R600: Expand vselect for v4i32 and v2i32

v2: Add vselect v4i32 test

Patch by: Aaron Watry

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Aaron Watry <awatry@gmail.com>
NOTE: This is a candidate for the 3.3 branch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181576 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp
index c6e2136ff48cadd36970de78de603906fcb1c4cc..6dec4d1dbe3684fcb565d84496029f31d910d671 100644 (file)
--- a/lib/Target/R600/R600ISelLowering.cpp
+++ b/lib/Target/R600/R600ISelLowering.cpp
@@ -78,6 +78,9 @@ R600TargetLowering::R600TargetLowering(TargetMachine &TM) :
   setOperationAction(ISD::SELECT, MVT::i32, Custom);
   setOperationAction(ISD::SELECT, MVT::f32, Custom);
 
+  setOperationAction(ISD::VSELECT, MVT::v4i32, Expand);
+  setOperationAction(ISD::VSELECT, MVT::v2i32, Expand);
+
   // Legalize loads and stores to the private address space.
   setOperationAction(ISD::LOAD, MVT::i32, Custom);
   setOperationAction(ISD::LOAD, MVT::v2i32, Custom);

diff --git a/test/CodeGen/R600/vselect.ll b/test/CodeGen/R600/vselect.ll
new file mode 100644 (file)
index 0000000..6e459df
--- /dev/null
+++ b/test/CodeGen/R600/vselect.ll
@@ -0,0 +1,17 @@
+;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
+
+; CHECK: @test_select_v4i32
+; CHECK: CNDE_INT T{{[0-9]+\.[XYZW], PV\.[xyzw], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; CHECK: CNDE_INT * T{{[0-9]+\.[XYZW], PV\.[xyzw], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; CHECK: CNDE_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; CHECK: CNDE_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+
+define void @test_select_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in0, <4 x i32> addrspace(1)* %in1) {
+entry:
+  %0 = load <4 x i32> addrspace(1)* %in0
+  %1 = load <4 x i32> addrspace(1)* %in1
+  %cmp = icmp ne <4 x i32> %0, %1
+  %result = select <4 x i1> %cmp, <4 x i32> %0, <4 x i32> %1
+  store <4 x i32> %result, <4 x i32> addrspace(1)* %out
+  ret void
+}