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/store-v3i64.ll

128 lines
3.8 KiB
LLVM
Raw Normal View History

AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI %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=GCN -check-prefix=VI %s
R600/SI: Add failing test for 3 x i64 vectors. Stores of <4 x i64> do work (although they do expand to 4 stores instead of 2), but 3 x i64 vectors fail to select. llvm-svn: 200989
2014-02-08 04:29:40 +08:00
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
; GCN-LABEL: {{^}}global_store_v3i64:
; GCN-DAG: buffer_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:16
; GCN-DAG: buffer_store_dwordx4 v{{\[[0-9]+:[0-9]+\]}}, off, s{{\[[0-9]+:[0-9]+\]}}, 0{{$}}
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 @global_store_v3i64(<3 x i64> addrspace(1)* %out, <3 x i64> %x) {
R600/SI: Add failing test for 3 x i64 vectors. Stores of <4 x i64> do work (although they do expand to 4 stores instead of 2), but 3 x i64 vectors fail to select. llvm-svn: 200989
2014-02-08 04:29:40 +08:00
store <3 x i64> %x, <3 x i64> addrspace(1)* %out, align 32
ret void
}
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
; GCN-LABEL: {{^}}global_store_v3i64_unaligned:
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
; GCN: buffer_store_byte
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 @global_store_v3i64_unaligned(<3 x i64> addrspace(1)* %out, <3 x i64> %x) {
R600/SI: Add failing test for 3 x i64 vectors. Stores of <4 x i64> do work (although they do expand to 4 stores instead of 2), but 3 x i64 vectors fail to select. llvm-svn: 200989
2014-02-08 04:29:40 +08:00
store <3 x i64> %x, <3 x i64> addrspace(1)* %out, align 1
ret void
}
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
; GCN-LABEL: {{^}}local_store_v3i64:
AMDGPU/SI: Improve SILoadStoreOptimizer and run it before the scheduler Summary: The SILoadStoreOptimizer can now look ahead more then one instruction when looking for instructions to merge, which greatly improves the number of loads/stores that we are able to merge. Moving the pass before scheduling avoids increasing register pressure after the scheduler, so that the scheduler's register pressure estimates will be more accurate. It also gives more consistent results, since it is no longer affected by minor scheduling changes. Reviewers: arsenm Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23814 llvm-svn: 279991
2016-08-30 03:15:22 +08:00
; GCN: ds_write2_b64
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
; GCN: ds_write_b64
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 @local_store_v3i64(<3 x i64> addrspace(3)* %out, <3 x i64> %x) {
R600/SI: Add failing test for 3 x i64 vectors. Stores of <4 x i64> do work (although they do expand to 4 stores instead of 2), but 3 x i64 vectors fail to select. llvm-svn: 200989
2014-02-08 04:29:40 +08:00
store <3 x i64> %x, <3 x i64> addrspace(3)* %out, align 32
ret void
}
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
; GCN-LABEL: {{^}}local_store_v3i64_unaligned:
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
; GCN: ds_write_b8
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 @local_store_v3i64_unaligned(<3 x i64> addrspace(3)* %out, <3 x i64> %x) {
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
store <3 x i64> %x, <3 x i64> addrspace(3)* %out, align 1
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v3i64_to_v3i32:
; GCN-DAG: buffer_store_dwordx2
; GCN-DAG: buffer_store_dword v
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 @global_truncstore_v3i64_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i64> %x) {
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
%trunc = trunc <3 x i64> %x to <3 x i32>
store <3 x i32> %trunc, <3 x i32> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v3i64_to_v3i16:
; GCN-DAG: buffer_store_short
; GCN-DAG: buffer_store_dword v
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 @global_truncstore_v3i64_to_v3i16(<3 x i16> addrspace(1)* %out, <3 x i64> %x) {
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
%trunc = trunc <3 x i64> %x to <3 x i16>
store <3 x i16> %trunc, <3 x i16> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v3i64_to_v3i8:
; GCN-DAG: buffer_store_short
; GCN-DAG: buffer_store_byte v
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 @global_truncstore_v3i64_to_v3i8(<3 x i8> addrspace(1)* %out, <3 x i64> %x) {
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
%trunc = trunc <3 x i64> %x to <3 x i8>
store <3 x i8> %trunc, <3 x i8> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v3i64_to_v3i1:
; GCN-DAG: buffer_store_byte v
; GCN-DAG: buffer_store_byte v
; GCN-DAG: buffer_store_byte v
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 @global_truncstore_v3i64_to_v3i1(<3 x i1> addrspace(1)* %out, <3 x i64> %x) {
AMDGPU: Cleanup lowering actions These are kind of a mess and hard to follow, particularly for loads and stores. Fix various redundant, unnecessary and dead settings. llvm-svn: 270307
2016-05-21 10:27:49 +08:00
%trunc = trunc <3 x i64> %x to <3 x i1>
store <3 x i1> %trunc, <3 x i1> addrspace(1)* %out
R600/SI: Add failing test for 3 x i64 vectors. Stores of <4 x i64> do work (although they do expand to 4 stores instead of 2), but 3 x i64 vectors fail to select. llvm-svn: 200989
2014-02-08 04:29:40 +08:00
ret void
}