[llvm-commits] [llvm] r140097 - in /llvm/trunk: lib/Target/X86/X86InstrSSE.td test/CodeGen/X86/avx-vinsertf128.ll

[Bruno Cardoso Lopes]

Author: bruno
Date: Mon Sep 19 18:36:50 2011
New Revision: 140097

URL: http://llvm.org/viewvc/llvm-project?rev=140097&view=rev
Log:
Based on the small opt Zvi's patch was trying to achieve, eliminate
128-bit undef subvector insertion into a 256-bit vector

Modified:
    llvm/trunk/lib/Target/X86/X86InstrSSE.td
    llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll

Modified: llvm/trunk/lib/Target/X86/X86InstrSSE.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrSSE.td?rev=140097&r1=140096&r2=140097&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrSSE.td (original)
+++ llvm/trunk/lib/Target/X86/X86InstrSSE.td Mon Sep 19 18:36:50 2011
@@ -157,6 +157,21 @@
 def : Pat<(insert_subvector undef, (v16i8 VR128:$src), (i32 0)),
           (INSERT_SUBREG (v32i8 (IMPLICIT_DEF)), VR128:$src, sub_xmm)>;
 
+// Inserting a 128-bit undef vector into the high part of a 256-bit
+// vector should return the 256-bit vector itself.
+def : Pat<(insert_subvector (v8i32 VR256:$src), undef, (i32 4)),
+          (v8i32 VR256:$src)>;
+def : Pat<(insert_subvector (v8f32 VR256:$src), undef, (i32 4)),
+          (v8f32 VR256:$src)>;
+def : Pat<(insert_subvector (v4i64 VR256:$src), undef, (i32 4)),
+          (v4i64 VR256:$src)>;
+def : Pat<(insert_subvector (v4f64 VR256:$src), undef, (i32 4)),
+          (v4f64 VR256:$src)>;
+def : Pat<(insert_subvector (v16i16 VR256:$src), undef, (i32 4)),
+          (v16i16 VR256:$src)>;
+def : Pat<(insert_subvector (v32i8 VR256:$src), undef, (i32 4)),
+          (v32i8 VR256:$src)>;
+
 // Implicitly promote a 32-bit scalar to a vector.
 def : Pat<(v4f32 (scalar_to_vector FR32:$src)),
           (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FR32:$src, sub_ss)>;

Modified: llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll?rev=140097&r1=140096&r2=140097&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx-vinsertf128.ll Mon Sep 19 18:36:50 2011
@@ -36,3 +36,11 @@
   store <4 x i32> %blendAsInt.i503, <4 x i32>* undef, align 4
   ret void
 }
+
+; CHECK: _C
+; CHECK-NOT: vinsertf128 $1
+define <4 x i32> @C(<4 x i32> %v1) nounwind readonly {
+  %1 = shufflevector <4 x i32> %v1, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %2 = shufflevector <8 x i32> %1, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  ret <4 x i32> %2
+}