[VPlan] Narrow VPWidenCastRecipe to scalar cast recipe. #166514
+165
−98
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-vectorizers @llvm/pr-subscribers-backend-risc-v Author: Mel Chen (Mel-Chen) ChangesThis patch narrows uniform VPWidenCastRecipe into scalar cast recipes. Since cast operations involve type conversions, directly cloning them would produce an incorrect destination type. Therefore, we emit scalar cast recipes instead of using VPReplicateRecipe. Based on #143552 Patch is 30.05 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/166514.diff 8 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 9d9bb14530539..2740fcd1a21fc 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1386,7 +1386,8 @@ static void narrowToSingleScalarRecipes(VPlan &Plan) {
for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
vp_depth_first_shallow(Plan.getVectorLoopRegion()->getEntry()))) {
for (VPRecipeBase &R : make_early_inc_range(reverse(*VPBB))) {
- if (!isa<VPWidenRecipe, VPWidenSelectRecipe, VPReplicateRecipe>(&R))
+ if (!isa<VPWidenRecipe, VPWidenCastRecipe, VPWidenSelectRecipe,
+ VPReplicateRecipe>(&R))
continue;
auto *RepR = dyn_cast<VPReplicateRecipe>(&R);
if (RepR && (RepR->isSingleScalar() || RepR->isPredicated()))
@@ -1422,6 +1423,15 @@ static void narrowToSingleScalarRecipes(VPlan &Plan) {
}))
continue;
+ if (auto *CastR = dyn_cast<VPWidenCastRecipe>(RepOrWidenR)) {
+ VPBuilder Builder(CastR);
+ auto *Clone = Builder.createScalarCast(
+ CastR->getOpcode(), CastR->getOperand(0), CastR->getResultType(),
+ CastR->getDebugLoc());
+ CastR->replaceAllUsesWith(Clone);
+ CastR->eraseFromParent();
+ continue;
+ }
auto *Clone = new VPReplicateRecipe(RepOrWidenR->getUnderlyingInstr(),
RepOrWidenR->operands(),
true /*IsSingleScalar*/);
diff --git a/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp b/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
index c6380d30ab2e2..6dd4e5ac697c1 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
@@ -171,6 +171,10 @@ bool vputils::isSingleScalar(const VPValue *VPV) {
return PreservesUniformity(WidenR->getOpcode()) &&
all_of(WidenR->operands(), isSingleScalar);
}
+ if (auto *CastR = dyn_cast<VPWidenCastRecipe>(VPV)) {
+ return PreservesUniformity(CastR->getOpcode()) &&
+ all_of(CastR->operands(), isSingleScalar);
+ }
if (auto *VPI = dyn_cast<VPInstruction>(VPV))
return VPI->isSingleScalar() || VPI->isVectorToScalar() ||
(PreservesUniformity(VPI->getOpcode()) &&
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
index b430efc9e5283..a5f7764898055 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
@@ -492,18 +492,18 @@ define i64 @partial_reduction_mul_two_users(i64 %n, ptr %a, i16 %b, i32 %c) {
; CHECK-NEXT: [[TMP3:%.*]] = zext <8 x i32> [[TMP2]] to <8 x i64>
; CHECK-NEXT: [[PARTIAL_REDUCE]] = call <4 x i64> @llvm.vector.partial.reduce.add.v4i64.v8i64(<4 x i64> [[VEC_PHI]], <8 x i64> [[TMP3]])
; CHECK-NEXT: [[TMP5:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
-; CHECK-NEXT: [[TMP6:%.*]] = sext <8 x i32> [[TMP5]] to <8 x i64>
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <8 x i32> [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP9:%.*]] = sext i32 [[TMP6]] to i64
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP8:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[PARTIAL_REDUCE]])
-; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <8 x i64> [[TMP6]], i32 7
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
-; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[VECTOR_RECUR_EXTRACT]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[TMP9]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP8]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
@@ -520,7 +520,7 @@ define i64 @partial_reduction_mul_two_users(i64 %n, ptr %a, i16 %b, i32 %c) {
; CHECK-NEXT: [[LOAD_EXT:%.*]] = sext i16 [[LOAD]] to i32
; CHECK-NEXT: [[LOAD_EXT_EXT]] = sext i32 [[LOAD_EXT]] to i64
; CHECK-NEXT: [[EXITCOND740_NOT:%.*]] = icmp eq i64 [[IV]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND740_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP19:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND740_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi i64 [ [[ADD]], %[[LOOP]] ], [ [[TMP8]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i64 [[ADD_LCSSA]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll
index 1dcd665817196..4642144f8d6d4 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll
@@ -66,63 +66,150 @@ define void @test_predicated_load_cast_hint(ptr %dst.1, ptr %dst.2, ptr %src, i8
; CHECK-NEXT: [[CONFLICT_RDX15:%.*]] = or i1 [[CONFLICT_RDX]], [[FOUND_CONFLICT14]]
; CHECK-NEXT: br i1 [[CONFLICT_RDX15]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 0, i32 [[TMP2]])
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 0, i32 [[TMP2]])
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
-; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE22:.*]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], %[[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %[[PRED_STORE_CONTINUE22]] ]
-; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 4, i8 8, i8 12>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[PRED_STORE_CONTINUE22]] ]
-; CHECK-NEXT: [[TMP28:%.*]] = load i8, ptr [[SRC]], align 1, !alias.scope [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[TMP28]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP25:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT]] to <4 x i64>
-; CHECK-NEXT: [[TMP26:%.*]] = zext <4 x i8> [[VEC_IND]] to <4 x i64>
-; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 0
-; CHECK-NEXT: br i1 [[TMP27]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE46:.*]] ]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <16 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], %[[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %[[PRED_STORE_CONTINUE46]] ]
+; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i8> [ <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 32, i8 36, i8 40, i8 44, i8 48, i8 52, i8 56, i8 60>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[PRED_STORE_CONTINUE46]] ]
+; CHECK-NEXT: [[TMP25:%.*]] = load i8, ptr [[SRC]], align 1, !alias.scope [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
+; CHECK-NEXT: [[TMP29:%.*]] = zext i8 [[TMP25]] to i64
+; CHECK-NEXT: [[TMP30:%.*]] = or i64 [[TMP29]], 1
+; CHECK-NEXT: [[TMP27:%.*]] = zext <16 x i8> [[VEC_IND]] to <16 x i64>
+; CHECK-NEXT: [[TMP28:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 0
+; CHECK-NEXT: br i1 [[TMP28]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
; CHECK: [[PRED_STORE_IF]]:
-; CHECK-NEXT: [[TMP102:%.*]] = extractelement <4 x i64> [[TMP26]], i32 0
+; CHECK-NEXT: [[TMP102:%.*]] = extractelement <16 x i64> [[TMP27]], i32 0
; CHECK-NEXT: [[TMP103:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP102]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP104:%.*]] = extractelement <4 x i64> [[TMP25]], i32 0
-; CHECK-NEXT: [[TMP105:%.*]] = or i64 [[TMP104]], 1
-; CHECK-NEXT: store i64 [[TMP105]], ptr [[TMP103]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP103]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE]]
; CHECK: [[PRED_STORE_CONTINUE]]:
-; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 1
-; CHECK-NEXT: br i1 [[TMP32]], label %[[PRED_STORE_IF17:.*]], label %[[PRED_STORE_CONTINUE18:.*]]
+; CHECK-NEXT: [[TMP31:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 1
+; CHECK-NEXT: br i1 [[TMP31]], label %[[PRED_STORE_IF17:.*]], label %[[PRED_STORE_CONTINUE18:.*]]
; CHECK: [[PRED_STORE_IF17]]:
-; CHECK-NEXT: [[TMP108:%.*]] = extractelement <4 x i64> [[TMP26]], i32 1
+; CHECK-NEXT: [[TMP108:%.*]] = extractelement <16 x i64> [[TMP27]], i32 1
; CHECK-NEXT: [[TMP109:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP108]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP110:%.*]] = extractelement <4 x i64> [[TMP25]], i32 1
-; CHECK-NEXT: [[TMP111:%.*]] = or i64 [[TMP110]], 1
-; CHECK-NEXT: store i64 [[TMP111]], ptr [[TMP109]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP109]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE18]]
; CHECK: [[PRED_STORE_CONTINUE18]]:
-; CHECK-NEXT: [[TMP37:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 2
-; CHECK-NEXT: br i1 [[TMP37]], label %[[PRED_STORE_IF19:.*]], label %[[PRED_STORE_CONTINUE20:.*]]
+; CHECK-NEXT: [[TMP34:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 2
+; CHECK-NEXT: br i1 [[TMP34]], label %[[PRED_STORE_IF19:.*]], label %[[PRED_STORE_CONTINUE20:.*]]
; CHECK: [[PRED_STORE_IF19]]:
-; CHECK-NEXT: [[TMP114:%.*]] = extractelement <4 x i64> [[TMP26]], i32 2
+; CHECK-NEXT: [[TMP114:%.*]] = extractelement <16 x i64> [[TMP27]], i32 2
; CHECK-NEXT: [[TMP115:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP114]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP116:%.*]] = extractelement <4 x i64> [[TMP25]], i32 2
-; CHECK-NEXT: [[TMP117:%.*]] = or i64 [[TMP116]], 1
-; CHECK-NEXT: store i64 [[TMP117]], ptr [[TMP115]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP115]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE20]]
; CHECK: [[PRED_STORE_CONTINUE20]]:
-; CHECK-NEXT: [[TMP42:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 3
-; CHECK-NEXT: br i1 [[TMP42]], label %[[PRED_STORE_IF21:.*]], label %[[PRED_STORE_CONTINUE22]]
+; CHECK-NEXT: [[TMP37:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 3
+; CHECK-NEXT: br i1 [[TMP37]], label %[[PRED_STORE_IF21:.*]], label %[[PRED_STORE_CONTINUE22:.*]]
; CHECK: [[PRED_STORE_IF21]]:
-; CHECK-NEXT: [[TMP120:%.*]] = extractelement <4 x i64> [[TMP26]], i32 3
+; CHECK-NEXT: [[TMP120:%.*]] = extractelement <16 x i64> [[TMP27]], i32 3
; CHECK-NEXT: [[TMP121:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP120]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP122:%.*]] = extractelement <4 x i64> [[TMP25]], i32 3
-; CHECK-NEXT: [[TMP123:%.*]] = or i64 [[TMP122]], 1
-; CHECK-NEXT: store i64 [[TMP123]], ptr [[TMP121]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP121]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE22]]
; CHECK: [[PRED_STORE_CONTINUE22]]:
+; CHECK-NEXT: [[TMP40:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 4
+; CHECK-NEXT: br i1 [[TMP40]], label %[[PRED_STORE_IF23:.*]], label %[[PRED_STORE_CONTINUE24:.*]]
+; CHECK: [[PRED_STORE_IF23]]:
+; CHECK-NEXT: [[TMP41:%.*]] = extractelement <16 x i64> [[TMP27]], i32 4
+; CHECK-NEXT: [[TMP42:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP41]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP42]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE24]]
+; CHECK: [[PRED_STORE_CONTINUE24]]:
+; CHECK-NEXT: [[TMP43:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 5
+; CHECK-NEXT: br i1 [[TMP43]], label %[[PRED_STORE_IF25:.*]], label %[[PRED_STORE_CONTINUE26:.*]]
+; CHECK: [[PRED_STORE_IF25]]:
+; CHECK-NEXT: [[TMP44:%.*]] = extractelement <16 x i64> [[TMP27]], i32 5
+; CHECK-NEXT: [[TMP45:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP44]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP45]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE26]]
+; CHECK: [[PRED_STORE_CONTINUE26]]:
+; CHECK-NEXT: [[TMP46:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 6
+; CHECK-NEXT: br i1 [[TMP46]], label %[[PRED_STORE_IF27:.*]], label %[[PRED_STORE_CONTINUE28:.*]]
+; CHECK: [[PRED_STORE_IF27]]:
+; CHECK-NEXT: [[TMP76:%.*]] = extractelement <16 x i64> [[TMP27]], i32 6
+; CHECK-NEXT: [[TMP77:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP76]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP77]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE28]]
+; CHECK: [[PRED_STORE_CONTINUE28]]:
+; CHECK-NEXT: [[TMP49:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 7
+; CHECK-NEXT: br i1 [[TMP49]], label %[[PRED_STORE_IF29:.*]], label %[[PRED_STORE_CONTINUE30:.*]]
+; CHECK: [[PRED_STORE_IF29]]:
+; CHECK-NEXT: [[TMP50:%.*]] = extractelement <16 x i64> [[TMP27]], i32 7
+; CHECK-NEXT: [[TMP51:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP50]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP51]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE30]]
+; CHECK: [[PRED_STORE_CONTINUE30]]:
+; CHECK-NEXT: [[TMP52:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 8
+; CHECK-NEXT: br i1 [[TMP52]], label %[[PRED_STORE_IF31:.*]], label %[[PRED_STORE_CONTINUE32:.*]]
+; CHECK: [[PRED_STORE_IF31]]:
+; CHECK-NEXT: [[TMP53:%.*]] = extractelement <16 x i64> [[TMP27]], i32 8
+; CHECK-NEXT: [[TMP54:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP53]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP54]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE32]]
+; CHECK: [[PRED_STORE_CONTINUE32]]:
+; CHECK-NEXT: [[TMP55:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 9
+; CHECK-NEXT: br i1 [[TMP55]], label %[[PRED_STORE_IF33:.*]], label %[[PRED_STORE_CONTINUE34:.*]]
+; CHECK: [[PRED_STORE_IF33]]:
+; CHECK-NEXT: [[TMP56:%.*]] = extractelement <16 x i64> [[TMP27]], i32 9
+; CHECK-NEXT: [[TMP57:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP56]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP57]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE34]]
+; CHECK: [[PRED_STORE_CONTINUE34]]:
+; CHECK-NEXT: [[TMP58:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 10
+; CHECK-NEXT: br i1 [[TMP58]], label %[[PRED_STORE_IF35:.*]], label %[[PRED_STORE_CONTINUE36:.*]]
+; CHECK: [[PRED_STORE_IF35]]:
+; CHECK-NEXT: [[TMP59:%.*]] = extractelement <16 x i64> [[TMP27]], i32 10
+; CHECK-NEXT: [[TMP60:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP59]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP60]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE36]]
+; CHECK: [[PRED_STORE_CONTINUE36]]:
+; CHECK-NEXT: [[TMP61:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 11
+; CHECK-NEXT: br i1 [[TMP61]], label %[[PRED_STORE_IF37:.*]], label %[[PRED_STORE_CONTINUE38:.*]]
+; CHECK: [[PRED_STORE_IF37]]:
+; CHECK-NEXT: [[TMP62:%.*]] = extractelement <16 x i64> [[TMP27]], i32 11
+; CHECK-NEXT: [[TMP63:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP62]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP63]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE38]]
+; CHECK: [[PRED_STORE_CONTINUE38]]:
+; CHECK-NEXT: [[TMP64:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 12
+; CHECK-NEXT: br i1 [[TMP64]], label %[[PRED_STORE_IF39:.*]], label %[[PRED_STORE_CONTINUE40:.*]]
+; CHECK: [[PRED_STORE_IF39]]:
+; CHECK-NEXT: [[TMP65:%.*]] = extractelement <16 x i64> [[TMP27]], i32 12
+; CHECK-NEXT: [[TMP66:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP65]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP66]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE40]]
+; CHECK: [[PRED_STORE_CONTINUE40]]:
+; CHECK-NEXT: [[TMP67:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 13
+; CHECK-NEXT: br i1 [[TMP67]], label %[[PRED_STORE_IF41:.*]], label %[[PRED_STORE_CONTINUE42:.*]]
+; CHECK: [[PRED_STORE_IF41]]:
+; CHECK-NEXT: [[TMP68:%.*]] = extractelement <16 x i64> [[TMP27]], i32 13
+; CHECK-NEXT: [[TMP69:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP68]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP69]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE42]]
+; CHECK: [[PRED_STORE_CONTINUE42]]:
+; CHECK-NEXT: [[TMP70:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 14
+; CHECK-NEXT: br i1 [[TMP70]], label %[[PRED_STORE_IF43:.*]], label %[[PRED_STORE_CONTINUE44:.*]]
+; CHECK: [[PRED_STORE_IF43]]:
+; CHECK-NEXT: [[TMP71:%.*]] = extractelement <16 x i64> [[TMP27]], i32 14
+; CHECK-NEXT: [[TMP72:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP71]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP72]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE44]]
+; CHECK: [[PRED_STORE_CONTINUE44]]:
+; CHECK-NEXT: [[TMP73:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 15
+; CHECK-NEXT: br i1 [[TMP73]], label %[[PRED_STORE_IF45:.*]], label %[[PRED_STORE_CONTINUE46]]
+; CHECK: [[PRED_STORE_IF45]]:
+; CHECK-NEXT: [[TMP74:%.*]] = extractelement <16 x i64> [[TMP27]], i32 15
+; CHECK-NEXT: [[TMP75:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP74]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP75]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE46]]
+; CHECK: [[PRED_STORE_CONTINUE46]]:
; CHECK-NEXT: store i8 0, ptr [[DST_2]], align 1, !alias.scope [[META5:![0-9]+]], !noalias [[META7:![0-9]+]]
-; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX_NEXT]], i32 [[TMP2]])
-; CHECK-NEXT: [[TMP47:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 16
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX_NEXT]], i32 [[TMP2]])
+; CHECK-NEXT: [[TMP47:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
; CHECK-NEXT: [[TMP48:%.*]] = xor i1 [[TMP47]], true
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 16)
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i8> [[VEC_IND]], splat (i8 64)
; CHECK-NEXT: br i1 [[TMP48]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
diff --git a/llvm/test/Transforms/L...
[truncated]
|
|
@llvm/pr-subscribers-llvm-transforms Author: Mel Chen (Mel-Chen) ChangesThis patch narrows uniform VPWidenCastRecipe into scalar cast recipes. Since cast operations involve type conversions, directly cloning them would produce an incorrect destination type. Therefore, we emit scalar cast recipes instead of using VPReplicateRecipe. Based on #143552 Patch is 30.05 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/166514.diff 8 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 9d9bb14530539..2740fcd1a21fc 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1386,7 +1386,8 @@ static void narrowToSingleScalarRecipes(VPlan &Plan) {
for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
vp_depth_first_shallow(Plan.getVectorLoopRegion()->getEntry()))) {
for (VPRecipeBase &R : make_early_inc_range(reverse(*VPBB))) {
- if (!isa<VPWidenRecipe, VPWidenSelectRecipe, VPReplicateRecipe>(&R))
+ if (!isa<VPWidenRecipe, VPWidenCastRecipe, VPWidenSelectRecipe,
+ VPReplicateRecipe>(&R))
continue;
auto *RepR = dyn_cast<VPReplicateRecipe>(&R);
if (RepR && (RepR->isSingleScalar() || RepR->isPredicated()))
@@ -1422,6 +1423,15 @@ static void narrowToSingleScalarRecipes(VPlan &Plan) {
}))
continue;
+ if (auto *CastR = dyn_cast<VPWidenCastRecipe>(RepOrWidenR)) {
+ VPBuilder Builder(CastR);
+ auto *Clone = Builder.createScalarCast(
+ CastR->getOpcode(), CastR->getOperand(0), CastR->getResultType(),
+ CastR->getDebugLoc());
+ CastR->replaceAllUsesWith(Clone);
+ CastR->eraseFromParent();
+ continue;
+ }
auto *Clone = new VPReplicateRecipe(RepOrWidenR->getUnderlyingInstr(),
RepOrWidenR->operands(),
true /*IsSingleScalar*/);
diff --git a/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp b/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
index c6380d30ab2e2..6dd4e5ac697c1 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
@@ -171,6 +171,10 @@ bool vputils::isSingleScalar(const VPValue *VPV) {
return PreservesUniformity(WidenR->getOpcode()) &&
all_of(WidenR->operands(), isSingleScalar);
}
+ if (auto *CastR = dyn_cast<VPWidenCastRecipe>(VPV)) {
+ return PreservesUniformity(CastR->getOpcode()) &&
+ all_of(CastR->operands(), isSingleScalar);
+ }
if (auto *VPI = dyn_cast<VPInstruction>(VPV))
return VPI->isSingleScalar() || VPI->isVectorToScalar() ||
(PreservesUniformity(VPI->getOpcode()) &&
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
index b430efc9e5283..a5f7764898055 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
@@ -492,18 +492,18 @@ define i64 @partial_reduction_mul_two_users(i64 %n, ptr %a, i16 %b, i32 %c) {
; CHECK-NEXT: [[TMP3:%.*]] = zext <8 x i32> [[TMP2]] to <8 x i64>
; CHECK-NEXT: [[PARTIAL_REDUCE]] = call <4 x i64> @llvm.vector.partial.reduce.add.v4i64.v8i64(<4 x i64> [[VEC_PHI]], <8 x i64> [[TMP3]])
; CHECK-NEXT: [[TMP5:%.*]] = sext <8 x i16> [[BROADCAST_SPLAT2]] to <8 x i32>
-; CHECK-NEXT: [[TMP6:%.*]] = sext <8 x i32> [[TMP5]] to <8 x i64>
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <8 x i32> [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP9:%.*]] = sext i32 [[TMP6]] to i64
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP8:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[PARTIAL_REDUCE]])
-; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <8 x i64> [[TMP6]], i32 7
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
-; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[VECTOR_RECUR_EXTRACT]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[TMP9]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i64 [ [[TMP8]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
@@ -520,7 +520,7 @@ define i64 @partial_reduction_mul_two_users(i64 %n, ptr %a, i16 %b, i32 %c) {
; CHECK-NEXT: [[LOAD_EXT:%.*]] = sext i16 [[LOAD]] to i32
; CHECK-NEXT: [[LOAD_EXT_EXT]] = sext i32 [[LOAD_EXT]] to i64
; CHECK-NEXT: [[EXITCOND740_NOT:%.*]] = icmp eq i64 [[IV]], [[N]]
-; CHECK-NEXT: br i1 [[EXITCOND740_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP19:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND740_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi i64 [ [[ADD]], %[[LOOP]] ], [ [[TMP8]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i64 [[ADD_LCSSA]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll
index 1dcd665817196..4642144f8d6d4 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/predicated-costs.ll
@@ -66,63 +66,150 @@ define void @test_predicated_load_cast_hint(ptr %dst.1, ptr %dst.2, ptr %src, i8
; CHECK-NEXT: [[CONFLICT_RDX15:%.*]] = or i1 [[CONFLICT_RDX]], [[FOUND_CONFLICT14]]
; CHECK-NEXT: br i1 [[CONFLICT_RDX15]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 0, i32 [[TMP2]])
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 0, i32 [[TMP2]])
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
-; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE22:.*]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], %[[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %[[PRED_STORE_CONTINUE22]] ]
-; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 4, i8 8, i8 12>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[PRED_STORE_CONTINUE22]] ]
-; CHECK-NEXT: [[TMP28:%.*]] = load i8, ptr [[SRC]], align 1, !alias.scope [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[TMP28]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP25:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT]] to <4 x i64>
-; CHECK-NEXT: [[TMP26:%.*]] = zext <4 x i8> [[VEC_IND]] to <4 x i64>
-; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 0
-; CHECK-NEXT: br i1 [[TMP27]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE46:.*]] ]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <16 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], %[[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %[[PRED_STORE_CONTINUE46]] ]
+; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i8> [ <i8 0, i8 4, i8 8, i8 12, i8 16, i8 20, i8 24, i8 28, i8 32, i8 36, i8 40, i8 44, i8 48, i8 52, i8 56, i8 60>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[PRED_STORE_CONTINUE46]] ]
+; CHECK-NEXT: [[TMP25:%.*]] = load i8, ptr [[SRC]], align 1, !alias.scope [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
+; CHECK-NEXT: [[TMP29:%.*]] = zext i8 [[TMP25]] to i64
+; CHECK-NEXT: [[TMP30:%.*]] = or i64 [[TMP29]], 1
+; CHECK-NEXT: [[TMP27:%.*]] = zext <16 x i8> [[VEC_IND]] to <16 x i64>
+; CHECK-NEXT: [[TMP28:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 0
+; CHECK-NEXT: br i1 [[TMP28]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
; CHECK: [[PRED_STORE_IF]]:
-; CHECK-NEXT: [[TMP102:%.*]] = extractelement <4 x i64> [[TMP26]], i32 0
+; CHECK-NEXT: [[TMP102:%.*]] = extractelement <16 x i64> [[TMP27]], i32 0
; CHECK-NEXT: [[TMP103:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP102]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP104:%.*]] = extractelement <4 x i64> [[TMP25]], i32 0
-; CHECK-NEXT: [[TMP105:%.*]] = or i64 [[TMP104]], 1
-; CHECK-NEXT: store i64 [[TMP105]], ptr [[TMP103]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP103]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE]]
; CHECK: [[PRED_STORE_CONTINUE]]:
-; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 1
-; CHECK-NEXT: br i1 [[TMP32]], label %[[PRED_STORE_IF17:.*]], label %[[PRED_STORE_CONTINUE18:.*]]
+; CHECK-NEXT: [[TMP31:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 1
+; CHECK-NEXT: br i1 [[TMP31]], label %[[PRED_STORE_IF17:.*]], label %[[PRED_STORE_CONTINUE18:.*]]
; CHECK: [[PRED_STORE_IF17]]:
-; CHECK-NEXT: [[TMP108:%.*]] = extractelement <4 x i64> [[TMP26]], i32 1
+; CHECK-NEXT: [[TMP108:%.*]] = extractelement <16 x i64> [[TMP27]], i32 1
; CHECK-NEXT: [[TMP109:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP108]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP110:%.*]] = extractelement <4 x i64> [[TMP25]], i32 1
-; CHECK-NEXT: [[TMP111:%.*]] = or i64 [[TMP110]], 1
-; CHECK-NEXT: store i64 [[TMP111]], ptr [[TMP109]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP109]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE18]]
; CHECK: [[PRED_STORE_CONTINUE18]]:
-; CHECK-NEXT: [[TMP37:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 2
-; CHECK-NEXT: br i1 [[TMP37]], label %[[PRED_STORE_IF19:.*]], label %[[PRED_STORE_CONTINUE20:.*]]
+; CHECK-NEXT: [[TMP34:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 2
+; CHECK-NEXT: br i1 [[TMP34]], label %[[PRED_STORE_IF19:.*]], label %[[PRED_STORE_CONTINUE20:.*]]
; CHECK: [[PRED_STORE_IF19]]:
-; CHECK-NEXT: [[TMP114:%.*]] = extractelement <4 x i64> [[TMP26]], i32 2
+; CHECK-NEXT: [[TMP114:%.*]] = extractelement <16 x i64> [[TMP27]], i32 2
; CHECK-NEXT: [[TMP115:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP114]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP116:%.*]] = extractelement <4 x i64> [[TMP25]], i32 2
-; CHECK-NEXT: [[TMP117:%.*]] = or i64 [[TMP116]], 1
-; CHECK-NEXT: store i64 [[TMP117]], ptr [[TMP115]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP115]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE20]]
; CHECK: [[PRED_STORE_CONTINUE20]]:
-; CHECK-NEXT: [[TMP42:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 3
-; CHECK-NEXT: br i1 [[TMP42]], label %[[PRED_STORE_IF21:.*]], label %[[PRED_STORE_CONTINUE22]]
+; CHECK-NEXT: [[TMP37:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 3
+; CHECK-NEXT: br i1 [[TMP37]], label %[[PRED_STORE_IF21:.*]], label %[[PRED_STORE_CONTINUE22:.*]]
; CHECK: [[PRED_STORE_IF21]]:
-; CHECK-NEXT: [[TMP120:%.*]] = extractelement <4 x i64> [[TMP26]], i32 3
+; CHECK-NEXT: [[TMP120:%.*]] = extractelement <16 x i64> [[TMP27]], i32 3
; CHECK-NEXT: [[TMP121:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP120]], i64 [[OFF]]
-; CHECK-NEXT: [[TMP122:%.*]] = extractelement <4 x i64> [[TMP25]], i32 3
-; CHECK-NEXT: [[TMP123:%.*]] = or i64 [[TMP122]], 1
-; CHECK-NEXT: store i64 [[TMP123]], ptr [[TMP121]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP121]], align 8, !alias.scope [[META3]]
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE22]]
; CHECK: [[PRED_STORE_CONTINUE22]]:
+; CHECK-NEXT: [[TMP40:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 4
+; CHECK-NEXT: br i1 [[TMP40]], label %[[PRED_STORE_IF23:.*]], label %[[PRED_STORE_CONTINUE24:.*]]
+; CHECK: [[PRED_STORE_IF23]]:
+; CHECK-NEXT: [[TMP41:%.*]] = extractelement <16 x i64> [[TMP27]], i32 4
+; CHECK-NEXT: [[TMP42:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP41]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP42]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE24]]
+; CHECK: [[PRED_STORE_CONTINUE24]]:
+; CHECK-NEXT: [[TMP43:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 5
+; CHECK-NEXT: br i1 [[TMP43]], label %[[PRED_STORE_IF25:.*]], label %[[PRED_STORE_CONTINUE26:.*]]
+; CHECK: [[PRED_STORE_IF25]]:
+; CHECK-NEXT: [[TMP44:%.*]] = extractelement <16 x i64> [[TMP27]], i32 5
+; CHECK-NEXT: [[TMP45:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP44]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP45]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE26]]
+; CHECK: [[PRED_STORE_CONTINUE26]]:
+; CHECK-NEXT: [[TMP46:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 6
+; CHECK-NEXT: br i1 [[TMP46]], label %[[PRED_STORE_IF27:.*]], label %[[PRED_STORE_CONTINUE28:.*]]
+; CHECK: [[PRED_STORE_IF27]]:
+; CHECK-NEXT: [[TMP76:%.*]] = extractelement <16 x i64> [[TMP27]], i32 6
+; CHECK-NEXT: [[TMP77:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP76]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP77]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE28]]
+; CHECK: [[PRED_STORE_CONTINUE28]]:
+; CHECK-NEXT: [[TMP49:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 7
+; CHECK-NEXT: br i1 [[TMP49]], label %[[PRED_STORE_IF29:.*]], label %[[PRED_STORE_CONTINUE30:.*]]
+; CHECK: [[PRED_STORE_IF29]]:
+; CHECK-NEXT: [[TMP50:%.*]] = extractelement <16 x i64> [[TMP27]], i32 7
+; CHECK-NEXT: [[TMP51:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP50]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP51]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE30]]
+; CHECK: [[PRED_STORE_CONTINUE30]]:
+; CHECK-NEXT: [[TMP52:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 8
+; CHECK-NEXT: br i1 [[TMP52]], label %[[PRED_STORE_IF31:.*]], label %[[PRED_STORE_CONTINUE32:.*]]
+; CHECK: [[PRED_STORE_IF31]]:
+; CHECK-NEXT: [[TMP53:%.*]] = extractelement <16 x i64> [[TMP27]], i32 8
+; CHECK-NEXT: [[TMP54:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP53]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP54]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE32]]
+; CHECK: [[PRED_STORE_CONTINUE32]]:
+; CHECK-NEXT: [[TMP55:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 9
+; CHECK-NEXT: br i1 [[TMP55]], label %[[PRED_STORE_IF33:.*]], label %[[PRED_STORE_CONTINUE34:.*]]
+; CHECK: [[PRED_STORE_IF33]]:
+; CHECK-NEXT: [[TMP56:%.*]] = extractelement <16 x i64> [[TMP27]], i32 9
+; CHECK-NEXT: [[TMP57:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP56]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP57]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE34]]
+; CHECK: [[PRED_STORE_CONTINUE34]]:
+; CHECK-NEXT: [[TMP58:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 10
+; CHECK-NEXT: br i1 [[TMP58]], label %[[PRED_STORE_IF35:.*]], label %[[PRED_STORE_CONTINUE36:.*]]
+; CHECK: [[PRED_STORE_IF35]]:
+; CHECK-NEXT: [[TMP59:%.*]] = extractelement <16 x i64> [[TMP27]], i32 10
+; CHECK-NEXT: [[TMP60:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP59]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP60]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE36]]
+; CHECK: [[PRED_STORE_CONTINUE36]]:
+; CHECK-NEXT: [[TMP61:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 11
+; CHECK-NEXT: br i1 [[TMP61]], label %[[PRED_STORE_IF37:.*]], label %[[PRED_STORE_CONTINUE38:.*]]
+; CHECK: [[PRED_STORE_IF37]]:
+; CHECK-NEXT: [[TMP62:%.*]] = extractelement <16 x i64> [[TMP27]], i32 11
+; CHECK-NEXT: [[TMP63:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP62]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP63]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE38]]
+; CHECK: [[PRED_STORE_CONTINUE38]]:
+; CHECK-NEXT: [[TMP64:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 12
+; CHECK-NEXT: br i1 [[TMP64]], label %[[PRED_STORE_IF39:.*]], label %[[PRED_STORE_CONTINUE40:.*]]
+; CHECK: [[PRED_STORE_IF39]]:
+; CHECK-NEXT: [[TMP65:%.*]] = extractelement <16 x i64> [[TMP27]], i32 12
+; CHECK-NEXT: [[TMP66:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP65]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP66]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE40]]
+; CHECK: [[PRED_STORE_CONTINUE40]]:
+; CHECK-NEXT: [[TMP67:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 13
+; CHECK-NEXT: br i1 [[TMP67]], label %[[PRED_STORE_IF41:.*]], label %[[PRED_STORE_CONTINUE42:.*]]
+; CHECK: [[PRED_STORE_IF41]]:
+; CHECK-NEXT: [[TMP68:%.*]] = extractelement <16 x i64> [[TMP27]], i32 13
+; CHECK-NEXT: [[TMP69:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP68]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP69]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE42]]
+; CHECK: [[PRED_STORE_CONTINUE42]]:
+; CHECK-NEXT: [[TMP70:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 14
+; CHECK-NEXT: br i1 [[TMP70]], label %[[PRED_STORE_IF43:.*]], label %[[PRED_STORE_CONTINUE44:.*]]
+; CHECK: [[PRED_STORE_IF43]]:
+; CHECK-NEXT: [[TMP71:%.*]] = extractelement <16 x i64> [[TMP27]], i32 14
+; CHECK-NEXT: [[TMP72:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP71]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP72]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE44]]
+; CHECK: [[PRED_STORE_CONTINUE44]]:
+; CHECK-NEXT: [[TMP73:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK]], i32 15
+; CHECK-NEXT: br i1 [[TMP73]], label %[[PRED_STORE_IF45:.*]], label %[[PRED_STORE_CONTINUE46]]
+; CHECK: [[PRED_STORE_IF45]]:
+; CHECK-NEXT: [[TMP74:%.*]] = extractelement <16 x i64> [[TMP27]], i32 15
+; CHECK-NEXT: [[TMP75:%.*]] = getelementptr [16 x i64], ptr [[DST_1]], i64 [[TMP74]], i64 [[OFF]]
+; CHECK-NEXT: store i64 [[TMP30]], ptr [[TMP75]], align 8, !alias.scope [[META3]]
+; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE46]]
+; CHECK: [[PRED_STORE_CONTINUE46]]:
; CHECK-NEXT: store i8 0, ptr [[DST_2]], align 1, !alias.scope [[META5:![0-9]+]], !noalias [[META7:![0-9]+]]
-; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[INDEX_NEXT]], i32 [[TMP2]])
-; CHECK-NEXT: [[TMP47:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 16
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX_NEXT]], i32 [[TMP2]])
+; CHECK-NEXT: [[TMP47:%.*]] = extractelement <16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
; CHECK-NEXT: [[TMP48:%.*]] = xor i1 [[TMP47]], true
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 16)
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i8> [[VEC_IND]], splat (i8 64)
; CHECK-NEXT: br i1 [[TMP48]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
diff --git a/llvm/test/Transforms/L...
[truncated]
|
lukel97
reviewed
Nov 5, 2025
There was a problem hiding this comment.
I would have thought that a VPWidenCastRecipe could have been replicated with its original underlying instruction, but I see now that it's sometimes used for synthetic instructions with no underlying value. We should probably finish moving those over to VPInstructionWithType
artagnon
reviewed
Nov 5, 2025
Comment on lines
167
to
168
| if (isa<VPWidenGEPRecipe, VPDerivedIVRecipe, VPBlendRecipe, | ||
| VPWidenSelectRecipe>(VPV)) |
There was a problem hiding this comment.
I think you can add WidenCast to this isa.
| CastR->getOpcode(), CastR->getOperand(0), CastR->getResultType(), | ||
| CastR->getDebugLoc()); | ||
| CastR->replaceAllUsesWith(Clone); | ||
| CastR->eraseFromParent(); |
There was a problem hiding this comment.
I don't think we need this: remove deadRecipes should automatically take care of this.
There was a problem hiding this comment.
simplifyRecipes runs after this before removeDeadRecipes, which is sensitive to the number of users. So we should remove the dead recipes if we can
There was a problem hiding this comment.
We can then guard it with isDeadRecipe as it is done for the replicate below?
Comment on lines
+1426
to
+1434
| if (auto *CastR = dyn_cast<VPWidenCastRecipe>(RepOrWidenR)) { | ||
| VPBuilder Builder(CastR); | ||
| auto *Clone = Builder.createScalarCast( | ||
| CastR->getOpcode(), CastR->getOperand(0), CastR->getResultType(), | ||
| CastR->getDebugLoc()); | ||
| CastR->replaceAllUsesWith(Clone); | ||
| CastR->eraseFromParent(); | ||
| continue; | ||
| } |
There was a problem hiding this comment.
I think vputils::getSingleScalarClone would be cleaner, but I'm happy to land this first. #161667.
There was a problem hiding this comment.
I think you dropped the flags and metadata.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This patch narrows uniform VPWidenCastRecipe into scalar cast recipes. Since cast operations involve type conversions, directly cloning them would produce an incorrect destination type. Therefore, we emit scalar cast recipes instead of using VPReplicateRecipe.
Based on #143552