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/extract_vector_elt-i64.ll

63 lines
2.5 KiB
LLVM
Raw Normal View History

AMDGPU: Remove remnants of old address space mapping llvm-svn: 341165
2018-08-31 13:49:54 +08:00
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
AMDGPU: Handle i64->v2i32 loads/stores in PreprocessISelDAG This fixes a select error when the i64 source was also bitcasted to v2i32 in the original source. Instead of awkwardly trying to select the modified source value and the store, replace before isel begins. Uses a worklist to avoid possible problems from mutating the DAG, although it seems to work OK without it. llvm-svn: 248589
2015-09-26 01:27:08 +08:00
; How the replacement of i64 stores with v2i32 stores resulted in
; breaking other users of the bitcast if they already existed
; GCN-LABEL: {{^}}extract_vector_elt_select_error:
; GCN: buffer_store_dword
; GCN: buffer_store_dword
; GCN: buffer_store_dwordx2
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 @extract_vector_elt_select_error(i32 addrspace(1)* %out, i64 addrspace(1)* %in, i64 %val) #0 {
AMDGPU: Handle i64->v2i32 loads/stores in PreprocessISelDAG This fixes a select error when the i64 source was also bitcasted to v2i32 in the original source. Instead of awkwardly trying to select the modified source value and the store, replace before isel begins. Uses a worklist to avoid possible problems from mutating the DAG, although it seems to work OK without it. llvm-svn: 248589
2015-09-26 01:27:08 +08:00
%vec = bitcast i64 %val to <2 x i32>
%elt0 = extractelement <2 x i32> %vec, i32 0
%elt1 = extractelement <2 x i32> %vec, i32 1
store volatile i32 %elt0, i32 addrspace(1)* %out
store volatile i32 %elt1, i32 addrspace(1)* %out
store volatile i64 %val, i64 addrspace(1)* %in
ret void
}
AMDGPU: Make v2i64/v2f64 legal types. They can be loaded and stored, so count them as legal. This is mostly to fix a number of common cases for load/store merging. llvm-svn: 254086
2015-11-26 03:58:34 +08:00
AMDGPU: Cleanup vector insert/extract tests This mostly makes sure that 3-vector dynamic inserts and extracts are covered. llvm-svn: 271082
2016-05-28 08:51:06 +08:00
; GCN-LABEL: {{^}}extract_vector_elt_v2i64:
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 @extract_vector_elt_v2i64(i64 addrspace(1)* %out, <2 x i64> %foo) #0 {
AMDGPU: Make v2i64/v2f64 legal types. They can be loaded and stored, so count them as legal. This is mostly to fix a number of common cases for load/store merging. llvm-svn: 254086
2015-11-26 03:58:34 +08:00
%p0 = extractelement <2 x i64> %foo, i32 0
%p1 = extractelement <2 x i64> %foo, i32 1
%out1 = getelementptr i64, i64 addrspace(1)* %out, i32 1
store volatile i64 %p1, i64 addrspace(1)* %out
store volatile i64 %p0, i64 addrspace(1)* %out1
ret void
}
AMDGPU: Cleanup vector insert/extract tests This mostly makes sure that 3-vector dynamic inserts and extracts are covered. llvm-svn: 271082
2016-05-28 08:51:06 +08:00
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v2i64:
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 @dyn_extract_vector_elt_v2i64(i64 addrspace(1)* %out, <2 x i64> %foo, i32 %elt) #0 {
AMDGPU: Make v2i64/v2f64 legal types. They can be loaded and stored, so count them as legal. This is mostly to fix a number of common cases for load/store merging. llvm-svn: 254086
2015-11-26 03:58:34 +08:00
%dynelt = extractelement <2 x i64> %foo, i32 %elt
store volatile i64 %dynelt, i64 addrspace(1)* %out
ret void
}
AMDGPU: Cleanup vector insert/extract tests This mostly makes sure that 3-vector dynamic inserts and extracts are covered. llvm-svn: 271082
2016-05-28 08:51:06 +08:00
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v2i64_2:
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 @dyn_extract_vector_elt_v2i64_2(i64 addrspace(1)* %out, <2 x i64> addrspace(1)* %foo, i32 %elt, <2 x i64> %arst) #0 {
AMDGPU: Make v2i64/v2f64 legal types. They can be loaded and stored, so count them as legal. This is mostly to fix a number of common cases for load/store merging. llvm-svn: 254086
2015-11-26 03:58:34 +08:00
%load = load volatile <2 x i64>, <2 x i64> addrspace(1)* %foo
%or = or <2 x i64> %load, %arst
%dynelt = extractelement <2 x i64> %or, i32 %elt
store volatile i64 %dynelt, i64 addrspace(1)* %out
ret void
}
AMDGPU: Cleanup vector insert/extract tests This mostly makes sure that 3-vector dynamic inserts and extracts are covered. llvm-svn: 271082
2016-05-28 08:51:06 +08:00
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v3i64:
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 @dyn_extract_vector_elt_v3i64(i64 addrspace(1)* %out, <3 x i64> %foo, i32 %elt) #0 {
AMDGPU: Cleanup vector insert/extract tests This mostly makes sure that 3-vector dynamic inserts and extracts are covered. llvm-svn: 271082
2016-05-28 08:51:06 +08:00
%dynelt = extractelement <3 x i64> %foo, i32 %elt
store volatile i64 %dynelt, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v4i64:
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 @dyn_extract_vector_elt_v4i64(i64 addrspace(1)* %out, <4 x i64> %foo, i32 %elt) #0 {
AMDGPU: Cleanup vector insert/extract tests This mostly makes sure that 3-vector dynamic inserts and extracts are covered. llvm-svn: 271082
2016-05-28 08:51:06 +08:00
%dynelt = extractelement <4 x i64> %foo, i32 %elt
store volatile i64 %dynelt, i64 addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }