diff options
Diffstat (limited to 'llvm/test/Transforms/InterleavedAccess')
| -rw-r--r-- | llvm/test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/llvm/test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll b/llvm/test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll index dcef57fc625..1a48be2e7cd 100644 --- a/llvm/test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll +++ b/llvm/test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll @@ -217,3 +217,20 @@ define void @store_factorf64_4_arbitraryMask(<16 x double>* %ptr, <16 x double> store <16 x double> %interleaved.vec, <16 x double>* %ptr, align 16 ret void } + +; This verifies whether the test passes and does not hit any assertions. +; Today, X86InterleavedAccess could have handled this case and +; generate transposed sequence by extending the current implementation +; which would be creating dummy vectors of undef. But it decided not to +; optimize these cases where the load-size is less than Factor * NumberOfElements. +; Because a better sequence can easily be generated by CG. + +@a = local_unnamed_addr global <4 x double> zeroinitializer, align 32 +; Function Attrs: norecurse nounwind readonly uwtable +define <4 x double> @test_unhandled(<4 x double> %b) { +entry: + %0 = load <4 x double>, <4 x double>* @a, align 32 + %1 = shufflevector <4 x double> %0, <4 x double> undef, <4 x i32> <i32 3, i32 undef, i32 undef, i32 undef> + %shuffle = shufflevector <4 x double> %1, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 0, i32 0> + ret <4 x double> %shuffle +} |
