2015-01-06 18:00:21 +00:00
|
|
|
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs< %s | FileCheck --check-prefix=SI --check-prefix=CHECK %s
|
|
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs< %s | FileCheck --check-prefix=CI --check-prefix=CHECK %s
|
2013-10-21 20:03:54 +00:00
|
|
|
|
|
|
|
define void @use_gep_address_space([1024 x i32] addrspace(3)* %array) nounwind {
|
2014-10-01 17:15:17 +00:00
|
|
|
; CHECK-LABEL: {{^}}use_gep_address_space:
|
2014-11-05 14:50:53 +00:00
|
|
|
; CHECK: v_mov_b32_e32 [[PTR:v[0-9]+]], s{{[0-9]+}}
|
|
|
|
; CHECK: ds_write_b32 [[PTR]], v{{[0-9]+}} offset:64
|
2013-10-21 20:03:54 +00:00
|
|
|
%p = getelementptr [1024 x i32] addrspace(3)* %array, i16 0, i16 16
|
|
|
|
store i32 99, i32 addrspace(3)* %p
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
2014-03-19 22:19:49 +00:00
|
|
|
define void @use_gep_address_space_large_offset([1024 x i32] addrspace(3)* %array) nounwind {
|
2014-10-01 17:15:17 +00:00
|
|
|
; CHECK-LABEL: {{^}}use_gep_address_space_large_offset:
|
2014-08-22 18:49:33 +00:00
|
|
|
; The LDS offset will be 65536 bytes, which is larger than the size of LDS on
|
|
|
|
; SI, which is why it is being OR'd with the base pointer.
|
2014-11-05 14:50:53 +00:00
|
|
|
; SI: s_or_b32
|
|
|
|
; CI: s_add_i32
|
|
|
|
; CHECK: ds_write_b32
|
2014-03-19 22:19:49 +00:00
|
|
|
%p = getelementptr [1024 x i32] addrspace(3)* %array, i16 0, i16 16384
|
|
|
|
store i32 99, i32 addrspace(3)* %p
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
2013-10-21 20:03:58 +00:00
|
|
|
define void @gep_as_vector_v4(<4 x [1024 x i32] addrspace(3)*> %array) nounwind {
|
2014-10-01 17:15:17 +00:00
|
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v4:
|
2014-11-05 14:50:53 +00:00
|
|
|
; CHECK: s_add_i32
|
|
|
|
; CHECK: s_add_i32
|
|
|
|
; CHECK: s_add_i32
|
|
|
|
; CHECK: s_add_i32
|
2013-10-21 20:03:58 +00:00
|
|
|
%p = getelementptr <4 x [1024 x i32] addrspace(3)*> %array, <4 x i16> zeroinitializer, <4 x i16> <i16 16, i16 16, i16 16, i16 16>
|
|
|
|
%p0 = extractelement <4 x i32 addrspace(3)*> %p, i32 0
|
|
|
|
%p1 = extractelement <4 x i32 addrspace(3)*> %p, i32 1
|
|
|
|
%p2 = extractelement <4 x i32 addrspace(3)*> %p, i32 2
|
|
|
|
%p3 = extractelement <4 x i32 addrspace(3)*> %p, i32 3
|
|
|
|
store i32 99, i32 addrspace(3)* %p0
|
|
|
|
store i32 99, i32 addrspace(3)* %p1
|
|
|
|
store i32 99, i32 addrspace(3)* %p2
|
|
|
|
store i32 99, i32 addrspace(3)* %p3
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
|
|
|
define void @gep_as_vector_v2(<2 x [1024 x i32] addrspace(3)*> %array) nounwind {
|
2014-10-01 17:15:17 +00:00
|
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v2:
|
2014-11-05 14:50:53 +00:00
|
|
|
; CHECK: s_add_i32
|
|
|
|
; CHECK: s_add_i32
|
2013-10-21 20:03:58 +00:00
|
|
|
%p = getelementptr <2 x [1024 x i32] addrspace(3)*> %array, <2 x i16> zeroinitializer, <2 x i16> <i16 16, i16 16>
|
|
|
|
%p0 = extractelement <2 x i32 addrspace(3)*> %p, i32 0
|
|
|
|
%p1 = extractelement <2 x i32 addrspace(3)*> %p, i32 1
|
|
|
|
store i32 99, i32 addrspace(3)* %p0
|
|
|
|
store i32 99, i32 addrspace(3)* %p1
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|