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-f64.ll

49 lines
2.5 KiB
LLVM
Raw Normal View History

[AMDGPU] combine extractelement into several selects An extractelement with non-constant index will be lowered either to scratch or movrel loop in most cases. This patch converts such instruction into a set of selects if vector size is not too big. Differential Revision: https://reviews.llvm.org/D54351 llvm-svn: 346800
2018-11-14 05:18:21 +08:00
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
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_v3f64_2:
; GCN: buffer_load_dwordx4
; GCN: buffer_load_dwordx2
; 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_v3f64_2(double addrspace(1)* %out, <3 x double> addrspace(1)* %in) #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
%ld = load volatile <3 x double>, <3 x double> addrspace(1)* %in
%elt = extractelement <3 x double> %ld, i32 2
store volatile double %elt, double addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v3f64:
[AMDGPU] combine extractelement into several selects An extractelement with non-constant index will be lowered either to scratch or movrel loop in most cases. This patch converts such instruction into a set of selects if vector size is not too big. Differential Revision: https://reviews.llvm.org/D54351 llvm-svn: 346800
2018-11-14 05:18:21 +08:00
; GCN-NOT: buffer_load
; GCN-DAG: v_cmp_eq_u32_e64 [[C1:[^,]+]], [[IDX:s[0-9]+]], 1
; GCN-DAG: v_cmp_eq_u32_e64 [[C2:[^,]+]], [[IDX]], 2
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C1]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C1]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C2]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C2]]
; GCN: store_dwordx2 v[{{[0-9:]+}}]
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_v3f64(double addrspace(1)* %out, <3 x double> %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 double> %foo, i32 %elt
store volatile double %dynelt, double addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}dyn_extract_vector_elt_v4f64:
[AMDGPU] combine extractelement into several selects An extractelement with non-constant index will be lowered either to scratch or movrel loop in most cases. This patch converts such instruction into a set of selects if vector size is not too big. Differential Revision: https://reviews.llvm.org/D54351 llvm-svn: 346800
2018-11-14 05:18:21 +08:00
; GCN-NOT: buffer_load
; GCN-DAG: v_cmp_eq_u32_e64 [[C1:[^,]+]], [[IDX:s[0-9]+]], 1
; GCN-DAG: v_cmp_eq_u32_e64 [[C2:[^,]+]], [[IDX]], 2
; GCN-DAG: v_cmp_eq_u32_e64 [[C3:[^,]+]], [[IDX]], 3
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C1]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C1]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C2]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C2]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C3]]
; GCN-DAG: v_cndmask_b32_e{{32|64}} v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[C3]]
; GCN: store_dwordx2 v[{{[0-9:]+}}]
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_v4f64(double addrspace(1)* %out, <4 x double> %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 double> %foo, i32 %elt
store volatile double %dynelt, double addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }