R600: Expand MUL for v4i32/v2i32

Fixes piglit test for OpenCL builtin mul24, and allows mad24 to run.

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@181578 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp
index ac56ed86438f4e3348acc9d9cd565d9fb03deec0..b9822799e76d628d8234d5171f18d5c7f5a7a04b 100644 (file)
--- a/lib/Target/R600/R600ISelLowering.cpp
+++ b/lib/Target/R600/R600ISelLowering.cpp
@@ -43,6 +43,8 @@ R600TargetLowering::R600TargetLowering(TargetMachine &TM) :
   setOperationAction(ISD::AND,  MVT::v4i32, Expand);
   setOperationAction(ISD::FP_TO_SINT, MVT::v4i32, Expand);
   setOperationAction(ISD::FP_TO_UINT, MVT::v4i32, Expand);
+  setOperationAction(ISD::MUL,  MVT::v2i32, Expand);
+  setOperationAction(ISD::MUL,  MVT::v4i32, Expand);
   setOperationAction(ISD::OR, MVT::v4i32, Expand);
   setOperationAction(ISD::OR, MVT::v2i32, Expand);
   setOperationAction(ISD::SINT_TO_FP, MVT::v4i32, Expand);

diff --git a/test/CodeGen/R600/mul.ll b/test/CodeGen/R600/mul.ll
new file mode 100644 (file)
index 0000000..7278e90
--- /dev/null
+++ b/test/CodeGen/R600/mul.ll
@@ -0,0 +1,16 @@
+;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
+
+; mul24 and mad24 are affected
+;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+
+define void @test(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
+  %b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
+  %a = load <4 x i32> addrspace(1) * %in
+  %b = load <4 x i32> addrspace(1) * %b_ptr
+  %result = mul <4 x i32> %a, %b
+  store <4 x i32> %result, <4 x i32> addrspace(1)* %out
+  ret void
+}