[NVPTX] Add missing .v4 qualifier on vector store instruction

llvm-svn: 213276

diff --git a/llvm/lib/Target/NVPTX/NVPTXInstrInfo.td b/llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
index d2c0373..5919fe1 100644 (file)
--- a/llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
+++ b/llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
@@ -1917,7 +1917,7 @@ def StoreParamV2I8   : StoreParamV2Inst<Int16Regs, ".b8">;
 def StoreParamV4I32    : NVPTXInst<(outs), (ins Int32Regs:$val, Int32Regs:$val2,
                                                Int32Regs:$val3, Int32Regs:$val4,
                                                 i32imm:$a, i32imm:$b),
-                   "st.param.b32\t[param$a+$b], {{$val, $val2, $val3, $val4}};",
+                "st.param.v4.b32\t[param$a+$b], {{$val, $val2, $val3, $val4}};",
                          []>;
 
 def StoreParamV4I16    : NVPTXInst<(outs), (ins Int16Regs:$val, Int16Regs:$val2,

diff --git a/llvm/test/CodeGen/NVPTX/vector-call.ll b/llvm/test/CodeGen/NVPTX/vector-call.ll
new file mode 100644 (file)
index 0000000..a03d7fd
--- /dev/null
+++ b/llvm/test/CodeGen/NVPTX/vector-call.ll
@@ -0,0 +1,12 @@
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
+
+target triple = "nvptx-unknown-cuda"
+
+declare void @bar(<4 x i32>)
+
+; CHECK-LABEL @foo
+define void @foo(<4 x i32> %a) {
+; CHECK: st.param.v4.b32
+  tail call void @bar(<4 x i32> %a)
+  ret void
+}