mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-24 06:30:19 +00:00
a2dca4cc04
There seem to be only 2 places that produce these, and it's kind of tricky to hit them. Also fixes failure to bitcast between i64 and v2f32, although this for some reason wasn't actually broken in the simple bitcast testcase, but did in the scalar_to_vector one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210664 91177308-0d34-0410-b5e6-96231b3b80d8
81 lines
3.3 KiB
LLVM
81 lines
3.3 KiB
LLVM
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
|
|
; FUNC-LABEL: @scalar_to_vector_v2i32
|
|
; SI: BUFFER_LOAD_DWORD [[VAL:v[0-9]+]],
|
|
; SI: V_LSHRREV_B32_e32 [[RESULT:v[0-9]+]], 16, [[VAL]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: S_ENDPGM
|
|
define void @scalar_to_vector_v2i32(<4 x i16> addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%tmp1 = load i32 addrspace(1)* %in, align 4
|
|
%bc = bitcast i32 %tmp1 to <2 x i16>
|
|
%tmp2 = shufflevector <2 x i16> %bc, <2 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
store <4 x i16> %tmp2, <4 x i16> addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: @scalar_to_vector_v2f32
|
|
; SI: BUFFER_LOAD_DWORD [[VAL:v[0-9]+]],
|
|
; SI: V_LSHRREV_B32_e32 [[RESULT:v[0-9]+]], 16, [[VAL]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: BUFFER_STORE_SHORT [[RESULT]]
|
|
; SI: S_ENDPGM
|
|
define void @scalar_to_vector_v2f32(<4 x i16> addrspace(1)* %out, float addrspace(1)* %in) nounwind {
|
|
%tmp1 = load float addrspace(1)* %in, align 4
|
|
%bc = bitcast float %tmp1 to <2 x i16>
|
|
%tmp2 = shufflevector <2 x i16> %bc, <2 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
store <4 x i16> %tmp2, <4 x i16> addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; Getting a SCALAR_TO_VECTOR seems to be tricky. These cases managed
|
|
; to produce one, but for some reason never made it to selection.
|
|
|
|
|
|
; define void @scalar_to_vector_test2(<8 x i8> addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
; %tmp1 = load i32 addrspace(1)* %in, align 4
|
|
; %bc = bitcast i32 %tmp1 to <4 x i8>
|
|
|
|
; %tmp2 = shufflevector <4 x i8> %bc, <4 x i8> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
; store <8 x i8> %tmp2, <8 x i8> addrspace(1)* %out, align 4
|
|
; ret void
|
|
; }
|
|
|
|
; define void @scalar_to_vector_test3(<4 x i32> addrspace(1)* %out) nounwind {
|
|
; %newvec0 = insertelement <2 x i64> undef, i64 12345, i32 0
|
|
; %newvec1 = insertelement <2 x i64> %newvec0, i64 undef, i32 1
|
|
; %bc = bitcast <2 x i64> %newvec1 to <4 x i32>
|
|
; %add = add <4 x i32> %bc, <i32 1, i32 2, i32 3, i32 4>
|
|
; store <4 x i32> %add, <4 x i32> addrspace(1)* %out, align 16
|
|
; ret void
|
|
; }
|
|
|
|
; define void @scalar_to_vector_test4(<8 x i16> addrspace(1)* %out) nounwind {
|
|
; %newvec0 = insertelement <4 x i32> undef, i32 12345, i32 0
|
|
; %bc = bitcast <4 x i32> %newvec0 to <8 x i16>
|
|
; %add = add <8 x i16> %bc, <i16 1, i16 2, i16 3, i16 4, i16 1, i16 2, i16 3, i16 4>
|
|
; store <8 x i16> %add, <8 x i16> addrspace(1)* %out, align 16
|
|
; ret void
|
|
; }
|
|
|
|
; define void @scalar_to_vector_test5(<4 x i16> addrspace(1)* %out) nounwind {
|
|
; %newvec0 = insertelement <2 x i32> undef, i32 12345, i32 0
|
|
; %bc = bitcast <2 x i32> %newvec0 to <4 x i16>
|
|
; %add = add <4 x i16> %bc, <i16 1, i16 2, i16 3, i16 4>
|
|
; store <4 x i16> %add, <4 x i16> addrspace(1)* %out, align 16
|
|
; ret void
|
|
; }
|
|
|
|
; define void @scalar_to_vector_test6(<4 x i16> addrspace(1)* %out) nounwind {
|
|
; %newvec0 = insertelement <2 x i32> undef, i32 12345, i32 0
|
|
; %bc = bitcast <2 x i32> %newvec0 to <4 x i16>
|
|
; %add = add <4 x i16> %bc, <i16 1, i16 2, i16 3, i16 4>
|
|
; store <4 x i16> %add, <4 x i16> addrspace(1)* %out, align 16
|
|
; ret void
|
|
; }
|