Index: lib/Target/NVPTX/NVPTXAsmPrinter.cpp
===================================================================
--- lib/Target/NVPTX/NVPTXAsmPrinter.cpp
+++ lib/Target/NVPTX/NVPTXAsmPrinter.cpp
@@ -1589,7 +1589,18 @@
       unsigned align = PAL.getParamAlignment(paramIndex + 1);
       if (align == 0)
         align = DL.getABITypeAlignment(ETy);
-
+      // Work around a bug in ptxas. When PTX code takes address of
+      // byval parameter with alignment < 4, ptxas generates code to
+      // spill argument into memory. Alas on sm_50+ ptxas generates
+      // SASS code that fails with misaligned access. To work around
+      // the problem, make sure that we align byval parameters by at
+      // least 4. Matching change must be made in LowerCall() where we
+      // prepare parameters for the call.
+      //
+      // TODO: this will need to be undone when we get to support multi-TU
+      // device-side compilation. Hopefully ptxas bug is fixed by then.
+      if (!isKernelFunc && align < 4)
+        align = 4;
       unsigned sz = DL.getTypeAllocSize(ETy);
       O << "\t.param .align " << align << " .b8 ";
       printParamName(I, paramIndex, O);
Index: lib/Target/NVPTX/NVPTXISelLowering.cpp
===================================================================
--- lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -1072,6 +1072,7 @@
   MachineFunction &MF = DAG.getMachineFunction();
   const Function *F = MF.getFunction();
   auto &DL = MF.getDataLayout();
+  bool isKernel = llvm::isKernelFunction(*F);
 
   SDValue tempChain = Chain;
   Chain = DAG.getCALLSEQ_START(Chain,
@@ -1337,11 +1338,15 @@
     // The ByValAlign in the Outs[OIdx].Flags is alway set at this point,
     // so we don't need to worry about natural alignment or not.
     // See TargetLowering::LowerCallTo().
-    SDValue DeclareParamOps[] = {
-      Chain, DAG.getConstant(Outs[OIdx].Flags.getByValAlign(), dl, MVT::i32),
-      DAG.getConstant(paramCount, dl, MVT::i32),
-      DAG.getConstant(sz, dl, MVT::i32), InFlag
-    };
+
+    // Enforce minumum alignment of 4 to work around ptxas miscompile
+    // for sm_50+. See corresponding change in emitFunctionParamList()
+    // for details.
+    if (!isKernel && ArgAlign < 4)
+      ArgAlign = 4;
+    SDValue DeclareParamOps[] = {Chain, DAG.getConstant(ArgAlign, dl, MVT::i32),
+                                 DAG.getConstant(paramCount, dl, MVT::i32),
+                                 DAG.getConstant(sz, dl, MVT::i32), InFlag};
     Chain = DAG.getNode(NVPTXISD::DeclareParam, dl, DeclareParamVTs,
                         DeclareParamOps);
     InFlag = Chain.getValue(1);
Index: test/CodeGen/NVPTX/param-align.ll
===================================================================
--- test/CodeGen/NVPTX/param-align.ll
+++ test/CodeGen/NVPTX/param-align.ll
@@ -23,3 +23,11 @@
 ; CHECK: .param .align 4 .b8 t3_param_0[8]
   ret void
 }
+
+;;; Need at least 4-byte alignment in order to avoid miscompilation by
+;;; ptxas for sm_50+
+define ptx_device void @t4(i8* byval %x) {
+; CHECK: .func t4
+; CHECK: .param .align 4 .b8 t4_param_0[1]
+  ret void
+}