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/trunc-store.ll

19 lines
850 B
LLVM
Raw Normal View History

AMDGPU: Fix v16i32 to v16i8 truncstore llvm-svn: 243731
2015-07-31 12:12:04 +08:00
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
AMDGPU: Fix v16i32 to v16i8 truncstore llvm-svn: 243731
2015-07-31 12:12:04 +08:00
; FUNC-LABEL: {{^}}truncstore_arg_v16i32_to_v16i8:
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: buffer_store_dwordx4
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 @truncstore_arg_v16i32_to_v16i8(<16 x i8> addrspace(1)* %out, <16 x i32> %in) {
AMDGPU: Fix v16i32 to v16i8 truncstore llvm-svn: 243731
2015-07-31 12:12:04 +08:00
%trunc = trunc <16 x i32> %in to <16 x i8>
store <16 x i8> %trunc, <16 x i8> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}truncstore_arg_v16i64_to_v16i8:
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: buffer_store_dwordx4
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 @truncstore_arg_v16i64_to_v16i8(<16 x i8> addrspace(1)* %out, <16 x i64> %in) {
AMDGPU: Fix v16i32 to v16i8 truncstore llvm-svn: 243731
2015-07-31 12:12:04 +08:00
%trunc = trunc <16 x i64> %in to <16 x i8>
store <16 x i8> %trunc, <16 x i8> addrspace(1)* %out
ret void
}