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-global-i8.ll

980 lines
40 KiB
LLVM
Raw Normal View History

[FileCheck] Add -allow-deprecated-dag-overlap to failing llvm tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47171 This commit drops that patch's changes to: llvm/test/CodeGen/NVPTX/f16x2-instructions.ll llvm/test/CodeGen/NVPTX/param-load-store.ll For some reason, the dos line endings there prevent me from commiting via the monorepo. A follow-up commit (not via the monorepo) will finish the patch. llvm-svn: 336843
2018-07-12 04:25:49 +08:00
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,GCN-NOHSA,SI,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,GCN-HSA,SI,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefixes=GCN,GCN-NOHSA,VI,FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=EG -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cayman -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=EG -check-prefix=FUNC %s
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; FUNC-LABEL: {{^}}global_load_i8:
; GCN-NOHSA: buffer_load_ubyte v{{[0-9]+}}
; GCN-HSA: flat_load_ubyte
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; TODO: NOT AND
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_load_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load i8, i8 addrspace(1)* %in
store i8 %ld, i8 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v2i8:
; GCN-NOHSA: buffer_load_ushort v
; GCN-HSA: flat_load_ushort v
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_load_v2i8(<2 x i8> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <2 x i8>, <2 x i8> addrspace(1)* %in
store <2 x i8> %ld, <2 x i8> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v3i8:
; GCN-NOHSA: buffer_load_dword v
; GCN-HSA: flat_load_dword v
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_load_v3i8(<3 x i8> addrspace(1)* %out, <3 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <3 x i8>, <3 x i8> addrspace(1)* %in
store <3 x i8> %ld, <3 x i8> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v4i8:
; GCN-NOHSA: buffer_load_dword v
; GCN-HSA: flat_load_dword v
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_load_v4i8(<4 x i8> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <4 x i8>, <4 x i8> addrspace(1)* %in
store <4 x i8> %ld, <4 x i8> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v8i8:
; GCN-NOHSA: buffer_load_dwordx2
; GCN-HSA: flat_load_dwordx2
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 T{{[0-9]+}}.XY, T{{[0-9]+}}.X, 0, #1
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_load_v8i8(<8 x i8> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <8 x i8>, <8 x i8> addrspace(1)* %in
store <8 x i8> %ld, <8 x i8> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v16i8:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
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_load_v16i8(<16 x i8> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <16 x i8>, <16 x i8> addrspace(1)* %in
store <16 x i8> %ld, <16 x i8> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_i8_to_i32:
; GCN-NOHSA: buffer_load_ubyte v{{[0-9]+}},
; GCN-HSA: flat_load_ubyte
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_i8_to_i32(i32 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%a = load i8, i8 addrspace(1)* %in
%ext = zext i8 %a to i32
store i32 %ext, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_i8_to_i32:
; GCN-NOHSA: buffer_load_sbyte
; GCN-HSA: flat_load_sbyte
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 [[DST:T[0-9]\.[XYZW]]], [[DST]], 0, #1
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; EG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, [[DST]], 0.0, literal
; EG: 8
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_sextload_i8_to_i32(i32 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%ld = load i8, i8 addrspace(1)* %in
%ext = sext i8 %ld to i32
store i32 %ext, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v1i8_to_v1i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_v1i8_to_v1i32(<1 x i32> addrspace(1)* %out, <1 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <1 x i8>, <1 x i8> addrspace(1)* %in
%ext = zext <1 x i8> %load to <1 x i32>
store <1 x i32> %ext, <1 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v1i8_to_v1i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 [[DST:T[0-9]\.[XYZW]]], [[DST]], 0, #1
; EG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, [[DST]], 0.0, literal
; EG: 8
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_sextload_v1i8_to_v1i32(<1 x i32> addrspace(1)* %out, <1 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <1 x i8>, <1 x i8> addrspace(1)* %in
%ext = sext <1 x i8> %load to <1 x i32>
store <1 x i32> %ext, <1 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v2i8_to_v2i32:
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
; GCN-NOHSA: buffer_load_ushort
; GCN-HSA: flat_load_ushort
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 [[DST:T[0-9]+\.X]], T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, literal
; EG-DAG: 8
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_zextload_v2i8_to_v2i32(<2 x i32> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <2 x i8>, <2 x i8> addrspace(1)* %in
%ext = zext <2 x i8> %load to <2 x i32>
store <2 x i32> %ext, <2 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v2i8_to_v2i32:
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
; GCN-NOHSA: buffer_load_ushort
; GCN-HSA: flat_load_ushort
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 [[DST:T[0-9]+\.X]], T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; EG-DAG: 8
; EG-DAG: 8
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_sextload_v2i8_to_v2i32(<2 x i32> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <2 x i8>, <2 x i8> addrspace(1)* %in
%ext = sext <2 x i8> %load to <2 x i32>
store <2 x i32> %ext, <2 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v3i8_to_v3i32:
; GCN-NOHSA: buffer_load_dword v
; GCN-HSA: flat_load_dword v
AMDGPU: Add VI i16 support Patch By: Wei Ding Differential Revision: https://reviews.llvm.org/D18049 llvm-svn: 286464
2016-11-11 00:02:37 +08:00
; SI-DAG: v_bfe_u32 v{{[0-9]+}}, v{{[0-9]+}}, 8, 8
; VI-DAG: v_lshrrev_b16_e32 v{{[0-9]+}}, 8, v{{[0-9]+}}
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; GCN-DAG: v_bfe_u32 v{{[0-9]+}}, v{{[0-9]+}}, 16, 8
; GCN-DAG: v_and_b32_e32 v{{[0-9]+}}, 0xff,
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: 8
; EG-DAG: 8
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_zextload_v3i8_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <3 x i8>, <3 x i8> addrspace(1)* %in
%ext = zext <3 x i8> %ld to <3 x i32>
store <3 x i32> %ext, <3 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v3i8_to_v3i32:
; GCN-NOHSA: buffer_load_dword v
; GCN-HSA: flat_load_dword v
AMDGPU: Add VI i16 support Patch By: Wei Ding Differential Revision: https://reviews.llvm.org/D18049 llvm-svn: 286464
2016-11-11 00:02:37 +08:00
;FIXME: Need to optimize this sequence to avoid extra shift on VI.
; t23: i16 = truncate t18
; t49: i16 = srl t23, Constant:i32<8>
; t57: i32 = any_extend t49
; t58: i32 = sign_extend_inreg t57, ValueType:ch:i8
; SI-DAG: v_bfe_i32 v{{[0-9]+}}, v{{[0-9]+}}, 8, 8
; VI-DAG: v_lshrrev_b16_e32 [[SHIFT:v[0-9]+]], 8, v{{[0-9]+}}
; VI-DAG: v_bfe_i32 v{{[0-9]+}}, [[SHIFT]], 0, 8
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; GCN-DAG: v_bfe_i32 v{{[0-9]+}}, v{{[0-9]+}}, 0, 8
; GCN-DAG: v_bfe_i32 v{{[0-9]+}}, v{{[0-9]+}}, 16, 8
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 [[DST:T[0-9]+\.X]], T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_sextload_v3i8_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
entry:
%ld = load <3 x i8>, <3 x i8> addrspace(1)* %in
%ext = sext <3 x i8> %ld to <3 x i32>
store <3 x i32> %ext, <3 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v4i8_to_v4i32:
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
; GCN-NOHSA: buffer_load_dword
; GCN-HSA: flat_load_dword
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_zextload_v4i8_to_v4i32(<4 x i32> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in
%ext = zext <4 x i8> %load to <4 x i32>
store <4 x i32> %ext, <4 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v4i8_to_v4i32:
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
; GCN-NOHSA: buffer_load_dword
; GCN-HSA: flat_load_dword
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 [[DST:T[0-9]+\.X]], T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_sextload_v4i8_to_v4i32(<4 x i32> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in
%ext = sext <4 x i8> %load to <4 x i32>
store <4 x i32> %ext, <4 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v8i8_to_v8i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 T{{[0-9]+}}.XY, T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_zextload_v8i8_to_v8i32(<8 x i32> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <8 x i8>, <8 x i8> addrspace(1)* %in
%ext = zext <8 x i8> %load to <8 x i32>
store <8 x i32> %ext, <8 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v8i8_to_v8i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 [[DST:T[0-9]+\.XY]], T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_sextload_v8i8_to_v8i32(<8 x i32> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <8 x i8>, <8 x i8> addrspace(1)* %in
%ext = sext <8 x i8> %load to <8 x i32>
store <8 x i32> %ext, <8 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v16i8_to_v16i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_zextload_v16i8_to_v16i32(<16 x i32> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <16 x i8>, <16 x i8> addrspace(1)* %in
%ext = zext <16 x i8> %load to <16 x i32>
store <16 x i32> %ext, <16 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v16i8_to_v16i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 [[DST:T[0-9]+\.XYZW]], T{{[0-9]+}}.X, 0, #1
; TODO: These should use DST, but for some there are redundant MOVs
Re-land MachineInstr: Reason locally about some memory objects before going to AA. Summary: Reverts r311008 to reinstate r310825 with a fix. Refine alias checking for pseudo vs value to be conservative. This fixes the original failure in builtbot unittest SingleSource/UnitTests/2003-07-09-SignedArgs. Reviewers: hfinkel, nemanjai, efriedma Reviewed By: efriedma Subscribers: bjope, mcrosier, nhaehnle, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D36900 llvm-svn: 312126
2017-08-30 22:57:12 +08:00
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_sextload_v16i8_to_v16i32(<16 x i32> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <16 x i8>, <16 x i8> addrspace(1)* %in
%ext = sext <16 x i8> %load to <16 x i32>
store <16 x i32> %ext, <16 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v32i8_to_v32i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 16, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: BFE_UINT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, {{.*}}literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_zextload_v32i8_to_v32i32(<32 x i32> addrspace(1)* %out, <32 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <32 x i8>, <32 x i8> addrspace(1)* %in
%ext = zext <32 x i8> %load to <32 x i32>
store <32 x i32> %ext, <32 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v32i8_to_v32i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 [[DST_LO:T[0-9]+\.XYZW]], T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 [[DST_HI:T[0-9]+\.XYZW]], T{{[0-9]+}}.X, 16, #1
; TODO: These should use DST, but for some there are redundant MOVs
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]+.[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
; EG-DAG: 8
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_sextload_v32i8_to_v32i32(<32 x i32> addrspace(1)* %out, <32 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <32 x i8>, <32 x i8> addrspace(1)* %in
%ext = sext <32 x i8> %load to <32 x i32>
store <32 x i32> %ext, <32 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v64i8_to_v64i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 16, #1
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 32, #1
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 48, #1
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_zextload_v64i8_to_v64i32(<64 x i32> addrspace(1)* %out, <64 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <64 x i8>, <64 x i8> addrspace(1)* %in
%ext = zext <64 x i8> %load to <64 x i32>
store <64 x i32> %ext, <64 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v64i8_to_v64i32:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 16, #1
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 32, #1
; EG-DAG: VTX_READ_128 {{T[0-9]+\.XYZW}}, T{{[0-9]+}}.X, 48, #1
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_sextload_v64i8_to_v64i32(<64 x i32> addrspace(1)* %out, <64 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <64 x i8>, <64 x i8> addrspace(1)* %in
%ext = sext <64 x i8> %load to <64 x i32>
store <64 x i32> %ext, <64 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_i8_to_i64:
; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0{{$}}
; GCN-NOHSA-DAG: buffer_load_ubyte v[[LO:[0-9]+]],
; GCN-NOHSA: buffer_store_dwordx2 v{{\[}}[[LO]]:[[HI]]]
; GCN-HSA-DAG: flat_load_ubyte v[[LO:[0-9]+]],
; GCN-HSA: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[}}[[LO]]:[[HI]]]
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG: MOV {{.*}}, 0.0
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_zextload_i8_to_i64(i64 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%a = load i8, i8 addrspace(1)* %in
%ext = zext i8 %a to i64
store i64 %ext, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_i8_to_i64:
; GCN-NOHSA: buffer_load_sbyte v[[LO:[0-9]+]],
; GCN-HSA: flat_load_sbyte v[[LO:[0-9]+]],
; GCN: v_ashrrev_i32_e32 v[[HI:[0-9]+]], 31, v[[LO]]
; GCN-NOHSA: buffer_store_dwordx2 v{{\[}}[[LO]]:[[HI]]{{\]}}
; GCN-HSA: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG: ASHR {{\**}} {{T[0-9]\.[XYZW]}}, {{.*}}, literal
; TODO: Why not 7 ?
; EG: 31
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_sextload_i8_to_i64(i64 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%a = load i8, i8 addrspace(1)* %in
%ext = sext i8 %a to i64
store i64 %ext, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v1i8_to_v1i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG: MOV {{.*}}, 0.0
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_zextload_v1i8_to_v1i64(<1 x i64> addrspace(1)* %out, <1 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <1 x i8>, <1 x i8> addrspace(1)* %in
%ext = zext <1 x i8> %load to <1 x i64>
store <1 x i64> %ext, <1 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v1i8_to_v1i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG: ASHR {{\**}} {{T[0-9]\.[XYZW]}}, {{.*}}, literal
; TODO: Why not 7 ?
; EG: 31
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_sextload_v1i8_to_v1i64(<1 x i64> addrspace(1)* %out, <1 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <1 x i8>, <1 x i8> addrspace(1)* %in
%ext = sext <1 x i8> %load to <1 x i64>
store <1 x i64> %ext, <1 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v2i8_to_v2i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_v2i8_to_v2i64(<2 x i64> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <2 x i8>, <2 x i8> addrspace(1)* %in
%ext = zext <2 x i8> %load to <2 x i64>
store <2 x i64> %ext, <2 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v2i8_to_v2i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_sextload_v2i8_to_v2i64(<2 x i64> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <2 x i8>, <2 x i8> addrspace(1)* %in
%ext = sext <2 x i8> %load to <2 x i64>
store <2 x i64> %ext, <2 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v4i8_to_v4i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_v4i8_to_v4i64(<4 x i64> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in
%ext = zext <4 x i8> %load to <4 x i64>
store <4 x i64> %ext, <4 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v4i8_to_v4i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_sextload_v4i8_to_v4i64(<4 x i64> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in
%ext = sext <4 x i8> %load to <4 x i64>
store <4 x i64> %ext, <4 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v8i8_to_v8i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 T{{[0-9]+}}.XY, T{{[0-9]+}}.X, 0, #1
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_zextload_v8i8_to_v8i64(<8 x i64> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <8 x i8>, <8 x i8> addrspace(1)* %in
%ext = zext <8 x i8> %load to <8 x i64>
store <8 x i64> %ext, <8 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v8i8_to_v8i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 T{{[0-9]+}}.XY, T{{[0-9]+}}.X, 0, #1
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_sextload_v8i8_to_v8i64(<8 x i64> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <8 x i8>, <8 x i8> addrspace(1)* %in
%ext = sext <8 x i8> %load to <8 x i64>
store <8 x i64> %ext, <8 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v16i8_to_v16i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
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_zextload_v16i8_to_v16i64(<16 x i64> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <16 x i8>, <16 x i8> addrspace(1)* %in
%ext = zext <16 x i8> %load to <16 x i64>
store <16 x i64> %ext, <16 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v16i8_to_v16i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
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_sextload_v16i8_to_v16i64(<16 x i64> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <16 x i8>, <16 x i8> addrspace(1)* %in
%ext = sext <16 x i8> %load to <16 x i64>
store <16 x i64> %ext, <16 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v32i8_to_v32i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 16, #1
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_zextload_v32i8_to_v32i64(<32 x i64> addrspace(1)* %out, <32 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <32 x i8>, <32 x i8> addrspace(1)* %in
%ext = zext <32 x i8> %load to <32 x i64>
store <32 x i64> %ext, <32 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v32i8_to_v32i64:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 16, #1
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_sextload_v32i8_to_v32i64(<32 x i64> addrspace(1)* %out, <32 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <32 x i8>, <32 x i8> addrspace(1)* %in
%ext = sext <32 x i8> %load to <32 x i64>
store <32 x i64> %ext, <32 x i64> addrspace(1)* %out
ret void
}
; XFUNC-LABEL: {{^}}global_zextload_v64i8_to_v64i64:
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_zextload_v64i8_to_v64i64(<64 x i64> addrspace(1)* %out, <64 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; %load = load <64 x i8>, <64 x i8> addrspace(1)* %in
; %ext = zext <64 x i8> %load to <64 x i64>
; store <64 x i64> %ext, <64 x i64> addrspace(1)* %out
; ret void
; }
; XFUNC-LABEL: {{^}}global_sextload_v64i8_to_v64i64:
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_sextload_v64i8_to_v64i64(<64 x i64> addrspace(1)* %out, <64 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; %load = load <64 x i8>, <64 x i8> addrspace(1)* %in
; %ext = sext <64 x i8> %load to <64 x i64>
; store <64 x i64> %ext, <64 x i64> addrspace(1)* %out
; ret void
; }
; FUNC-LABEL: {{^}}global_zextload_i8_to_i16:
; GCN-NOHSA: buffer_load_ubyte v[[VAL:[0-9]+]],
; GCN-NOHSA: buffer_store_short v[[VAL]]
; GCN-HSA: flat_load_ubyte v[[VAL:[0-9]+]],
; GCN-HSA: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, v[[VAL]]
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_i8_to_i16(i16 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%a = load i8, i8 addrspace(1)* %in
%ext = zext i8 %a to i16
store i16 %ext, i16 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_i8_to_i16:
; GCN-NOHSA: buffer_load_sbyte v[[VAL:[0-9]+]],
; GCN-HSA: flat_load_sbyte v[[VAL:[0-9]+]],
; GCN-NOHSA: buffer_store_short v[[VAL]]
; GCN-HSA: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, v[[VAL]]
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_i8_to_i16(i16 addrspace(1)* %out, i8 addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%a = load i8, i8 addrspace(1)* %in
%ext = sext i8 %a to i16
store i16 %ext, i16 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v1i8_to_v1i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_v1i8_to_v1i16(<1 x i16> addrspace(1)* %out, <1 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <1 x i8>, <1 x i8> addrspace(1)* %in
%ext = zext <1 x i8> %load to <1 x i16>
store <1 x i16> %ext, <1 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v1i8_to_v1i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_8 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_v1i8_to_v1i16(<1 x i16> addrspace(1)* %out, <1 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <1 x i8>, <1 x i8> addrspace(1)* %in
%ext = sext <1 x i8> %load to <1 x i16>
store <1 x i16> %ext, <1 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v2i8_to_v2i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_v2i8_to_v2i16(<2 x i16> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <2 x i8>, <2 x i8> addrspace(1)* %in
%ext = zext <2 x i8> %load to <2 x i16>
store <2 x i16> %ext, <2 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v2i8_to_v2i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_v2i8_to_v2i16(<2 x i16> addrspace(1)* %out, <2 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <2 x i8>, <2 x i8> addrspace(1)* %in
%ext = sext <2 x i8> %load to <2 x i16>
store <2 x i16> %ext, <2 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v4i8_to_v4i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
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_zextload_v4i8_to_v4i16(<4 x i16> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in
%ext = zext <4 x i8> %load to <4 x i16>
store <4 x i16> %ext, <4 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v4i8_to_v4i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_v4i8_to_v4i16(<4 x i16> addrspace(1)* %out, <4 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in
%ext = sext <4 x i8> %load to <4 x i16>
store <4 x i16> %ext, <4 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v8i8_to_v8i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 T{{[0-9]+}}.XY, T{{[0-9]+}}.X, 0, #1
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_zextload_v8i8_to_v8i16(<8 x i16> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <8 x i8>, <8 x i8> addrspace(1)* %in
%ext = zext <8 x i8> %load to <8 x i16>
store <8 x i16> %ext, <8 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v8i8_to_v8i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_64 T{{[0-9]+}}.XY, T{{[0-9]+}}.X, 0, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_v8i8_to_v8i16(<8 x i16> addrspace(1)* %out, <8 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <8 x i8>, <8 x i8> addrspace(1)* %in
%ext = sext <8 x i8> %load to <8 x i16>
store <8 x i16> %ext, <8 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v16i8_to_v16i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
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_zextload_v16i8_to_v16i16(<16 x i16> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <16 x i8>, <16 x i8> addrspace(1)* %in
%ext = zext <16 x i8> %load to <16 x i16>
store <16 x i16> %ext, <16 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v16i8_to_v16i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_v16i8_to_v16i16(<16 x i16> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <16 x i8>, <16 x i8> addrspace(1)* %in
%ext = sext <16 x i8> %load to <16 x i16>
store <16 x i16> %ext, <16 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v32i8_to_v32i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 16, #1
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_zextload_v32i8_to_v32i16(<32 x i16> addrspace(1)* %out, <32 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <32 x i8>, <32 x i8> addrspace(1)* %in
%ext = zext <32 x i8> %load to <32 x i16>
store <32 x i16> %ext, <32 x i16> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v32i8_to_v32i16:
AMDGPU/R600: Enable Load combine Fix and improve tests Differential Revision: https://reviews.llvm.org/D23899 llvm-svn: 279925
2016-08-28 03:09:43 +08:00
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 0, #1
; EG-DAG: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 16, #1
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
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_sextload_v32i8_to_v32i16(<32 x i16> addrspace(1)* %out, <32 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
%load = load <32 x i8>, <32 x i8> addrspace(1)* %in
%ext = sext <32 x i8> %load to <32 x i16>
store <32 x i16> %ext, <32 x i16> addrspace(1)* %out
ret void
}
; XFUNC-LABEL: {{^}}global_zextload_v64i8_to_v64i16:
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_zextload_v64i8_to_v64i16(<64 x i16> addrspace(1)* %out, <64 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; %load = load <64 x i8>, <64 x i8> addrspace(1)* %in
; %ext = zext <64 x i8> %load to <64 x i16>
; store <64 x i16> %ext, <64 x i16> addrspace(1)* %out
; ret void
; }
; XFUNC-LABEL: {{^}}global_sextload_v64i8_to_v64i16:
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_sextload_v64i8_to_v64i16(<64 x i16> addrspace(1)* %out, <64 x i8> addrspace(1)* %in) #0 {
AMDGPU: Cleanup load tests There are a lot of different kinds of loads to test for, and these were scattered around inconsistently with some redundancy. Try to comprehensively test all loads in a consistent way. llvm-svn: 271571
2016-06-03 03:54:26 +08:00
; %load = load <64 x i8>, <64 x i8> addrspace(1)* %in
; %ext = sext <64 x i8> %load to <64 x i16>
; store <64 x i16> %ext, <64 x i16> addrspace(1)* %out
; ret void
; }
attributes #0 = { nounwind }