[X86] Add a temporary testcase for PR21876/r223996.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224074 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index a4af16a14b4bc60070412ad3e02c6739df03e892..a9ca166c1c7f39916bea266899a2b501c64ce69a 100644 (file)
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -6178,6 +6178,7 @@ multiclass SS41I_pmovx_avx2_patterns<string OpcPrefix, SDNode ExtOp> {
             (!cast<I>(OpcPrefix#DQYrr) VR128:$src)>;
 
   // On AVX2, we also support 256bit inputs.
+  // FIXME: remove these patterns when the old shuffle lowering goes away.
   def : Pat<(v16i16 (ExtOp (v32i8 VR256:$src))),
             (!cast<I>(OpcPrefix#BWYrr) (EXTRACT_SUBREG VR256:$src, sub_xmm))>;
   def : Pat<(v8i32 (ExtOp (v32i8 VR256:$src))),

diff --git a/test/CodeGen/X86/avx2-pmovx-256-old-shuffle.ll b/test/CodeGen/X86/avx2-pmovx-256-old-shuffle.ll
new file mode 100644 (file)
index 0000000..44eb42a
--- /dev/null
+++ b/test/CodeGen/X86/avx2-pmovx-256-old-shuffle.ll
@@ -0,0 +1,29 @@
+; RUN: llc < %s -x86-experimental-vector-shuffle-lowering=false -mattr=+avx2 | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-darwin"
+
+; PR21876
+; The old shuffle lowering sometimes generates VZEXT nodes with both input
+; and output same-sized types, here 256-bits.  For instance, a v8i8 to v8i32
+; zero-extend would become a (v8i32 (VZEXT v32i8)) node, which can't happen
+; otherwise.  The companion commit r223996 added those patterns temporarily.
+; This test, along with the VR256 for AVX2 PMOVXrr instructions, should be
+; removed once the old vector shuffle lowering goes away.
+
+define void @test_avx2_pmovx_256(<8 x i8>* %tmp64, <8 x float>* %tmp75) {
+; CHECK-LABEL: test_avx2_pmovx_256
+; We really don't care about the generated code.
+; CHECK: vpmovzxbd
+; CHECK: vpbroadcastd
+; CHECK: vpand
+; CHECK: vcvtdq2ps
+; CHECK: vmovups
+; CHECK: vzeroupper
+; CHECK: retq
+
+  %wide.load458 = load <8 x i8>* %tmp64, align 1
+  %tmp68 = uitofp <8 x i8> %wide.load458 to <8 x float>
+  store <8 x float> %tmp68, <8 x float>* %tmp75, align 4
+  ret void
+}