; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes=loop-vectorize < %s -mcpu=skylake | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:10:11:12:13"
target triple = "x86_64-unknown-linux-gnu"
@jlplt_ijl_alloc_array_1d_10294_got = external dso_local local_unnamed_addr global ptr
define ptr addrspace(10) @japi1_vect_42283(ptr nocapture readonly %0, i32 %1) local_unnamed_addr #0 {
; CHECK-LABEL: @japi1_vect_42283(
; CHECK-NEXT: top:
; CHECK-NEXT: [[TMP2:%.*]] = sext i32 [[TMP1:%.*]] to i64
; CHECK-NEXT: [[TMP3:%.*]] = load atomic ptr, ptr @jlplt_ijl_alloc_array_1d_10294_got unordered, align 8
; CHECK-NEXT: [[TMP4:%.*]] = tail call ptr addrspace(10) [[TMP3]](ptr addrspace(10) null, i64 0)
; CHECK-NEXT: [[TMP5:%.*]] = load ptr addrspace(10), ptr [[TMP0:%.*]], align 8, !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: [[TMP6:%.*]] = addrspacecast ptr addrspace(10) [[TMP4]] to ptr addrspace(11)
; CHECK-NEXT: [[TMP7:%.*]] = load ptr addrspace(13), ptr addrspace(11) [[TMP6]], align 8, !tbaa [[TBAA5:![0-9]+]]
; CHECK-NEXT: [[DOTELT:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(10) [[TMP5]], i64 0, i32 0
; CHECK-NEXT: [[DOTUNPACK:%.*]] = load ptr addrspace(10), ptr addrspace(10) [[DOTELT]], align 8, !tbaa [[TBAA8:![0-9]+]]
; CHECK-NEXT: [[DOTELT1:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(10) [[TMP5]], i64 0, i32 1
; CHECK-NEXT: [[DOTUNPACK2:%.*]] = load i64, ptr addrspace(10) [[DOTELT1]], align 8, !tbaa [[TBAA8]]
; CHECK-NEXT: [[TMP8:%.*]] = add nsw i64 [[TMP2]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP8]], 60
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK: vector.scevcheck:
; CHECK-NEXT: [[MUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[TMP2]])
; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i64, i1 } [[MUL]], 0
; CHECK-NEXT: [[MUL_OVERFLOW:%.*]] = extractvalue { i64, i1 } [[MUL]], 1
; CHECK-NEXT: [[TMP9:%.*]] = sub i64 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr i8, ptr addrspace(13) [[TMP7]], i64 [[MUL_RESULT]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp ult ptr addrspace(13) [[TMP10]], [[TMP7]]
; CHECK-NEXT: [[TMP12:%.*]] = or i1 [[TMP11]], [[MUL_OVERFLOW]]
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr addrspace(13) [[TMP7]], i64 8
; CHECK-NEXT: [[MUL1:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[TMP2]])
; CHECK-NEXT: [[MUL_RESULT2:%.*]] = extractvalue { i64, i1 } [[MUL1]], 0
; CHECK-NEXT: [[MUL_OVERFLOW3:%.*]] = extractvalue { i64, i1 } [[MUL1]], 1
; CHECK-NEXT: [[TMP13:%.*]] = sub i64 0, [[MUL_RESULT2]]
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr i8, ptr addrspace(13) [[SCEVGEP]], i64 [[MUL_RESULT2]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ult ptr addrspace(13) [[TMP14]], [[SCEVGEP]]
; CHECK-NEXT: [[TMP16:%.*]] = or i1 [[TMP15]], [[MUL_OVERFLOW3]]
; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP12]], [[TMP16]]
; CHECK-NEXT: br i1 [[TMP17]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP8]], 16
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP8]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr addrspace(10)> poison, ptr addrspace(10) [[DOTUNPACK]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr addrspace(10)> [[BROADCAST_SPLATINSERT]], <4 x ptr addrspace(10)> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <4 x i64> poison, i64 [[DOTUNPACK2]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT8:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT7]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[STEP_ADD:%.*]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT: [[STEP_ADD4:%.*]] = add <4 x i64> [[STEP_ADD]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT: [[STEP_ADD5:%.*]] = add <4 x i64> [[STEP_ADD4]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[VEC_IND]], i32 0
; CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[STEP_ADD]], i32 0
; CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[STEP_ADD4]], i32 0
; CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[STEP_ADD5]], i32 0
; CHECK-NEXT: call void @llvm.masked.scatter.v4p10.v4p13(<4 x ptr addrspace(10)> [[BROADCAST_SPLAT]], <4 x ptr addrspace(13)> [[TMP18]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10:![0-9]+]]
; CHECK-NEXT: call void @llvm.masked.scatter.v4p10.v4p13(<4 x ptr addrspace(10)> [[BROADCAST_SPLAT]], <4 x ptr addrspace(13)> [[TMP19]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: call void @llvm.masked.scatter.v4p10.v4p13(<4 x ptr addrspace(10)> [[BROADCAST_SPLAT]], <4 x ptr addrspace(13)> [[TMP20]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: call void @llvm.masked.scatter.v4p10.v4p13(<4 x ptr addrspace(10)> [[BROADCAST_SPLAT]], <4 x ptr addrspace(13)> [[TMP21]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[VEC_IND]], i32 1
; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[STEP_ADD]], i32 1
; CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[STEP_ADD4]], i32 1
; CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], <4 x i64> [[STEP_ADD5]], i32 1
; CHECK-NEXT: call void @llvm.masked.scatter.v4i64.v4p13(<4 x i64> [[BROADCAST_SPLAT8]], <4 x ptr addrspace(13)> [[TMP22]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: call void @llvm.masked.scatter.v4i64.v4p13(<4 x i64> [[BROADCAST_SPLAT8]], <4 x ptr addrspace(13)> [[TMP23]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: call void @llvm.masked.scatter.v4i64.v4p13(<4 x i64> [[BROADCAST_SPLAT8]], <4 x ptr addrspace(13)> [[TMP24]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: call void @llvm.masked.scatter.v4i64.v4p13(<4 x i64> [[BROADCAST_SPLAT8]], <4 x ptr addrspace(13)> [[TMP25]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>), !tbaa [[TBAA10]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[STEP_ADD5]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT: [[TMP26:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP26]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP8]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[L44:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[TOP:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
; CHECK-NEXT: br label [[L26:%.*]]
; CHECK: L26:
; CHECK-NEXT: [[VALUE_PHI5:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[TMP27:%.*]], [[L26]] ]
; CHECK-NEXT: [[DOTREPACK:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], i64 [[VALUE_PHI5]], i32 0
; CHECK-NEXT: store ptr addrspace(10) [[DOTUNPACK]], ptr addrspace(13) [[DOTREPACK]], align 8, !tbaa [[TBAA10]]
; CHECK-NEXT: [[DOTREPACK4:%.*]] = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) [[TMP7]], i64 [[VALUE_PHI5]], i32 1
; CHECK-NEXT: store i64 [[DOTUNPACK2]], ptr addrspace(13) [[DOTREPACK4]], align 8, !tbaa [[TBAA10]]
; CHECK-NEXT: [[TMP27]] = add i64 [[VALUE_PHI5]], 1
; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i64 [[VALUE_PHI5]], [[TMP2]]
; CHECK-NEXT: br i1 [[DOTNOT]], label [[L44]], label [[L26]], !llvm.loop [[LOOP15:![0-9]+]]
; CHECK: L44:
; CHECK-NEXT: ret ptr addrspace(10) null
;
top:
%2 = sext i32 %1 to i64
%3 = load atomic ptr addrspace(10) (ptr addrspace(10), i64)*, ptr addrspace(10) (ptr addrspace(10), i64)** bitcast (ptr @jlplt_ijl_alloc_array_1d_10294_got to ptr addrspace(10) (ptr addrspace(10), i64)**) unordered, align 8
%4 = tail call ptr addrspace(10) %3(ptr addrspace(10) null, i64 0)
%5 = load ptr addrspace(10), ptr %0, align 8, !tbaa !0
%6 = addrspacecast ptr addrspace(10) %4 to ptr addrspace(11)
%7 = load ptr addrspace(13), ptr addrspace(11) %6, align 8, !tbaa !5
%.elt = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(10) %5, i64 0, i32 0
%.unpack = load ptr addrspace(10), ptr addrspace(10) %.elt, align 8, !tbaa !8
%.elt1 = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(10) %5, i64 0, i32 1
%.unpack2 = load i64, ptr addrspace(10) %.elt1, align 8, !tbaa !8
br label %L26
L26: ; preds = %L26, %top
%value_phi5 = phi i64 [ 0, %top ], [ %8, %L26 ]
%.repack = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) %7, i64 %value_phi5, i32 0
store ptr addrspace(10) %.unpack, ptr addrspace(13) %.repack, align 8, !tbaa !10
%.repack4 = getelementptr inbounds { ptr addrspace(10), i64 }, ptr addrspace(13) %7, i64 %value_phi5, i32 1
store i64 %.unpack2, ptr addrspace(13) %.repack4, align 8, !tbaa !10
%8 = add i64 %value_phi5, 1
%.not = icmp eq i64 %value_phi5, %2
br i1 %.not, label %L44, label %L26
L44: ; preds = %L26
ret ptr addrspace(10) null
}
attributes #0 = { "target-cpu"="skylake-avx512" "target-features"="+xsaves,+xsavec,+prfchw,+lzcnt,+sahf,+pku,+avx512vl,+avx512bw,+avx512cd,+clwb,+clflushopt,+adx,+avx512dq,+avx512f,+bmi2,+avx2,+bmi,+fsgsbase,+f16c,+avx,+xsave,+aes,+popcnt,+movbe,+sse4.2,+sse4.1,+cx16,+fma,+ssse3,+pclmul,+sse3,-rdrnd,-rtm,-rdseed,-avx512ifma,-avx512pf,-sha,-avx512vbmi,-waitpkg,-avx512vbmi2,-shstk,-gfni,-vaes,-vpclmulqdq,-avx512vnni,-avx512bitalg,-avx512vpopcntdq,-rdpid,-cldemote,-movdiri,-movdir64b,-enqcmd,-avx512vp2intersect,-serialize,-tsxldtrk,-pconfig,-amx-bf16,-amx-tile,-amx-int8,-sse4a,-xop,-lwp,-fma4,-tbm,-mwaitx,-xsaveopt,-clzero,-wbnoinvd,-avx512bf16,-ptwrite,+sse2,+mmx,+fxsr,+64bit,+cx8" }
attributes #1 = { inaccessiblemem_or_argmemonly }
attributes #2 = { allocsize(1) }
!0 = !{!1, !1, i64 0}
!1 = !{!"jtbaa_value", !2, i64 0}
!2 = !{!"jtbaa_data", !3, i64 0}
!3 = !{!"jtbaa", !4, i64 0}
!4 = !{!"jtbaa"}
!5 = !{!6, !6, i64 0}
!6 = !{!"jtbaa_arrayptr", !7, i64 0}
!7 = !{!"jtbaa_array", !3, i64 0}
!8 = !{!9, !9, i64 0}
!9 = !{!"jtbaa_immut", !1, i64 0}
!10 = !{!11, !11, i64 0}
!11 = !{!"jtbaa_arraybuf", !2, i64 0}
Codebase Browser
llvm