[llvm] [VPlan] Handle VPWidenCastRecipe without underlying value in EVL transform (PR #120194)

Luke Lau via llvm-commits llvm-commits at lists.llvm.org
Tue Dec 17 00:17:49 PST 2024


https://github.com/lukel97 updated https://github.com/llvm/llvm-project/pull/120194

>From 1634aaf401c82eb738091c59496cb290b741c154 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 17 Dec 2024 15:15:33 +0800
Subject: [PATCH 1/4] [VPlan] Handle VPWidenCastRecipe without underlying value
 in EVL transform

This fixes a crash that shows up when building SPEC CPU 2017 with EVL tail folding on RISC-V.

A VPWidenCastRecipe doesn't always have an underlying value, and in the case of this crash this happens whenever a widened cast is created via truncateToMinimalBitwidths.

Fix this by just using the opcode stored in the recipe itself.

I think a similar issue exists with VPWidenIntrinsicRecipe and how it's widened, but I haven't run into any crashes with it just yet.
---
 .../Transforms/Vectorize/VPlanTransforms.cpp  |   7 +-
 ...ize-force-tail-with-evl-cast-intrinsics.ll | 121 ++++++++++++++++++
 2 files changed, 124 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 9a3b82fe57c12a..066232775e46a7 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1506,9 +1506,8 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
                   })
               .Case<VPWidenCastRecipe>(
                   [&](VPWidenCastRecipe *CInst) -> VPRecipeBase * {
-                    auto *CI = dyn_cast<CastInst>(CInst->getUnderlyingInstr());
                     Intrinsic::ID VPID =
-                        VPIntrinsic::getForOpcode(CI->getOpcode());
+                        VPIntrinsic::getForOpcode(CInst->getOpcode());
                     assert(VPID != Intrinsic::not_intrinsic &&
                            "Expected vp.casts Instrinsic");
 
@@ -1516,8 +1515,8 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
                     assert(VPIntrinsic::getMaskParamPos(VPID) &&
                            VPIntrinsic::getVectorLengthParamPos(VPID) &&
                            "Expected VP intrinsic");
-                    VPValue *Mask = Plan.getOrAddLiveIn(ConstantInt::getTrue(
-                        IntegerType::getInt1Ty(CI->getContext())));
+                    VPValue *Mask = Plan.getOrAddLiveIn(
+                        ConstantInt::getTrue(IntegerType::getInt1Ty(Ctx)));
                     Ops.push_back(Mask);
                     Ops.push_back(&EVL);
                     return new VPWidenIntrinsicRecipe(
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
index 4557e95f1e1b6a..48f9cec34d974f 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
@@ -1058,6 +1058,125 @@ loop:
 exit:
   ret void
 }
+
+define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, ptr noalias %src, i32 %mvx) {
+; IF-EVL-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
+; IF-EVL-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
+; IF-EVL-NEXT:  [[ENTRY:.*:]]
+; IF-EVL-NEXT:    [[CMP111:%.*]] = icmp sgt i32 [[MVX]], 0
+; IF-EVL-NEXT:    br i1 [[CMP111]], label %[[FOR_BODY13_PREHEADER:.*]], label %[[FOR_COND_CLEANUP12:.*]]
+; IF-EVL:       [[FOR_BODY13_PREHEADER]]:
+; IF-EVL-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
+; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; IF-EVL:       [[VECTOR_PH]]:
+; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 16
+; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 [[WIDE_TRIP_COUNT]], [[TMP2]]
+; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 16
+; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[MVX]], i64 0
+; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
+; IF-EVL-NEXT:    [[TMP5:%.*]] = trunc <vscale x 16 x i32> [[BROADCAST_SPLAT]] to <vscale x 16 x i16>
+; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <vscale x 16 x ptr> poison, ptr [[DST]], i64 0
+; IF-EVL-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <vscale x 16 x ptr> [[BROADCAST_SPLATINSERT2]], <vscale x 16 x ptr> poison, <vscale x 16 x i32> zeroinitializer
+; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
+; IF-EVL:       [[VECTOR_BODY]]:
+; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 16, i1 true)
+; IF-EVL-NEXT:    [[TMP7:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP7]]
+; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[TMP8]], i32 0
+; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP9]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP10:%.*]] = call <vscale x 16 x i16> @llvm.vp.zext.nxv16i16.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[VP_OP:%.*]] = call <vscale x 16 x i16> @llvm.vp.mul.nxv16i16(<vscale x 16 x i16> [[TMP5]], <vscale x 16 x i16> [[TMP10]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[VP_OP1:%.*]] = call <vscale x 16 x i16> @llvm.vp.lshr.nxv16i16(<vscale x 16 x i16> [[VP_OP]], <vscale x 16 x i16> trunc (<vscale x 16 x i32> splat (i32 1) to <vscale x 16 x i16>), <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 16 x i8> @llvm.vp.trunc.nxv16i8.nxv16i16(<vscale x 16 x i16> [[VP_OP1]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP11]], <vscale x 16 x ptr> align 1 [[BROADCAST_SPLAT3]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP12:%.*]] = zext i32 [[TMP6]] to i64
+; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT:    br i1 [[TMP13]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP47:![0-9]+]]
+; IF-EVL:       [[MIDDLE_BLOCK]]:
+; IF-EVL-NEXT:    br i1 true, label %[[FOR_COND_CLEANUP12_LOOPEXIT:.*]], label %[[SCALAR_PH]]
+; IF-EVL:       [[SCALAR_PH]]:
+; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[FOR_BODY13_PREHEADER]] ]
+; IF-EVL-NEXT:    br label %[[FOR_BODY13:.*]]
+; IF-EVL:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
+; IF-EVL-NEXT:    br label %[[FOR_COND_CLEANUP12]]
+; IF-EVL:       [[FOR_COND_CLEANUP12]]:
+; IF-EVL-NEXT:    ret void
+; IF-EVL:       [[FOR_BODY13]]:
+; IF-EVL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
+; IF-EVL-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
+; IF-EVL-NEXT:    [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX15]], align 1
+; IF-EVL-NEXT:    [[CONV:%.*]] = zext i8 [[TMP14]] to i32
+; IF-EVL-NEXT:    [[MUL16:%.*]] = mul i32 [[MVX]], [[CONV]]
+; IF-EVL-NEXT:    [[SHR35:%.*]] = lshr i32 [[MUL16]], 1
+; IF-EVL-NEXT:    [[CONV36:%.*]] = trunc i32 [[SHR35]] to i8
+; IF-EVL-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
+; IF-EVL-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]], !llvm.loop [[LOOP48:![0-9]+]]
+;
+; NO-VP-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
+; NO-VP-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
+; NO-VP-NEXT:  [[ENTRY:.*:]]
+; NO-VP-NEXT:    [[CMP111:%.*]] = icmp sgt i32 [[MVX]], 0
+; NO-VP-NEXT:    br i1 [[CMP111]], label %[[FOR_BODY13_PREHEADER:.*]], label %[[FOR_COND_CLEANUP12:.*]]
+; NO-VP:       [[FOR_BODY13_PREHEADER]]:
+; NO-VP-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
+; NO-VP-NEXT:    br label %[[FOR_BODY13:.*]]
+; NO-VP:       [[FOR_COND_CLEANUP12_LOOPEXIT:.*]]:
+; NO-VP-NEXT:    br label %[[FOR_COND_CLEANUP12]]
+; NO-VP:       [[FOR_COND_CLEANUP12]]:
+; NO-VP-NEXT:    ret void
+; NO-VP:       [[FOR_BODY13]]:
+; NO-VP-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[FOR_BODY13_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
+; NO-VP-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
+; NO-VP-NEXT:    [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX15]], align 1
+; NO-VP-NEXT:    [[CONV:%.*]] = zext i8 [[TMP0]] to i32
+; NO-VP-NEXT:    [[MUL16:%.*]] = mul i32 [[MVX]], [[CONV]]
+; NO-VP-NEXT:    [[SHR35:%.*]] = lshr i32 [[MUL16]], 1
+; NO-VP-NEXT:    [[CONV36:%.*]] = trunc i32 [[SHR35]] to i8
+; NO-VP-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
+; NO-VP-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; NO-VP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]]
+;
+entry:
+  %cmp111 = icmp sgt i32 %mvx, 0
+  br i1 %cmp111, label %for.body13.preheader, label %for.cond.cleanup12
+
+for.body13.preheader:                             ; preds = %entry
+  %wide.trip.count = zext nneg i32 %mvx to i64
+  br label %for.body13
+
+for.cond.cleanup12.loopexit:                      ; preds = %for.body13
+  br label %for.cond.cleanup12
+
+for.cond.cleanup12:                               ; preds = %for.cond.cleanup12.loopexit, %entry
+  ret void
+
+for.body13:                                       ; preds = %for.body13.preheader, %for.body13
+  %indvars.iv = phi i64 [ 0, %for.body13.preheader ], [ %indvars.iv.next, %for.body13 ]
+  %arrayidx15 = getelementptr i8, ptr %src, i64 %indvars.iv
+  %0 = load i8, ptr %arrayidx15, align 1
+  %conv = zext i8 %0 to i32
+  %mul16 = mul i32 %mvx, %conv
+  %shr35 = lshr i32 %mul16, 1
+  %conv36 = trunc i32 %shr35 to i8
+  store i8 %conv36, ptr %dst, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  br i1 %exitcond.not, label %for.cond.cleanup12.loopexit, label %for.body13
+}
+
 ;.
 ; IF-EVL: [[META0]] = !{[[META1:![0-9]+]]}
 ; IF-EVL: [[META1]] = distinct !{[[META1]], [[META2:![0-9]+]]}
@@ -1106,4 +1225,6 @@ exit:
 ; IF-EVL: [[LOOP44]] = distinct !{[[LOOP44]], [[META6]]}
 ; IF-EVL: [[LOOP45]] = distinct !{[[LOOP45]], [[META6]], [[META7]]}
 ; IF-EVL: [[LOOP46]] = distinct !{[[LOOP46]], [[META6]]}
+; IF-EVL: [[LOOP47]] = distinct !{[[LOOP47]], [[META6]], [[META7]]}
+; IF-EVL: [[LOOP48]] = distinct !{[[LOOP48]], [[META7]], [[META6]]}
 ;.

>From 6dd9322f3b7865e46e0b1cdaf5d9b97c2e0b09d6 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 17 Dec 2024 16:00:00 +0800
Subject: [PATCH 2/4] Remove redundant IntegerType::get, remove redundant block
 in tests

---
 .../Transforms/Vectorize/VPlanTransforms.cpp  |  4 +--
 ...ize-force-tail-with-evl-cast-intrinsics.ll | 29 +++++++++----------
 2 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 066232775e46a7..85931a9d95a85b 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1515,8 +1515,8 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
                     assert(VPIntrinsic::getMaskParamPos(VPID) &&
                            VPIntrinsic::getVectorLengthParamPos(VPID) &&
                            "Expected VP intrinsic");
-                    VPValue *Mask = Plan.getOrAddLiveIn(
-                        ConstantInt::getTrue(IntegerType::getInt1Ty(Ctx)));
+                    VPValue *Mask =
+                        Plan.getOrAddLiveIn(ConstantInt::getTrue(Ctx));
                     Ops.push_back(Mask);
                     Ops.push_back(&EVL);
                     return new VPWidenIntrinsicRecipe(
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
index 48f9cec34d974f..3f4f8b60d45d60 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
@@ -1107,10 +1107,6 @@ define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, p
 ; IF-EVL:       [[SCALAR_PH]]:
 ; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[FOR_BODY13_PREHEADER]] ]
 ; IF-EVL-NEXT:    br label %[[FOR_BODY13:.*]]
-; IF-EVL:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
-; IF-EVL-NEXT:    br label %[[FOR_COND_CLEANUP12]]
-; IF-EVL:       [[FOR_COND_CLEANUP12]]:
-; IF-EVL-NEXT:    ret void
 ; IF-EVL:       [[FOR_BODY13]]:
 ; IF-EVL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
 ; IF-EVL-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
@@ -1123,6 +1119,10 @@ define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, p
 ; IF-EVL-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
 ; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
 ; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]], !llvm.loop [[LOOP48:![0-9]+]]
+; IF-EVL:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
+; IF-EVL-NEXT:    br label %[[FOR_COND_CLEANUP12]]
+; IF-EVL:       [[FOR_COND_CLEANUP12]]:
+; IF-EVL-NEXT:    ret void
 ;
 ; NO-VP-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
 ; NO-VP-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
@@ -1132,10 +1132,6 @@ define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, p
 ; NO-VP:       [[FOR_BODY13_PREHEADER]]:
 ; NO-VP-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
 ; NO-VP-NEXT:    br label %[[FOR_BODY13:.*]]
-; NO-VP:       [[FOR_COND_CLEANUP12_LOOPEXIT:.*]]:
-; NO-VP-NEXT:    br label %[[FOR_COND_CLEANUP12]]
-; NO-VP:       [[FOR_COND_CLEANUP12]]:
-; NO-VP-NEXT:    ret void
 ; NO-VP:       [[FOR_BODY13]]:
 ; NO-VP-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[FOR_BODY13_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
 ; NO-VP-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
@@ -1147,7 +1143,11 @@ define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, p
 ; NO-VP-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
 ; NO-VP-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
 ; NO-VP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
-; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]]
+; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT:.*]], label %[[FOR_BODY13]]
+; NO-VP:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
+; NO-VP-NEXT:    br label %[[FOR_COND_CLEANUP12]]
+; NO-VP:       [[FOR_COND_CLEANUP12]]:
+; NO-VP-NEXT:    ret void
 ;
 entry:
   %cmp111 = icmp sgt i32 %mvx, 0
@@ -1157,12 +1157,6 @@ for.body13.preheader:                             ; preds = %entry
   %wide.trip.count = zext nneg i32 %mvx to i64
   br label %for.body13
 
-for.cond.cleanup12.loopexit:                      ; preds = %for.body13
-  br label %for.cond.cleanup12
-
-for.cond.cleanup12:                               ; preds = %for.cond.cleanup12.loopexit, %entry
-  ret void
-
 for.body13:                                       ; preds = %for.body13.preheader, %for.body13
   %indvars.iv = phi i64 [ 0, %for.body13.preheader ], [ %indvars.iv.next, %for.body13 ]
   %arrayidx15 = getelementptr i8, ptr %src, i64 %indvars.iv
@@ -1174,7 +1168,10 @@ for.body13:                                       ; preds = %for.body13.preheade
   store i8 %conv36, ptr %dst, align 1
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
-  br i1 %exitcond.not, label %for.cond.cleanup12.loopexit, label %for.body13
+  br i1 %exitcond.not, label %for.cond.cleanup12, label %for.body13
+
+for.cond.cleanup12:                               ; preds = %for.body13, %entry
+  ret void
 }
 
 ;.

>From b61144631a222f5ee303aab9e747820c80de2b1a Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 17 Dec 2024 16:08:36 +0800
Subject: [PATCH 3/4] Move to new test without FileCheck/UTC

---
 .../truncate-to-minimal-bitwidth-evl-crash.ll |  31 +++++
 ...ize-force-tail-with-evl-cast-intrinsics.ll | 118 ------------------
 2 files changed, 31 insertions(+), 118 deletions(-)
 create mode 100644 llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll

diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
new file mode 100644
index 00000000000000..b0a3968a7ca2fd
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
@@ -0,0 +1,31 @@
+; RUN: opt -passes=loop-vectorize -force-tail-folding-style=data-with-evl -prefer-predicate-over-epilogue=predicate-dont-vectorize -mtriple=riscv64 -mattr=+v -S %s
+
+; Make sure we don't crash when transforming a VPWidenCastRecipe is created
+; without an underlying value. This occurs in this test via
+; VPlanTransforms::truncateToMinimalBitwidths
+
+define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr %dst, ptr %src, i32 %mvx) {
+entry:
+  %cmp111 = icmp sgt i32 %mvx, 0
+  br i1 %cmp111, label %for.body13.preheader, label %for.cond.cleanup12
+
+for.body13.preheader:                             ; preds = %entry
+  %wide.trip.count = zext nneg i32 %mvx to i64
+  br label %for.body13
+
+for.body13:                                       ; preds = %for.body13.preheader, %for.body13
+  %indvars.iv = phi i64 [ 0, %for.body13.preheader ], [ %indvars.iv.next, %for.body13 ]
+  %arrayidx15 = getelementptr i8, ptr %src, i64 %indvars.iv
+  %0 = load i8, ptr %arrayidx15, align 1
+  %conv = zext i8 %0 to i32
+  %mul16 = mul i32 %mvx, %conv
+  %shr35 = lshr i32 %mul16, 1
+  %conv36 = trunc i32 %shr35 to i8
+  store i8 %conv36, ptr %dst, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  br i1 %exitcond.not, label %for.cond.cleanup12, label %for.body13
+
+for.cond.cleanup12:                               ; preds = %for.body13, %entry
+  ret void
+}
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
index 3f4f8b60d45d60..4557e95f1e1b6a 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cast-intrinsics.ll
@@ -1058,122 +1058,6 @@ loop:
 exit:
   ret void
 }
-
-define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, ptr noalias %src, i32 %mvx) {
-; IF-EVL-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
-; IF-EVL-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
-; IF-EVL-NEXT:  [[ENTRY:.*:]]
-; IF-EVL-NEXT:    [[CMP111:%.*]] = icmp sgt i32 [[MVX]], 0
-; IF-EVL-NEXT:    br i1 [[CMP111]], label %[[FOR_BODY13_PREHEADER:.*]], label %[[FOR_COND_CLEANUP12:.*]]
-; IF-EVL:       [[FOR_BODY13_PREHEADER]]:
-; IF-EVL-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
-; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; IF-EVL:       [[VECTOR_PH]]:
-; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 16
-; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
-; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 [[WIDE_TRIP_COUNT]], [[TMP2]]
-; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 16
-; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[MVX]], i64 0
-; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
-; IF-EVL-NEXT:    [[TMP5:%.*]] = trunc <vscale x 16 x i32> [[BROADCAST_SPLAT]] to <vscale x 16 x i16>
-; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <vscale x 16 x ptr> poison, ptr [[DST]], i64 0
-; IF-EVL-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <vscale x 16 x ptr> [[BROADCAST_SPLATINSERT2]], <vscale x 16 x ptr> poison, <vscale x 16 x i32> zeroinitializer
-; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
-; IF-EVL:       [[VECTOR_BODY]]:
-; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[EVL_BASED_IV]]
-; IF-EVL-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 16, i1 true)
-; IF-EVL-NEXT:    [[TMP7:%.*]] = add i64 [[EVL_BASED_IV]], 0
-; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP7]]
-; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[TMP8]], i32 0
-; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP9]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-NEXT:    [[TMP10:%.*]] = call <vscale x 16 x i16> @llvm.vp.zext.nxv16i16.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-NEXT:    [[VP_OP:%.*]] = call <vscale x 16 x i16> @llvm.vp.mul.nxv16i16(<vscale x 16 x i16> [[TMP5]], <vscale x 16 x i16> [[TMP10]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-NEXT:    [[VP_OP1:%.*]] = call <vscale x 16 x i16> @llvm.vp.lshr.nxv16i16(<vscale x 16 x i16> [[VP_OP]], <vscale x 16 x i16> trunc (<vscale x 16 x i32> splat (i32 1) to <vscale x 16 x i16>), <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 16 x i8> @llvm.vp.trunc.nxv16i8.nxv16i16(<vscale x 16 x i16> [[VP_OP1]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-NEXT:    call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP11]], <vscale x 16 x ptr> align 1 [[BROADCAST_SPLAT3]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
-; IF-EVL-NEXT:    [[TMP12:%.*]] = zext i32 [[TMP6]] to i64
-; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
-; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
-; IF-EVL-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; IF-EVL-NEXT:    br i1 [[TMP13]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP47:![0-9]+]]
-; IF-EVL:       [[MIDDLE_BLOCK]]:
-; IF-EVL-NEXT:    br i1 true, label %[[FOR_COND_CLEANUP12_LOOPEXIT:.*]], label %[[SCALAR_PH]]
-; IF-EVL:       [[SCALAR_PH]]:
-; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[FOR_BODY13_PREHEADER]] ]
-; IF-EVL-NEXT:    br label %[[FOR_BODY13:.*]]
-; IF-EVL:       [[FOR_BODY13]]:
-; IF-EVL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
-; IF-EVL-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
-; IF-EVL-NEXT:    [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX15]], align 1
-; IF-EVL-NEXT:    [[CONV:%.*]] = zext i8 [[TMP14]] to i32
-; IF-EVL-NEXT:    [[MUL16:%.*]] = mul i32 [[MVX]], [[CONV]]
-; IF-EVL-NEXT:    [[SHR35:%.*]] = lshr i32 [[MUL16]], 1
-; IF-EVL-NEXT:    [[CONV36:%.*]] = trunc i32 [[SHR35]] to i8
-; IF-EVL-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
-; IF-EVL-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
-; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]], !llvm.loop [[LOOP48:![0-9]+]]
-; IF-EVL:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
-; IF-EVL-NEXT:    br label %[[FOR_COND_CLEANUP12]]
-; IF-EVL:       [[FOR_COND_CLEANUP12]]:
-; IF-EVL-NEXT:    ret void
-;
-; NO-VP-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
-; NO-VP-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
-; NO-VP-NEXT:  [[ENTRY:.*:]]
-; NO-VP-NEXT:    [[CMP111:%.*]] = icmp sgt i32 [[MVX]], 0
-; NO-VP-NEXT:    br i1 [[CMP111]], label %[[FOR_BODY13_PREHEADER:.*]], label %[[FOR_COND_CLEANUP12:.*]]
-; NO-VP:       [[FOR_BODY13_PREHEADER]]:
-; NO-VP-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
-; NO-VP-NEXT:    br label %[[FOR_BODY13:.*]]
-; NO-VP:       [[FOR_BODY13]]:
-; NO-VP-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[FOR_BODY13_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
-; NO-VP-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
-; NO-VP-NEXT:    [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX15]], align 1
-; NO-VP-NEXT:    [[CONV:%.*]] = zext i8 [[TMP0]] to i32
-; NO-VP-NEXT:    [[MUL16:%.*]] = mul i32 [[MVX]], [[CONV]]
-; NO-VP-NEXT:    [[SHR35:%.*]] = lshr i32 [[MUL16]], 1
-; NO-VP-NEXT:    [[CONV36:%.*]] = trunc i32 [[SHR35]] to i8
-; NO-VP-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
-; NO-VP-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; NO-VP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
-; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT:.*]], label %[[FOR_BODY13]]
-; NO-VP:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
-; NO-VP-NEXT:    br label %[[FOR_COND_CLEANUP12]]
-; NO-VP:       [[FOR_COND_CLEANUP12]]:
-; NO-VP-NEXT:    ret void
-;
-entry:
-  %cmp111 = icmp sgt i32 %mvx, 0
-  br i1 %cmp111, label %for.body13.preheader, label %for.cond.cleanup12
-
-for.body13.preheader:                             ; preds = %entry
-  %wide.trip.count = zext nneg i32 %mvx to i64
-  br label %for.body13
-
-for.body13:                                       ; preds = %for.body13.preheader, %for.body13
-  %indvars.iv = phi i64 [ 0, %for.body13.preheader ], [ %indvars.iv.next, %for.body13 ]
-  %arrayidx15 = getelementptr i8, ptr %src, i64 %indvars.iv
-  %0 = load i8, ptr %arrayidx15, align 1
-  %conv = zext i8 %0 to i32
-  %mul16 = mul i32 %mvx, %conv
-  %shr35 = lshr i32 %mul16, 1
-  %conv36 = trunc i32 %shr35 to i8
-  store i8 %conv36, ptr %dst, align 1
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
-  br i1 %exitcond.not, label %for.cond.cleanup12, label %for.body13
-
-for.cond.cleanup12:                               ; preds = %for.body13, %entry
-  ret void
-}
-
 ;.
 ; IF-EVL: [[META0]] = !{[[META1:![0-9]+]]}
 ; IF-EVL: [[META1]] = distinct !{[[META1]], [[META2:![0-9]+]]}
@@ -1222,6 +1106,4 @@ for.cond.cleanup12:                               ; preds = %for.body13, %entry
 ; IF-EVL: [[LOOP44]] = distinct !{[[LOOP44]], [[META6]]}
 ; IF-EVL: [[LOOP45]] = distinct !{[[LOOP45]], [[META6]], [[META7]]}
 ; IF-EVL: [[LOOP46]] = distinct !{[[LOOP46]], [[META6]]}
-; IF-EVL: [[LOOP47]] = distinct !{[[LOOP47]], [[META6]], [[META7]]}
-; IF-EVL: [[LOOP48]] = distinct !{[[LOOP48]], [[META7]], [[META6]]}
 ;.

>From f57e06afe0ac9e86e55f16f464754ab5231e0524 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 17 Dec 2024 16:17:24 +0800
Subject: [PATCH 4/4] Fix comment

---
 .../RISCV/truncate-to-minimal-bitwidth-evl-crash.ll           | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
index b0a3968a7ca2fd..ade23538e97502 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-evl-crash.ll
@@ -1,7 +1,7 @@
 ; RUN: opt -passes=loop-vectorize -force-tail-folding-style=data-with-evl -prefer-predicate-over-epilogue=predicate-dont-vectorize -mtriple=riscv64 -mattr=+v -S %s
 
-; Make sure we don't crash when transforming a VPWidenCastRecipe is created
-; without an underlying value. This occurs in this test via
+; Make sure we don't crash when transforming a VPWidenCastRecipe created without
+; an underlying value to an EVL recipe. This occurs in this test via
 ; VPlanTransforms::truncateToMinimalBitwidths
 
 define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr %dst, ptr %src, i32 %mvx) {



More information about the llvm-commits mailing list