From 6c40d40d709d987dd2674a7c44dcd4c53a80fc23 Mon Sep 17 00:00:00 2001 From: Tom Stellard Date: Fri, 10 May 2013 02:09:34 +0000 Subject: [PATCH] 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 Signed-off-by: Aaron Watry 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 --- lib/Target/R600/R600ISelLowering.cpp | 2 ++ test/CodeGen/R600/mul.ll | 16 ++++++++++++++++ 2 files changed, 18 insertions(+) create mode 100644 test/CodeGen/R600/mul.ll diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp index ac56ed86438..b9822799e76 100644 --- 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 index 00000000000..7278e903984 --- /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 +}