; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes=slp-vectorizer < %s | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128-ni:1-p2:32:8:8:32-ni:2"
target triple = "x86_64-unknown-linux-gnu"
; Make sure we do not generate malformed phis not in the beginning of block.
define void @test() #0 {
; CHECK-LABEL: @test(
; CHECK-NEXT: bb:
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[TMP:%.*]] = phi i32 [ undef, [[BB1]] ], [ undef, [[BB:%.*]] ]
; CHECK-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP18:%.*]], [[BB1]] ], [ undef, [[BB]] ]
; CHECK-NEXT: [[TMP3:%.*]] = mul i32 undef, [[TMP]]
; CHECK-NEXT: [[TMP4:%.*]] = mul i32 [[TMP3]], [[TMP]]
; CHECK-NEXT: [[TMP5:%.*]] = mul i32 [[TMP4]], [[TMP]]
; CHECK-NEXT: [[TMP6:%.*]] = mul i32 [[TMP5]], [[TMP]]
; CHECK-NEXT: [[TMP7:%.*]] = mul i32 [[TMP6]], [[TMP]]
; CHECK-NEXT: [[TMP8:%.*]] = mul i32 [[TMP7]], [[TMP]]
; CHECK-NEXT: [[TMP9:%.*]] = mul i32 [[TMP8]], [[TMP]]
; CHECK-NEXT: [[TMP10:%.*]] = mul i32 [[TMP9]], [[TMP]]
; CHECK-NEXT: [[TMP11:%.*]] = mul i32 [[TMP10]], [[TMP]]
; CHECK-NEXT: [[TMP12:%.*]] = mul i32 [[TMP11]], [[TMP]]
; CHECK-NEXT: [[TMP13:%.*]] = mul i32 [[TMP12]], [[TMP]]
; CHECK-NEXT: [[TMP14:%.*]] = mul i32 [[TMP13]], [[TMP]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i32 [[TMP14]], [[TMP]]
; CHECK-NEXT: [[TMP16:%.*]] = mul i32 [[TMP15]], [[TMP]]
; CHECK-NEXT: [[TMP17:%.*]] = mul i32 [[TMP16]], [[TMP]]
; CHECK-NEXT: [[TMP18]] = mul i32 [[TMP17]], [[TMP]]
; CHECK-NEXT: br label [[BB1]]
;
bb:
br label %bb1
bb1: ; preds = %bb1, %bb
%tmp = phi i32 [ undef, %bb1 ], [ undef, %bb ]
%tmp2 = phi i32 [ %tmp18, %bb1 ], [ undef, %bb ]
%tmp3 = mul i32 undef, %tmp
%tmp4 = mul i32 %tmp3, %tmp
%tmp5 = mul i32 %tmp4, %tmp
%tmp6 = mul i32 %tmp5, %tmp
%tmp7 = mul i32 %tmp6, %tmp
%tmp8 = mul i32 %tmp7, %tmp
%tmp9 = mul i32 %tmp8, %tmp
%tmp10 = mul i32 %tmp9, %tmp
%tmp11 = mul i32 %tmp10, %tmp
%tmp12 = mul i32 %tmp11, %tmp
%tmp13 = mul i32 %tmp12, %tmp
%tmp14 = mul i32 %tmp13, %tmp
%tmp15 = mul i32 %tmp14, %tmp
%tmp16 = mul i32 %tmp15, %tmp
%tmp17 = mul i32 %tmp16, %tmp
%tmp18 = mul i32 %tmp17, %tmp
br label %bb1
}
define void @test_2(ptr addrspace(1) %arg, i32 %arg1) #0 {
; CHECK-LABEL: @test_2(
; CHECK-NEXT: bb:
; CHECK-NEXT: br label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[TMP:%.*]] = phi i32 [ undef, [[BB:%.*]] ], [ undef, [[BB2]] ]
; CHECK-NEXT: [[TMP3:%.*]] = phi i32 [ 0, [[BB]] ], [ undef, [[BB2]] ]
; CHECK-NEXT: [[TMP0:%.*]] = mul i32 [[TMP]], 8
; CHECK-NEXT: [[OP_RDX:%.*]] = add i32 undef, [[TMP0]]
; CHECK-NEXT: call void @use(i32 [[OP_RDX]])
; CHECK-NEXT: br label [[BB2]]
;
bb:
br label %bb2
bb2: ; preds = %bb2, %bb
%tmp = phi i32 [ undef, %bb ], [ undef, %bb2 ]
%tmp3 = phi i32 [ 0, %bb ], [ undef, %bb2 ]
%tmp4 = add i32 %tmp, undef
%tmp5 = add i32 undef, %tmp4
%tmp6 = add i32 %tmp, %tmp5
%tmp7 = add i32 undef, %tmp6
%tmp8 = add i32 %tmp, %tmp7
%tmp9 = add i32 undef, %tmp8
%tmp10 = add i32 %tmp, %tmp9
%tmp11 = add i32 undef, %tmp10
%tmp12 = add i32 %tmp, %tmp11
%tmp13 = add i32 undef, %tmp12
%tmp14 = add i32 %tmp, %tmp13
%tmp15 = add i32 undef, %tmp14
%tmp16 = add i32 %tmp, %tmp15
%tmp17 = add i32 undef, %tmp16
%tmp18 = add i32 %tmp, %tmp17
%tmp19 = add i32 undef, %tmp18
call void @use(i32 %tmp19)
br label %bb2
}
; Make sure we don't crash.
define i64 @test_3() #0 {
; CHECK-LABEL: @test_3(
; CHECK-NEXT: bb:
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB3]]
; CHECK: bb3:
; CHECK-NEXT: [[VAL:%.*]] = phi i32 [ undef, [[BB1]] ], [ undef, [[BB2:%.*]] ]
; CHECK-NEXT: [[VAL4:%.*]] = phi i32 [ undef, [[BB1]] ], [ undef, [[BB2]] ]
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <32 x i32> poison, i32 [[VAL4]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <32 x i32> [[TMP0]], <32 x i32> poison, <32 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.vector.reduce.mul.v32i32(<32 x i32> [[TMP1]])
; CHECK-NEXT: [[OP_RDX:%.*]] = mul i32 [[TMP2]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX1:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX2:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX3:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX4:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX5:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX6:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX7:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX8:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX9:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX10:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX11:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX12:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX13:%.*]] = mul i32 [[VAL4]], [[VAL4]]
; CHECK-NEXT: [[OP_RDX14:%.*]] = mul i32 [[OP_RDX]], [[OP_RDX1]]
; CHECK-NEXT: [[OP_RDX15:%.*]] = mul i32 [[OP_RDX2]], [[OP_RDX3]]
; CHECK-NEXT: [[OP_RDX16:%.*]] = mul i32 [[OP_RDX4]], [[OP_RDX5]]
; CHECK-NEXT: [[OP_RDX17:%.*]] = mul i32 [[OP_RDX6]], [[OP_RDX7]]
; CHECK-NEXT: [[OP_RDX18:%.*]] = mul i32 [[OP_RDX8]], [[OP_RDX9]]
; CHECK-NEXT: [[OP_RDX19:%.*]] = mul i32 [[OP_RDX10]], [[OP_RDX11]]
; CHECK-NEXT: [[OP_RDX20:%.*]] = mul i32 [[OP_RDX12]], [[OP_RDX13]]
; CHECK-NEXT: [[OP_RDX21:%.*]] = mul i32 [[OP_RDX14]], [[OP_RDX15]]
; CHECK-NEXT: [[OP_RDX22:%.*]] = mul i32 [[OP_RDX16]], [[OP_RDX17]]
; CHECK-NEXT: [[OP_RDX23:%.*]] = mul i32 [[OP_RDX18]], [[OP_RDX19]]
; CHECK-NEXT: [[OP_RDX24:%.*]] = mul i32 [[OP_RDX20]], [[VAL]]
; CHECK-NEXT: [[OP_RDX25:%.*]] = mul i32 [[OP_RDX21]], [[OP_RDX22]]
; CHECK-NEXT: [[OP_RDX26:%.*]] = mul i32 [[OP_RDX23]], [[OP_RDX24]]
; CHECK-NEXT: [[OP_RDX27:%.*]] = mul i32 [[OP_RDX25]], [[OP_RDX26]]
; CHECK-NEXT: [[VAL64:%.*]] = add i32 undef, [[OP_RDX27]]
; CHECK-NEXT: [[VAL65:%.*]] = sext i32 [[VAL64]] to i64
; CHECK-NEXT: ret i64 [[VAL65]]
;
bb:
br label %bb1
bb1: ; preds = %bb
br label %bb3
bb2: ; No predecessors!
br label %bb3
bb3: ; preds = %bb2, %bb1
%val = phi i32 [ undef, %bb1 ], [ undef, %bb2 ]
%val4 = phi i32 [ undef, %bb1 ], [ undef, %bb2 ]
%val5 = mul i32 %val, %val4
%val6 = mul i32 %val5, %val4
%val7 = mul i32 %val6, %val4
%val8 = mul i32 %val7, %val4
%val9 = mul i32 %val8, %val4
%val10 = mul i32 %val9, %val4
%val11 = mul i32 %val10, %val4
%val12 = mul i32 %val11, %val4
%val13 = mul i32 %val12, %val4
%val14 = mul i32 %val13, %val4
%val15 = mul i32 %val14, %val4
%val16 = mul i32 %val15, %val4
%val17 = mul i32 %val16, %val4
%val18 = mul i32 %val17, %val4
%val19 = mul i32 %val18, %val4
%val20 = mul i32 %val19, %val4
%val21 = mul i32 %val20, %val4
%val22 = mul i32 %val21, %val4
%val23 = mul i32 %val22, %val4
%val24 = mul i32 %val23, %val4
%val25 = mul i32 %val24, %val4
%val26 = mul i32 %val25, %val4
%val27 = mul i32 %val26, %val4
%val28 = mul i32 %val27, %val4
%val29 = mul i32 %val28, %val4
%val30 = mul i32 %val29, %val4
%val31 = mul i32 %val30, %val4
%val32 = mul i32 %val31, %val4
%val33 = mul i32 %val32, %val4
%val34 = mul i32 %val33, %val4
%val35 = mul i32 %val34, %val4
%val36 = mul i32 %val35, %val4
%val37 = mul i32 %val36, %val4
%val38 = mul i32 %val37, %val4
%val39 = mul i32 %val38, %val4
%val40 = mul i32 %val39, %val4
%val41 = mul i32 %val40, %val4
%val42 = mul i32 %val41, %val4
%val43 = mul i32 %val42, %val4
%val44 = mul i32 %val43, %val4
%val45 = mul i32 %val44, %val4
%val46 = mul i32 %val45, %val4
%val47 = mul i32 %val46, %val4
%val48 = mul i32 %val47, %val4
%val49 = mul i32 %val48, %val4
%val50 = mul i32 %val49, %val4
%val51 = mul i32 %val50, %val4
%val52 = mul i32 %val51, %val4
%val53 = mul i32 %val52, %val4
%val54 = mul i32 %val53, %val4
%val55 = mul i32 %val54, %val4
%val56 = mul i32 %val55, %val4
%val57 = mul i32 %val56, %val4
%val58 = mul i32 %val57, %val4
%val59 = mul i32 %val58, %val4
%val60 = mul i32 %val59, %val4
%val61 = mul i32 %val60, %val4
%val62 = mul i32 %val61, %val4
%val63 = mul i32 %val62, %val4
%val64 = add i32 undef, %val63
%val65 = sext i32 %val64 to i64
ret i64 %val65
}
declare void @use(i32) #0
attributes #0 = { "target-features"="+sse4.1" }