From: James Molloy Date: Wed, 7 May 2014 11:28:53 +0000 (+0000) Subject: [ARM64-BE] Implement the crazy bitcast handling for big endian vectors. X-Git-Url: http://plrg.eecs.uci.edu/git/?a=commitdiff_plain;h=737c2ac4fcbda3ec109b68d7c17a6a4334f5245d;p=oota-llvm.git [ARM64-BE] Implement the crazy bitcast handling for big endian vectors. Because we've canonicalised on using LD1/ST1, every time we do a bitcast between vector types we must do an equivalent lane reversal. Consider a simple memory load followed by a bitconvert then a store. v0 = load v2i32 v1 = BITCAST v2i32 v0 to v4i16 store v4i16 v2 In big endian mode every memory access has an implicit byte swap. LDR and STR do a 64-bit byte swap, whereas LD1/ST1 do a byte swap per lane - that is, they treat the vector as a sequence of elements to be byte-swapped. The two pairs of instructions are fundamentally incompatible. We've decided to use LD1/ST1 only to simplify compiler implementation. LD1/ST1 perform the equivalent of a sequence of LDR/STR + REV. This makes the original code sequence: v0 = load v2i32 v1 = REV v2i32 (implicit) v2 = BITCAST v2i32 v1 to v4i16 v3 = REV v4i16 v2 (implicit) store v4i16 v3 But this is now broken - the value stored is different to the value loaded due to lane reordering. To fix this, on every BITCAST we must perform two other REVs: v0 = load v2i32 v1 = REV v2i32 (implicit) v2 = REV v2i32 v3 = BITCAST v2i32 v2 to v4i16 v4 = REV v4i16 v5 = REV v4i16 v4 (implicit) store v4i16 v5 This means an extra two instructions, but actually in most cases the two REV instructions can be combined into one. For example: (REV64_2s (REV64_4h X)) === (REV32_4h X) There is also no 128-bit REV instruction. This must be synthesized with an EXT instruction. Most bitconverts require some sort of conversion. The only exceptions are: a) Identity conversions - vNfX <-> vNiX b) Single-lane-to-scalar - v1fX <-> fX or v1iX <-> iX Even though there are hundreds of changed lines, I have a fairly high confidence that they are somewhat correct. The changes to add two REV instructions per bitcast were pretty mechanical, and once I'd done that I threw the resulting .td at a script I wrote which combined the two REVs together (and added an EXT instruction, for f128) based on an instruction description I gave it. This was much less prone to error than doing it all manually, plus my brain would not just have melted but would have vapourised. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@208194 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/Target/ARM64/ARM64InstrInfo.td b/lib/Target/ARM64/ARM64InstrInfo.td index 10f74b3c743..e5dd3e49e0a 100644 --- a/lib/Target/ARM64/ARM64InstrInfo.td +++ b/lib/Target/ARM64/ARM64InstrInfo.td @@ -2037,40 +2037,6 @@ defm FMOV : UnscaledConversion<"fmov">; def : Pat<(f32 (fpimm0)), (FMOVWSr WZR)>, Requires<[NoZCZ]>; def : Pat<(f64 (fpimm0)), (FMOVXDr XZR)>, Requires<[NoZCZ]>; -def : Pat<(v8i8 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v4i16 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v2i32 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v1i64 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v2f32 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v1f64 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v1i64 (scalar_to_vector GPR64:$Xn)), - (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v1f64 (scalar_to_vector GPR64:$Xn)), - (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(v1f64 (scalar_to_vector (f64 FPR64:$Xn))), (v1f64 FPR64:$Xn)>; - -def : Pat<(i64 (bitconvert (v8i8 V64:$Vn))), - (COPY_TO_REGCLASS V64:$Vn, GPR64)>; -def : Pat<(i64 (bitconvert (v4i16 V64:$Vn))), - (COPY_TO_REGCLASS V64:$Vn, GPR64)>; -def : Pat<(i64 (bitconvert (v2i32 V64:$Vn))), - (COPY_TO_REGCLASS V64:$Vn, GPR64)>; -def : Pat<(i64 (bitconvert (v1i64 V64:$Vn))), - (COPY_TO_REGCLASS V64:$Vn, GPR64)>; -def : Pat<(i64 (bitconvert (v2f32 V64:$Vn))), - (COPY_TO_REGCLASS V64:$Vn, GPR64)>; -def : Pat<(i64 (bitconvert (v1f64 V64:$Vn))), - (COPY_TO_REGCLASS V64:$Vn, GPR64)>; - -def : Pat<(f32 (bitconvert (i32 GPR32:$Xn))), - (COPY_TO_REGCLASS GPR32:$Xn, FPR32)>; -def : Pat<(i32 (bitconvert (f32 FPR32:$Xn))), - (COPY_TO_REGCLASS FPR32:$Xn, GPR32)>; -def : Pat<(f64 (bitconvert (i64 GPR64:$Xn))), - (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; -def : Pat<(i64 (bitconvert (f64 FPR64:$Xn))), - (COPY_TO_REGCLASS FPR64:$Xn, GPR64)>; - //===----------------------------------------------------------------------===// // Floating point conversion instruction. //===----------------------------------------------------------------------===// @@ -4631,104 +4597,418 @@ def : Pat<(i32 (trunc GPR64sp:$src)), def : Pat<(trap), (BRK 1)>; // Conversions within AdvSIMD types in the same register size are free. +// But because we need a consistent lane ordering, in big endian many +// conversions require one or more REV instructions. +// +// Consider a simple memory load followed by a bitconvert then a store. +// v0 = load v2i32 +// v1 = BITCAST v2i32 v0 to v4i16 +// store v4i16 v2 +// +// In big endian mode every memory access has an implicit byte swap. LDR and +// STR do a 64-bit byte swap, whereas LD1/ST1 do a byte swap per lane - that +// is, they treat the vector as a sequence of elements to be byte-swapped. +// The two pairs of instructions are fundamentally incompatible. We've decided +// to use LD1/ST1 only to simplify compiler implementation. +// +// LD1/ST1 perform the equivalent of a sequence of LDR/STR + REV. This makes +// the original code sequence: +// v0 = load v2i32 +// v1 = REV v2i32 (implicit) +// v2 = BITCAST v2i32 v1 to v4i16 +// v3 = REV v4i16 v2 (implicit) +// store v4i16 v3 +// +// But this is now broken - the value stored is different to the value loaded +// due to lane reordering. To fix this, on every BITCAST we must perform two +// other REVs: +// v0 = load v2i32 +// v1 = REV v2i32 (implicit) +// v2 = REV v2i32 +// v3 = BITCAST v2i32 v2 to v4i16 +// v4 = REV v4i16 +// v5 = REV v4i16 v4 (implicit) +// store v4i16 v5 +// +// This means an extra two instructions, but actually in most cases the two REV +// instructions can be combined into one. For example: +// (REV64_2s (REV64_4h X)) === (REV32_4h X) +// +// There is also no 128-bit REV instruction. This must be synthesized with an +// EXT instruction. +// +// Most bitconverts require some sort of conversion. The only exceptions are: +// a) Identity conversions - vNfX <-> vNiX +// b) Single-lane-to-scalar - v1fX <-> fX or v1iX <-> iX +// + +let Predicates = [IsLE] in { +def : Pat<(v8i8 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(v4i16 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(v2i32 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(v2f32 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; + +def : Pat<(i64 (bitconvert (v8i8 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; +def : Pat<(i64 (bitconvert (v4i16 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; +def : Pat<(i64 (bitconvert (v2i32 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; +def : Pat<(i64 (bitconvert (v2f32 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; +def : Pat<(i64 (bitconvert (v1f64 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; +} +let Predicates = [IsBE] in { +def : Pat<(v8i8 (bitconvert GPR64:$Xn)), + (REV64v8i8 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>; +def : Pat<(v4i16 (bitconvert GPR64:$Xn)), + (REV64v4i16 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>; +def : Pat<(v2i32 (bitconvert GPR64:$Xn)), + (REV64v2i32 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>; +def : Pat<(v2f32 (bitconvert GPR64:$Xn)), + (REV64v2i32 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>; +def : Pat<(i64 (bitconvert (v8i8 V64:$Vn))), + (REV64v8i8 (COPY_TO_REGCLASS V64:$Vn, GPR64))>; +def : Pat<(i64 (bitconvert (v4i16 V64:$Vn))), + (REV64v4i16 (COPY_TO_REGCLASS V64:$Vn, GPR64))>; +def : Pat<(i64 (bitconvert (v2i32 V64:$Vn))), + (REV64v2i32 (COPY_TO_REGCLASS V64:$Vn, GPR64))>; +def : Pat<(i64 (bitconvert (v2f32 V64:$Vn))), + (REV64v2i32 (COPY_TO_REGCLASS V64:$Vn, GPR64))>; +} +def : Pat<(v1i64 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(v1f64 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(i64 (bitconvert (v1i64 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; +def : Pat<(v1i64 (scalar_to_vector GPR64:$Xn)), + (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(v1f64 (scalar_to_vector GPR64:$Xn)), + (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(v1f64 (scalar_to_vector (f64 FPR64:$Xn))), (v1f64 FPR64:$Xn)>; + +def : Pat<(f32 (bitconvert (i32 GPR32:$Xn))), + (COPY_TO_REGCLASS GPR32:$Xn, FPR32)>; +def : Pat<(i32 (bitconvert (f32 FPR32:$Xn))), + (COPY_TO_REGCLASS FPR32:$Xn, GPR32)>; +def : Pat<(f64 (bitconvert (i64 GPR64:$Xn))), + (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>; +def : Pat<(i64 (bitconvert (f64 FPR64:$Xn))), + (COPY_TO_REGCLASS FPR64:$Xn, GPR64)>; +def : Pat<(i64 (bitconvert (v1f64 V64:$Vn))), + (COPY_TO_REGCLASS V64:$Vn, GPR64)>; + +let Predicates = [IsLE] in { def : Pat<(v1i64 (bitconvert (v2i32 FPR64:$src))), (v1i64 FPR64:$src)>; def : Pat<(v1i64 (bitconvert (v4i16 FPR64:$src))), (v1i64 FPR64:$src)>; def : Pat<(v1i64 (bitconvert (v8i8 FPR64:$src))), (v1i64 FPR64:$src)>; -def : Pat<(v1i64 (bitconvert (f64 FPR64:$src))), (v1i64 FPR64:$src)>; def : Pat<(v1i64 (bitconvert (v2f32 FPR64:$src))), (v1i64 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v1i64 (bitconvert (v2i32 FPR64:$src))), + (v1i64 (REV64v2i32 FPR64:$src))>; +def : Pat<(v1i64 (bitconvert (v4i16 FPR64:$src))), + (v1i64 (REV64v4i16 FPR64:$src))>; +def : Pat<(v1i64 (bitconvert (v8i8 FPR64:$src))), + (v1i64 (REV64v8i8 FPR64:$src))>; +def : Pat<(v1i64 (bitconvert (v2f32 FPR64:$src))), + (v1i64 (REV64v2i32 FPR64:$src))>; +} def : Pat<(v1i64 (bitconvert (v1f64 FPR64:$src))), (v1i64 FPR64:$src)>; +def : Pat<(v1i64 (bitconvert (f64 FPR64:$src))), (v1i64 FPR64:$src)>; +let Predicates = [IsLE] in { def : Pat<(v2i32 (bitconvert (v1i64 FPR64:$src))), (v2i32 FPR64:$src)>; def : Pat<(v2i32 (bitconvert (v4i16 FPR64:$src))), (v2i32 FPR64:$src)>; def : Pat<(v2i32 (bitconvert (v8i8 FPR64:$src))), (v2i32 FPR64:$src)>; def : Pat<(v2i32 (bitconvert (f64 FPR64:$src))), (v2i32 FPR64:$src)>; -def : Pat<(v2i32 (bitconvert (v2f32 FPR64:$src))), (v2i32 FPR64:$src)>; def : Pat<(v2i32 (bitconvert (v1f64 FPR64:$src))), (v2i32 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v2i32 (bitconvert (v1i64 FPR64:$src))), + (v2i32 (REV64v2i32 FPR64:$src))>; +def : Pat<(v2i32 (bitconvert (v4i16 FPR64:$src))), + (v2i32 (REV32v4i16 FPR64:$src))>; +def : Pat<(v2i32 (bitconvert (v8i8 FPR64:$src))), + (v2i32 (REV32v8i8 FPR64:$src))>; +def : Pat<(v2i32 (bitconvert (f64 FPR64:$src))), + (v2i32 (REV64v2i32 FPR64:$src))>; +def : Pat<(v2i32 (bitconvert (v1f64 FPR64:$src))), + (v2i32 (REV64v2i32 FPR64:$src))>; +} +def : Pat<(v2i32 (bitconvert (v2f32 FPR64:$src))), (v2i32 FPR64:$src)>; +let Predicates = [IsLE] in { def : Pat<(v4i16 (bitconvert (v1i64 FPR64:$src))), (v4i16 FPR64:$src)>; def : Pat<(v4i16 (bitconvert (v2i32 FPR64:$src))), (v4i16 FPR64:$src)>; def : Pat<(v4i16 (bitconvert (v8i8 FPR64:$src))), (v4i16 FPR64:$src)>; def : Pat<(v4i16 (bitconvert (f64 FPR64:$src))), (v4i16 FPR64:$src)>; def : Pat<(v4i16 (bitconvert (v2f32 FPR64:$src))), (v4i16 FPR64:$src)>; def : Pat<(v4i16 (bitconvert (v1f64 FPR64:$src))), (v4i16 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v4i16 (bitconvert (v1i64 FPR64:$src))), + (v4i16 (REV64v4i16 FPR64:$src))>; +def : Pat<(v4i16 (bitconvert (v2i32 FPR64:$src))), + (v4i16 (REV32v4i16 FPR64:$src))>; +def : Pat<(v4i16 (bitconvert (v8i8 FPR64:$src))), + (v4i16 (REV16v8i8 FPR64:$src))>; +def : Pat<(v4i16 (bitconvert (f64 FPR64:$src))), + (v4i16 (REV64v4i16 FPR64:$src))>; +def : Pat<(v4i16 (bitconvert (v2f32 FPR64:$src))), + (v4i16 (REV32v4i16 FPR64:$src))>; +def : Pat<(v4i16 (bitconvert (v1f64 FPR64:$src))), + (v4i16 (REV64v4i16 FPR64:$src))>; +} +let Predicates = [IsLE] in { def : Pat<(v8i8 (bitconvert (v1i64 FPR64:$src))), (v8i8 FPR64:$src)>; def : Pat<(v8i8 (bitconvert (v2i32 FPR64:$src))), (v8i8 FPR64:$src)>; def : Pat<(v8i8 (bitconvert (v4i16 FPR64:$src))), (v8i8 FPR64:$src)>; def : Pat<(v8i8 (bitconvert (f64 FPR64:$src))), (v8i8 FPR64:$src)>; def : Pat<(v8i8 (bitconvert (v2f32 FPR64:$src))), (v8i8 FPR64:$src)>; def : Pat<(v8i8 (bitconvert (v1f64 FPR64:$src))), (v8i8 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v8i8 (bitconvert (v1i64 FPR64:$src))), + (v8i8 (REV64v8i8 FPR64:$src))>; +def : Pat<(v8i8 (bitconvert (v2i32 FPR64:$src))), + (v8i8 (REV32v8i8 FPR64:$src))>; +def : Pat<(v8i8 (bitconvert (v4i16 FPR64:$src))), + (v8i8 (REV16v8i8 FPR64:$src))>; +def : Pat<(v8i8 (bitconvert (f64 FPR64:$src))), + (v8i8 (REV64v8i8 FPR64:$src))>; +def : Pat<(v8i8 (bitconvert (v2f32 FPR64:$src))), + (v8i8 (REV32v8i8 FPR64:$src))>; +def : Pat<(v8i8 (bitconvert (v1f64 FPR64:$src))), + (v8i8 (REV64v8i8 FPR64:$src))>; +} -def : Pat<(f64 (bitconvert (v1i64 FPR64:$src))), (f64 FPR64:$src)>; +let Predicates = [IsLE] in { def : Pat<(f64 (bitconvert (v2i32 FPR64:$src))), (f64 FPR64:$src)>; def : Pat<(f64 (bitconvert (v4i16 FPR64:$src))), (f64 FPR64:$src)>; -def : Pat<(f64 (bitconvert (v8i8 FPR64:$src))), (f64 FPR64:$src)>; def : Pat<(f64 (bitconvert (v2f32 FPR64:$src))), (f64 FPR64:$src)>; +def : Pat<(f64 (bitconvert (v8i8 FPR64:$src))), (f64 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(f64 (bitconvert (v2i32 FPR64:$src))), + (f64 (REV64v2i32 FPR64:$src))>; +def : Pat<(f64 (bitconvert (v4i16 FPR64:$src))), + (f64 (REV64v4i16 FPR64:$src))>; +def : Pat<(f64 (bitconvert (v2f32 FPR64:$src))), + (f64 (REV64v2i32 FPR64:$src))>; +def : Pat<(f64 (bitconvert (v8i8 FPR64:$src))), + (f64 (REV64v8i8 FPR64:$src))>; +} +def : Pat<(f64 (bitconvert (v1i64 FPR64:$src))), (f64 FPR64:$src)>; def : Pat<(f64 (bitconvert (v1f64 FPR64:$src))), (f64 FPR64:$src)>; -def : Pat<(v1f64 (bitconvert (v1i64 FPR64:$src))), (v1f64 FPR64:$src)>; +let Predicates = [IsLE] in { def : Pat<(v1f64 (bitconvert (v2i32 FPR64:$src))), (v1f64 FPR64:$src)>; def : Pat<(v1f64 (bitconvert (v4i16 FPR64:$src))), (v1f64 FPR64:$src)>; def : Pat<(v1f64 (bitconvert (v8i8 FPR64:$src))), (v1f64 FPR64:$src)>; -def : Pat<(v1f64 (bitconvert (f64 FPR64:$src))), (v1f64 FPR64:$src)>; def : Pat<(v1f64 (bitconvert (v2f32 FPR64:$src))), (v1f64 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v1f64 (bitconvert (v2i32 FPR64:$src))), + (v1f64 (REV64v2i32 FPR64:$src))>; +def : Pat<(v1f64 (bitconvert (v4i16 FPR64:$src))), + (v1f64 (REV64v4i16 FPR64:$src))>; +def : Pat<(v1f64 (bitconvert (v8i8 FPR64:$src))), + (v1f64 (REV64v8i8 FPR64:$src))>; +def : Pat<(v1f64 (bitconvert (v2f32 FPR64:$src))), + (v1f64 (REV64v2i32 FPR64:$src))>; +} +def : Pat<(v1f64 (bitconvert (v1i64 FPR64:$src))), (v1f64 FPR64:$src)>; +def : Pat<(v1f64 (bitconvert (f64 FPR64:$src))), (v1f64 FPR64:$src)>; -def : Pat<(v2f32 (bitconvert (f64 FPR64:$src))), (v2f32 FPR64:$src)>; +let Predicates = [IsLE] in { def : Pat<(v2f32 (bitconvert (v1i64 FPR64:$src))), (v2f32 FPR64:$src)>; -def : Pat<(v2f32 (bitconvert (v2i32 FPR64:$src))), (v2f32 FPR64:$src)>; def : Pat<(v2f32 (bitconvert (v4i16 FPR64:$src))), (v2f32 FPR64:$src)>; def : Pat<(v2f32 (bitconvert (v8i8 FPR64:$src))), (v2f32 FPR64:$src)>; def : Pat<(v2f32 (bitconvert (v1f64 FPR64:$src))), (v2f32 FPR64:$src)>; +def : Pat<(v2f32 (bitconvert (f64 FPR64:$src))), (v2f32 FPR64:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v2f32 (bitconvert (v1i64 FPR64:$src))), + (v2f32 (REV64v2i32 FPR64:$src))>; +def : Pat<(v2f32 (bitconvert (v4i16 FPR64:$src))), + (v2f32 (REV32v4i16 FPR64:$src))>; +def : Pat<(v2f32 (bitconvert (v8i8 FPR64:$src))), + (v2f32 (REV32v8i8 FPR64:$src))>; +def : Pat<(v2f32 (bitconvert (v1f64 FPR64:$src))), + (v2f32 (REV64v2i32 FPR64:$src))>; +def : Pat<(v2f32 (bitconvert (f64 FPR64:$src))), + (v2f32 (REV64v2i32 FPR64:$src))>; +} +def : Pat<(v2f32 (bitconvert (v2i32 FPR64:$src))), (v2f32 FPR64:$src)>; - +let Predicates = [IsLE] in { def : Pat<(f128 (bitconvert (v2i64 FPR128:$src))), (f128 FPR128:$src)>; def : Pat<(f128 (bitconvert (v4i32 FPR128:$src))), (f128 FPR128:$src)>; def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))), (f128 FPR128:$src)>; def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))), (f128 FPR128:$src)>; def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))), (f128 FPR128:$src)>; +def : Pat<(f128 (bitconvert (v16i8 FPR128:$src))), (f128 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(f128 (bitconvert (v2i64 FPR128:$src))), + (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>; +def : Pat<(f128 (bitconvert (v4i32 FPR128:$src))), + (f128 (EXTv16i8 (REV64v4i32 FPR128:$src), + (REV64v4i32 FPR128:$src), (i32 8)))>; +def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))), + (f128 (EXTv16i8 (REV64v8i16 FPR128:$src), + (REV64v8i16 FPR128:$src), (i32 8)))>; +def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))), + (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>; +def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))), + (f128 (EXTv16i8 (REV64v4i32 FPR128:$src), + (REV64v4i32 FPR128:$src), (i32 8)))>; +def : Pat<(f128 (bitconvert (v16i8 FPR128:$src))), + (f128 (EXTv16i8 (REV64v16i8 FPR128:$src), + (REV64v16i8 FPR128:$src), (i32 8)))>; +} +let Predicates = [IsLE] in { def : Pat<(v2f64 (bitconvert (f128 FPR128:$src))), (v2f64 FPR128:$src)>; def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))), (v2f64 FPR128:$src)>; def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))), (v2f64 FPR128:$src)>; def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))), (v2f64 FPR128:$src)>; -def : Pat<(v2f64 (bitconvert (v2i64 FPR128:$src))), (v2f64 FPR128:$src)>; def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))), (v2f64 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v2f64 (bitconvert (f128 FPR128:$src))), + (v2f64 (EXTv16i8 FPR128:$src, + FPR128:$src, (i32 8)))>; +def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))), + (v2f64 (REV64v4i32 FPR128:$src))>; +def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))), + (v2f64 (REV64v8i16 FPR128:$src))>; +def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))), + (v2f64 (REV64v16i8 FPR128:$src))>; +def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))), + (v2f64 (REV64v4i32 FPR128:$src))>; +} +def : Pat<(v2f64 (bitconvert (v2i64 FPR128:$src))), (v2f64 FPR128:$src)>; +let Predicates = [IsLE] in { def : Pat<(v4f32 (bitconvert (f128 FPR128:$src))), (v4f32 FPR128:$src)>; -def : Pat<(v4f32 (bitconvert (v4i32 FPR128:$src))), (v4f32 FPR128:$src)>; def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))), (v4f32 FPR128:$src)>; def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))), (v4f32 FPR128:$src)>; def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))), (v4f32 FPR128:$src)>; def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))), (v4f32 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v4f32 (bitconvert (f128 FPR128:$src))), + (v4f32 (EXTv16i8 (REV64v4i32 FPR128:$src), + (REV64v4i32 FPR128:$src), (i32 8)))>; +def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))), + (v4f32 (REV32v8i16 FPR128:$src))>; +def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))), + (v4f32 (REV32v16i8 FPR128:$src))>; +def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))), + (v4f32 (REV64v4i32 FPR128:$src))>; +def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))), + (v4f32 (REV64v4i32 FPR128:$src))>; +} +def : Pat<(v4f32 (bitconvert (v4i32 FPR128:$src))), (v4f32 FPR128:$src)>; +let Predicates = [IsLE] in { def : Pat<(v2i64 (bitconvert (f128 FPR128:$src))), (v2i64 FPR128:$src)>; def : Pat<(v2i64 (bitconvert (v4i32 FPR128:$src))), (v2i64 FPR128:$src)>; def : Pat<(v2i64 (bitconvert (v8i16 FPR128:$src))), (v2i64 FPR128:$src)>; def : Pat<(v2i64 (bitconvert (v16i8 FPR128:$src))), (v2i64 FPR128:$src)>; -def : Pat<(v2i64 (bitconvert (v2f64 FPR128:$src))), (v2i64 FPR128:$src)>; def : Pat<(v2i64 (bitconvert (v4f32 FPR128:$src))), (v2i64 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v2i64 (bitconvert (f128 FPR128:$src))), + (v2i64 (EXTv16i8 FPR128:$src, + FPR128:$src, (i32 8)))>; +def : Pat<(v2i64 (bitconvert (v4i32 FPR128:$src))), + (v2i64 (REV64v4i32 FPR128:$src))>; +def : Pat<(v2i64 (bitconvert (v8i16 FPR128:$src))), + (v2i64 (REV64v8i16 FPR128:$src))>; +def : Pat<(v2i64 (bitconvert (v16i8 FPR128:$src))), + (v2i64 (REV64v16i8 FPR128:$src))>; +def : Pat<(v2i64 (bitconvert (v4f32 FPR128:$src))), + (v2i64 (REV64v4i32 FPR128:$src))>; +} +def : Pat<(v2i64 (bitconvert (v2f64 FPR128:$src))), (v2i64 FPR128:$src)>; +let Predicates = [IsLE] in { def : Pat<(v4i32 (bitconvert (f128 FPR128:$src))), (v4i32 FPR128:$src)>; def : Pat<(v4i32 (bitconvert (v2i64 FPR128:$src))), (v4i32 FPR128:$src)>; def : Pat<(v4i32 (bitconvert (v8i16 FPR128:$src))), (v4i32 FPR128:$src)>; def : Pat<(v4i32 (bitconvert (v16i8 FPR128:$src))), (v4i32 FPR128:$src)>; def : Pat<(v4i32 (bitconvert (v2f64 FPR128:$src))), (v4i32 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v4i32 (bitconvert (f128 FPR128:$src))), + (v4i32 (EXTv16i8 (REV64v4i32 FPR128:$src), + (REV64v4i32 FPR128:$src), + (i32 8)))>; +def : Pat<(v4i32 (bitconvert (v2i64 FPR128:$src))), + (v4i32 (REV64v4i32 FPR128:$src))>; +def : Pat<(v4i32 (bitconvert (v8i16 FPR128:$src))), + (v4i32 (REV32v8i16 FPR128:$src))>; +def : Pat<(v4i32 (bitconvert (v16i8 FPR128:$src))), + (v4i32 (REV32v16i8 FPR128:$src))>; +def : Pat<(v4i32 (bitconvert (v2f64 FPR128:$src))), + (v4i32 (REV64v4i32 FPR128:$src))>; +} def : Pat<(v4i32 (bitconvert (v4f32 FPR128:$src))), (v4i32 FPR128:$src)>; +let Predicates = [IsLE] in { def : Pat<(v8i16 (bitconvert (f128 FPR128:$src))), (v8i16 FPR128:$src)>; def : Pat<(v8i16 (bitconvert (v2i64 FPR128:$src))), (v8i16 FPR128:$src)>; def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))), (v8i16 FPR128:$src)>; def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))), (v8i16 FPR128:$src)>; def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))), (v8i16 FPR128:$src)>; def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))), (v8i16 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v8i16 (bitconvert (f128 FPR128:$src))), + (v8i16 (EXTv16i8 (REV64v8i16 FPR128:$src), + (REV64v8i16 FPR128:$src), + (i32 8)))>; +def : Pat<(v8i16 (bitconvert (v2i64 FPR128:$src))), + (v8i16 (REV64v8i16 FPR128:$src))>; +def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))), + (v8i16 (REV32v8i16 FPR128:$src))>; +def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))), + (v8i16 (REV16v16i8 FPR128:$src))>; +def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))), + (v8i16 (REV64v8i16 FPR128:$src))>; +def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))), + (v8i16 (REV32v8i16 FPR128:$src))>; +} +let Predicates = [IsLE] in { def : Pat<(v16i8 (bitconvert (f128 FPR128:$src))), (v16i8 FPR128:$src)>; def : Pat<(v16i8 (bitconvert (v2i64 FPR128:$src))), (v16i8 FPR128:$src)>; def : Pat<(v16i8 (bitconvert (v4i32 FPR128:$src))), (v16i8 FPR128:$src)>; def : Pat<(v16i8 (bitconvert (v8i16 FPR128:$src))), (v16i8 FPR128:$src)>; def : Pat<(v16i8 (bitconvert (v2f64 FPR128:$src))), (v16i8 FPR128:$src)>; def : Pat<(v16i8 (bitconvert (v4f32 FPR128:$src))), (v16i8 FPR128:$src)>; +} +let Predicates = [IsBE] in { +def : Pat<(v16i8 (bitconvert (f128 FPR128:$src))), + (v16i8 (EXTv16i8 (REV64v16i8 FPR128:$src), + (REV64v16i8 FPR128:$src), + (i32 8)))>; +def : Pat<(v16i8 (bitconvert (v2i64 FPR128:$src))), + (v16i8 (REV64v16i8 FPR128:$src))>; +def : Pat<(v16i8 (bitconvert (v4i32 FPR128:$src))), + (v16i8 (REV32v16i8 FPR128:$src))>; +def : Pat<(v16i8 (bitconvert (v8i16 FPR128:$src))), + (v16i8 (REV16v16i8 FPR128:$src))>; +def : Pat<(v16i8 (bitconvert (v2f64 FPR128:$src))), + (v16i8 (REV64v16i8 FPR128:$src))>; +def : Pat<(v16i8 (bitconvert (v4f32 FPR128:$src))), + (v16i8 (REV32v16i8 FPR128:$src))>; +} def : Pat<(v8i8 (extract_subvector (v16i8 FPR128:$Rn), (i64 1))), (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>; diff --git a/test/CodeGen/ARM64/big-endian-bitconverts.ll b/test/CodeGen/ARM64/big-endian-bitconverts.ll new file mode 100644 index 00000000000..51ea42611c2 --- /dev/null +++ b/test/CodeGen/ARM64/big-endian-bitconverts.ll @@ -0,0 +1,1100 @@ +; RUN: llc -mtriple arm64_be < %s -arm64-load-store-opt=false -o - | FileCheck %s + +; CHECK-LABEL: test_i64_f64: +define void @test_i64_f64(double* %p, i64* %q) { +; CHECK: ldr +; CHECK: str + %1 = load double* %p + %2 = fadd double %1, %1 + %3 = bitcast double %2 to i64 + %4 = add i64 %3, %3 + store i64 %4, i64* %q + ret void +} + +; CHECK-LABEL: test_i64_v1i64: +define void @test_i64_v1i64(<1 x i64>* %p, i64* %q) { +; CHECK: ldr +; CHECK: str + %1 = load <1 x i64>* %p + %2 = add <1 x i64> %1, %1 + %3 = bitcast <1 x i64> %2 to i64 + %4 = add i64 %3, %3 + store i64 %4, i64* %q + ret void +} + +; CHECK-LABEL: test_i64_v2f32: +define void @test_i64_v2f32(<2 x float>* %p, i64* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: str + %1 = load <2 x float>* %p + %2 = fadd <2 x float> %1, %1 + %3 = bitcast <2 x float> %2 to i64 + %4 = add i64 %3, %3 + store i64 %4, i64* %q + ret void +} + +; CHECK-LABEL: test_i64_v2i32: +define void @test_i64_v2i32(<2 x i32>* %p, i64* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: str + %1 = load <2 x i32>* %p + %2 = add <2 x i32> %1, %1 + %3 = bitcast <2 x i32> %2 to i64 + %4 = add i64 %3, %3 + store i64 %4, i64* %q + ret void +} + +; CHECK-LABEL: test_i64_v4i16: +define void @test_i64_v4i16(<4 x i16>* %p, i64* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4h } +; CHECK: rev64 v{{[0-9]+}}.4h +; CHECK: str + %1 = load <4 x i16>* %p + %2 = add <4 x i16> %1, %1 + %3 = bitcast <4 x i16> %2 to i64 + %4 = add i64 %3, %3 + store i64 %4, i64* %q + ret void +} + +; CHECK-LABEL: test_i64_v8i8: +define void @test_i64_v8i8(<8 x i8>* %p, i64* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8b } +; CHECK: rev64 v{{[0-9]+}}.8b +; CHECK: str + %1 = load <8 x i8>* %p + %2 = add <8 x i8> %1, %1 + %3 = bitcast <8 x i8> %2 to i64 + %4 = add i64 %3, %3 + store i64 %4, i64* %q + ret void +} + +; CHECK-LABEL: test_f64_i64: +define void @test_f64_i64(i64* %p, double* %q) { +; CHECK: ldr +; CHECK: str + %1 = load i64* %p + %2 = add i64 %1, %1 + %3 = bitcast i64 %2 to double + %4 = fadd double %3, %3 + store double %4, double* %q + ret void +} + +; CHECK-LABEL: test_f64_v1i64: +define void @test_f64_v1i64(<1 x i64>* %p, double* %q) { +; CHECK: ldr +; CHECK: str + %1 = load <1 x i64>* %p + %2 = add <1 x i64> %1, %1 + %3 = bitcast <1 x i64> %2 to double + %4 = fadd double %3, %3 + store double %4, double* %q + ret void +} + +; CHECK-LABEL: test_f64_v2f32: +define void @test_f64_v2f32(<2 x float>* %p, double* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: str + %1 = load <2 x float>* %p + %2 = fadd <2 x float> %1, %1 + %3 = bitcast <2 x float> %2 to double + %4 = fadd double %3, %3 + store double %4, double* %q + ret void +} + +; CHECK-LABEL: test_f64_v2i32: +define void @test_f64_v2i32(<2 x i32>* %p, double* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: str + %1 = load <2 x i32>* %p + %2 = add <2 x i32> %1, %1 + %3 = bitcast <2 x i32> %2 to double + %4 = fadd double %3, %3 + store double %4, double* %q + ret void +} + +; CHECK-LABEL: test_f64_v4i16: +define void @test_f64_v4i16(<4 x i16>* %p, double* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4h } +; CHECK: rev64 v{{[0-9]+}}.4h +; CHECK: str + %1 = load <4 x i16>* %p + %2 = add <4 x i16> %1, %1 + %3 = bitcast <4 x i16> %2 to double + %4 = fadd double %3, %3 + store double %4, double* %q + ret void +} + +; CHECK-LABEL: test_f64_v8i8: +define void @test_f64_v8i8(<8 x i8>* %p, double* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8b } +; CHECK: rev64 v{{[0-9]+}}.8b +; CHECK: str + %1 = load <8 x i8>* %p + %2 = add <8 x i8> %1, %1 + %3 = bitcast <8 x i8> %2 to double + %4 = fadd double %3, %3 + store double %4, double* %q + ret void +} + +; CHECK-LABEL: test_v1i64_i64: +define void @test_v1i64_i64(i64* %p, <1 x i64>* %q) { +; CHECK: ldr +; CHECK: str + %1 = load i64* %p + %2 = add i64 %1, %1 + %3 = bitcast i64 %2 to <1 x i64> + %4 = add <1 x i64> %3, %3 + store <1 x i64> %4, <1 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v1i64_f64: +define void @test_v1i64_f64(double* %p, <1 x i64>* %q) { +; CHECK: ldr +; CHECK: str + %1 = load double* %p + %2 = fadd double %1, %1 + %3 = bitcast double %2 to <1 x i64> + %4 = add <1 x i64> %3, %3 + store <1 x i64> %4, <1 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v1i64_v2f32: +define void @test_v1i64_v2f32(<2 x float>* %p, <1 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: str + %1 = load <2 x float>* %p + %2 = fadd <2 x float> %1, %1 + %3 = bitcast <2 x float> %2 to <1 x i64> + %4 = add <1 x i64> %3, %3 + store <1 x i64> %4, <1 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v1i64_v2i32: +define void @test_v1i64_v2i32(<2 x i32>* %p, <1 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: str + %1 = load <2 x i32>* %p + %2 = add <2 x i32> %1, %1 + %3 = bitcast <2 x i32> %2 to <1 x i64> + %4 = add <1 x i64> %3, %3 + store <1 x i64> %4, <1 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v1i64_v4i16: +define void @test_v1i64_v4i16(<4 x i16>* %p, <1 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4h } +; CHECK: rev64 v{{[0-9]+}}.4h +; CHECK: str + %1 = load <4 x i16>* %p + %2 = add <4 x i16> %1, %1 + %3 = bitcast <4 x i16> %2 to <1 x i64> + %4 = add <1 x i64> %3, %3 + store <1 x i64> %4, <1 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v1i64_v8i8: +define void @test_v1i64_v8i8(<8 x i8>* %p, <1 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8b } +; CHECK: rev64 v{{[0-9]+}}.8b +; CHECK: str + %1 = load <8 x i8>* %p + %2 = add <8 x i8> %1, %1 + %3 = bitcast <8 x i8> %2 to <1 x i64> + %4 = add <1 x i64> %3, %3 + store <1 x i64> %4, <1 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v2f32_i64: +define void @test_v2f32_i64(i64* %p, <2 x float>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load i64* %p + %2 = add i64 %1, %1 + %3 = bitcast i64 %2 to <2 x float> + %4 = fadd <2 x float> %3, %3 + store <2 x float> %4, <2 x float>* %q + ret void +} + +; CHECK-LABEL: test_v2f32_f64: +define void @test_v2f32_f64(double* %p, <2 x float>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load double* %p + %2 = fadd double %1, %1 + %3 = bitcast double %2 to <2 x float> + %4 = fadd <2 x float> %3, %3 + store <2 x float> %4, <2 x float>* %q + ret void +} + +; CHECK-LABEL: test_v2f32_v1i64: +define void @test_v2f32_v1i64(<1 x i64>* %p, <2 x float>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <1 x i64>* %p + %2 = add <1 x i64> %1, %1 + %3 = bitcast <1 x i64> %2 to <2 x float> + %4 = fadd <2 x float> %3, %3 + store <2 x float> %4, <2 x float>* %q + ret void +} + +; CHECK-LABEL: test_v2f32_v2i32: +define void @test_v2f32_v2i32(<2 x i32>* %p, <2 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <2 x i32>* %p + %2 = add <2 x i32> %1, %1 + %3 = bitcast <2 x i32> %2 to <2 x float> + %4 = fadd <2 x float> %3, %3 + store <2 x float> %4, <2 x float>* %q + ret void +} + +; CHECK-LABEL: test_v2f32_v4i16: +define void @test_v2f32_v4i16(<4 x i16>* %p, <2 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4h } +; CHECK: rev32 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <4 x i16>* %p + %2 = add <4 x i16> %1, %1 + %3 = bitcast <4 x i16> %2 to <2 x float> + %4 = fadd <2 x float> %3, %3 + store <2 x float> %4, <2 x float>* %q + ret void +} + +; CHECK-LABEL: test_v2f32_v8i8: +define void @test_v2f32_v8i8(<8 x i8>* %p, <2 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8b } +; CHECK: rev32 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <8 x i8>* %p + %2 = add <8 x i8> %1, %1 + %3 = bitcast <8 x i8> %2 to <2 x float> + %4 = fadd <2 x float> %3, %3 + store <2 x float> %4, <2 x float>* %q + ret void +} + +; CHECK-LABEL: test_v2i32_i64: +define void @test_v2i32_i64(i64* %p, <2 x i32>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load i64* %p + %2 = add i64 %1, %1 + %3 = bitcast i64 %2 to <2 x i32> + %4 = add <2 x i32> %3, %3 + store <2 x i32> %4, <2 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v2i32_f64: +define void @test_v2i32_f64(double* %p, <2 x i32>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load double* %p + %2 = fadd double %1, %1 + %3 = bitcast double %2 to <2 x i32> + %4 = add <2 x i32> %3, %3 + store <2 x i32> %4, <2 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v2i32_v1i64: +define void @test_v2i32_v1i64(<1 x i64>* %p, <2 x i32>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.2s +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <1 x i64>* %p + %2 = add <1 x i64> %1, %1 + %3 = bitcast <1 x i64> %2 to <2 x i32> + %4 = add <2 x i32> %3, %3 + store <2 x i32> %4, <2 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v2i32_v2f32: +define void @test_v2i32_v2f32(<2 x float>* %p, <2 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <2 x float>* %p + %2 = fadd <2 x float> %1, %1 + %3 = bitcast <2 x float> %2 to <2 x i32> + %4 = add <2 x i32> %3, %3 + store <2 x i32> %4, <2 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v2i32_v4i16: +define void @test_v2i32_v4i16(<4 x i16>* %p, <2 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4h } +; CHECK: rev32 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <4 x i16>* %p + %2 = add <4 x i16> %1, %1 + %3 = bitcast <4 x i16> %2 to <2 x i32> + %4 = add <2 x i32> %3, %3 + store <2 x i32> %4, <2 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v2i32_v8i8: +define void @test_v2i32_v8i8(<8 x i8>* %p, <2 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8b } +; CHECK: rev32 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.2s } + %1 = load <8 x i8>* %p + %2 = add <8 x i8> %1, %1 + %3 = bitcast <8 x i8> %2 to <2 x i32> + %4 = add <2 x i32> %3, %3 + store <2 x i32> %4, <2 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v4i16_i64: +define void @test_v4i16_i64(i64* %p, <4 x i16>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.4h } + %1 = load i64* %p + %2 = add i64 %1, %1 + %3 = bitcast i64 %2 to <4 x i16> + %4 = add <4 x i16> %3, %3 + store <4 x i16> %4, <4 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v4i16_f64: +define void @test_v4i16_f64(double* %p, <4 x i16>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.4h } + %1 = load double* %p + %2 = fadd double %1, %1 + %3 = bitcast double %2 to <4 x i16> + %4 = add <4 x i16> %3, %3 + store <4 x i16> %4, <4 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v4i16_v1i64: +define void @test_v4i16_v1i64(<1 x i64>* %p, <4 x i16>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.4h } + %1 = load <1 x i64>* %p + %2 = add <1 x i64> %1, %1 + %3 = bitcast <1 x i64> %2 to <4 x i16> + %4 = add <4 x i16> %3, %3 + store <4 x i16> %4, <4 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v4i16_v2f32: +define void @test_v4i16_v2f32(<2 x float>* %p, <4 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev32 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.4h } + %1 = load <2 x float>* %p + %2 = fadd <2 x float> %1, %1 + %3 = bitcast <2 x float> %2 to <4 x i16> + %4 = add <4 x i16> %3, %3 + store <4 x i16> %4, <4 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v4i16_v2i32: +define void @test_v4i16_v2i32(<2 x i32>* %p, <4 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev32 v{{[0-9]+}}.4h +; CHECK: st1 { v{{[0-9]+}}.4h } + %1 = load <2 x i32>* %p + %2 = add <2 x i32> %1, %1 + %3 = bitcast <2 x i32> %2 to <4 x i16> + %4 = add <4 x i16> %3, %3 + store <4 x i16> %4, <4 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v4i16_v8i8: +define void @test_v4i16_v8i8(<8 x i8>* %p, <4 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8b } +; CHECK: rev16 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.4h } + %1 = load <8 x i8>* %p + %2 = add <8 x i8> %1, %1 + %3 = bitcast <8 x i8> %2 to <4 x i16> + %4 = add <4 x i16> %3, %3 + store <4 x i16> %4, <4 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v8i8_i64: +define void @test_v8i8_i64(i64* %p, <8 x i8>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.8b } + %1 = load i64* %p + %2 = add i64 %1, %1 + %3 = bitcast i64 %2 to <8 x i8> + %4 = add <8 x i8> %3, %3 + store <8 x i8> %4, <8 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v8i8_f64: +define void @test_v8i8_f64(double* %p, <8 x i8>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.8b } + %1 = load double* %p + %2 = fadd double %1, %1 + %3 = bitcast double %2 to <8 x i8> + %4 = add <8 x i8> %3, %3 + store <8 x i8> %4, <8 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v8i8_v1i64: +define void @test_v8i8_v1i64(<1 x i64>* %p, <8 x i8>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.8b } + %1 = load <1 x i64>* %p + %2 = add <1 x i64> %1, %1 + %3 = bitcast <1 x i64> %2 to <8 x i8> + %4 = add <8 x i8> %3, %3 + store <8 x i8> %4, <8 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v8i8_v2f32: +define void @test_v8i8_v2f32(<2 x float>* %p, <8 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev32 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.8b } + %1 = load <2 x float>* %p + %2 = fadd <2 x float> %1, %1 + %3 = bitcast <2 x float> %2 to <8 x i8> + %4 = add <8 x i8> %3, %3 + store <8 x i8> %4, <8 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v8i8_v2i32: +define void @test_v8i8_v2i32(<2 x i32>* %p, <8 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2s } +; CHECK: rev32 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.8b } + %1 = load <2 x i32>* %p + %2 = add <2 x i32> %1, %1 + %3 = bitcast <2 x i32> %2 to <8 x i8> + %4 = add <8 x i8> %3, %3 + store <8 x i8> %4, <8 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v8i8_v4i16: +define void @test_v8i8_v4i16(<4 x i16>* %p, <8 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4h } +; CHECK: rev16 v{{[0-9]+}}.8b +; CHECK: st1 { v{{[0-9]+}}.8b } + %1 = load <4 x i16>* %p + %2 = add <4 x i16> %1, %1 + %3 = bitcast <4 x i16> %2 to <8 x i8> + %4 = add <8 x i8> %3, %3 + store <8 x i8> %4, <8 x i8>* %q + ret void +} + +; CHECK-LABEL: test_f128_v2f64: +define void @test_f128_v2f64(<2 x double>* %p, fp128* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: ext +; CHECK: str + %1 = load <2 x double>* %p + %2 = fadd <2 x double> %1, %1 + %3 = bitcast <2 x double> %2 to fp128 + %4 = fadd fp128 %3, %3 + store fp128 %4, fp128* %q + ret void +} + +; CHECK-LABEL: test_f128_v2i64: +define void @test_f128_v2i64(<2 x i64>* %p, fp128* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: ext +; CHECK: str + %1 = load <2 x i64>* %p + %2 = add <2 x i64> %1, %1 + %3 = bitcast <2 x i64> %2 to fp128 + %4 = fadd fp128 %3, %3 + store fp128 %4, fp128* %q + ret void +} + +; CHECK-LABEL: test_f128_v4f32: +define void @test_f128_v4f32(<4 x float>* %p, fp128* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: ext +; CHECK: str q + %1 = load <4 x float>* %p + %2 = fadd <4 x float> %1, %1 + %3 = bitcast <4 x float> %2 to fp128 + %4 = fadd fp128 %3, %3 + store fp128 %4, fp128* %q + ret void +} + +; CHECK-LABEL: test_f128_v4i32: +define void @test_f128_v4i32(<4 x i32>* %p, fp128* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4s } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: ext +; CHECK: str + %1 = load <4 x i32>* %p + %2 = add <4 x i32> %1, %1 + %3 = bitcast <4 x i32> %2 to fp128 + %4 = fadd fp128 %3, %3 + store fp128 %4, fp128* %q + ret void +} + +; CHECK-LABEL: test_f128_v8i16: +define void @test_f128_v8i16(<8 x i16>* %p, fp128* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8h } +; CHECK: rev64 v{{[0-9]+}}.8h +; CHECK: ext +; CHECK: str + %1 = load <8 x i16>* %p + %2 = add <8 x i16> %1, %1 + %3 = bitcast <8 x i16> %2 to fp128 + %4 = fadd fp128 %3, %3 + store fp128 %4, fp128* %q + ret void +} + +; CHECK-LABEL: test_f128_v16i8: +define void @test_f128_v16i8(<16 x i8>* %p, fp128* %q) { +; CHECK: ld1 { v{{[0-9]+}}.16b } +; CHECK: ext +; CHECK: str q + %1 = load <16 x i8>* %p + %2 = add <16 x i8> %1, %1 + %3 = bitcast <16 x i8> %2 to fp128 + %4 = fadd fp128 %3, %3 + store fp128 %4, fp128* %q + ret void +} + +; CHECK-LABEL: test_v2f64_f128: +define void @test_v2f64_f128(fp128* %p, <2 x double>* %q) { +; CHECK: ldr +; CHECK: ext +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load fp128* %p + %2 = fadd fp128 %1, %1 + %3 = bitcast fp128 %2 to <2 x double> + %4 = fadd <2 x double> %3, %3 + store <2 x double> %4, <2 x double>* %q + ret void +} + +; CHECK-LABEL: test_v2f64_v2i64: +define void @test_v2f64_v2i64(<2 x i64>* %p, <2 x double>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <2 x i64>* %p + %2 = add <2 x i64> %1, %1 + %3 = bitcast <2 x i64> %2 to <2 x double> + %4 = fadd <2 x double> %3, %3 + store <2 x double> %4, <2 x double>* %q + ret void +} + +; CHECK-LABEL: test_v2f64_v4f32: +define void @test_v2f64_v4f32(<4 x float>* %p, <2 x double>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <4 x float>* %p + %2 = fadd <4 x float> %1, %1 + %3 = bitcast <4 x float> %2 to <2 x double> + %4 = fadd <2 x double> %3, %3 + store <2 x double> %4, <2 x double>* %q + ret void +} + +; CHECK-LABEL: test_v2f64_v4i32: +define void @test_v2f64_v4i32(<4 x i32>* %p, <2 x double>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4s } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <4 x i32>* %p + %2 = add <4 x i32> %1, %1 + %3 = bitcast <4 x i32> %2 to <2 x double> + %4 = fadd <2 x double> %3, %3 + store <2 x double> %4, <2 x double>* %q + ret void +} + +; CHECK-LABEL: test_v2f64_v8i16: +define void @test_v2f64_v8i16(<8 x i16>* %p, <2 x double>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8h } +; CHECK: rev64 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <8 x i16>* %p + %2 = add <8 x i16> %1, %1 + %3 = bitcast <8 x i16> %2 to <2 x double> + %4 = fadd <2 x double> %3, %3 + store <2 x double> %4, <2 x double>* %q + ret void +} + +; CHECK-LABEL: test_v2f64_v16i8: +define void @test_v2f64_v16i8(<16 x i8>* %p, <2 x double>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.16b } +; CHECK: rev64 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <16 x i8>* %p + %2 = add <16 x i8> %1, %1 + %3 = bitcast <16 x i8> %2 to <2 x double> + %4 = fadd <2 x double> %3, %3 + store <2 x double> %4, <2 x double>* %q + ret void +} + +; CHECK-LABEL: test_v2i64_f128: +define void @test_v2i64_f128(fp128* %p, <2 x i64>* %q) { +; CHECK: ldr +; CHECK: ext +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load fp128* %p + %2 = fadd fp128 %1, %1 + %3 = bitcast fp128 %2 to <2 x i64> + %4 = add <2 x i64> %3, %3 + store <2 x i64> %4, <2 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v2i64_v2f64: +define void @test_v2i64_v2f64(<2 x double>* %p, <2 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <2 x double>* %p + %2 = fadd <2 x double> %1, %1 + %3 = bitcast <2 x double> %2 to <2 x i64> + %4 = add <2 x i64> %3, %3 + store <2 x i64> %4, <2 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v2i64_v4f32: +define void @test_v2i64_v4f32(<4 x float>* %p, <2 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <4 x float>* %p + %2 = fadd <4 x float> %1, %1 + %3 = bitcast <4 x float> %2 to <2 x i64> + %4 = add <2 x i64> %3, %3 + store <2 x i64> %4, <2 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v2i64_v4i32: +define void @test_v2i64_v4i32(<4 x i32>* %p, <2 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4s } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <4 x i32>* %p + %2 = add <4 x i32> %1, %1 + %3 = bitcast <4 x i32> %2 to <2 x i64> + %4 = add <2 x i64> %3, %3 + store <2 x i64> %4, <2 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v2i64_v8i16: +define void @test_v2i64_v8i16(<8 x i16>* %p, <2 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8h } +; CHECK: rev64 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <8 x i16>* %p + %2 = add <8 x i16> %1, %1 + %3 = bitcast <8 x i16> %2 to <2 x i64> + %4 = add <2 x i64> %3, %3 + store <2 x i64> %4, <2 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v2i64_v16i8: +define void @test_v2i64_v16i8(<16 x i8>* %p, <2 x i64>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.16b } +; CHECK: rev64 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <16 x i8>* %p + %2 = add <16 x i8> %1, %1 + %3 = bitcast <16 x i8> %2 to <2 x i64> + %4 = add <2 x i64> %3, %3 + store <2 x i64> %4, <2 x i64>* %q + ret void +} + +; CHECK-LABEL: test_v4f32_f128: +define void @test_v4f32_f128(fp128* %p, <4 x float>* %q) { +; CHECK: ldr q +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: ext +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load fp128* %p + %2 = fadd fp128 %1, %1 + %3 = bitcast fp128 %2 to <4 x float> + %4 = fadd <4 x float> %3, %3 + store <4 x float> %4, <4 x float>* %q + ret void +} + +; CHECK-LABEL: test_v4f32_v2f64: +define void @test_v4f32_v2f64(<2 x double>* %p, <4 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <2 x double>* %p + %2 = fadd <2 x double> %1, %1 + %3 = bitcast <2 x double> %2 to <4 x float> + %4 = fadd <4 x float> %3, %3 + store <4 x float> %4, <4 x float>* %q + ret void +} + +; CHECK-LABEL: test_v4f32_v2i64: +define void @test_v4f32_v2i64(<2 x i64>* %p, <4 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <2 x i64>* %p + %2 = add <2 x i64> %1, %1 + %3 = bitcast <2 x i64> %2 to <4 x float> + %4 = fadd <4 x float> %3, %3 + store <4 x float> %4, <4 x float>* %q + ret void +} + +; CHECK-LABEL: test_v4f32_v4i32: +define void @test_v4f32_v4i32(<4 x i32>* %p, <4 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4s } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <4 x i32>* %p + %2 = add <4 x i32> %1, %1 + %3 = bitcast <4 x i32> %2 to <4 x float> + %4 = fadd <4 x float> %3, %3 + store <4 x float> %4, <4 x float>* %q + ret void +} + +; CHECK-LABEL: test_v4f32_v8i16: +define void @test_v4f32_v8i16(<8 x i16>* %p, <4 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8h } +; CHECK: rev32 v{{[0-9]+}}.8h +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <8 x i16>* %p + %2 = add <8 x i16> %1, %1 + %3 = bitcast <8 x i16> %2 to <4 x float> + %4 = fadd <4 x float> %3, %3 + store <4 x float> %4, <4 x float>* %q + ret void +} + +; CHECK-LABEL: test_v4f32_v16i8: +define void @test_v4f32_v16i8(<16 x i8>* %p, <4 x float>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.16b } +; CHECK: rev32 v{{[0-9]+}}.16b +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.2d } + %1 = load <16 x i8>* %p + %2 = add <16 x i8> %1, %1 + %3 = bitcast <16 x i8> %2 to <4 x float> + %4 = fadd <4 x float> %3, %3 + store <4 x float> %4, <4 x float>* %q + ret void +} + +; CHECK-LABEL: test_v4i32_f128: +define void @test_v4i32_f128(fp128* %p, <4 x i32>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: ext +; CHECK: st1 { v{{[0-9]+}}.4s } + %1 = load fp128* %p + %2 = fadd fp128 %1, %1 + %3 = bitcast fp128 %2 to <4 x i32> + %4 = add <4 x i32> %3, %3 + store <4 x i32> %4, <4 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v4i32_v2f64: +define void @test_v4i32_v2f64(<2 x double>* %p, <4 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.4s } + %1 = load <2 x double>* %p + %2 = fadd <2 x double> %1, %1 + %3 = bitcast <2 x double> %2 to <4 x i32> + %4 = add <4 x i32> %3, %3 + store <4 x i32> %4, <4 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v4i32_v2i64: +define void @test_v4i32_v2i64(<2 x i64>* %p, <4 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.4s } + %1 = load <2 x i64>* %p + %2 = add <2 x i64> %1, %1 + %3 = bitcast <2 x i64> %2 to <4 x i32> + %4 = add <4 x i32> %3, %3 + store <4 x i32> %4, <4 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v4i32_v4f32: +define void @test_v4i32_v4f32(<4 x float>* %p, <4 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: st1 { v{{[0-9]+}}.4s } + %1 = load <4 x float>* %p + %2 = fadd <4 x float> %1, %1 + %3 = bitcast <4 x float> %2 to <4 x i32> + %4 = add <4 x i32> %3, %3 + store <4 x i32> %4, <4 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v4i32_v8i16: +define void @test_v4i32_v8i16(<8 x i16>* %p, <4 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8h } +; CHECK: rev32 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.4s } + %1 = load <8 x i16>* %p + %2 = add <8 x i16> %1, %1 + %3 = bitcast <8 x i16> %2 to <4 x i32> + %4 = add <4 x i32> %3, %3 + store <4 x i32> %4, <4 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v4i32_v16i8: +define void @test_v4i32_v16i8(<16 x i8>* %p, <4 x i32>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.16b } +; CHECK: rev32 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.4s } + %1 = load <16 x i8>* %p + %2 = add <16 x i8> %1, %1 + %3 = bitcast <16 x i8> %2 to <4 x i32> + %4 = add <4 x i32> %3, %3 + store <4 x i32> %4, <4 x i32>* %q + ret void +} + +; CHECK-LABEL: test_v8i16_f128: +define void @test_v8i16_f128(fp128* %p, <8 x i16>* %q) { +; CHECK: ldr +; CHECK: rev64 v{{[0-9]+}}.8h +; CHECK: ext +; CHECK: st1 { v{{[0-9]+}}.8h } + %1 = load fp128* %p + %2 = fadd fp128 %1, %1 + %3 = bitcast fp128 %2 to <8 x i16> + %4 = add <8 x i16> %3, %3 + store <8 x i16> %4, <8 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v8i16_v2f64: +define void @test_v8i16_v2f64(<2 x double>* %p, <8 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.8h } + %1 = load <2 x double>* %p + %2 = fadd <2 x double> %1, %1 + %3 = bitcast <2 x double> %2 to <8 x i16> + %4 = add <8 x i16> %3, %3 + store <8 x i16> %4, <8 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v8i16_v2i64: +define void @test_v8i16_v2i64(<2 x i64>* %p, <8 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.8h } + %1 = load <2 x i64>* %p + %2 = add <2 x i64> %1, %1 + %3 = bitcast <2 x i64> %2 to <8 x i16> + %4 = add <8 x i16> %3, %3 + store <8 x i16> %4, <8 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v8i16_v4f32: +define void @test_v8i16_v4f32(<4 x float>* %p, <8 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev32 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.8h } + %1 = load <4 x float>* %p + %2 = fadd <4 x float> %1, %1 + %3 = bitcast <4 x float> %2 to <8 x i16> + %4 = add <8 x i16> %3, %3 + store <8 x i16> %4, <8 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v8i16_v4i32: +define void @test_v8i16_v4i32(<4 x i32>* %p, <8 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4s } +; CHECK: rev32 v{{[0-9]+}}.8h +; CHECK: st1 { v{{[0-9]+}}.8h } + %1 = load <4 x i32>* %p + %2 = add <4 x i32> %1, %1 + %3 = bitcast <4 x i32> %2 to <8 x i16> + %4 = add <8 x i16> %3, %3 + store <8 x i16> %4, <8 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v8i16_v16i8: +define void @test_v8i16_v16i8(<16 x i8>* %p, <8 x i16>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.16b } +; CHECK: rev16 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.8h } + %1 = load <16 x i8>* %p + %2 = add <16 x i8> %1, %1 + %3 = bitcast <16 x i8> %2 to <8 x i16> + %4 = add <8 x i16> %3, %3 + store <8 x i16> %4, <8 x i16>* %q + ret void +} + +; CHECK-LABEL: test_v16i8_f128: +define void @test_v16i8_f128(fp128* %p, <16 x i8>* %q) { +; CHECK: ldr q +; CHECK: rev64 v{{[0-9]+}}.16b +; CHECK: ext +; CHECK: st1 { v{{[0-9]+}}.16b } + %1 = load fp128* %p + %2 = fadd fp128 %1, %1 + %3 = bitcast fp128 %2 to <16 x i8> + %4 = add <16 x i8> %3, %3 + store <16 x i8> %4, <16 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v16i8_v2f64: +define void @test_v16i8_v2f64(<2 x double>* %p, <16 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.16b } + %1 = load <2 x double>* %p + %2 = fadd <2 x double> %1, %1 + %3 = bitcast <2 x double> %2 to <16 x i8> + %4 = add <16 x i8> %3, %3 + store <16 x i8> %4, <16 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v16i8_v2i64: +define void @test_v16i8_v2i64(<2 x i64>* %p, <16 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.16b } + %1 = load <2 x i64>* %p + %2 = add <2 x i64> %1, %1 + %3 = bitcast <2 x i64> %2 to <16 x i8> + %4 = add <16 x i8> %3, %3 + store <16 x i8> %4, <16 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v16i8_v4f32: +define void @test_v16i8_v4f32(<4 x float>* %p, <16 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.2d } +; CHECK: rev64 v{{[0-9]+}}.4s +; CHECK: rev32 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.16b } + %1 = load <4 x float>* %p + %2 = fadd <4 x float> %1, %1 + %3 = bitcast <4 x float> %2 to <16 x i8> + %4 = add <16 x i8> %3, %3 + store <16 x i8> %4, <16 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v16i8_v4i32: +define void @test_v16i8_v4i32(<4 x i32>* %p, <16 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.4s } +; CHECK: rev32 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.16b } + %1 = load <4 x i32>* %p + %2 = add <4 x i32> %1, %1 + %3 = bitcast <4 x i32> %2 to <16 x i8> + %4 = add <16 x i8> %3, %3 + store <16 x i8> %4, <16 x i8>* %q + ret void +} + +; CHECK-LABEL: test_v16i8_v8i16: +define void @test_v16i8_v8i16(<8 x i16>* %p, <16 x i8>* %q) { +; CHECK: ld1 { v{{[0-9]+}}.8h } +; CHECK: rev16 v{{[0-9]+}}.16b +; CHECK: st1 { v{{[0-9]+}}.16b } + %1 = load <8 x i16>* %p + %2 = add <8 x i16> %1, %1 + %3 = bitcast <8 x i16> %2 to <16 x i8> + %4 = add <16 x i8> %3, %3 + store <16 x i8> %4, <16 x i8>* %q + ret void +}