1; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=yonah -regalloc=linearscan | FileCheck --check-prefix=I386 %s 2; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck --check-prefix=X86-64 %s 3 4; This testcase shouldn't need to spill the -1 value, 5; so it should just use pcmpeqd to materialize an all-ones vector. 6; For i386, cp load of -1 are folded. 7 8; With -regalloc=greedy, the live range is split before spilling, so the first 9; pcmpeq doesn't get folded as a constant pool load. 10 11; I386-NOT: pcmpeqd 12; I386: orps LCPI0_2, %xmm 13; I386-NOT: pcmpeqd 14; I386: orps LCPI0_2, %xmm 15 16; X86-64: pcmpeqd 17; X86-64-NOT: pcmpeqd 18 19 %struct.__ImageExecInfo = type <{ <4 x i32>, <4 x float>, <2 x i64>, i8*, i8*, i8*, i32, i32, i32, i32, i32 }> 20 %struct._cl_image_format_t = type <{ i32, i32, i32 }> 21 %struct._image2d_t = type <{ i8*, %struct._cl_image_format_t, i32, i32, i32, i32, i32, i32 }> 22 23define void @program_1(%struct._image2d_t* %dest, %struct._image2d_t* %t0, <4 x float> %p0, <4 x float> %p1, <4 x float> %p4, <4 x float> %p5, <4 x float> %p6) nounwind { 24entry: 25 %tmp3.i = load i32* null ; <i32> [#uses=1] 26 %cmp = icmp sgt i32 %tmp3.i, 200 ; <i1> [#uses=1] 27 br i1 %cmp, label %forcond, label %ifthen 28 29ifthen: ; preds = %entry 30 ret void 31 32forcond: ; preds = %entry 33 %tmp3.i536 = load i32* null ; <i32> [#uses=1] 34 %cmp12 = icmp slt i32 0, %tmp3.i536 ; <i1> [#uses=1] 35 br i1 %cmp12, label %forbody, label %afterfor 36 37forbody: ; preds = %forcond 38 %bitcast204.i313 = bitcast <4 x i32> zeroinitializer to <4 x float> ; <<4 x float>> [#uses=1] 39 %mul233 = fmul <4 x float> %bitcast204.i313, zeroinitializer ; <<4 x float>> [#uses=1] 40 %mul257 = fmul <4 x float> %mul233, zeroinitializer ; <<4 x float>> [#uses=1] 41 %mul275 = fmul <4 x float> %mul257, zeroinitializer ; <<4 x float>> [#uses=1] 42 %tmp51 = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %mul275, <4 x float> zeroinitializer) nounwind ; <<4 x float>> [#uses=1] 43 %bitcast198.i182 = bitcast <4 x float> zeroinitializer to <4 x i32> ; <<4 x i32>> [#uses=0] 44 %bitcast204.i185 = bitcast <4 x i32> zeroinitializer to <4 x float> ; <<4 x float>> [#uses=1] 45 %tmp69 = call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> zeroinitializer) nounwind ; <<4 x i32>> [#uses=1] 46 %tmp70 = call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp69) nounwind ; <<4 x float>> [#uses=1] 47 %sub140.i78 = fsub <4 x float> zeroinitializer, %tmp70 ; <<4 x float>> [#uses=2] 48 %mul166.i86 = fmul <4 x float> zeroinitializer, %sub140.i78 ; <<4 x float>> [#uses=1] 49 %add167.i87 = fadd <4 x float> %mul166.i86, < float 0x3FE62ACB60000000, float 0x3FE62ACB60000000, float 0x3FE62ACB60000000, float 0x3FE62ACB60000000 > ; <<4 x float>> [#uses=1] 50 %mul171.i88 = fmul <4 x float> %add167.i87, %sub140.i78 ; <<4 x float>> [#uses=1] 51 %add172.i89 = fadd <4 x float> %mul171.i88, < float 0x3FF0000A40000000, float 0x3FF0000A40000000, float 0x3FF0000A40000000, float 0x3FF0000A40000000 > ; <<4 x float>> [#uses=1] 52 %bitcast176.i90 = bitcast <4 x float> %add172.i89 to <4 x i32> ; <<4 x i32>> [#uses=1] 53 %andnps178.i92 = and <4 x i32> %bitcast176.i90, zeroinitializer ; <<4 x i32>> [#uses=1] 54 %bitcast179.i93 = bitcast <4 x i32> %andnps178.i92 to <4 x float> ; <<4 x float>> [#uses=1] 55 %mul186.i96 = fmul <4 x float> %bitcast179.i93, zeroinitializer ; <<4 x float>> [#uses=1] 56 %bitcast190.i98 = bitcast <4 x float> %mul186.i96 to <4 x i32> ; <<4 x i32>> [#uses=1] 57 %andnps192.i100 = and <4 x i32> %bitcast190.i98, zeroinitializer ; <<4 x i32>> [#uses=1] 58 %xorps.i102 = xor <4 x i32> zeroinitializer, < i32 -1, i32 -1, i32 -1, i32 -1 > ; <<4 x i32>> [#uses=1] 59 %orps203.i103 = or <4 x i32> %andnps192.i100, %xorps.i102 ; <<4 x i32>> [#uses=1] 60 %bitcast204.i104 = bitcast <4 x i32> %orps203.i103 to <4 x float> ; <<4 x float>> [#uses=1] 61 %cmple.i = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> zeroinitializer, <4 x float> %tmp51, i8 2) nounwind ; <<4 x float>> [#uses=1] 62 %tmp80 = call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> zeroinitializer) nounwind ; <<4 x float>> [#uses=1] 63 %sub140.i = fsub <4 x float> zeroinitializer, %tmp80 ; <<4 x float>> [#uses=1] 64 %bitcast148.i = bitcast <4 x float> zeroinitializer to <4 x i32> ; <<4 x i32>> [#uses=1] 65 %andnps150.i = and <4 x i32> %bitcast148.i, < i32 -2139095041, i32 -2139095041, i32 -2139095041, i32 -2139095041 > ; <<4 x i32>> [#uses=0] 66 %mul171.i = fmul <4 x float> zeroinitializer, %sub140.i ; <<4 x float>> [#uses=1] 67 %add172.i = fadd <4 x float> %mul171.i, < float 0x3FF0000A40000000, float 0x3FF0000A40000000, float 0x3FF0000A40000000, float 0x3FF0000A40000000 > ; <<4 x float>> [#uses=1] 68 %bitcast176.i = bitcast <4 x float> %add172.i to <4 x i32> ; <<4 x i32>> [#uses=1] 69 %andnps178.i = and <4 x i32> %bitcast176.i, zeroinitializer ; <<4 x i32>> [#uses=1] 70 %bitcast179.i = bitcast <4 x i32> %andnps178.i to <4 x float> ; <<4 x float>> [#uses=1] 71 %mul186.i = fmul <4 x float> %bitcast179.i, zeroinitializer ; <<4 x float>> [#uses=1] 72 %bitcast189.i = bitcast <4 x float> zeroinitializer to <4 x i32> ; <<4 x i32>> [#uses=0] 73 %bitcast190.i = bitcast <4 x float> %mul186.i to <4 x i32> ; <<4 x i32>> [#uses=1] 74 %andnps192.i = and <4 x i32> %bitcast190.i, zeroinitializer ; <<4 x i32>> [#uses=1] 75 %bitcast198.i = bitcast <4 x float> %cmple.i to <4 x i32> ; <<4 x i32>> [#uses=1] 76 %xorps.i = xor <4 x i32> %bitcast198.i, < i32 -1, i32 -1, i32 -1, i32 -1 > ; <<4 x i32>> [#uses=1] 77 %orps203.i = or <4 x i32> %andnps192.i, %xorps.i ; <<4 x i32>> [#uses=1] 78 %bitcast204.i = bitcast <4 x i32> %orps203.i to <4 x float> ; <<4 x float>> [#uses=1] 79 %mul307 = fmul <4 x float> %bitcast204.i185, zeroinitializer ; <<4 x float>> [#uses=1] 80 %mul310 = fmul <4 x float> %bitcast204.i104, zeroinitializer ; <<4 x float>> [#uses=2] 81 %mul313 = fmul <4 x float> %bitcast204.i, zeroinitializer ; <<4 x float>> [#uses=1] 82 %tmp82 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %mul307, <4 x float> zeroinitializer) nounwind ; <<4 x float>> [#uses=1] 83 %bitcast11.i15 = bitcast <4 x float> %tmp82 to <4 x i32> ; <<4 x i32>> [#uses=1] 84 %andnps.i17 = and <4 x i32> %bitcast11.i15, zeroinitializer ; <<4 x i32>> [#uses=1] 85 %orps.i18 = or <4 x i32> %andnps.i17, zeroinitializer ; <<4 x i32>> [#uses=1] 86 %bitcast17.i19 = bitcast <4 x i32> %orps.i18 to <4 x float> ; <<4 x float>> [#uses=1] 87 %tmp83 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %mul310, <4 x float> zeroinitializer) nounwind ; <<4 x float>> [#uses=1] 88 %bitcast.i3 = bitcast <4 x float> %mul310 to <4 x i32> ; <<4 x i32>> [#uses=1] 89 %bitcast6.i4 = bitcast <4 x float> zeroinitializer to <4 x i32> ; <<4 x i32>> [#uses=2] 90 %andps.i5 = and <4 x i32> %bitcast.i3, %bitcast6.i4 ; <<4 x i32>> [#uses=1] 91 %bitcast11.i6 = bitcast <4 x float> %tmp83 to <4 x i32> ; <<4 x i32>> [#uses=1] 92 %not.i7 = xor <4 x i32> %bitcast6.i4, < i32 -1, i32 -1, i32 -1, i32 -1 > ; <<4 x i32>> [#uses=1] 93 %andnps.i8 = and <4 x i32> %bitcast11.i6, %not.i7 ; <<4 x i32>> [#uses=1] 94 %orps.i9 = or <4 x i32> %andnps.i8, %andps.i5 ; <<4 x i32>> [#uses=1] 95 %bitcast17.i10 = bitcast <4 x i32> %orps.i9 to <4 x float> ; <<4 x float>> [#uses=1] 96 %bitcast.i = bitcast <4 x float> %mul313 to <4 x i32> ; <<4 x i32>> [#uses=1] 97 %andps.i = and <4 x i32> %bitcast.i, zeroinitializer ; <<4 x i32>> [#uses=1] 98 %orps.i = or <4 x i32> zeroinitializer, %andps.i ; <<4 x i32>> [#uses=1] 99 %bitcast17.i = bitcast <4 x i32> %orps.i to <4 x float> ; <<4 x float>> [#uses=1] 100 call void null(<4 x float> %bitcast17.i19, <4 x float> %bitcast17.i10, <4 x float> %bitcast17.i, <4 x float> zeroinitializer, %struct.__ImageExecInfo* null, <4 x i32> zeroinitializer) nounwind 101 unreachable 102 103afterfor: ; preds = %forcond 104 ret void 105} 106 107declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone 108 109declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>) nounwind readnone 110 111declare <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float>) nounwind readnone 112 113declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone 114 115declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone 116