R600/SI: Expand add for v2i32 and v4i32

Also add SI tests to existing file and a v2i32 test for both
R600 and SI.

Patch by: Aaron Watry

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Aaron Watry <awatry@gmail.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184481 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tom Stellard 2013-06-20 21:55:30 +00:00
parent eb3aa070c9
commit fe91c515d7
2 changed files with 33 additions and 6 deletions

View File

@ -65,6 +65,8 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
setOperationAction(ISD::ADD, MVT::i64, Legal);
setOperationAction(ISD::ADD, MVT::i32, Legal);
setOperationAction(ISD::ADD, MVT::v4i32, Expand);
setOperationAction(ISD::ADD, MVT::v2i32, Expand);
setOperationAction(ISD::SELECT_CC, MVT::f32, Custom);
setOperationAction(ISD::SELECT_CC, MVT::i32, Custom);

View File

@ -1,11 +1,36 @@
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK %s
; RUN: llc < %s -march=r600 -mcpu=verde | FileCheck --check-prefix=SI-CHECK %s
;CHECK: ADD_INT T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: @test2
;EG-CHECK: ADD_INT T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], literal\.[xyzw]}}
define void @test(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
;SI-CHECK: @test2
;SI-CHECK: V_ADD_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_ADD_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
%b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
%a = load <2 x i32> addrspace(1) * %in
%b = load <2 x i32> addrspace(1) * %b_ptr
%result = add <2 x i32> %a, %b
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
ret void
}
;EG-CHECK: @test4
;EG-CHECK: ADD_INT T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: ADD_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;SI-CHECK: @test4
;SI-CHECK: V_ADD_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_ADD_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_ADD_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_ADD_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
define void @test4(<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