Instead of always leaving the work to the generic legalizer when

there is no support for native 256-bit shuffles, be more smart in some
cases, for example, when you can extract specific 128-bit parts and use
regular 128-bit shuffles for them. Example:

For this shuffle:
  shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32>
                <i32 1, i32 0, i32 7, i32 6>

This was expanded to:
  vextractf128  $1, %ymm1, %xmm2
  vpextrq $0, %xmm2, %rax
  vmovd %rax, %xmm1
  vpextrq $1, %xmm2, %rax
  vmovd %rax, %xmm2
  vpunpcklqdq %xmm1, %xmm2, %xmm1
  vpextrq $0, %xmm0, %rax
  vmovd %rax, %xmm2
  vpextrq $1, %xmm0, %rax
  vmovd %rax, %xmm0
  vpunpcklqdq %xmm2, %xmm0, %xmm0
  vinsertf128 $1, %xmm1, %ymm0, %ymm0
  ret

Now we get:
  vshufpd $1, %xmm0, %xmm0, %xmm0
  vextractf128  $1, %ymm1, %xmm1
  vshufpd $1, %xmm1, %xmm1, %xmm1
  vinsertf128 $1, %xmm1, %ymm0, %ymm0

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137733 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 43 insertions, 0 deletions

diff --git a/test/CodeGen/X86/avx-basic.ll b/test/CodeGen/X86/avx-basic.ll
index 162f29d..1c10814 100644
--- a/test/CodeGen/X86/avx-basic.ll
+++ b/test/CodeGen/X86/avx-basic.ll
@@ -50,3 +50,46 @@ entry:
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 4>
   ret <4 x i64> %shuffle
 }
+
+;;;
+;;; Check that some 256-bit vectors are xformed into 128 ops
+; CHECK: _A
+; CHECK: vshufpd $1
+; CHECK-NEXT: vextractf128 $1
+; CHECK-NEXT: vshufpd $1
+; CHECK-NEXT: vinsertf128 $1
+define <4 x i64> @A(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 0, i32 7, i32 6>
+  ret <4 x i64> %shuffle
+}
+
+; CHECK: vpunpckhqdq
+; CHECK-NEXT: vextractf128  $1
+; CHECK-NEXT: movlhps
+; CHECK-NEXT: vinsertf128 $1
+define <4 x i64> @B(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 undef, i32 undef, i32 6>
+  ret <4 x i64> %shuffle
+}
+
+; CHECK: movlhps
+; CHECK-NEXT: vextractf128  $1
+; CHECK-NEXT: movlhps
+; CHECK-NEXT: vinsertf128 $1
+define <4 x i64> @C(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 undef, i32 0, i32 undef, i32 6>
+  ret <4 x i64> %shuffle
+}
+
+; CHECK: vpshufd $-96
+; CHECK: vpshufd $-6
+; CHECK: vinsertf128 $1
+define <8 x i32> @D(<8 x i32> %a, <8 x i32> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 10, i32 10, i32 11, i32 11>
+  ret <8 x i32> %shuffle
+}
+