llvm/test/CodeGen/AMDGPU/extract_vector_elt-f64.ll
Matt Arsenault c3eeba0f4c AMDGPU: Cleanup vector insert/extract tests
This mostly makes sure that 3-vector dynamic inserts
and extracts are covered.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@271082 91177308-0d34-0410-b5e6-96231b3b80d8
2016-05-28 00:51:06 +00:00

30 lines
1.2 KiB
LLVM

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}extract_vector_elt_v3f64_2:
; GCN: buffer_load_dwordx4
; GCN: buffer_load_dwordx2
; GCN: buffer_store_dwordx2
define void @extract_vector_elt_v3f64_2(double addrspace(1)* %out, <3 x double> addrspace(1)* %in) #0 {
%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:
define void @dyn_extract_vector_elt_v3f64(double addrspace(1)* %out, <3 x double> %foo, i32 %elt) #0 {
%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:
define void @dyn_extract_vector_elt_v4f64(double addrspace(1)* %out, <4 x double> %foo, i32 %elt) #0 {
%dynelt = extractelement <4 x double> %foo, i32 %elt
store volatile double %dynelt, double addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }