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.
llvm-svn: 181578
diff --git a/llvm/test/CodeGen/R600/mul.ll b/llvm/test/CodeGen/R600/mul.ll
new file mode 100644
index 0000000..7278e90
--- /dev/null
+++ b/llvm/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
+}