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/private-element-size.ll

253 lines
15 KiB
LLVM
Raw Normal View History

AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-16 -verify-machineinstrs < %s | FileCheck -check-prefix=ELT16 -check-prefix=HSA -check-prefix=HSA-ELT16 -check-prefix=ALL -check-prefix=HSA_ELTGE8 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-8 -verify-machineinstrs < %s | FileCheck -check-prefix=ELT8 -check-prefix=HSA -check-prefix=HSA-ELT8 -check-prefix=ALL -check-prefix=HSA-ELTGE8 %s
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-4 -verify-machineinstrs < %s | FileCheck -check-prefix=ELT4 -check-prefix=HSA -check-prefix=HSA-ELT4 -check-prefix=ALL %s
; ALL-LABEL: {{^}}private_elt_size_v4i32:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:8
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:24
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:4{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:8{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:12{{$}}
Revert "AMDGPU: Don't use offen if it is 0" This reverts commit r282999. Tests are not passing: http://lab.llvm.org:8011/builders/clang-x86_64-linux-selfhost-modules/builds/20038 llvm-svn: 283003
2016-10-01 10:35:24 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16{{$}}
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:28{{$}}
Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." This reverts commit r284151 which appears to be triggering a LTO failures on Hexagon llvm-svn: 284157
2016-10-14 04:23:25 +08:00
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
define void @private_elt_size_v4i32(<4 x i32> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x <4 x i32>], align 16
%gep0 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %alloca, i32 0, i32 1
store <4 x i32> zeroinitializer, <4 x i32>* %gep0
store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32>* %gep1
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
%gep2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %alloca, i32 0, i32 %index
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
%load = load <4 x i32>, <4 x i32>* %gep2
store <4 x i32> %load, <4 x i32> addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_v8i32:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:16
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:32
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:48
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:8
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:16
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:24
Revert "AMDGPU: Don't use offen if it is 0" This reverts commit r282999. Tests are not passing: http://lab.llvm.org:8011/builders/clang-x86_64-linux-selfhost-modules/builds/20038 llvm-svn: 283003
2016-10-01 10:35:24 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:32
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:40
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:48
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:56
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:4{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:8{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:12{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:16{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:28{{$}}
Revert "AMDGPU: Don't use offen if it is 0" This reverts commit r282999. Tests are not passing: http://lab.llvm.org:8011/builders/clang-x86_64-linux-selfhost-modules/builds/20038 llvm-svn: 283003
2016-10-01 10:35:24 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:32{{$}}
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:36{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:40{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:44{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:48{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:52{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:56{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:60{{$}}
AMDGPU: More bits of frame index are known to be zero The maximum private allocation for the whole GPU is 4G, so the maximum possible index for a single workitem is the maximum size divided by the smallest granularity for a dispatch. This increases the number of known zero high bits, which enables more offset folding. The maximum private size per workitem with this is 128M but may be smaller still. llvm-svn: 262153
2016-02-28 04:26:57 +08:00
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:20{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:24{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:28{{$}}
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
define void @private_elt_size_v8i32(<8 x i32> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x <8 x i32>], align 16
%gep0 = getelementptr inbounds [2 x <8 x i32>], [2 x <8 x i32>]* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x <8 x i32>], [2 x <8 x i32>]* %alloca, i32 0, i32 1
store <8 x i32> zeroinitializer, <8 x i32>* %gep0
store <8 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>, <8 x i32>* %gep1
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
%gep2 = getelementptr inbounds [2 x <8 x i32>], [2 x <8 x i32>]* %alloca, i32 0, i32 %index
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
%load = load <8 x i32>, <8 x i32>* %gep2
store <8 x i32> %load, <8 x i32> addrspace(1)* %out
ret void
}
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
; ALL-LABEL: {{^}}private_elt_size_i64:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8
; HSA-ELTGE8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:4{{$}}
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
define void @private_elt_size_i64(i64 addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x i64], align 16
%gep0 = getelementptr inbounds [2 x i64], [2 x i64]* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x i64], [2 x i64]* %alloca, i32 0, i32 1
store i64 0, i64* %gep0
store i64 34359738602, i64* %gep1
%gep2 = getelementptr inbounds [2 x i64], [2 x i64]* %alloca, i32 0, i32 %index
%load = load i64, i64* %gep2
store i64 %load, i64 addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_f64:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8
; HSA-ELTGE8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:4{{$}}
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
define void @private_elt_size_f64(double addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x double], align 16
%gep0 = getelementptr inbounds [2 x double], [2 x double]* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x double], [2 x double]* %alloca, i32 0, i32 1
store double 0.0, double* %gep0
store double 4.0, double* %gep1
%gep2 = getelementptr inbounds [2 x double], [2 x double]* %alloca, i32 0, i32 %index
%load = load double, double* %gep2
store double %load, double addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_v2i64:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], s9 offset:8
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen offset:24
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], s9 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
Reapply "AMDGPU: Don't use offen if it is 0" This reverts r283003 llvm-svn: 285203
2016-10-26 23:08:16 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:4{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:8{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], s9 offset:12{{$}}
Revert "AMDGPU: Don't use offen if it is 0" This reverts commit r282999. Tests are not passing: http://lab.llvm.org:8011/builders/clang-x86_64-linux-selfhost-modules/builds/20038 llvm-svn: 283003
2016-10-01 10:35:24 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:16{{$}}
AMDGPU: Add some private element size tests llvm-svn: 269712
2016-05-17 06:17:27 +08:00
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:28{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:8{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], s9 offen offset:12{{$}}
define void @private_elt_size_v2i64(<2 x i64> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x <2 x i64>], align 16
%gep0 = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>]* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>]* %alloca, i32 0, i32 1
store <2 x i64> zeroinitializer, <2 x i64>* %gep0
store <2 x i64> <i64 1, i64 2>, <2 x i64>* %gep1
%gep2 = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>]* %alloca, i32 0, i32 %index
%load = load <2 x i64>, <2 x i64>* %gep2
store <2 x i64> %load, <2 x i64> addrspace(1)* %out
ret void
}
AMDGPU: Prepare for reducing private element size. Tests for the new scalarize all private access options will be included with a future commit. The only functional change is to make the split/scalarize behavior for private access of > 4 element vectors to be consistent with the flat/global handling. This makes the spilling worse in the two changed tests. llvm-svn: 260804
2016-02-13 12:18:53 +08:00
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }