hls::stream<ap_axis<N,0,0,0>> and hls::stream<ap_axiu<N,0,0,0>> represent an AXI4-Stream with API to specify the tkeep per byte.
However, the stream implementation inside the AI Engine and adf stream API
do not support a per-byte tkeep, instead per-word tkeep is supported. As a result,
ap_axis<N,0,0,0> and ap_axiu<N,0,0,0> are assumed to be fully packed
within each 32-bit word boundary when used inside data flow graphs. The following
tables specify the allowed connections between hls::stream and adf stream and
window data types in various scenarios where users want to pack and unpack data
using ap_axis and ap_axiu.
T1
|
T2
|
|---|---|
ap_axis<32,0,0,0>
|
int8, int16, int32, cint16
|
ap_axis<64,0,0,0>
|
int8, int16, int32, int64,
cint16, cint32
|
ap_axis<128,0,0,0>
|
int8, int16, int32, int64,
cint16, cint32
|
ap_axiu<32,0,0,0>
|
uint8, uint32
|
ap_axiu<64,0,0,0>
|
uint8, uint32, uint64
|
ap_axiu<128,0,0,0>
|
uint8, uint32, uint64
|
T1
|
T2
|
|---|---|
ap_axis<32,0,0,0>
|
int8, int16, int32, cint16
|
ap_axis<64,0,0,0>
|
int8, int16, int32, int64,
cint16, cint32
|
ap_axis<128,0,0,0>
|
int8, int16, int32, int64,
cint16, cint32
|
ap_axiu<32,0,0,0>
|
uint8, uint16, uint32
|
ap_axiu<64,0,0,0>
|
uint8, uint16,uint32, uint64
|
ap_axiu<128,0,0,0>
|
uint8, uint16,uint32, uint64
|
T1
|
T2
|
|---|---|
ap_axis<32,0,0,0>
|
int32, cint16
|
ap_axis<64,0,0,0>
|
int32, int64, cint16, cint32
|
ap_axis<128,0,0,0>
|
int32, int64, cint16, cint32
|
ap_axiu<32,0,0,0>
|
uint32
|
ap_axiu<64,0,0,0>
|
uint32,
uint64
|
ap_axiu<128,0,0,0>
|
uint32,
uint64
|
hls::stream and adf
stream and window data types for ap_int, ap_uint, std::complex,
and native C/C++ element data types.
T1
|
T2
|
|---|---|
ap_int<32>
|
int32
|
ap_uint<32>
|
uint32
|
ap_int<64>
|
int64
|
ap_uint<64>
|
uint64
|
std::complex<short>
|
cint16
|
std::complex<int>
|
cint32
|
std::complex<float>
|
cfloat
|
int
|
int32
|
unsigned
int
|
uint32
|
long
long
|
int64
|
unsigned long
long
|
uint64
|
float
|
float
|