[llvm] 1abc28f - [NFC][LV] Add test for vectorizing fmuladd with another call (#68601)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Oct 20 02:23:35 PDT 2023
Author: Graham Hunter
Date: 2023-10-20T10:23:31+01:00
New Revision: 1abc28fea0a2f6955b4a6a72495766a2f1d5e3a3
URL: https://github.com/llvm/llvm-project/commit/1abc28fea0a2f6955b4a6a72495766a2f1d5e3a3
DIFF: https://github.com/llvm/llvm-project/commit/1abc28fea0a2f6955b4a6a72495766a2f1d5e3a3.diff
LOG: [NFC][LV] Add test for vectorizing fmuladd with another call (#68601)
As requested in (#66521)
I confirmed a crash with "return" instead of "continue" in
setVectorizedCallDecision's fmuladd reduction recognition.
Added:
Modified:
llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
Removed:
################################################################################
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
index 904dcd4fed30e15..a78878c55a1fc93 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize,instsimplify -force-vector-interleave=1 -S | FileCheck %s --check-prefixes=TFNONE
-; RUN: opt < %s -passes=loop-vectorize,instsimplify -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S | FileCheck %s --check-prefixes=TFALWAYS
-; RUN: opt < %s -passes=loop-vectorize,instsimplify -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s --check-prefixes=TFFALLBACK
+; RUN: opt < %s -passes=loop-vectorize,instsimplify,simplifycfg -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S | FileCheck %s --check-prefixes=TFCOMMON,TFALWAYS
+; RUN: opt < %s -passes=loop-vectorize,instsimplify,simplifycfg -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -S | FileCheck %s --check-prefixes=TFCOMMON,TFFALLBACK
target triple = "aarch64-unknown-linux-gnu"
@@ -41,7 +41,7 @@ define void @test_widen(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; TFNONE-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
; TFNONE-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR2:[0-9]+]]
+; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR3:[0-9]+]]
; TFNONE-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
; TFNONE-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
; TFNONE-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
@@ -50,99 +50,35 @@ define void @test_widen(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE: for.cond.cleanup:
; TFNONE-NEXT: ret void
;
-; TFALWAYS-LABEL: @test_widen(
-; TFALWAYS-NEXT: entry:
-; TFALWAYS-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFALWAYS: vector.ph:
-; TFALWAYS-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFALWAYS-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
-; TFALWAYS-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
-; TFALWAYS-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
-; TFALWAYS-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; TFALWAYS-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
-; TFALWAYS-NEXT: br label [[VECTOR_BODY:%.*]]
-; TFALWAYS: vector.body:
-; TFALWAYS-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[TMP5:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDEX]]
-; TFALWAYS-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; TFALWAYS-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TFALWAYS-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; TFALWAYS-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP6]], ptr [[TMP7]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TFALWAYS-NEXT: [[TMP8:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP9:%.*]] = mul i64 [[TMP8]], 2
-; TFALWAYS-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP9]]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
-; TFALWAYS-NEXT: [[TMP10:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP11:%.*]] = extractelement <vscale x 2 x i1> [[TMP10]], i32 0
-; TFALWAYS-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
-; TFALWAYS: middle.block:
-; TFALWAYS-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFALWAYS: scalar.ph:
-; TFALWAYS-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFALWAYS-NEXT: br label [[FOR_BODY:%.*]]
-; TFALWAYS: for.body:
-; TFALWAYS-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
-; TFALWAYS-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFALWAYS-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR4:[0-9]+]]
-; TFALWAYS-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
-; TFALWAYS-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFALWAYS-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFALWAYS-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
-; TFALWAYS: for.cond.cleanup:
-; TFALWAYS-NEXT: ret void
-;
-; TFFALLBACK-LABEL: @test_widen(
-; TFFALLBACK-NEXT: entry:
-; TFFALLBACK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFFALLBACK: vector.ph:
-; TFFALLBACK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFFALLBACK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
-; TFFALLBACK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
-; TFFALLBACK-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
-; TFFALLBACK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; TFFALLBACK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
-; TFFALLBACK-NEXT: br label [[VECTOR_BODY:%.*]]
-; TFFALLBACK: vector.body:
-; TFFALLBACK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[TMP5:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDEX]]
-; TFFALLBACK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; TFFALLBACK-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TFFALLBACK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; TFFALLBACK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP6]], ptr [[TMP7]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TFFALLBACK-NEXT: [[TMP8:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP9:%.*]] = mul i64 [[TMP8]], 2
-; TFFALLBACK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP9]]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
-; TFFALLBACK-NEXT: [[TMP10:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP11:%.*]] = extractelement <vscale x 2 x i1> [[TMP10]], i32 0
-; TFFALLBACK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
-; TFFALLBACK: middle.block:
-; TFFALLBACK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFFALLBACK: scalar.ph:
-; TFFALLBACK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFFALLBACK-NEXT: br label [[FOR_BODY:%.*]]
-; TFFALLBACK: for.body:
-; TFFALLBACK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
-; TFFALLBACK-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFFALLBACK-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR4:[0-9]+]]
-; TFFALLBACK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
-; TFFALLBACK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFFALLBACK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFFALLBACK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
-; TFFALLBACK: for.cond.cleanup:
-; TFFALLBACK-NEXT: ret void
+; TFCOMMON-LABEL: @test_widen(
+; TFCOMMON-NEXT: entry:
+; TFCOMMON-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFCOMMON-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFCOMMON-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
+; TFCOMMON-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
+; TFCOMMON-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; TFCOMMON-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
+; TFCOMMON-NEXT: br label [[VECTOR_BODY:%.*]]
+; TFCOMMON: vector.body:
+; TFCOMMON-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFCOMMON-NEXT: [[TMP5:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDEX]]
+; TFCOMMON-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; TFCOMMON-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TFCOMMON-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; TFCOMMON-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP6]], ptr [[TMP7]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TFCOMMON-NEXT: [[TMP8:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP9:%.*]] = mul i64 [[TMP8]], 2
+; TFCOMMON-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP9]]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
+; TFCOMMON-NEXT: [[TMP10:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP11:%.*]] = extractelement <vscale x 2 x i1> [[TMP10]], i32 0
+; TFCOMMON-NEXT: br i1 [[TMP11]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; TFCOMMON: for.cond.cleanup:
+; TFCOMMON-NEXT: ret void
;
entry:
br label %for.body
@@ -203,7 +139,7 @@ define void @test_if_then(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE-NEXT: [[CMP:%.*]] = icmp ugt i64 [[TMP12]], 50
; TFNONE-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END]]
; TFNONE: if.then:
-; TFNONE-NEXT: [[TMP13:%.*]] = call i64 @foo(i64 [[TMP12]]) #[[ATTR2]]
+; TFNONE-NEXT: [[TMP13:%.*]] = call i64 @foo(i64 [[TMP12]]) #[[ATTR3]]
; TFNONE-NEXT: br label [[IF_END]]
; TFNONE: if.end:
; TFNONE-NEXT: [[TMP14:%.*]] = phi i64 [ [[TMP13]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
@@ -215,123 +151,41 @@ define void @test_if_then(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE: for.cond.cleanup:
; TFNONE-NEXT: ret void
;
-; TFALWAYS-LABEL: @test_if_then(
-; TFALWAYS-NEXT: entry:
-; TFALWAYS-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFALWAYS: vector.ph:
-; TFALWAYS-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFALWAYS-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
-; TFALWAYS-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
-; TFALWAYS-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
-; TFALWAYS-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; TFALWAYS-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
-; TFALWAYS-NEXT: br label [[VECTOR_BODY:%.*]]
-; TFALWAYS: vector.body:
-; TFALWAYS-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; TFALWAYS-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; TFALWAYS-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 50, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP7:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i1> zeroinitializer
-; TFALWAYS-NEXT: [[TMP8:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[TMP7]])
-; TFALWAYS-NEXT: [[TMP9:%.*]] = xor <vscale x 2 x i1> [[TMP6]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i1> zeroinitializer
-; TFALWAYS-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP10]], <vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> [[TMP8]]
-; TFALWAYS-NEXT: [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
-; TFALWAYS-NEXT: [[TMP12:%.*]] = or <vscale x 2 x i1> [[TMP7]], [[TMP10]]
-; TFALWAYS-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[PREDPHI]], ptr [[TMP11]], i32 8, <vscale x 2 x i1> [[TMP12]])
-; TFALWAYS-NEXT: [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP14:%.*]] = mul i64 [[TMP13]], 2
-; TFALWAYS-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP14]]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
-; TFALWAYS-NEXT: [[TMP15:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP16:%.*]] = extractelement <vscale x 2 x i1> [[TMP15]], i32 0
-; TFALWAYS-NEXT: br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
-; TFALWAYS: middle.block:
-; TFALWAYS-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFALWAYS: scalar.ph:
-; TFALWAYS-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFALWAYS-NEXT: br label [[FOR_BODY:%.*]]
-; TFALWAYS: for.body:
-; TFALWAYS-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; TFALWAYS-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: [[TMP17:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
-; TFALWAYS-NEXT: [[CMP:%.*]] = icmp ugt i64 [[TMP17]], 50
-; TFALWAYS-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END]]
-; TFALWAYS: if.then:
-; TFALWAYS-NEXT: [[TMP18:%.*]] = call i64 @foo(i64 [[TMP17]]) #[[ATTR4]]
-; TFALWAYS-NEXT: br label [[IF_END]]
-; TFALWAYS: if.end:
-; TFALWAYS-NEXT: [[TMP19:%.*]] = phi i64 [ [[TMP18]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
-; TFALWAYS-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: store i64 [[TMP19]], ptr [[ARRAYIDX1]], align 8
-; TFALWAYS-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFALWAYS-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFALWAYS-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
-; TFALWAYS: for.cond.cleanup:
-; TFALWAYS-NEXT: ret void
-;
-; TFFALLBACK-LABEL: @test_if_then(
-; TFFALLBACK-NEXT: entry:
-; TFFALLBACK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFFALLBACK: vector.ph:
-; TFFALLBACK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFFALLBACK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
-; TFFALLBACK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
-; TFFALLBACK-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
-; TFFALLBACK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; TFFALLBACK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
-; TFFALLBACK-NEXT: br label [[VECTOR_BODY:%.*]]
-; TFFALLBACK: vector.body:
-; TFFALLBACK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; TFFALLBACK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; TFFALLBACK-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 50, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP7:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i1> zeroinitializer
-; TFFALLBACK-NEXT: [[TMP8:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[TMP7]])
-; TFFALLBACK-NEXT: [[TMP9:%.*]] = xor <vscale x 2 x i1> [[TMP6]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i1> zeroinitializer
-; TFFALLBACK-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP10]], <vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> [[TMP8]]
-; TFFALLBACK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
-; TFFALLBACK-NEXT: [[TMP12:%.*]] = or <vscale x 2 x i1> [[TMP7]], [[TMP10]]
-; TFFALLBACK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[PREDPHI]], ptr [[TMP11]], i32 8, <vscale x 2 x i1> [[TMP12]])
-; TFFALLBACK-NEXT: [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP14:%.*]] = mul i64 [[TMP13]], 2
-; TFFALLBACK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP14]]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
-; TFFALLBACK-NEXT: [[TMP15:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP16:%.*]] = extractelement <vscale x 2 x i1> [[TMP15]], i32 0
-; TFFALLBACK-NEXT: br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
-; TFFALLBACK: middle.block:
-; TFFALLBACK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFFALLBACK: scalar.ph:
-; TFFALLBACK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFFALLBACK-NEXT: br label [[FOR_BODY:%.*]]
-; TFFALLBACK: for.body:
-; TFFALLBACK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; TFFALLBACK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: [[TMP17:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
-; TFFALLBACK-NEXT: [[CMP:%.*]] = icmp ugt i64 [[TMP17]], 50
-; TFFALLBACK-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END]]
-; TFFALLBACK: if.then:
-; TFFALLBACK-NEXT: [[TMP18:%.*]] = call i64 @foo(i64 [[TMP17]]) #[[ATTR4]]
-; TFFALLBACK-NEXT: br label [[IF_END]]
-; TFFALLBACK: if.end:
-; TFFALLBACK-NEXT: [[TMP19:%.*]] = phi i64 [ [[TMP18]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
-; TFFALLBACK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: store i64 [[TMP19]], ptr [[ARRAYIDX1]], align 8
-; TFFALLBACK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFFALLBACK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFFALLBACK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
-; TFFALLBACK: for.cond.cleanup:
-; TFFALLBACK-NEXT: ret void
+; TFCOMMON-LABEL: @test_if_then(
+; TFCOMMON-NEXT: entry:
+; TFCOMMON-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFCOMMON-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFCOMMON-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
+; TFCOMMON-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
+; TFCOMMON-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; TFCOMMON-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
+; TFCOMMON-NEXT: br label [[VECTOR_BODY:%.*]]
+; TFCOMMON: vector.body:
+; TFCOMMON-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFCOMMON-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; TFCOMMON-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; TFCOMMON-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 50, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP7:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i1> zeroinitializer
+; TFCOMMON-NEXT: [[TMP8:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[TMP7]])
+; TFCOMMON-NEXT: [[TMP9:%.*]] = xor <vscale x 2 x i1> [[TMP6]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i1> zeroinitializer
+; TFCOMMON-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP10]], <vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> [[TMP8]]
+; TFCOMMON-NEXT: [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
+; TFCOMMON-NEXT: [[TMP12:%.*]] = or <vscale x 2 x i1> [[TMP7]], [[TMP10]]
+; TFCOMMON-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[PREDPHI]], ptr [[TMP11]], i32 8, <vscale x 2 x i1> [[TMP12]])
+; TFCOMMON-NEXT: [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP14:%.*]] = mul i64 [[TMP13]], 2
+; TFCOMMON-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP14]]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
+; TFCOMMON-NEXT: [[TMP15:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP16:%.*]] = extractelement <vscale x 2 x i1> [[TMP15]], i32 0
+; TFCOMMON-NEXT: br i1 [[TMP16]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; TFCOMMON: for.cond.cleanup:
+; TFCOMMON-NEXT: ret void
;
entry:
br label %for.body
@@ -404,10 +258,10 @@ define void @test_widen_if_then_else(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE-NEXT: [[CMP:%.*]] = icmp ugt i64 [[TMP13]], 50
; TFNONE-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
; TFNONE: if.then:
-; TFNONE-NEXT: [[TMP14:%.*]] = call i64 @foo(i64 [[TMP13]]) #[[ATTR3:[0-9]+]]
+; TFNONE-NEXT: [[TMP14:%.*]] = call i64 @foo(i64 [[TMP13]]) #[[ATTR4:[0-9]+]]
; TFNONE-NEXT: br label [[IF_END]]
; TFNONE: if.else:
-; TFNONE-NEXT: [[TMP15:%.*]] = call i64 @foo(i64 0) #[[ATTR3]]
+; TFNONE-NEXT: [[TMP15:%.*]] = call i64 @foo(i64 0) #[[ATTR4]]
; TFNONE-NEXT: br label [[IF_END]]
; TFNONE: if.end:
; TFNONE-NEXT: [[TMP16:%.*]] = phi i64 [ [[TMP14]], [[IF_THEN]] ], [ [[TMP15]], [[IF_ELSE]] ]
@@ -419,131 +273,42 @@ define void @test_widen_if_then_else(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE: for.cond.cleanup:
; TFNONE-NEXT: ret void
;
-; TFALWAYS-LABEL: @test_widen_if_then_else(
-; TFALWAYS-NEXT: entry:
-; TFALWAYS-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFALWAYS: vector.ph:
-; TFALWAYS-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFALWAYS-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
-; TFALWAYS-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
-; TFALWAYS-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
-; TFALWAYS-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; TFALWAYS-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
-; TFALWAYS-NEXT: br label [[VECTOR_BODY:%.*]]
-; TFALWAYS: vector.body:
-; TFALWAYS-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; TFALWAYS-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; TFALWAYS-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 50, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP7:%.*]] = xor <vscale x 2 x i1> [[TMP6]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP8:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP7]], <vscale x 2 x i1> zeroinitializer
-; TFALWAYS-NEXT: [[TMP9:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i1> [[TMP8]])
-; TFALWAYS-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i1> zeroinitializer
-; TFALWAYS-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[TMP10]])
-; TFALWAYS-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP8]], <vscale x 2 x i64> [[TMP9]], <vscale x 2 x i64> [[TMP11]]
-; TFALWAYS-NEXT: [[TMP12:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
-; TFALWAYS-NEXT: [[TMP13:%.*]] = or <vscale x 2 x i1> [[TMP8]], [[TMP10]]
-; TFALWAYS-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[PREDPHI]], ptr [[TMP12]], i32 8, <vscale x 2 x i1> [[TMP13]])
-; TFALWAYS-NEXT: [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
-; TFALWAYS-NEXT: [[TMP15:%.*]] = mul i64 [[TMP14]], 2
-; TFALWAYS-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP15]]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
-; TFALWAYS-NEXT: [[TMP16:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFALWAYS-NEXT: [[TMP17:%.*]] = extractelement <vscale x 2 x i1> [[TMP16]], i32 0
-; TFALWAYS-NEXT: br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
-; TFALWAYS: middle.block:
-; TFALWAYS-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFALWAYS: scalar.ph:
-; TFALWAYS-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFALWAYS-NEXT: br label [[FOR_BODY:%.*]]
-; TFALWAYS: for.body:
-; TFALWAYS-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; TFALWAYS-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: [[TMP18:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
-; TFALWAYS-NEXT: [[CMP:%.*]] = icmp ugt i64 [[TMP18]], 50
-; TFALWAYS-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
-; TFALWAYS: if.then:
-; TFALWAYS-NEXT: [[TMP19:%.*]] = call i64 @foo(i64 [[TMP18]]) #[[ATTR5:[0-9]+]]
-; TFALWAYS-NEXT: br label [[IF_END]]
-; TFALWAYS: if.else:
-; TFALWAYS-NEXT: [[TMP20:%.*]] = call i64 @foo(i64 0) #[[ATTR5]]
-; TFALWAYS-NEXT: br label [[IF_END]]
-; TFALWAYS: if.end:
-; TFALWAYS-NEXT: [[TMP21:%.*]] = phi i64 [ [[TMP19]], [[IF_THEN]] ], [ [[TMP20]], [[IF_ELSE]] ]
-; TFALWAYS-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: store i64 [[TMP21]], ptr [[ARRAYIDX1]], align 8
-; TFALWAYS-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFALWAYS-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFALWAYS-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
-; TFALWAYS: for.cond.cleanup:
-; TFALWAYS-NEXT: ret void
-;
-; TFFALLBACK-LABEL: @test_widen_if_then_else(
-; TFFALLBACK-NEXT: entry:
-; TFFALLBACK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFFALLBACK: vector.ph:
-; TFFALLBACK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFFALLBACK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
-; TFFALLBACK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
-; TFFALLBACK-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
-; TFFALLBACK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
-; TFFALLBACK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
-; TFFALLBACK-NEXT: br label [[VECTOR_BODY:%.*]]
-; TFFALLBACK: vector.body:
-; TFFALLBACK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; TFFALLBACK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; TFFALLBACK-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 50, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP7:%.*]] = xor <vscale x 2 x i1> [[TMP6]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP8:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP7]], <vscale x 2 x i1> zeroinitializer
-; TFFALLBACK-NEXT: [[TMP9:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i1> [[TMP8]])
-; TFFALLBACK-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i1> zeroinitializer
-; TFFALLBACK-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[TMP10]])
-; TFFALLBACK-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP8]], <vscale x 2 x i64> [[TMP9]], <vscale x 2 x i64> [[TMP11]]
-; TFFALLBACK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
-; TFFALLBACK-NEXT: [[TMP13:%.*]] = or <vscale x 2 x i1> [[TMP8]], [[TMP10]]
-; TFFALLBACK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[PREDPHI]], ptr [[TMP12]], i32 8, <vscale x 2 x i1> [[TMP13]])
-; TFFALLBACK-NEXT: [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT: [[TMP15:%.*]] = mul i64 [[TMP14]], 2
-; TFFALLBACK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP15]]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
-; TFFALLBACK-NEXT: [[TMP16:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
-; TFFALLBACK-NEXT: [[TMP17:%.*]] = extractelement <vscale x 2 x i1> [[TMP16]], i32 0
-; TFFALLBACK-NEXT: br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
-; TFFALLBACK: middle.block:
-; TFFALLBACK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFFALLBACK: scalar.ph:
-; TFFALLBACK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFFALLBACK-NEXT: br label [[FOR_BODY:%.*]]
-; TFFALLBACK: for.body:
-; TFFALLBACK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; TFFALLBACK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: [[TMP18:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
-; TFFALLBACK-NEXT: [[CMP:%.*]] = icmp ugt i64 [[TMP18]], 50
-; TFFALLBACK-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
-; TFFALLBACK: if.then:
-; TFFALLBACK-NEXT: [[TMP19:%.*]] = call i64 @foo(i64 [[TMP18]]) #[[ATTR5:[0-9]+]]
-; TFFALLBACK-NEXT: br label [[IF_END]]
-; TFFALLBACK: if.else:
-; TFFALLBACK-NEXT: [[TMP20:%.*]] = call i64 @foo(i64 0) #[[ATTR5]]
-; TFFALLBACK-NEXT: br label [[IF_END]]
-; TFFALLBACK: if.end:
-; TFFALLBACK-NEXT: [[TMP21:%.*]] = phi i64 [ [[TMP19]], [[IF_THEN]] ], [ [[TMP20]], [[IF_ELSE]] ]
-; TFFALLBACK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: store i64 [[TMP21]], ptr [[ARRAYIDX1]], align 8
-; TFFALLBACK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFFALLBACK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFFALLBACK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
-; TFFALLBACK: for.cond.cleanup:
-; TFFALLBACK-NEXT: ret void
+; TFCOMMON-LABEL: @test_widen_if_then_else(
+; TFCOMMON-NEXT: entry:
+; TFCOMMON-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFCOMMON-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFCOMMON-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
+; TFCOMMON-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
+; TFCOMMON-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; TFCOMMON-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
+; TFCOMMON-NEXT: br label [[VECTOR_BODY:%.*]]
+; TFCOMMON: vector.body:
+; TFCOMMON-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFCOMMON-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; TFCOMMON-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; TFCOMMON-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 50, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP7:%.*]] = xor <vscale x 2 x i1> [[TMP6]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP8:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP7]], <vscale x 2 x i1> zeroinitializer
+; TFCOMMON-NEXT: [[TMP9:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i1> [[TMP8]])
+; TFCOMMON-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP6]], <vscale x 2 x i1> zeroinitializer
+; TFCOMMON-NEXT: [[TMP11:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[TMP10]])
+; TFCOMMON-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP8]], <vscale x 2 x i64> [[TMP9]], <vscale x 2 x i64> [[TMP11]]
+; TFCOMMON-NEXT: [[TMP12:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
+; TFCOMMON-NEXT: [[TMP13:%.*]] = or <vscale x 2 x i1> [[TMP8]], [[TMP10]]
+; TFCOMMON-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[PREDPHI]], ptr [[TMP12]], i32 8, <vscale x 2 x i1> [[TMP13]])
+; TFCOMMON-NEXT: [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
+; TFCOMMON-NEXT: [[TMP15:%.*]] = mul i64 [[TMP14]], 2
+; TFCOMMON-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP15]]
+; TFCOMMON-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
+; TFCOMMON-NEXT: [[TMP16:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFCOMMON-NEXT: [[TMP17:%.*]] = extractelement <vscale x 2 x i1> [[TMP16]], i32 0
+; TFCOMMON-NEXT: br i1 [[TMP17]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; TFCOMMON: for.cond.cleanup:
+; TFCOMMON-NEXT: ret void
;
entry:
br label %for.body
@@ -612,7 +377,7 @@ define void @test_widen_nomask(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; TFNONE-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
; TFNONE-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR4:[0-9]+]]
+; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
; TFNONE-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
; TFNONE-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
; TFNONE-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
@@ -628,7 +393,7 @@ define void @test_widen_nomask(ptr noalias %a, ptr readnone %b) #4 {
; TFALWAYS-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; TFALWAYS-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDVARS_IV]]
; TFALWAYS-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFALWAYS-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR6:[0-9]+]]
+; TFALWAYS-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
; TFALWAYS-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDVARS_IV]]
; TFALWAYS-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
; TFALWAYS-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
@@ -660,22 +425,20 @@ define void @test_widen_nomask(ptr noalias %a, ptr readnone %b) #4 {
; TFFALLBACK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 2
; TFFALLBACK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP8]]
; TFFALLBACK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TFFALLBACK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
-; TFFALLBACK: middle.block:
-; TFFALLBACK-NEXT: br i1 false, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFFALLBACK-NEXT: br i1 [[TMP9]], label [[SCALAR_PH]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; TFFALLBACK: scalar.ph:
-; TFFALLBACK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFFALLBACK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[N_VEC]], [[VECTOR_BODY]] ]
; TFFALLBACK-NEXT: br label [[FOR_BODY:%.*]]
; TFFALLBACK: for.body:
; TFFALLBACK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; TFFALLBACK-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
; TFFALLBACK-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFFALLBACK-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR6:[0-9]+]]
+; TFFALLBACK-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
; TFFALLBACK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
; TFFALLBACK-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
; TFFALLBACK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; TFFALLBACK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFFALLBACK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; TFFALLBACK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; TFFALLBACK: for.cond.cleanup:
; TFFALLBACK-NEXT: ret void
;
@@ -734,7 +497,7 @@ define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
; TFNONE-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; TFNONE-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
; TFNONE-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
+; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR6:[0-9]+]]
; TFNONE-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
; TFNONE-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
; TFNONE-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
@@ -745,8 +508,6 @@ define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
;
; TFALWAYS-LABEL: @test_widen_optmask(
; TFALWAYS-NEXT: entry:
-; TFALWAYS-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFALWAYS: vector.ph:
; TFALWAYS-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; TFALWAYS-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; TFALWAYS-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
@@ -758,8 +519,8 @@ define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
; TFALWAYS-NEXT: br label [[VECTOR_BODY:%.*]]
; TFALWAYS: vector.body:
-; TFALWAYS-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFALWAYS-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; TFALWAYS-NEXT: [[TMP5:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDEX]]
; TFALWAYS-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
; TFALWAYS-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
@@ -771,29 +532,12 @@ define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
; TFALWAYS-NEXT: [[TMP10:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
; TFALWAYS-NEXT: [[TMP11:%.*]] = extractelement <vscale x 2 x i1> [[TMP10]], i32 0
-; TFALWAYS-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
-; TFALWAYS: middle.block:
-; TFALWAYS-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFALWAYS: scalar.ph:
-; TFALWAYS-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFALWAYS-NEXT: br label [[FOR_BODY:%.*]]
-; TFALWAYS: for.body:
-; TFALWAYS-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
-; TFALWAYS-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFALWAYS-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR7:[0-9]+]]
-; TFALWAYS-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFALWAYS-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
-; TFALWAYS-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFALWAYS-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFALWAYS-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; TFALWAYS-NEXT: br i1 [[TMP11]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; TFALWAYS: for.cond.cleanup:
; TFALWAYS-NEXT: ret void
;
; TFFALLBACK-LABEL: @test_widen_optmask(
; TFFALLBACK-NEXT: entry:
-; TFFALLBACK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFFALLBACK: vector.ph:
; TFFALLBACK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; TFFALLBACK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; TFFALLBACK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
@@ -805,8 +549,8 @@ define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
; TFFALLBACK-NEXT: br label [[VECTOR_BODY:%.*]]
; TFFALLBACK: vector.body:
-; TFFALLBACK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; TFFALLBACK-NEXT: [[TMP5:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDEX]]
; TFFALLBACK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP5]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
; TFFALLBACK-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
@@ -818,22 +562,7 @@ define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
; TFFALLBACK-NEXT: [[TMP10:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
; TFFALLBACK-NEXT: [[TMP11:%.*]] = extractelement <vscale x 2 x i1> [[TMP10]], i32 0
-; TFFALLBACK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
-; TFFALLBACK: middle.block:
-; TFFALLBACK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
-; TFFALLBACK: scalar.ph:
-; TFFALLBACK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; TFFALLBACK-NEXT: br label [[FOR_BODY:%.*]]
-; TFFALLBACK: for.body:
-; TFFALLBACK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
-; TFFALLBACK-NEXT: [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: [[LOAD:%.*]] = load i64, ptr [[GEP]], align 4
-; TFFALLBACK-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR7:[0-9]+]]
-; TFFALLBACK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
-; TFFALLBACK-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
-; TFFALLBACK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; TFFALLBACK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
-; TFFALLBACK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; TFFALLBACK-NEXT: br i1 [[TMP11]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; TFFALLBACK: for.cond.cleanup:
; TFFALLBACK-NEXT: ret void
;
@@ -855,7 +584,160 @@ for.cond.cleanup:
ret void
}
+
+; An fmuladd intrinsic followed by a call; we want to make sure we correctly
+; pick up the second call and assign a vector variant to it.
+define double @test_widen_fmuladd_and_call(ptr noalias %a, ptr readnone %b, double %m) #4 {
+; TFNONE-LABEL: @test_widen_fmuladd_and_call(
+; TFNONE-NEXT: entry:
+; TFNONE-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFNONE-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
+; TFNONE-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE: vector.ph:
+; TFNONE-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFNONE-NEXT: [[N_MOD_VF:%.*]] = urem i64 1025, [[TMP3]]
+; TFNONE-NEXT: [[N_VEC:%.*]] = sub i64 1025, [[N_MOD_VF]]
+; TFNONE-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[M:%.*]], i64 0
+; TFNONE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x double> [[BROADCAST_SPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+; TFNONE-NEXT: br label [[VECTOR_BODY:%.*]]
+; TFNONE: vector.body:
+; TFNONE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFNONE-NEXT: [[VEC_PHI:%.*]] = phi double [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
+; TFNONE-NEXT: [[TMP4:%.*]] = getelementptr double, ptr [[B:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 2 x double>, ptr [[TMP4]], align 8
+; TFNONE-NEXT: [[TMP5:%.*]] = fmul <vscale x 2 x double> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
+; TFNONE-NEXT: [[TMP6:%.*]] = fptoui <vscale x 2 x double> [[WIDE_LOAD]] to <vscale x 2 x i64>
+; TFNONE-NEXT: [[TMP7:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[TMP6]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; TFNONE-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; TFNONE-NEXT: store <vscale x 2 x i64> [[TMP7]], ptr [[TMP8]], align 4
+; TFNONE-NEXT: [[TMP9]] = call double @llvm.vector.reduce.fadd.nxv2f64(double [[VEC_PHI]], <vscale x 2 x double> [[TMP5]])
+; TFNONE-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; TFNONE-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 2
+; TFNONE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
+; TFNONE-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; TFNONE-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; TFNONE: middle.block:
+; TFNONE-NEXT: br i1 false, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
+; TFNONE: scalar.ph:
+; TFNONE-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; TFNONE-NEXT: [[BC_MERGE_RDX:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[TMP9]], [[MIDDLE_BLOCK]] ]
+; TFNONE-NEXT: br label [[FOR_BODY:%.*]]
+; TFNONE: for.body:
+; TFNONE-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFNONE-NEXT: [[FMA_SUM:%.*]] = phi double [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[MULADD:%.*]], [[FOR_BODY]] ]
+; TFNONE-NEXT: [[GEP:%.*]] = getelementptr double, ptr [[B]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT: [[LOAD:%.*]] = load double, ptr [[GEP]], align 8
+; TFNONE-NEXT: [[MULADD]] = tail call double @llvm.fmuladd.f64(double [[LOAD]], double [[M]], double [[FMA_SUM]])
+; TFNONE-NEXT: [[TOINT:%.*]] = fptoui double [[LOAD]] to i64
+; TFNONE-NEXT: [[CALL:%.*]] = call i64 @foo(i64 [[TOINT]]) #[[ATTR3]]
+; TFNONE-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDVARS_IV]]
+; TFNONE-NEXT: store i64 [[CALL]], ptr [[ARRAYIDX]], align 4
+; TFNONE-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; TFNONE-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1025
+; TFNONE-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; TFNONE: for.cond.cleanup:
+; TFNONE-NEXT: [[MULADD_LCSSA:%.*]] = phi double [ [[MULADD]], [[FOR_BODY]] ], [ [[TMP9]], [[MIDDLE_BLOCK]] ]
+; TFNONE-NEXT: ret double [[MULADD_LCSSA]]
+;
+; TFALWAYS-LABEL: @test_widen_fmuladd_and_call(
+; TFALWAYS-NEXT: entry:
+; TFALWAYS-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFALWAYS-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFALWAYS-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFALWAYS-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFALWAYS-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
+; TFALWAYS-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
+; TFALWAYS-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; TFALWAYS-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
+; TFALWAYS-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[M:%.*]], i64 0
+; TFALWAYS-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x double> [[BROADCAST_SPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+; TFALWAYS-NEXT: br label [[VECTOR_BODY:%.*]]
+; TFALWAYS: vector.body:
+; TFALWAYS-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFALWAYS-NEXT: [[VEC_PHI:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
+; TFALWAYS-NEXT: [[TMP5:%.*]] = getelementptr double, ptr [[B:%.*]], i64 [[INDEX]]
+; TFALWAYS-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x double> poison)
+; TFALWAYS-NEXT: [[TMP6:%.*]] = fmul <vscale x 2 x double> [[WIDE_MASKED_LOAD]], [[BROADCAST_SPLAT]]
+; TFALWAYS-NEXT: [[TMP7:%.*]] = fptoui <vscale x 2 x double> [[WIDE_MASKED_LOAD]] to <vscale x 2 x i64>
+; TFALWAYS-NEXT: [[TMP8:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[TMP7]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TFALWAYS-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; TFALWAYS-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP8]], ptr [[TMP9]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TFALWAYS-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x double> [[TMP6]], <vscale x 2 x double> shufflevector (<vscale x 2 x double> insertelement (<vscale x 2 x double> poison, double -0.000000e+00, i64 0), <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer)
+; TFALWAYS-NEXT: [[TMP11]] = call double @llvm.vector.reduce.fadd.nxv2f64(double [[VEC_PHI]], <vscale x 2 x double> [[TMP10]])
+; TFALWAYS-NEXT: [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
+; TFALWAYS-NEXT: [[TMP13:%.*]] = mul i64 [[TMP12]], 2
+; TFALWAYS-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP13]]
+; TFALWAYS-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
+; TFALWAYS-NEXT: [[TMP14:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFALWAYS-NEXT: [[TMP15:%.*]] = extractelement <vscale x 2 x i1> [[TMP14]], i32 0
+; TFALWAYS-NEXT: br i1 [[TMP15]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; TFALWAYS: for.cond.cleanup:
+; TFALWAYS-NEXT: ret double [[TMP11]]
+;
+; TFFALLBACK-LABEL: @test_widen_fmuladd_and_call(
+; TFFALLBACK-NEXT: entry:
+; TFFALLBACK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
+; TFFALLBACK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; TFFALLBACK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
+; TFFALLBACK-NEXT: [[N_RND_UP:%.*]] = add i64 1025, [[TMP4]]
+; TFFALLBACK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; TFFALLBACK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 0, i64 1025)
+; TFFALLBACK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[M:%.*]], i64 0
+; TFFALLBACK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x double> [[BROADCAST_SPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+; TFFALLBACK-NEXT: br label [[VECTOR_BODY:%.*]]
+; TFFALLBACK: vector.body:
+; TFFALLBACK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 2 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[ENTRY]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT: [[VEC_PHI:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT: [[TMP5:%.*]] = getelementptr double, ptr [[B:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0(ptr [[TMP5]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x double> poison)
+; TFFALLBACK-NEXT: [[TMP6:%.*]] = fmul <vscale x 2 x double> [[WIDE_MASKED_LOAD]], [[BROADCAST_SPLAT]]
+; TFFALLBACK-NEXT: [[TMP7:%.*]] = fptoui <vscale x 2 x double> [[WIDE_MASKED_LOAD]] to <vscale x 2 x i64>
+; TFFALLBACK-NEXT: [[TMP8:%.*]] = call <vscale x 2 x i64> @foo_vector(<vscale x 2 x i64> [[TMP7]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TFFALLBACK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; TFFALLBACK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP8]], ptr [[TMP9]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TFFALLBACK-NEXT: [[TMP10:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x double> [[TMP6]], <vscale x 2 x double> shufflevector (<vscale x 2 x double> insertelement (<vscale x 2 x double> poison, double -0.000000e+00, i64 0), <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer)
+; TFFALLBACK-NEXT: [[TMP11]] = call double @llvm.vector.reduce.fadd.nxv2f64(double [[VEC_PHI]], <vscale x 2 x double> [[TMP10]])
+; TFFALLBACK-NEXT: [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
+; TFFALLBACK-NEXT: [[TMP13:%.*]] = mul i64 [[TMP12]], 2
+; TFFALLBACK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP13]]
+; TFFALLBACK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX_NEXT]], i64 1025)
+; TFFALLBACK-NEXT: [[TMP14:%.*]] = xor <vscale x 2 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer)
+; TFFALLBACK-NEXT: [[TMP15:%.*]] = extractelement <vscale x 2 x i1> [[TMP14]], i32 0
+; TFFALLBACK-NEXT: br i1 [[TMP15]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; TFFALLBACK: for.cond.cleanup:
+; TFFALLBACK-NEXT: ret double [[TMP11]]
+;
+entry:
+ br label %for.body
+
+for.body:
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %fma_sum = phi double [ 0.000000e+00, %entry ], [ %muladd, %for.body ]
+ %gep = getelementptr double, ptr %b, i64 %indvars.iv
+ %load = load double, ptr %gep
+ %muladd = tail call double @llvm.fmuladd.f64(double %load, double %m, double %fma_sum)
+ %toint = fptoui double %load to i64
+ %call = call i64 @foo(i64 %toint) #1
+ %arrayidx = getelementptr inbounds i64, ptr %a, i64 %indvars.iv
+ store i64 %call, ptr %arrayidx
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %exitcond = icmp eq i64 %indvars.iv.next, 1025
+ br i1 %exitcond, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup:
+ ret double %muladd
+}
+
declare i64 @foo(i64)
+declare double @llvm.fmuladd.f64(double, double, double)
;; scalable vector variants of foo
declare <vscale x 2 x i64> @foo_uniform(i64, <vscale x 2 x i1>)
More information about the llvm-commits
mailing list