llvm/test/CodeGen/R600/or.ll
Aaron Watry b8ce77752b R600/SI: Expand or of v2i32/v4i32 for SI
Also add lit test for both cases on SI, and v2i32 for evergreen.

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184839 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-25 13:55:29 +00:00

41 lines
1.7 KiB
LLVM

;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
; EG-CHECK: @or_v2i32
; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;SI-CHECK: @or_v2i32
;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
define void @or_v2i32(<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 = or <2 x i32> %a, %b
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
ret void
}
; EG-CHECK: @or_v4i32
; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;SI-CHECK: @or_v4i32
;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
define void @or_v4i32(<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 = or <4 x i32> %a, %b
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
ret void
}