diff options
| author | Bill Wendling <isanbard@gmail.com> | 2013-11-26 10:57:43 +0000 |
|---|---|---|
| committer | Bill Wendling <isanbard@gmail.com> | 2013-11-26 10:57:43 +0000 |
| commit | 8a0ff1f236e77214878c9d493e786b30656ad2a1 (patch) | |
| tree | 0fe6119dbbb925eeb91b8f20267f14c0ff38af6a /test/CodeGen/AArch64 | |
| parent | 9ed81d16f71b60c246a7b8e9ed4fdd58a48ce4b9 (diff) | |
| download | external_llvm-8a0ff1f236e77214878c9d493e786b30656ad2a1.zip external_llvm-8a0ff1f236e77214878c9d493e786b30656ad2a1.tar.gz external_llvm-8a0ff1f236e77214878c9d493e786b30656ad2a1.tar.bz2 | |
Merging r195716:
------------------------------------------------------------------------
r195716 | kevinqin | 2013-11-25 19:26:47 -0800 (Mon, 25 Nov 2013) | 3 lines
Refactored the implementation of AArch64 NEON instruction ZIP, UZP
and TRN.
Fix a bug when mixed use of vget_high_u8() and vuzp_u8().
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_34@195735 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/AArch64')
| -rw-r--r-- | test/CodeGen/AArch64/neon-perm.ll | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/test/CodeGen/AArch64/neon-perm.ll b/test/CodeGen/AArch64/neon-perm.ll index 4db4771..4e1756e 100644 --- a/test/CodeGen/AArch64/neon-perm.ll +++ b/test/CodeGen/AArch64/neon-perm.ll @@ -1674,3 +1674,17 @@ entry: %.fca.0.1.insert = insertvalue %struct.poly16x8x2_t %.fca.0.0.insert, <8 x i16> %vtrn1.i, 0, 1 ret %struct.poly16x8x2_t %.fca.0.1.insert } + +define %struct.uint8x8x2_t @test_uzp(<16 x i8> %y) { +; CHECK: test_uzp: + + %vuzp.i = shufflevector <16 x i8> %y, <16 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> + %vuzp1.i = shufflevector <16 x i8> %y, <16 x i8> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> + %.fca.0.0.insert = insertvalue %struct.uint8x8x2_t undef, <8 x i8> %vuzp.i, 0, 0 + %.fca.0.1.insert = insertvalue %struct.uint8x8x2_t %.fca.0.0.insert, <8 x i8> %vuzp1.i, 0, 1 + ret %struct.uint8x8x2_t %.fca.0.1.insert + +; CHECK: dup {{d[0-9]+}}, {{v[0-9]+}}.d[1] +; CHECK-NEXT: uzp1 {{v[0-9]+}}.8b, {{v[0-9]+}}.8b, {{v[0-9]+}}.8b +; CHECK-NEXT: uzp2 {{v[0-9]+}}.8b, {{v[0-9]+}}.8b, {{v[0-9]+}}.8b +} |