[X86] Add some test cases for 512-bit truncate to 128-bits with min-legal-vector-width=0 and prefer-vector-width=256.

We currently split the 512 type, truncate each half to 128 bits,
concatenate them, and then truncate again. Probably better to
truncate each half to 64-bits and then concat the results
using vpunpcklqdq.

llvm-svn: 367600

1 files changed, 32 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/min-legal-vector-width.ll b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
index 3d39f96adb5..29b35ba7f61 100644
--- a/llvm/test/CodeGen/X86/min-legal-vector-width.ll
+++ b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
@@ -719,3 +719,35 @@ define <4 x i32> @mload_v4i32(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %d
   ret <4 x i32> %res
 }
 declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+
+define <16 x i8> @trunc_v16i32_v16i8(<16 x i32>* %x) nounwind "min-legal-vector-width"="256" {
+; CHECK-LABEL: trunc_v16i32_v16i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmovdqa (%rdi), %ymm0
+; CHECK-NEXT:    vmovdqa 32(%rdi), %ymm1
+; CHECK-NEXT:    vpmovdw %ymm0, %xmm0
+; CHECK-NEXT:    vpmovdw %ymm1, %xmm1
+; CHECK-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; CHECK-NEXT:    vpmovwb %ymm0, %xmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = trunc <16 x i32> %a to <16 x i8>
+  ret <16 x i8> %b
+}
+
+define <8 x i16> @trunc_v8i64_v8i16(<8 x i64>* %x) nounwind "min-legal-vector-width"="256" {
+; CHECK-LABEL: trunc_v8i64_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmovdqa (%rdi), %ymm0
+; CHECK-NEXT:    vmovdqa 32(%rdi), %ymm1
+; CHECK-NEXT:    vpmovqd %ymm0, %xmm0
+; CHECK-NEXT:    vpmovqd %ymm1, %xmm1
+; CHECK-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; CHECK-NEXT:    vpmovdw %ymm0, %xmm0
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %a = load <8 x i64>, <8 x i64>* %x
+  %b = trunc <8 x i64> %a to <8 x i16>
+  ret <8 x i16> %b
+}