mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-19 02:52:53 +02:00
c23a93c71f
Two issues found when doing codegen for splitting vector with non-zero alloca addr space: DAGTypeLegalizer::SplitVecRes_INSERT_VECTOR_ELT/SplitVecOp_EXTRACT_VECTOR_ELT uses dummy pointer info for creating SDStore. Since one pointer operand contains multiply and add, InferPointerInfo is unable to infer the correct pointer info, which ends up with a dummy pointer info for the target to lower store and results in isel failure. The fix is to introduce MachinePointerInfo::getUnknownStack to represent MachinePointerInfo which is known in alloca address space but without other information. TargetLowering::getVectorElementPointer uses value type of pointer in addr space 0 for multiplication of index and then add it to the pointer. However the pointer may be in an addr space which has different size than addr space 0. The fix is to use the pointer value type for index multiplication. Differential Revision: https://reviews.llvm.org/D39758 llvm-svn: 319622
152 lines
5.0 KiB
LLVM
152 lines
5.0 KiB
LLVM
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v1i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v1i8(i8 addrspace(1)* %out, <1 x i8> %foo) #0 {
|
|
%p0 = extractelement <1 x i8> %foo, i32 0
|
|
store i8 %p0, i8 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v2i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v2i8(i8 addrspace(1)* %out, <2 x i8> %foo) #0 {
|
|
%p0 = extractelement <2 x i8> %foo, i32 0
|
|
%p1 = extractelement <2 x i8> %foo, i32 1
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v3i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v3i8(i8 addrspace(1)* %out, <3 x i8> %foo) #0 {
|
|
%p0 = extractelement <3 x i8> %foo, i32 0
|
|
%p1 = extractelement <3 x i8> %foo, i32 2
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v4i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v4i8(i8 addrspace(1)* %out, <4 x i8> %foo) #0 {
|
|
%p0 = extractelement <4 x i8> %foo, i32 0
|
|
%p1 = extractelement <4 x i8> %foo, i32 2
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v8i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v8i8(i8 addrspace(1)* %out, <8 x i8> %foo) #0 {
|
|
%p0 = extractelement <8 x i8> %foo, i32 0
|
|
%p1 = extractelement <8 x i8> %foo, i32 2
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v16i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v16i8(i8 addrspace(1)* %out, <16 x i8> %foo) #0 {
|
|
%p0 = extractelement <16 x i8> %foo, i32 0
|
|
%p1 = extractelement <16 x i8> %foo, i32 2
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v32i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v32i8(i8 addrspace(1)* %out, <32 x i8> %foo) #0 {
|
|
%p0 = extractelement <32 x i8> %foo, i32 0
|
|
%p1 = extractelement <32 x i8> %foo, i32 2
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}extract_vector_elt_v64i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @extract_vector_elt_v64i8(i8 addrspace(1)* %out, <64 x i8> %foo) #0 {
|
|
%p0 = extractelement <64 x i8> %foo, i32 0
|
|
%p1 = extractelement <64 x i8> %foo, i32 2
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p1, i8 addrspace(1)* %out
|
|
store i8 %p0, i8 addrspace(1)* %out1
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}dynamic_extract_vector_elt_v3i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @dynamic_extract_vector_elt_v3i8(i8 addrspace(1)* %out, <3 x i8> %foo, i32 %idx) #0 {
|
|
%p0 = extractelement <3 x i8> %foo, i32 %idx
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p0, i8 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}dynamic_extract_vector_elt_v4i8:
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_load_ubyte
|
|
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_store_byte
|
|
|
|
; GCN: buffer_store_byte
|
|
; GCN: buffer_load_ubyte
|
|
; GCN: buffer_store_byte
|
|
define amdgpu_kernel void @dynamic_extract_vector_elt_v4i8(i8 addrspace(1)* %out, <4 x i8> %foo, i32 %idx) #0 {
|
|
%p0 = extractelement <4 x i8> %foo, i32 %idx
|
|
%out1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
|
|
store i8 %p0, i8 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|