[NVPTX] aligned byte-buffers for vector return types

Summary:
Fixes PR21100 which is caused by inconsistency between the declared return type
and the expected return type at the call site. The new behavior is consistent
with nvcc and the NVPTXTargetLowering::getPrototype function.

Test Plan: test/Codegen/NVPTX/vector-return.ll

Reviewers: jholewinski

Reviewed By: jholewinski

Subscribers: llvm-commits, meheff, eliben, jholewinski

Differential Revision: http://reviews.llvm.org/D5612

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220607 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/NVPTX/NVPTXISelLowering.cpp b/lib/Target/NVPTX/NVPTXISelLowering.cpp
index 6cccf93028d3ba41ae189d92ff4bca8375cc52d3..866017e49db5c6cebdf48c96d4f26f68cfd0b897 100644 (file)
--- a/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -1355,7 +1355,12 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
     //  .param .align 16 .b8 retval0[<size-in-bytes>], or
     //  .param .b<size-in-bits> retval0
     unsigned resultsz = TD->getTypeAllocSizeInBits(retTy);
-    if (retTy->isSingleValueType()) {
+    // Emit ".param .b<size-in-bits> retval0" instead of byte arrays only for
+    // these three types to match the logic in
+    // NVPTXAsmPrinter::printReturnValStr and NVPTXTargetLowering::getPrototype.
+    // Plus, this behavior is consistent with nvcc's.
+    if (retTy->isFloatingPointTy() || retTy->isIntegerTy() ||
+        retTy->isPointerTy()) {
       // Scalar needs to be at least 32bit wide
       if (resultsz < 32)
         resultsz = 32;

diff --git a/test/CodeGen/NVPTX/vector-return.ll b/test/CodeGen/NVPTX/vector-return.ll
new file mode 100644 (file)
index 0000000..15e50f8
--- /dev/null
+++ b/test/CodeGen/NVPTX/vector-return.ll
@@ -0,0 +1,14 @@
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_35 | FileCheck %s
+
+declare <2 x float> @bar(<2 x float> %input)
+
+define void @foo(<2 x float> %input, <2 x float>* %output) {
+; CHECK-LABEL: @foo
+entry:
+  %call = tail call <2 x float> @bar(<2 x float> %input)
+; CHECK: .param .align 8 .b8 retval0[8];
+; CHECK: ld.param.v2.f32 {[[ELEM1:%f[0-9]+]], [[ELEM2:%f[0-9]+]]}, [retval0+0];
+  store <2 x float> %call, <2 x float>* %output, align 8
+; CHECK: st.v2.f32 [{{%rd[0-9]+}}], {[[ELEM1]], [[ELEM2]]}
+  ret void
+}