3.6.6 SmartHLS Migration Guide

Learn how existing Vitis HLS / Vivado HLS designs can be easily migrated to SmartHLS.

3.6.6.1 SmartHLS Migration Guide

This section describes how existing Vitis HLS / Vivado HLS designs can be easily migrated to SmartHLS. When migrating an existing C++ design from Vitis HLS / Vivado HLS, the pragmas and libraries used in the source code should be changed to the equivalent ones in SmartHLS. Changes to the C++ source code may also be necessary.

3.6.6.2 General Porting

Vitis HLS / Vivado HLSSmartHLS
set_top <FUNC> (in synthesis Tcl file)On the first line of <FUNC>, add #pragma HLS function top
#include <ap_int.h>

#include <hls/ap_int.hpp>

Depending on the type(s) used, add using hls::ap_uint;, and/or using hls::ap_int;

#include <ap_fixed.h>

#include <hls/ap_fixpt.hpp>

Depending on the type(s) used, add using hls::ap_fixpt; #define ap_fixed ap_fixpt , and/or using hls::ap_ufixpt; #define ap_ufixed ap_ufixpt

#include <hls_stream.h>

#include <hls/streaming.hpp>

#define stream FIFO

hls::stream constructor

Vitis/Vivado HLS’s stream constructor optionally takes a string name as argument, while SmartHLS’s FIFO constructor optionally takes depth and type.VHLS’s stream assumes infinite size in C simulation, so set equivalent SmartHLS FIFOs’ depths very deep for C simulation.Example of mapping an external FIFO:

VHLS: hls::stream<int> data;

SmartHLS: hls::stream<int> data(1e4);

Example of mapping an internal FIFO:

VHLS:

hls::stream<int> data;
#pragma HLS stream variable = data depth = 2
SmartHLS:
#ifndef __SYNTHESIS__
#define INTERNAL_STREAM_DEPTH  1e4
#else
#define INTERNAL_STREAM_DEPTH  2
#endif
hls::stream<int> data(INTERNAL_STREAM_DEPTH);
VHLS’s stream constructor may take FIFO name as argument, which should be removed.
<AP_INT_VAR>.to_int()

<AP_INT_VAR>.to_uint64(), or <AP_INT_VAR>.to_int64()

VHLS’s ap_int has a list of C-type conversion functions (e.g. to_short(), to_int(), to_long()), while SmartHLS only has to_uint64()/to_int64() and expects users to add explicit casting to the return value.

<AP_INT_VAR>.range(7,0).to_int()

(ap_uint<...><AP_INT_VAR>.range(7,0)).to_int64()

In SmartHLS, the return value of <AP_INT_VAR>.range() cannot be used to directly invoke to_int64()/to_uint64().

stringstream >> ap_fixpt<W, IW, Q_M, O_M>
std::stringstream istr(line)
ap_fixpt<W, IW, Q_M, O_M> = args;
double args_temp;
istr >> args_temp;
args = args_temp;
#include <assert.h>
#ifdef __SYNTHESIS__
#define NDEBUG
#endif
#include <assert.h>

3.6.6.3 Pragmas

Vitis HLS / Vivado HLSSmartHLS
aggregate, data_packSee the Struct Variable/Argument Packing pragmas.
allocation

A global constraint of operation resources can be set via set_resource_constraint; constraining the operation resource within a function, a loop or a block of code is not yet available.

Functions that are not inlined (automatically by SmartHLS tool or specified via the Inline Function pragma) always have a single RTL module instance in hardware, and it is shared by all callers. Replication of a function instance in hardware can be achieved by the Replicate Function and Inline Function pragmas. In the case of multi-threading, each thread of a function creates an instance of the corresponding RTL module.

array_partition

See the Partition Top-Level Interface and Partition Memory pragmas.

If the variable is globally/locally declared variable, move the pragma to right before the variable declaration.

If the variable is a top-level function argument, add the pragma to the beginning of the function definition block.

Example:

VHLS: #pragma HLS array_partition variable=<VAR> <TYPE> dim=<DIM>

If <VAR> is a global/local declared variable, use #pragma HLS memory partition variable(<VAR>) type(<TYPE>) dim(<DIM>) + move it to right before the <VAR> variable declaration.

If <VAR> is a top-level function argument, use #pragma HLS memory partition argument(<VAR>) type(<TYPE>) dim(<DIM>) + add it add the beginning of the function definition block.

SmartHLS supports complete memory partitioning in either 1 or all dimensions, while Vitis HLS can apply complete memory partitioning in more than 1 discrete dimensions. To port such case, users may need to reshape the array. Below is an example.

VHLS:

ap_uint<12> buffer[DIM_X][DIM_Y][DIM_Z];
#pragma HLS_ARRAY_PARTITION variable=buffer complete dim=1
#pragma HLS_ARRAY_PARTITION variable=buffer complete dim=2
// Access macro of 'buffer'
#define BUFFER(x,y,z)  (buffer[x][y][z])
SHLS:
#pragma HLS memory partition variable(buffer) type(complete) dim(1)
ap_uint<12> buffer[DIM_X*DIM_Y][DIM_Z];
// Access macro of 'buffer'
#define BUFFER(x,y,z)  (buffer[(x)*DIM_Y+(y)][z])
dataflowData Flow Parallelism and Multi-threading can be used to implement a task-level (dataflow) pipeline.
dependenceSee the Loop Dependency pragma.

If inside a loop, the pragma should be moved outside the loop.

disaggregateSee the struct_fields option of the Partition Top-Level Interface pragma.
expression_balanceSee LATENCY_REDUCTION Tcl settings to control the expression balance optimization.
function_instantiateThe equivalent optimization can be achieved with the Inline Function pragma or C++ template functions.
inlineSee the Inline Function pragma.
inline offSee the Noinline Function pragma.
interfaceSee Top-Level RTL Interface for details about supported interfaces and corresponding pragmas.
loop_tripcount

See the Bound Loop pragma, and lift it out of the loop. Note that SmartHLS does not capture the average number of loop iterations.

Example:

VHLS: #pragma HLS loop_tripcount min=<MIN> max=<MAX> avg=<AVG>

SHLS: #pragma HLS loop bounds lower(<MIN>) upper(<MAX>) + lift outside the loop

pipeline, pipeline II=<II>

See Pipeline Function and Pipeline Loop pragmas.

If inside a loop, the pragma should be lifted outside the loop.

If inside a function, add the pragma to the beginning of the function definition block.

pipeline offRemove since pipelining is not applied by default.
stableSee the stable option of the Scalar Argument Interface pragma.
streamStreaming interface is implemented via the hls::FIFO Argument.
topSee the Set Top-Level Function pragma.
unrollSee the Unroll Loop pragma, and lift it outside the loop.

The SmartHLS tool currently does not support the following Vitis/Vivado HLS pragmas:

  • array_map
  • array_reshape
  • bind_op
  • bind_storage
  • disaggregate
  • latency
  • loop_flatten
  • loop_merge
  • occurrence
  • protocol
  • reset
  • shared

3.6.6.4 Libraries

Arbitrary Precision Data Types
Similar to Vitis/Vivado HLS, SmartHLS provides C++ Arbitrary Precision Integer Library and C++ Arbitrary Precision Fixed Point Library. Note that conversion of primitive type pointers to ap_int/ap_uint pointers by way of simple casting is permitted in Vitis/Vivado HLS, but will result in unexpected behaviour in SmartHLS.
Streaming Library
Similar to the hls::stream template class in Vitis/Vivado HLS, SmartHLS provides a hls::FIFO template class in the Streaming Library.
Math Library
While SmartHLS supports a subset of functions in the Math Library (math.h), SmartHLS also has a Fixed Point Math Library that is optimized for hardware implementation with customizable arbitrary precisions. This library is in active development.
Vision Library
Like Vitis/Vivado HLS, SmartHLS has a vision library designed to simplify the development of video processing solutions on Microchip FPGA devices. The library provides pre-optimized HLS C++ library functions for fast algorithm prototyping of video applications. Using this library, OpenCV-based designs can be ported onto FPGAs with a faster time to market.
Other Libraries
Other libraries such as FFT, FIR, DDS, and SRL libraries are not yet supported by SmartHLS. We are actively developing libraries, such as the computer vision IPs. If you are interested in having support of certain IPs, please email us at SmartHLS@microchip.com. Your feedback is valuable to us and will help to prioritize our production plan.