140 lines · plain
1; RUN: opt -passes=verify --disable-output %s2 3define void @test_vp_int(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n) {4 %r0 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)5 %r1 = call <8 x i32> @llvm.vp.sub.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)6 %r2 = call <8 x i32> @llvm.vp.mul.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)7 %r3 = call <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)8 %r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)9 %r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)10 %r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)11 %r7 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)12 %r8 = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)13 %r9 = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)14 %rA = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)15 %rB = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)16 %rC = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)17 ret void18}19 20 21define void @test_vp_fp(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n) {22 %r0 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)23 %r1 = call <8 x double> @llvm.vp.fsub.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)24 %r2 = call <8 x double> @llvm.vp.fmul.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)25 %r3 = call <8 x double> @llvm.vp.fdiv.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)26 %r4 = call <8 x double> @llvm.vp.frem.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)27 %r5 = call <8 x i1> @llvm.vp.is.fpclass.v8f64(<8 x double> %f0, i32 639, <8 x i1> %m, i32 %n)28 ret void29}30 31; TODO: test_vp_constrained_fp32 33 34define void @test_vp_reduction(i32 %x, <8 x i32> %vi, <8 x float> %vf, float %f, <8 x i1> %m, i32 %n) {35 %r0 = call i32 @llvm.vp.reduce.add.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)36 %r1 = call i32 @llvm.vp.reduce.mul.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)37 %r2 = call i32 @llvm.vp.reduce.and.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)38 %r3 = call i32 @llvm.vp.reduce.or.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)39 %r4 = call i32 @llvm.vp.reduce.xor.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)40 %r5 = call i32 @llvm.vp.reduce.smax.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)41 %r6 = call i32 @llvm.vp.reduce.smin.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)42 %r7 = call i32 @llvm.vp.reduce.umax.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)43 %r8 = call i32 @llvm.vp.reduce.umin.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)44 %r9 = call float @llvm.vp.reduce.fmin.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)45 %rA = call float @llvm.vp.reduce.fmax.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)46 %rB = call float @llvm.vp.reduce.fminimum.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)47 %rC = call float @llvm.vp.reduce.fmaximum.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)48 %rD = call float @llvm.vp.reduce.fadd.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)49 %rE = call float @llvm.vp.reduce.fmul.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)50 ret void51}52 53define void @test_vp_splice0(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %l0, i32 %l1) {54 %r0 = call <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x i32> %i0, <8 x i32> %i1, i32 2, <8 x i1> %m, i32 %l0, i32 %l1)55 ret void56}57 58define void @test_vp_splice1(<vscale x 8 x i32> %i0, <vscale x 8 x i32> %i1, <vscale x 8 x i1> %m, i32 %l0, i32 %l1) {59 %r0 = call <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32> %i0, <vscale x 8 x i32> %i1, i32 -1, <vscale x 8 x i1> %m, i32 %l0, i32 %l1)60 ret void61}62 63define void @test_vp_conversions(<8 x ptr> %p0, <8 x i32> %i0, <8 x i64> %i1, <8 x float> %f0, <8 x double> %f1, <8 x i1> %mask, i32 %evl) {64 %r0 = call <8 x i32> @llvm.vp.fptoui.v8i32.v8f32(<8 x float> %f0, <8 x i1> %mask, i32 %evl)65 %r1 = call <8 x i32> @llvm.vp.fptosi.v8i32.v8f32(<8 x float> %f0, <8 x i1> %mask, i32 %evl)66 %r2 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)67 %r3 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)68 %r4 = call <8 x float> @llvm.vp.fptrunc.v8f32.v8f64(<8 x double> %f1, <8 x i1> %mask, i32 %evl)69 %r5 = call <8 x double> @llvm.vp.fpext.v8f64.v8f32(<8 x float> %f0, <8 x i1> %mask, i32 %evl)70 %r6 = call <8 x i32> @llvm.vp.trunc.v8i32.v8i64(<8 x i64> %i1, <8 x i1> %mask, i32 %evl)71 %r7 = call <8 x i64> @llvm.vp.zext.v8i64.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)72 %r8 = call <8 x i64> @llvm.vp.sext.v8i64.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)73 %r9 = call <8 x i32> @llvm.vp.ptrtoint.v8i32.v8p0(<8 x ptr> %p0, <8 x i1> %mask, i32 %evl)74 %r10 = call <8 x ptr> @llvm.vp.inttoptr.v8p0.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)75 ret void76}77 78define void @test_vp_comparisons(<8 x float> %f0, <8 x float> %f1, <8 x i32> %i0, <8 x i32> %i1, <8 x i1> %mask, i32 %evl) {79 %r0 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"oeq", <8 x i1> %mask, i32 %evl)80 %r1 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"eq", <8 x i1> %mask, i32 %evl)81 ret void82}83 84; integer arith85declare <8 x i32> @llvm.vp.add.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)86declare <8 x i32> @llvm.vp.sub.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)87declare <8 x i32> @llvm.vp.mul.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)88declare <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)89declare <8 x i32> @llvm.vp.srem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)90declare <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)91declare <8 x i32> @llvm.vp.urem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)92; bit arith93declare <8 x i32> @llvm.vp.and.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)94declare <8 x i32> @llvm.vp.or.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)95declare <8 x i32> @llvm.vp.xor.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)96declare <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)97declare <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)98declare <8 x i32> @llvm.vp.shl.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)99; fp arith100declare <8 x double> @llvm.vp.fadd.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)101declare <8 x double> @llvm.vp.fsub.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)102declare <8 x double> @llvm.vp.fmul.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)103declare <8 x double> @llvm.vp.fdiv.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)104declare <8 x double> @llvm.vp.frem.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)105declare <8 x i1> @llvm.vp.is.fpclass.v8f64(<8 x double>, i32, <8 x i1>, i32)106; reductions107declare i32 @llvm.vp.reduce.add.v8i32(i32, <8 x i32>, <8 x i1>, i32)108declare i32 @llvm.vp.reduce.mul.v8i32(i32, <8 x i32>, <8 x i1>, i32)109declare i32 @llvm.vp.reduce.and.v8i32(i32, <8 x i32>, <8 x i1>, i32)110declare i32 @llvm.vp.reduce.or.v8i32(i32, <8 x i32>, <8 x i1>, i32)111declare i32 @llvm.vp.reduce.xor.v8i32(i32, <8 x i32>, <8 x i1>, i32)112declare i32 @llvm.vp.reduce.smax.v8i32(i32, <8 x i32>, <8 x i1>, i32)113declare i32 @llvm.vp.reduce.smin.v8i32(i32, <8 x i32>, <8 x i1>, i32)114declare i32 @llvm.vp.reduce.umax.v8i32(i32, <8 x i32>, <8 x i1>, i32)115declare i32 @llvm.vp.reduce.umin.v8i32(i32, <8 x i32>, <8 x i1>, i32)116declare float @llvm.vp.reduce.fmin.v8f32(float, <8 x float>, <8 x i1>, i32)117declare float @llvm.vp.reduce.fmax.v8f32(float, <8 x float>, <8 x i1>, i32)118declare float @llvm.vp.reduce.fminimum.v8f32(float, <8 x float>, <8 x i1>, i32)119declare float @llvm.vp.reduce.fmaximum.v8f32(float, <8 x float>, <8 x i1>, i32)120declare float @llvm.vp.reduce.fadd.v8f32(float, <8 x float>, <8 x i1>, i32)121declare float @llvm.vp.reduce.fmul.v8f32(float, <8 x float>, <8 x i1>, i32)122; casts123declare <8 x i32> @llvm.vp.fptoui.v8i32.v8f32(<8 x float>, <8 x i1>, i32)124declare <8 x i32> @llvm.vp.fptosi.v8i32.v8f32(<8 x float>, <8 x i1>, i32)125declare <8 x float> @llvm.vp.uitofp.v8f32.v8i32(<8 x i32>, <8 x i1>, i32)126declare <8 x float> @llvm.vp.sitofp.v8f32.v8i32(<8 x i32>, <8 x i1>, i32)127declare <8 x float> @llvm.vp.fptrunc.v8f32.v8f64(<8 x double>, <8 x i1>, i32)128declare <8 x double> @llvm.vp.fpext.v8f64.v8f32(<8 x float>, <8 x i1>, i32)129declare <8 x i32> @llvm.vp.trunc.v8i32.v8i64(<8 x i64>, <8 x i1>, i32)130declare <8 x i64> @llvm.vp.zext.v8i64.v8i32(<8 x i32>, <8 x i1>, i32)131declare <8 x i64> @llvm.vp.sext.v8i64.v8i32(<8 x i32>, <8 x i1>, i32)132declare <8 x i32> @llvm.vp.ptrtoint.v8i32.v8p0(<8 x ptr>, <8 x i1>, i32)133declare <8 x ptr> @llvm.vp.inttoptr.v8p0.v8i32(<8 x i32>, <8 x i1>, i32)134; compares135declare <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float>, <8 x float>, metadata, <8 x i1>, i32)136declare <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32>, <8 x i32>, metadata, <8 x i1>, i32)137; shuffles138declare <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x i32>, <8 x i32>, i32, <8 x i1>, i32, i32)139declare <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>, i32, <vscale x 8 x i1>, i32, i32)140