[NVPTX] Implement custom lowering of loads/stores for i1

Loads from i1 become loads from i8 followed by trunc
Stores to i1 become zext to i8 followed by store to i8

Fixes PR13291

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167948 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 26 insertions, 0 deletions

diff --git a/test/CodeGen/NVPTX/pr13291-i1-store.ll b/test/CodeGen/NVPTX/pr13291-i1-store.ll
new file mode 100644
index 0000000..779f779
--- /dev/null
+++ b/test/CodeGen/NVPTX/pr13291-i1-store.ll
@@ -0,0 +1,26 @@
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=PTX32
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix=PTX64
+
+define ptx_kernel void @t1(i1* %a) {
+; PTX32:      mov.u16 %rc{{[0-9]+}}, 0;
+; PTX32-NEXT: st.u8 [%r{{[0-9]+}}], %rc{{[0-9]+}};
+; PTX64:      mov.u16 %rc{{[0-9]+}}, 0;
+; PTX64-NEXT: st.u8 [%rl{{[0-9]+}}], %rc{{[0-9]+}};
+  store i1 false, i1* %a
+  ret void
+}
+
+
+define ptx_kernel void @t2(i1* %a, i8* %b) {
+; PTX32: ld.u8 %rc{{[0-9]+}}, [%r{{[0-9]+}}]
+; PTX32: and.b16 temp, %rc{{[0-9]+}}, 1;
+; PTX32: setp.b16.eq %p{{[0-9]+}}, temp, 1;
+; PTX64: ld.u8 %rc{{[0-9]+}}, [%rl{{[0-9]+}}]
+; PTX64: and.b16 temp, %rc{{[0-9]+}}, 1;
+; PTX64: setp.b16.eq %p{{[0-9]+}}, temp, 1;
+
+  %t1 = load i1* %a
+  %t2 = select i1 %t1, i8 1, i8 2
+  store i8 %t2, i8* %b
+  ret void
+}