
; CHECK-INTERLEAVED-NEXT: [[TMP13:%.*]] = mul <16 x i32> [[TMP12]], [[TMP8]]
-; CHECK-INTERLEAVED-NEXT: [[TMP14:%.*]] = shufflevector <16 x i32> [[TMP7]], <16 x i32> [[TMP13]], <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
-; CHECK-INTERLEAVED-NEXT: [[TMP9:%.*]] = add <16 x i32> [[TMP13]], [[TMP14]]
; CHECK-INTERLEAVED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
; CHECK-INTERLEAVED-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; CHECK-INTERLEAVED-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK-INTERLEAVED: middle.block:
+; CHECK-INTERLEAVED-NEXT: [[TMP14:%.*]] = shufflevector <16 x i32> [[TMP7]], <16 x i32> [[TMP13]], <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
+; CHECK-INTERLEAVED-NEXT: [[TMP9:%.*]] = add <16 x i32> [[TMP13]], [[TMP14]]
; CHECK-INTERLEAVED-NEXT: [[TMP11:%.*]] = extractelement <16 x i32> [[TMP9]], i32 15
; CHECK-INTERLEAVED-NEXT: br label [[FOR_EXIT:%.*]]
; CHECK-INTERLEAVED: for.exit:
@@ -553,12 +553,12 @@ define i32 @not_dotp_not_loop_carried(ptr %a, ptr %b) {
; CHECK-MAXBW-NEXT: [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP4]], align 1
; CHECK-MAXBW-NEXT: [[TMP6:%.*]] = zext <16 x i8> [[WIDE_LOAD1]] to <16 x i32>
; CHECK-MAXBW-NEXT: [[TMP7]] = mul <16 x i32> [[TMP6]], [[TMP3]]
-; CHECK-MAXBW-NEXT: [[TMP8:%.*]] = shufflevector <16 x i32> [[VECTOR_RECUR]], <16 x i32> [[TMP7]], <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
-; CHECK-MAXBW-NEXT: [[TMP9:%.*]] = add <16 x i32> [[TMP7]], [[TMP8]]
; CHECK-MAXBW-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-MAXBW-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; CHECK-MAXBW-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK-MAXBW: middle.block:
+; CHECK-MAXBW-NEXT: [[TMP8:%.*]] = shufflevector <16 x i32> [[VECTOR_RECUR]], <16 x i32> [[TMP7]], <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
+; CHECK-MAXBW-NEXT: [[TMP9:%.*]] = add <16 x i32> [[TMP7]], [[TMP8]]
; CHECK-MAXBW-NEXT: [[TMP11:%.*]] = extractelement <16 x i32> [[TMP9]], i32 15
; CHECK-MAXBW-NEXT: br label [[FOR_EXIT:%.*]]
; CHECK-MAXBW: for.exit:
@@ -1894,7 +1894,7 @@ define i32 @dotp_ext_mul(i64 %n, ptr %a, i8 %b) {
; CHECK-INTERLEAVE1-SAME: i64 [[N:%.*]], ptr [[A:%.*]], i8 [[B:%.*]]) #[[ATTR0]] {
; CHECK-INTERLEAVE1-NEXT: entry:
; CHECK-INTERLEAVE1-NEXT: [[TMP0:%.*]] = add i64 [[N]], 1
-; CHECK-INTERLEAVE1-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 8
+; CHECK-INTERLEAVE1-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 16
; CHECK-INTERLEAVE1-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-INTERLEAVE1: vector.ph:
; CHECK-INTERLEAVE1-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 8
@@ -1911,12 +1911,12 @@ define i32 @dotp_ext_mul(i64 %n, ptr %a, i8 %b) {
; CHECK-INTERLEAVE1-NEXT: [[TMP2:%.*]] = zext <8 x i8> [[BROADCAST_SPLAT]] to <8 x i32>
; CHECK-INTERLEAVE1-NEXT: [[TMP3:%.*]] = mul <8 x i32> [[TMP2]], [[TMP2]]
; CHECK-INTERLEAVE1-NEXT: [[PARTIAL_REDUCE]] = call <2 x i32> @llvm.vector.partial.reduce.add.v2i32.v8i32(<2 x i32> [[VEC_PHI]], <8 x i32> [[TMP3]])
-; CHECK-INTERLEAVE1-NEXT: [[TMP4:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
-; CHECK-INTERLEAVE1-NEXT: [[TMP5:%.*]] = sext <8 x i32> [[TMP4]] to <8 x i64>
; CHECK-INTERLEAVE1-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-INTERLEAVE1-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-INTERLEAVE1-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK-INTERLEAVE1: middle.block:
+; CHECK-INTERLEAVE1-NEXT: [[TMP8:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
+; CHECK-INTERLEAVE1-NEXT: [[TMP5:%.*]] = sext <8 x i32> [[TMP8]] to <8 x i64>
; CHECK-INTERLEAVE1-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[PARTIAL_REDUCE]])
; CHECK-INTERLEAVE1-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <8 x i64> [[TMP5]], i32 7
; CHECK-INTERLEAVE1-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
@@ -1946,12 +1946,12 @@ define i32 @dotp_ext_mul(i64 %n, ptr %a, i8 %b) {
; CHECK-INTERLEAVED-NEXT: [[TMP3:%.*]] = mul <8 x i32> [[TMP2]], [[TMP2]]
; CHECK-INTERLEAVED-NEXT: [[PARTIAL_REDUCE]] = call <2 x i32> @llvm.vector.partial.reduce.add.v2i32.v8i32(<2 x i32> [[VEC_PHI]], <8 x i32> [[TMP3]])
; CHECK-INTERLEAVED-NEXT: [[PARTIAL_REDUCE2]] = call <2 x i32> @llvm.vector.partial.reduce.add.v2i32.v8i32(<2 x i32> [[VEC_PHI1]], <8 x i32> [[TMP3]])
-; CHECK-INTERLEAVED-NEXT: [[TMP4:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT4]] to <8 x i32>
-; CHECK-INTERLEAVED-NEXT: [[TMP5:%.*]] = sext <8 x i32> [[TMP4]] to <8 x i64>
; CHECK-INTERLEAVED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-INTERLEAVED-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-INTERLEAVED-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK-INTERLEAVED: middle.block:
+; CHECK-INTERLEAVED-NEXT: [[TMP8:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT4]] to <8 x i32>
+; CHECK-INTERLEAVED-NEXT: [[TMP5:%.*]] = sext <8 x i32> [[TMP8]] to <8 x i64>
; CHECK-INTERLEAVED-NEXT: [[BIN_RDX:%.*]] = add <2 x i32> [[PARTIAL_REDUCE2]], [[PARTIAL_REDUCE]]
; CHECK-INTERLEAVED-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[BIN_RDX]])
; CHECK-INTERLEAVED-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <8 x i64> [[TMP5]], i32 7
@@ -1963,7 +1963,7 @@ define i32 @dotp_ext_mul(i64 %n, ptr %a, i8 %b) {
; CHECK-MAXBW-SAME: i64 [[N:%.*]], ptr [[A:%.*]], i8 [[B:%.*]]) #[[ATTR0]] {
; CHECK-MAXBW-NEXT: entry:
; CHECK-MAXBW-NEXT: [[TMP0:%.*]] = add i64 [[N]], 1
-; CHECK-MAXBW-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 8
+; CHECK-MAXBW-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 16
; CHECK-MAXBW-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-MAXBW: vector.ph:
; CHECK-MAXBW-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 8
@@ -1980,12 +1980,12 @@ define i32 @dotp_ext_mul(i64 %n, ptr %a, i8 %b) {
; CHECK-MAXBW-NEXT: [[TMP2:%.*]] = zext <8 x i8> [[BROADCAST_SPLAT]] to <8 x i32>
; CHECK-MAXBW-NEXT: [[TMP3:%.*]] = mul <8 x i32> [[TMP2]], [[TMP2]]
; CHECK-MAXBW-NEXT: [[PARTIAL_REDUCE]] = call <2 x i32> @llvm.vector.partial.reduce.add.v2i32.v8i32(<2 x i32> [[VEC_PHI]], <8 x i32> [[TMP3]])
-; CHECK-MAXBW-NEXT: [[TMP4:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
-; CHECK-MAXBW-NEXT: [[TMP5:%.*]] = sext <8 x i32> [[TMP4]] to <8 x i64>
; CHECK-MAXBW-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-MAXBW-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-MAXBW-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK-MAXBW: middle.block:
+; CHECK-MAXBW-NEXT: [[TMP8:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
+; CHECK-MAXBW-NEXT: [[TMP5:%.*]] = sext <8 x i32> [[TMP8]] to <8 x i64>
; CHECK-MAXBW-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[PARTIAL_REDUCE]])
; CHECK-MAXBW-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <8 x i64> [[TMP5]], i32 7
; CHECK-MAXBW-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
@@ -2019,7 +2019,7 @@ define i64 @not_dotp_ext_mul_8to64(i64 %n, ptr %a, i8 %b) {
; CHECK-INTERLEAVE1-SAME: i64 [[N:%.*]], ptr [[A:%.*]], i8 [[B:%.*]]) #[[ATTR0]] {
; CHECK-INTERLEAVE1-NEXT: entry:
; CHECK-INTERLEAVE1-NEXT: [[TMP0:%.*]] = add i64 [[N]], 1
-; CHECK-INTERLEAVE1-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 8
+; CHECK-INTERLEAVE1-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 16
; CHECK-INTERLEAVE1-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-INTERLEAVE1: vector.ph:
; CHECK-INTERLEAVE1-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 8
@@ -2037,12 +2037,12 @@ define i64 @not_dotp_ext_mul_8to64(i64 %n, ptr %a, i8 %b) {
; CHECK-INTERLEAVE1-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <8 x i16> poison, i16 [[TMP4]], i64 0
; CHECK-INTERLEAVE1-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <8 x i16> [[BROADCAST_SPLATINSERT1]], <8 x i16> poison, <8 x i32> zeroinitializer
; CHECK-INTERLEAVE1-NEXT: [[TMP5]] = add <8 x i64> [[VEC_PHI]], [[TMP3]]
-; CHECK-INTERLEAVE1-NEXT: [[TMP6:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
-; CHECK-INTERLEAVE1-NEXT: [[TMP7:%.*]] = sext <8 x i32> [[TMP6]] to <8 x i64>
; CHECK-INTERLEAVE1-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-INTERLEAVE1-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-INTERLEAVE1-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK-INTERLEAVE1: middle.block:
+; CHECK-INTERLEAVE1-NEXT: [[TMP10:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
+; CHECK-INTERLEAVE1-NEXT: [[TMP7:%.*]] = sext <8 x i32> [[TMP10]] to <8 x i64>
; CHECK-INTERLEAVE1-NEXT: [[TMP9:...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/172343
More information about the llvm-commits
mailing list