mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-18 10:31:57 +00:00
c0021e43ea
This is a union of these commits:
* R600/SI: Enable more tests for VI which need no changes
* R600/SI: Enable V_BCNT tests for VI
Differences:
- v_bcnt_..._e32 -> _e64
- s_load_dword* inline offset is in bytes instead of dwords
* R600/SI: Enable all tests for VI which use S_LOAD_DWORD
The inline offset is changed from dwords to bytes.
* R600/SI: Enable LDS tests for VI
Differences:
- the s_load_dword inline offset changed from dwords to bytes
- the tests checked very little on CI, so they have been fixed to check all
instructions that "SI" checked
* R600/SI: Enable lshr tests for VI
* R600/SI: Fix divrem64 tests
- "v_lshl_64" was missing "b" before "64"
- added VI-NOT checks
* R600/SI: Enable the SI.tid test for VI
* R600/SI: Enable the frem test for VI
Also, the frem_f64 checking is added for CI-VI.
* R600/SI: Add VI tests for rsq.clamped
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228830 91177308-0d34-0410-b5e6-96231b3b80d8
56 lines
2.3 KiB
LLVM
56 lines
2.3 KiB
LLVM
; 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
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs< %s | FileCheck --check-prefix=CI --check-prefix=CHECK %s
|
|
|
|
define void @use_gep_address_space([1024 x i32] addrspace(3)* %array) nounwind {
|
|
; CHECK-LABEL: {{^}}use_gep_address_space:
|
|
; CHECK: v_mov_b32_e32 [[PTR:v[0-9]+]], s{{[0-9]+}}
|
|
; CHECK: ds_write_b32 [[PTR]], v{{[0-9]+}} offset:64
|
|
%p = getelementptr [1024 x i32] addrspace(3)* %array, i16 0, i16 16
|
|
store i32 99, i32 addrspace(3)* %p
|
|
ret void
|
|
}
|
|
|
|
define void @use_gep_address_space_large_offset([1024 x i32] addrspace(3)* %array) nounwind {
|
|
; CHECK-LABEL: {{^}}use_gep_address_space_large_offset:
|
|
; 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.
|
|
; SI: s_or_b32
|
|
; CI: s_add_i32
|
|
; CHECK: ds_write_b32
|
|
%p = getelementptr [1024 x i32] addrspace(3)* %array, i16 0, i16 16384
|
|
store i32 99, i32 addrspace(3)* %p
|
|
ret void
|
|
}
|
|
|
|
define void @gep_as_vector_v4(<4 x [1024 x i32] addrspace(3)*> %array) nounwind {
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v4:
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
%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 {
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v2:
|
|
; CHECK: s_add_i32
|
|
; CHECK: s_add_i32
|
|
%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
|
|
}
|
|
|