maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/load-weird-sizes.ll

32 lines
1.6 KiB
LLVM
Raw Normal View History

[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI-NOHSA -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=CI-HSA -check-prefix=SI %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI-NOHSA -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=EG -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman < %s | FileCheck -check-prefix=R600 -check-prefix=CM -check-prefix=FUNC %s
AMDGPU: Improve load/store of illegal types. There was a combine before to handle the simple copy case. Split this into handling loads and stores separately. We might want to change how this handles some of the vector extloads, since this can result in large code size increases. llvm-svn: 274394
2016-07-02 06:47:50 +08:00
; FUNC-LABEL: {{^}}load_i24:
[AMDGPU] Prevent post-RA scheduler from breaking memory clauses The pre-RA scheduler does load/store clustering, but post-RA scheduler undoes it. Add mutation to prevent it. Differential Revision: https://reviews.llvm.org/D38014 llvm-svn: 313670
2017-09-20 04:54:38 +08:00
; SI-DAG: {{flat|buffer}}_load_ubyte
; SI-DAG: {{flat|buffer}}_load_ushort
AMDGPU: Improve load/store of illegal types. There was a combine before to handle the simple copy case. Split this into handling loads and stores separately. We might want to change how this handles some of the vector extloads, since this can result in large code size increases. llvm-svn: 274394
2016-07-02 06:47:50 +08:00
; SI: {{flat|buffer}}_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @load_i24(i32 addrspace(1)* %out, i24 addrspace(1)* %in) #0 {
AMDGPU: Improve load/store of illegal types. There was a combine before to handle the simple copy case. Split this into handling loads and stores separately. We might want to change how this handles some of the vector extloads, since this can result in large code size increases. llvm-svn: 274394
2016-07-02 06:47:50 +08:00
%1 = load i24, i24 addrspace(1)* %in
%2 = zext i24 %1 to i32
store i32 %2, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}load_i25:
; SI-NOHSA: buffer_load_dword [[VAL:v[0-9]+]]
; SI-NOHSA: buffer_store_dword [[VAL]]
; CI-HSA: flat_load_dword [[VAL:v[0-9]+]]
; CI-HSA: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[VAL]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @load_i25(i32 addrspace(1)* %out, i25 addrspace(1)* %in) #0 {
AMDGPU: Improve load/store of illegal types. There was a combine before to handle the simple copy case. Split this into handling loads and stores separately. We might want to change how this handles some of the vector extloads, since this can result in large code size increases. llvm-svn: 274394
2016-07-02 06:47:50 +08:00
%1 = load i25, i25 addrspace(1)* %in
%2 = zext i25 %1 to i32
store i32 %2, i32 addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }