riscv
/
OpenFPGA
mirror of https://github.com/lnis-uofu/OpenFPGA.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #116 from LNIS-Projects/dev 

Extended I/O Support for SoC I/O interface
This commit is contained in:
Laboratory for Nano Integrated Systems (LNIS) 2020-11-04 21:55:37 -07:00 committed by GitHub
parent 1f3e656f2e 93e7107d80
commit 55f7a2c187
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
88 changed files with 2339 additions and 176 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.travis/basic_reg_test.sh
View File

@ -98,4 +98,12 @@ python3 openfpga_flow/scripts/run_fpga_task.py basic_tests/k4_series/k4n4_frac_m
echo -e "Testing K4N5 with pattern based local routing";
python3 openfpga_flow/scripts/run_fpga_task.py basic_tests/k4_series/k4n5_pattern_local_routing --debug --show_thread_logs
echo -e "Testing different tile organizations";
echo -e "Testing tiles with pins only on top and left sides";
python3 openfpga_flow/scripts/run_fpga_task.py basic_tests/tile_organization/top_left_custom_pins --debug --show_thread_logs
echo -e "Testing tiles with pins only on top and right sides";
python3 openfpga_flow/scripts/run_fpga_task.py basic_tests/tile_organization/top_right_custom_pins --debug --show_thread_logs
echo -e "Testing tiles with pins only on bottom and right sides";
python3 openfpga_flow/scripts/run_fpga_task.py basic_tests/tile_organization/bottom_right_custom_pins --debug --show_thread_logs
end_section "OpenFPGA.TaskTun"

3
.travis/fpga_verilog_reg_test.sh
View File

@ -46,6 +46,9 @@ python3 openfpga_flow/scripts/run_fpga_task.py fpga_verilog/io/reduced_io --debu
echo -e "Testing Verilog generation with embedded I/Os for an FPGA ";
python3 openfpga_flow/scripts/run_fpga_task.py fpga_verilog/io/embedded_io --debug --show_thread_logs
echo -e "Testing Verilog generation with SoC I/Os for an FPGA ";
python3 openfpga_flow/scripts/run_fpga_task.py fpga_verilog/io/soc_io --debug --show_thread_logs
echo -e "Testing Verilog generation with adder chain across an FPGA";
python3 openfpga_flow/scripts/run_fpga_task.py fpga_verilog/fabric_chain/adder_chain --debug --show_thread_logs

49
libopenfpga/libarchopenfpga/src/check_circuit_library.cpp
View File

@ -571,31 +571,41 @@ static
size_t check_io_circuit_model(const CircuitLibrary& circuit_lib) {
size_t num_err = 0;
/* Embedded I/O interface may not have inout port
* iopad_port_types_required.push_back(CIRCUIT_MODEL_PORT_INOUT);
* Some I/Os may not have SRAM port, such as AIB interface
* iopad_port_types_required.push_back(CIRCUIT_MODEL_PORT_SRAM);
*/
std::vector<enum e_circuit_model_port_type> iopad_port_types_required;
iopad_port_types_required.push_back(CIRCUIT_MODEL_PORT_INOUT);
num_err += check_circuit_model_port_required(circuit_lib, CIRCUIT_MODEL_IOPAD, iopad_port_types_required);
/* Each I/O cell must have
* - One of the following ports
* - At least 1 ASIC-to-FPGA (A2F) port that is defined as global I/O
* - At least 1 FPGA-to-ASIC (F2A) port that is defined as global I/O!
* - At least 1 ASIC-to-FPGA (A2F) port that is defined as global data I/O
* - At least 1 FPGA-to-ASIC (F2A) port that is defined as global data I/O!
* - At least 1 regular port that is non-global which is connected to global routing architecture
*/
for (const auto& io_model : circuit_lib.models_by_type(CIRCUIT_MODEL_IOPAD)) {
bool has_global_io = false;
bool has_data_io = false;
bool has_data_input_only_io = false;
bool has_data_output_only_io = false;
bool has_internal_connection = false;
for (const auto& port : circuit_lib.model_ports(io_model)) {
if ( (true == circuit_lib.port_is_io(port)
&& (true == circuit_lib.port_is_global(port)))) {
has_global_io = true;
if ( (true == circuit_lib.port_is_io(port))
&& (true == circuit_lib.port_is_data_io(port))
&& (CIRCUIT_MODEL_PORT_INOUT == circuit_lib.port_type(port))
&& (true == circuit_lib.port_is_global(port))) {
has_data_io = true;
continue; /* Go to next */
}
if ( (true == circuit_lib.port_is_io(port))
&& (true == circuit_lib.port_is_data_io(port))
&& (CIRCUIT_MODEL_PORT_INPUT == circuit_lib.port_type(port))
&& (true == circuit_lib.port_is_global(port))) {
has_data_input_only_io = true;
continue; /* Go to next */
}
if ( (true == circuit_lib.port_is_io(port))
&& (true == circuit_lib.port_is_data_io(port))
&& (CIRCUIT_MODEL_PORT_OUTPUT == circuit_lib.port_type(port))
&& (true == circuit_lib.port_is_global(port))) {
has_data_output_only_io = true;
continue; /* Go to next */
}
if ( (false == circuit_lib.port_is_io(port)
&& (false == circuit_lib.port_is_global(port)))
&& (CIRCUIT_MODEL_PORT_SRAM != circuit_lib.port_type(port))) {
@ -604,9 +614,14 @@ size_t check_io_circuit_model(const CircuitLibrary& circuit_lib) {
}
}
if (false == has_global_io) {
/* Error out when
* - there is no data io, data input-only io and data output-only io
*/
if ( (false == has_data_io)
&& (false == has_data_input_only_io)
&& (false == has_data_output_only_io)) {
VTR_LOGF_ERROR(__FILE__, __LINE__,
"I/O circuit model '%s' does not have any I/O port defined!\n",
"I/O circuit model '%s' does not have any data I/O port defined!\n",
circuit_lib.model_name(io_model).c_str());
num_err++;
}

17
libopenfpga/libarchopenfpga/src/circuit_library.cpp
View File

@ -907,6 +907,13 @@ bool CircuitLibrary::port_is_io(const CircuitPortId& circuit_port_id) const {
return port_is_io_[circuit_port_id];
}
/* Return a flag if the port is used in mode-selection purpuse of a circuit model */
bool CircuitLibrary::port_is_data_io(const CircuitPortId& circuit_port_id) const {
/* validate the circuit_port_id */
VTR_ASSERT(valid_circuit_port_id(circuit_port_id));
return port_is_data_io_[circuit_port_id];
}
/* Return a flag if the port is used in mode-selection purpuse of a circuit model */
bool CircuitLibrary::port_is_mode_select(const CircuitPortId& circuit_port_id) const {
/* validate the circuit_port_id */
@ -1370,6 +1377,7 @@ CircuitPortId CircuitLibrary::add_model_port(const CircuitModelId& model_id,
port_inv_prefix_.emplace_back();
port_default_values_.push_back(-1);
port_is_io_.push_back(false);
port_is_data_io_.push_back(false);
port_is_mode_select_.push_back(false);
port_is_global_.push_back(false);
port_is_reset_.push_back(false);
@ -1449,6 +1457,15 @@ void CircuitLibrary::set_port_is_io(const CircuitPortId& circuit_port_id,
return;
}
/* Set the is_mode_select for a port of a circuit model */
void CircuitLibrary::set_port_is_data_io(const CircuitPortId& circuit_port_id,
const bool& is_data_io) {
/* validate the circuit_port_id */
VTR_ASSERT(valid_circuit_port_id(circuit_port_id));
port_is_data_io_[circuit_port_id] = is_data_io;
return;
}
/* Set the is_mode_select for a port of a circuit model */
void CircuitLibrary::set_port_is_mode_select(const CircuitPortId& circuit_port_id,
const bool& is_mode_select) {

48
libopenfpga/libarchopenfpga/src/circuit_library.h
View File

@ -79,27 +79,29 @@
* 2. pass_gate_logic_model_id_: specify the id of circuit model for the pass gate logic
*
* ------ Port information ------
* 1. port_ids_: unique id of ports belonging to a circuit model
* 1. port_model_ids_: unique id of the parent circuit model for the port
* 2. port_types_: types of ports belonging to a circuit model
* 3. port_sizes_: width of ports belonging to a circuit model
* 4. port_prefix_: prefix of a port when instance of a circuit model
* 5. port_lib_names_: port name in the standard cell library, only used when explicit_port_mapping is enabled
* 6. port_inv_prefix_: the prefix to be added for the inverted port. This is mainly used by SRAM ports, which have an coupled inverterd port
* 7. port_is_mode_select: specify if this port is used to select operating modes of the circuit model
* 8. port_is_global: specify if this port is a global signal shared by other circuit model
* 9. port_is_reset: specify if this port is a reset signal which needs special pulse widths in testbenches
* 10. port_is_set: specify if this port is a set signal which needs special pulse widths in testbenches
* 11. port_is_config_enable: specify if this port is a config_enable signal which needs special pulse widths in testbenches
* 12. port_is_prog: specify if this port is for FPGA programming use which needs special pulse widths in testbenches
* 13. port_tri_state_model_name: the name of circuit model linked to tri-state the port
* 14. port_tri_state_model_ids_: the Id of circuit model linked to tri-state the port
* 15. port_inv_model_names_: the name of inverter circuit model linked to the port
* 16. port_inv_model_ids_: the Id of inverter circuit model linked to the port
* 17. port_tri_state_map_: only applicable to inputs of LUTs, the tri-state map applied to each pin of this port
* 18. port_lut_frac_level_: only applicable to outputs of LUTs, indicate which level of outputs inside LUT multiplexing structure will be used
* 19. port_lut_output_mask_: only applicable to outputs of LUTs, indicate which output at an internal level of LUT multiplexing structure will be used
* 20. port_sram_orgz_: only applicable to SRAM ports, indicate how the SRAMs will be organized, either memory decoders or scan-chains
* - port_ids_: unique id of ports belonging to a circuit model
* - port_model_ids_: unique id of the parent circuit model for the port
* - port_types_: types of ports belonging to a circuit model
* - port_sizes_: width of ports belonging to a circuit model
* - port_prefix_: prefix of a port when instance of a circuit model
* - port_lib_names_: port name in the standard cell library, only used when explicit_port_mapping is enabled
* - port_inv_prefix_: the prefix to be added for the inverted port. This is mainly used by SRAM ports, which have an coupled inverterd port
* - port_is_mode_select: specify if this port is used to select operating modes of the circuit model
* - port_is_io: specify if this port is an io port
* - port_is_data_io: specify if this port is an io port that can be mapped to a signal from netlist
* - port_is_global: specify if this port is a global signal shared by other circuit model
* - port_is_reset: specify if this port is a reset signal which needs special pulse widths in testbenches
* - port_is_set: specify if this port is a set signal which needs special pulse widths in testbenches
* - port_is_config_enable: specify if this port is a config_enable signal which needs special pulse widths in testbenches
* - port_is_prog: specify if this port is for FPGA programming use which needs special pulse widths in testbenches
* - port_tri_state_model_name: the name of circuit model linked to tri-state the port
* - port_tri_state_model_ids_: the Id of circuit model linked to tri-state the port
* - port_inv_model_names_: the name of inverter circuit model linked to the port
* - port_inv_model_ids_: the Id of inverter circuit model linked to the port
* - port_tri_state_map_: only applicable to inputs of LUTs, the tri-state map applied to each pin of this port
* - port_lut_frac_level_: only applicable to outputs of LUTs, indicate which level of outputs inside LUT multiplexing structure will be used
* - port_lut_output_mask_: only applicable to outputs of LUTs, indicate which output at an internal level of LUT multiplexing structure will be used
* - port_sram_orgz_: only applicable to SRAM ports, indicate how the SRAMs will be organized, either memory decoders or scan-chains
*
* ------ Delay information ------
* 1. delay_types_: type of pin-to-pin delay, either rising_edge of falling_edge
@ -279,6 +281,7 @@ class CircuitLibrary {
std::string port_inv_prefix(const CircuitPortId& circuit_port_id) const;
size_t port_default_value(const CircuitPortId& circuit_port_id) const;
bool port_is_io(const CircuitPortId& circuit_port_id) const;
bool port_is_data_io(const CircuitPortId& circuit_port_id) const;
bool port_is_mode_select(const CircuitPortId& circuit_port_id) const;
bool port_is_global(const CircuitPortId& circuit_port_id) const;
bool port_is_reset(const CircuitPortId& circuit_port_id) const;
@ -354,6 +357,8 @@ class CircuitLibrary {
const size_t& default_val);
void set_port_is_io(const CircuitPortId& circuit_port_id,
const bool& is_io);
void set_port_is_data_io(const CircuitPortId& circuit_port_id,
const bool& is_data_io);
void set_port_is_mode_select(const CircuitPortId& circuit_port_id,
const bool& is_mode_select);
void set_port_is_global(const CircuitPortId& circuit_port_id,
@ -545,6 +550,7 @@ class CircuitLibrary {
vtr::vector<CircuitPortId, std::string> port_inv_prefix_;
vtr::vector<CircuitPortId, size_t> port_default_values_;
vtr::vector<CircuitPortId, bool> port_is_io_;
vtr::vector<CircuitPortId, bool> port_is_data_io_;
vtr::vector<CircuitPortId, bool> port_is_mode_select_;
vtr::vector<CircuitPortId, bool> port_is_global_;
vtr::vector<CircuitPortId, bool> port_is_reset_;

7
libopenfpga/libarchopenfpga/src/read_xml_circuit_library.cpp
View File

@ -418,6 +418,13 @@ void read_xml_circuit_port(pugi::xml_node& xml_port,
*/
circuit_lib.set_port_is_io(port, get_attribute(xml_port, "is_io", loc_data, pugiutil::ReqOpt::OPTIONAL).as_bool(false));
/* Identify if the port is a data io, ONLY applicable to I/O port
* By default, it will NOT be a data io port
*/
if (true == circuit_lib.port_is_io(port)) {
circuit_lib.set_port_is_data_io(port, get_attribute(xml_port, "is_data_io", loc_data, pugiutil::ReqOpt::OPTIONAL).as_bool(false));
}
/* Identify if the port is for mode selection, this is only applicable to SRAM ports.
* By default, it will NOT be a mode selection port
*/

9
libopenfpga/libarchopenfpga/src/write_xml_circuit_library.cpp
View File

@ -186,6 +186,15 @@ void write_xml_circuit_port(std::fstream& fp,
}
}
/* I/O port attributes */
if (true == circuit_lib.port_is_io(port)) {
write_xml_attribute(fp, "is_io", "true");
}
if (true == circuit_lib.port_is_data_io(port)) {
write_xml_attribute(fp, "is_data_io", "true");
}
/* Global, reset, set port attributes */
if (true == circuit_lib.port_is_global(port)) {
write_xml_attribute(fp, "is_global", "true");

22
openfpga/src/fabric/build_fabric_io_location_map.cpp
View File

@ -18,6 +18,7 @@
#include "openfpga_reserved_words.h"
#include "openfpga_naming.h"
#include "module_manager_utils.h"
#include "openfpga_device_grid_utils.h"
#include "build_fabric_io_location_map.h"
@ -74,7 +75,15 @@ IoLocationMap build_fabric_io_location_map(const ModuleManager& module_manager,
* Note: if you change the GPIO function, you should update here as well!
*/
for (int z = 0; z < grids[io_coordinate.x()][io_coordinate.y()].type->capacity; ++z) {
for (const BasicPort& gpio_port : module_manager.module_ports_by_type(grid_module, ModuleManager::MODULE_GPIO_PORT)) {
for (const ModuleManager::e_module_port_type& module_io_port_type : MODULE_IO_PORT_TYPES) {
for (const ModulePortId& gpio_port_id : module_manager.module_port_ids_by_type(grid_module, module_io_port_type)) {
/* Only care mappable I/O */
if (false == module_manager.port_is_mappable_io(grid_module, gpio_port_id)) {
continue;
}
const BasicPort& gpio_port = module_manager.module_port(grid_module, gpio_port_id);
auto curr_io_index = io_counter.find(gpio_port.get_name());
/* Index always start from zero */
if (curr_io_index == io_counter.end()) {
@ -88,15 +97,24 @@ IoLocationMap build_fabric_io_location_map(const ModuleManager& module_manager,
}
}
}
}
/* Check all the GPIO ports in the top-level module has been mapped */
std::string top_module_name = generate_fpga_top_module_name();
ModuleId top_module = module_manager.find_module(top_module_name);
VTR_ASSERT(true == module_manager.valid_module_id(top_module));
for (const BasicPort& gpio_port : module_manager.module_ports_by_type(top_module, ModuleManager::MODULE_GPIO_PORT)) {
for (const ModuleManager::e_module_port_type& module_io_port_type : MODULE_IO_PORT_TYPES) {
for (const ModulePortId& gpio_port_id : module_manager.module_port_ids_by_type(top_module, module_io_port_type)) {
/* Only care mappable I/O */
if (false == module_manager.port_is_mappable_io(top_module, gpio_port_id)) {
continue;
}
const BasicPort& gpio_port = module_manager.module_port(top_module, gpio_port_id);
VTR_ASSERT(io_counter[gpio_port.get_name()] == gpio_port.get_width());
}
}
return io_location_map;
}

5
openfpga/src/fabric/build_grid_modules.cpp
View File

@ -159,6 +159,11 @@ void add_primitive_module_fpga_global_io_port(ModuleManager& module_manager,
const CircuitPortId& circuit_port) {
BasicPort module_port(generate_fpga_global_io_port_name(std::string(GIO_INOUT_PREFIX), circuit_lib, primitive_model, circuit_port), circuit_lib.port_size(circuit_port));
ModulePortId primitive_io_port_id = module_manager.add_port(primitive_module, module_port, module_io_port_type);
/* Set if the port is mappable or not */
if (true == circuit_lib.port_is_data_io(circuit_port)) {
module_manager.set_port_is_mappable_io(primitive_module, primitive_io_port_id, true);
}
ModulePortId logic_io_port_id = module_manager.find_module_port(logic_module, circuit_lib.port_prefix(circuit_port));
BasicPort logic_io_port = module_manager.module_port(logic_module, logic_io_port_id);
VTR_ASSERT(logic_io_port.get_width() == module_port.get_width());

22
openfpga/src/fabric/module_manager.cpp
View File

@ -286,6 +286,12 @@ size_t ModuleManager::instance_id(const ModuleId& parent_module, const ModuleId&
return size_t(-1);
}
ModuleManager::e_module_port_type ModuleManager::port_type(const ModuleId& module, const ModulePortId& port) const {
/* validate both module id and port id*/
VTR_ASSERT(valid_module_port_id(module, port));
return port_types_[module][port];
}
/* Find if a port is a wire connection */
bool ModuleManager::port_is_wire(const ModuleId& module, const ModulePortId& port) const {
/* validate both module id and port id*/
@ -293,6 +299,13 @@ bool ModuleManager::port_is_wire(const ModuleId& module, const ModulePortId& por
return port_is_wire_[module][port];
}
/* Find if a port is a mappable i/o */
bool ModuleManager::port_is_mappable_io(const ModuleId& module, const ModulePortId& port) const {
/* validate both module id and port id*/
VTR_ASSERT(valid_module_port_id(module, port));
return port_is_mappable_io_[module][port];
}
/* Find if a port is register */
bool ModuleManager::port_is_register(const ModuleId& module, const ModulePortId& port) const {
/* validate both module id and port id*/
@ -529,6 +542,7 @@ ModuleId ModuleManager::add_module(const std::string& name) {
ports_.emplace_back();
port_types_.emplace_back();
port_is_wire_.emplace_back();
port_is_mappable_io_.emplace_back();
port_is_register_.emplace_back();
port_preproc_flags_.emplace_back();
@ -573,6 +587,7 @@ ModulePortId ModuleManager::add_port(const ModuleId& module,
ports_[module].push_back(port_info);
port_types_[module].push_back(port_type);
port_is_wire_[module].push_back(false);
port_is_mappable_io_[module].push_back(false);
port_is_register_[module].push_back(false);
port_preproc_flags_[module].emplace_back(); /* Create an empty string for the pre-processing flags */
@ -617,6 +632,13 @@ void ModuleManager::set_port_is_wire(const ModuleId& module, const std::string&
port_is_wire_[module][port] = is_wire;
}
/* Set a port to be a mappable I/O */
void ModuleManager::set_port_is_mappable_io(const ModuleId& module, const ModulePortId& port_id, const bool& is_mappable_io) {
/* Must find something, otherwise drop an error */
VTR_ASSERT(valid_module_port_id(module, port_id));
port_is_mappable_io_[module][port_id] = is_mappable_io;
}
/* Set a port to be a register */
void ModuleManager::set_port_is_register(const ModuleId& module, const std::string& port_name, const bool& is_register) {
/* Find the port */

7
openfpga/src/fabric/module_manager.h
View File

@ -184,8 +184,12 @@ class ModuleManager {
/* Find the instance id of a given instance name */
size_t instance_id(const ModuleId& parent_module, const ModuleId& child_module,
const std::string& instance_name) const;
/* Find the type of a port */
ModuleManager::e_module_port_type port_type(const ModuleId& module, const ModulePortId& port) const;
/* Find if a port is a wire connection */
bool port_is_wire(const ModuleId& module, const ModulePortId& port) const;
/* Find if a port is mappable to an I/O from users' implementations */
bool port_is_mappable_io(const ModuleId& module, const ModulePortId& port) const;
/* Find if a port is register */
bool port_is_register(const ModuleId& module, const ModulePortId& port) const;
/* Return the pre-processing flag of a port */
@ -238,6 +242,8 @@ class ModuleManager {
void set_module_usage(const ModuleId& module, const e_module_usage_type& usage);
/* Set a port to be a wire */
void set_port_is_wire(const ModuleId& module, const std::string& port_name, const bool& is_wire);
/* Set a port to be mappable to an I/O from users' implemenations */
void set_port_is_mappable_io(const ModuleId& module, const ModulePortId& port_id, const bool& is_mappable_io);
/* Set a port to be a register */
void set_port_is_register(const ModuleId& module, const std::string& port_name, const bool& is_register);
/* Set the preprocessing flag for a port */
@ -356,6 +362,7 @@ class ModuleManager {
vtr::vector<ModuleId, vtr::vector<ModulePortId, ModulePortId>> port_ids_; /* List of ports for each Module */
vtr::vector<ModuleId, vtr::vector<ModulePortId, BasicPort>> ports_; /* List of ports for each Module */
vtr::vector<ModuleId, vtr::vector<ModulePortId, enum e_module_port_type>> port_types_; /* Type of ports */
vtr::vector<ModuleId, vtr::vector<ModulePortId, bool>> port_is_mappable_io_; /* If the port is mappable to an I/O for user's implementations */
vtr::vector<ModuleId, vtr::vector<ModulePortId, bool>> port_is_wire_; /* If the port is a wire, use for Verilog port definition. If enabled: <port_type> reg <port_name> */
vtr::vector<ModuleId, vtr::vector<ModulePortId, bool>> port_is_register_; /* If the port is a register, use for Verilog port definition. If enabled: <port_type> reg <port_name> */
vtr::vector<ModuleId, vtr::vector<ModulePortId, std::string>> port_preproc_flags_; /* If a port is available only when a pre-processing flag is enabled. This is to record the pre-processing flags */

72
openfpga/src/fpga_verilog/verilog_testbench_utils.cpp
View File

@ -7,6 +7,7 @@
*******************************************************************/
#include <algorithm>
#include <iomanip>
#include <map>
/* Headers from vtrutil library */
#include "vtr_assert.h"
@ -17,6 +18,8 @@
#include "verilog_port_types.h"
#include "module_manager_utils.h"
#include "verilog_constants.h"
#include "verilog_writer_utils.h"
#include "verilog_testbench_utils.h"
@ -147,12 +150,29 @@ void print_verilog_testbench_connect_fpga_ios(std::fstream& fp,
/* Validate the file stream */
valid_file_stream(fp);
/* In this function, we support only 1 type of I/Os */
std::vector<BasicPort> module_io_ports = module_manager.module_ports_by_type(top_module, ModuleManager::MODULE_GPIO_PORT);
/* Only mappable i/o ports can be considered */
std::vector<ModulePortId> module_io_ports;
for (const ModuleManager::e_module_port_type& module_io_port_type : MODULE_IO_PORT_TYPES) {
for (const ModulePortId& gpio_port_id : module_manager.module_port_ids_by_type(top_module, module_io_port_type)) {
/* Only care mappable I/O */
if (false == module_manager.port_is_mappable_io(top_module, gpio_port_id)) {
continue;
}
module_io_ports.push_back(gpio_port_id);
}
}
/* Keep tracking which I/Os have been used */
for (const BasicPort& module_io_port : module_io_ports) {
std::vector<bool> io_used(module_io_port.get_width(), false);
std::map<ModulePortId, std::vector<bool>> io_used;
for (const ModulePortId& module_io_port_id : module_io_ports) {
const BasicPort& module_io_port = module_manager.module_port(top_module, module_io_port_id);
io_used[module_io_port_id] = std::vector<bool>(module_io_port.get_width(), false);
}
/* Type mapping between VPR block and Module port */
std::map<AtomBlockType, ModuleManager::e_module_port_type> atom_block_type_to_module_port_type;
atom_block_type_to_module_port_type[AtomBlockType::INPAD] = ModuleManager::MODULE_GPIN_PORT;
atom_block_type_to_module_port_type[AtomBlockType::OUTPAD] = ModuleManager::MODULE_GPOUT_PORT;
/* See if this I/O should be wired to a benchmark input/output */
/* Add signals from blif benchmark and short-wire them to FPGA I/O PADs
@ -167,19 +187,46 @@ void print_verilog_testbench_connect_fpga_ios(std::fstream& fp,
continue;
}
/* If there is a GPIO port, use it directly
* Otherwise, should find a GPIN for INPAD
* or should find a GPOUT for OUTPAD
*/
std::pair<ModulePortId, size_t> mapped_module_io_info = std::make_pair(ModulePortId::INVALID(), -1);
for (const ModulePortId& module_io_port_id : module_io_ports) {
const BasicPort& module_io_port = module_manager.module_port(top_module, module_io_port_id);
/* Find the index of the mapped GPIO in top-level FPGA fabric */
size_t io_index = io_location_map.io_index(place_ctx.block_locs[atom_ctx.lookup.atom_clb(atom_blk)].loc.x,
size_t temp_io_index = io_location_map.io_index(place_ctx.block_locs[atom_ctx.lookup.atom_clb(atom_blk)].loc.x,
place_ctx.block_locs[atom_ctx.lookup.atom_clb(atom_blk)].loc.y,
place_ctx.block_locs[atom_ctx.lookup.atom_clb(atom_blk)].loc.z,
module_io_port.get_name());
/* Bypass invalid index (not mapped to this GPIO port) */
if (size_t(-1) == io_index) {
if (size_t(-1) == temp_io_index) {
continue;
}
/* If the port is an GPIO port, just use it */
if (ModuleManager::MODULE_GPIO_PORT == module_manager.port_type(top_module, module_io_port_id)) {
mapped_module_io_info = std::make_pair(module_io_port_id, temp_io_index);
break;
}
/* If this is an INPAD, we can use an GPIN port (if available) */
if (atom_block_type_to_module_port_type[atom_ctx.nlist.block_type(atom_blk)] == module_manager.port_type(top_module, module_io_port_id)) {
mapped_module_io_info = std::make_pair(module_io_port_id, temp_io_index);
break;
}
}
/* We must find a valid one */
VTR_ASSERT(true == module_manager.valid_module_port_id(top_module, mapped_module_io_info.first));
VTR_ASSERT(size_t(-1) != mapped_module_io_info.second);
/* Ensure that IO index is in range */
BasicPort module_mapped_io_port = module_io_port;
BasicPort module_mapped_io_port = module_manager.module_port(top_module, mapped_module_io_info.first);
size_t io_index = mapped_module_io_info.second;
/* Set the port pin index */
VTR_ASSERT(io_index < module_mapped_io_port.get_width());
module_mapped_io_port.set_width(io_index, io_index);
@ -209,22 +256,23 @@ void print_verilog_testbench_connect_fpga_ios(std::fstream& fp,
}
/* Mark this I/O has been used/wired */
io_used[io_index] = true;
}
io_used[mapped_module_io_info.first][io_index] = true;
/* Add an empty line as a splitter */
fp << std::endl;
}
/* Wire the unused iopads to a constant */
print_verilog_comment(fp, std::string("----- Wire unused FPGA I/Os to constants -----"));
for (size_t io_index = 0; io_index < io_used.size(); ++io_index) {
for (const ModulePortId& module_io_port_id : module_io_ports) {
for (size_t io_index = 0; io_index < io_used[module_io_port_id].size(); ++io_index) {
/* Bypass used iopads */
if (true == io_used[io_index]) {
if (true == io_used[module_io_port_id][io_index]) {
continue;
}
/* Wire to a contant */
BasicPort module_unused_io_port = module_io_port;
BasicPort module_unused_io_port = module_manager.module_port(top_module, module_io_port_id);
/* Set the port pin index */
module_unused_io_port.set_width(io_index, io_index);

38
openfpga/src/utils/module_manager_utils.cpp
View File

@ -157,20 +157,29 @@ ModuleId add_circuit_model_to_module_manager(ModuleManager& module_manager,
*/
for (const auto& port : circuit_lib.model_global_ports(circuit_model, false)) {
BasicPort port_info(circuit_lib.port_prefix(port), circuit_lib.port_size(port));
ModulePortId module_port = ModulePortId::INVALID();
if ( (CIRCUIT_MODEL_PORT_INPUT == circuit_lib.port_type(port))
&& (false == circuit_lib.port_is_io(port)) ) {
module_manager.add_port(module, port_info, ModuleManager::MODULE_GLOBAL_PORT);
module_port = module_manager.add_port(module, port_info, ModuleManager::MODULE_GLOBAL_PORT);
} else if (CIRCUIT_MODEL_PORT_CLOCK == circuit_lib.port_type(port)) {
module_manager.add_port(module, port_info, ModuleManager::MODULE_GLOBAL_PORT);
module_port = module_manager.add_port(module, port_info, ModuleManager::MODULE_GLOBAL_PORT);
} else if ( (CIRCUIT_MODEL_PORT_INPUT == circuit_lib.port_type(port))
&& (true == circuit_lib.port_is_io(port)) ) {
module_manager.add_port(module, port_info, ModuleManager::MODULE_GPIN_PORT);
module_port = module_manager.add_port(module, port_info, ModuleManager::MODULE_GPIN_PORT);
} else if (CIRCUIT_MODEL_PORT_OUTPUT == circuit_lib.port_type(port)) {
VTR_ASSERT(true == circuit_lib.port_is_io(port));
module_manager.add_port(module, port_info, ModuleManager::MODULE_GPOUT_PORT);
module_port = module_manager.add_port(module, port_info, ModuleManager::MODULE_GPOUT_PORT);
} else if ( (CIRCUIT_MODEL_PORT_INOUT == circuit_lib.port_type(port))
&& (true == circuit_lib.port_is_io(port)) ) {
module_manager.add_port(module, port_info, ModuleManager::MODULE_GPIO_PORT);
module_port = module_manager.add_port(module, port_info, ModuleManager::MODULE_GPIO_PORT);
}
/* Specify if the port can be mapped to an data signal */
if (true == module_manager.valid_module_port_id(module, module_port)) {
if (true == circuit_lib.port_is_data_io(port)) {
module_manager.set_port_is_mappable_io(module, module_port, true);
}
}
}
@ -1454,20 +1463,27 @@ void add_module_io_ports_from_child_modules(ModuleManager& module_manager,
const ModuleId& module_id,
const ModuleManager::e_module_port_type& module_port_type) {
std::vector<BasicPort> gpio_ports_to_add;
std::vector<bool> mappable_gpio_ports;
/* Iterate over the child modules */
for (const ModuleId& child : module_manager.child_modules(module_id)) {
/* Iterate over the child instances */
for (size_t i = 0; i < module_manager.num_instance(module_id, child); ++i) {
/* Find all the global ports, whose port type is special */
for (BasicPort gpio_port : module_manager.module_ports_by_type(child, module_port_type)) {
for (const ModulePortId& gpio_port_id : module_manager.module_port_ids_by_type(child, module_port_type)) {
const BasicPort& gpio_port = module_manager.module_port(child, gpio_port_id);
/* If this port is not mergeable, we update the list */
bool is_mergeable = false;
for (BasicPort& gpio_port_to_add : gpio_ports_to_add) {
for (size_t i_gpio_port_to_add = 0; i_gpio_port_to_add < gpio_ports_to_add.size(); ++i_gpio_port_to_add) {
BasicPort& gpio_port_to_add = gpio_ports_to_add[i_gpio_port_to_add];
if (false == gpio_port_to_add.mergeable(gpio_port)) {
continue;
}
is_mergeable = true;
/* Mappable I/O property must match! Mismatch rarely happened
* but should error out avoid silent bugs!
*/
VTR_ASSERT(module_manager.port_is_mappable_io(child, gpio_port_id) == mappable_gpio_ports[i_gpio_port_to_add]);
/* For mergeable ports, we combine the port
* Note: do NOT use the merge() method!
* the GPIO ports should be accumulated by the sizes of ports
@ -1479,6 +1495,8 @@ void add_module_io_ports_from_child_modules(ModuleManager& module_manager,
if (false == is_mergeable) {
/* Reach here, this is an unique gpio port, update the list */
gpio_ports_to_add.push_back(gpio_port);
/* If the gpio port is a mappable I/O, we should herit from the child module */
mappable_gpio_ports.push_back(module_manager.port_is_mappable_io(child, gpio_port_id));
}
}
}
@ -1487,9 +1505,13 @@ void add_module_io_ports_from_child_modules(ModuleManager& module_manager,
/* Record the port id for each type of GPIO port */
std::vector<ModulePortId> gpio_port_ids;
/* Add the gpio ports for the module */
for (const BasicPort& gpio_port_to_add : gpio_ports_to_add) {
for (size_t iport = 0; iport < gpio_ports_to_add.size(); ++iport) {
const BasicPort& gpio_port_to_add = gpio_ports_to_add[iport];
ModulePortId port_id = module_manager.add_port(module_id, gpio_port_to_add, module_port_type);
gpio_port_ids.push_back(port_id);
if (true == mappable_gpio_ports[iport]) {
module_manager.set_port_is_mappable_io(module_id, port_id, true);
}
}
/* Set up a counter for each type of GPIO port */

2
openfpga/src/utils/module_manager_utils.h
View File

@ -32,6 +32,8 @@
/* begin namespace openfpga */
namespace openfpga {
constexpr std::array<ModuleManager::e_module_port_type, 3> MODULE_IO_PORT_TYPES = {ModuleManager::MODULE_GPIN_PORT, ModuleManager::MODULE_GPOUT_PORT, ModuleManager::MODULE_GPIO_PORT};
void reserve_module_manager_module_nets(ModuleManager& module_manager,
const ModuleId& module);

2
openfpga_flow/openfpga_arch/k4_N4_40nm_bank_openfpga.xml
View File

@ -159,7 +159,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAM" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_bank_use_both_set_reset_openfpga.xml
View File

@ -161,7 +161,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAMSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_bank_use_reset_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAMR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_bank_use_resetb_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAMRN" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_bank_use_set_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAMS" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_bank_use_setb_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAMSN" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_cc_openfpga.xml
View File

@ -150,7 +150,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFF" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_cc_use_both_set_reset_openfpga.xml
View File

@ -152,7 +152,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_cc_use_reset_openfpga.xml
View File

@ -151,7 +151,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_cc_use_resetb_openfpga.xml
View File

@ -151,7 +151,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFRN" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_cc_use_set_openfpga.xml
View File

@ -151,7 +151,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFS" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_cc_use_setb_openfpga.xml
View File

@ -151,7 +151,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFSN" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_fixed_sim_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_ccff_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_const_input_gnd_openfpga.xml
View File

@ -159,7 +159,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCH" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_no_const_input_openfpga.xml
View File

@ -144,7 +144,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCH" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_openfpga.xml
View File

@ -159,7 +159,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCH" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_scff_openfpga.xml
View File

@ -163,7 +163,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SDFFSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_use_both_set_reset_openfpga.xml
View File

@ -161,7 +161,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_use_reset_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_use_resetb_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHRN" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_use_set_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHS" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_frame_use_setb_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHSN" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_multi_region_bank_openfpga.xml
View File

@ -159,7 +159,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAM" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_multi_region_bank_use_both_set_reset_openfpga.xml
View File

@ -161,7 +161,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="SRAMSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_multi_region_cc_openfpga.xml
View File

@ -150,7 +150,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFF" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_multi_region_cc_use_both_set_reset_openfpga.xml
View File

@ -152,7 +152,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_multi_region_frame_openfpga.xml
View File

@ -159,7 +159,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCH" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_multi_region_frame_use_both_set_reset_openfpga.xml
View File

@ -161,7 +161,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHSR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_powergate_frame_openfpga.xml
View File

@ -166,7 +166,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_40nm_standalone_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N4_no_local_routing_40nm_frame_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_N5_pattern_local_routing_40nm_frame_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_frac_N4_40nm_cc_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_40nm_cc_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_40nm_frame_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_L124_40nm_frame_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_frac_dsp32_40nm_frame_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="LATCHR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k4_frac_N4_lut_use_and_switch_40nm_cc_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

250
openfpga_flow/openfpga_arch/k4_frac_N8_register_scan_chain_caravel_io_skywater130nm_fdhd_cc_openfpga.xml Normal file
View File

@ -0,0 +1,250 @@
<!-- Architecture annotation for OpenFPGA framework
This annotation supports the k4_frac_cc_sky130nm.xml
- General purpose logic block
- K = 6, N = 10, I = 40
- Single mode
- Routing architecture
- L = 4, fc_in = 0.15, fc_out = 0.1
- Skywater 130nm PDK
- circuit models are binded to the opensource skywater
foundry middle-speed (ms) standard cell library
-->
<openfpga_architecture>
<technology_library>
<device_library>
<device_model name="logic" type="transistor">
<lib type="industry" corner="TOP_TT" ref="M" path="${OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.pm"/>
<design vdd="0.9" pn_ratio="2"/>
<pmos name="pch" chan_length="40e-9" min_width="140e-9" variation="logic_transistor_var"/>
<nmos name="nch" chan_length="40e-9" min_width="140e-9" variation="logic_transistor_var"/>
</device_model>
<device_model name="io" type="transistor">
<lib type="academia" ref="M" path="${OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.pm"/>
<design vdd="2.5" pn_ratio="3"/>
<pmos name="pch_25" chan_length="270e-9" min_width="320e-9" variation="io_transistor_var"/>
<nmos name="nch_25" chan_length="270e-9" min_width="320e-9" variation="io_transistor_var"/>
</device_model>
</device_library>
<variation_library>
<variation name="logic_transistor_var" abs_deviation="0.1" num_sigma="3"/>
<variation name="io_transistor_var" abs_deviation="0.1" num_sigma="3"/>
</variation_library>
</technology_library>
<circuit_library>
<circuit_model type="inv_buf" name="sky130_fd_sc_hd__inv_1" prefix="sky130_fd_sc_hd__inv_1" is_default="true">
<design_technology type="cmos" topology="inverter" size="1"/>
<device_technology device_model_name="logic"/>
<port type="input" prefix="in" lib_name="A" size="1"/>
<port type="output" prefix="out" lib_name="Y" size="1"/>
<delay_matrix type="rise" in_port="in" out_port="out">
10e-12
</delay_matrix>
<delay_matrix type="fall" in_port="in" out_port="out">
10e-12
</delay_matrix>
</circuit_model>
<circuit_model type="inv_buf" name="sky130_fd_sc_hd__buf_2" prefix="sky130_fd_sc_hd__buf_2" is_default="false">
<design_technology type="cmos" topology="buffer" size="1" num_level="2" f_per_stage="2"/>
<device_technology device_model_name="logic"/>
<port type="input" prefix="in" lib_name="A" size="1"/>
<port type="output" prefix="out" lib_name="X" size="1"/>
<delay_matrix type="rise" in_port="in" out_port="out">
10e-12
</delay_matrix>
<delay_matrix type="fall" in_port="in" out_port="out">
10e-12
</delay_matrix>
</circuit_model>
<circuit_model type="inv_buf" name="sky130_fd_sc_hd__buf_4" prefix="sky130_fd_sc_hd__buf_4" is_default="false">
<design_technology type="cmos" topology="buffer" size="1" num_level="2" f_per_stage="4"/>
<device_technology device_model_name="logic"/>
<port type="input" prefix="in" lib_name="A" size="1"/>
<port type="output" prefix="out" lib_name="X" size="1"/>
<delay_matrix type="rise" in_port="in" out_port="out">
10e-12
</delay_matrix>
<delay_matrix type="fall" in_port="in" out_port="out">
10e-12
</delay_matrix>
</circuit_model>
<circuit_model type="inv_buf" name="sky130_fd_sc_hd__inv_2" prefix="sky130_fd_sc_hd__inv_2" is_default="false">
<design_technology type="cmos" topology="buffer" size="1"/>
<device_technology device_model_name="logic"/>
<port type="input" prefix="in" lib_name="A" size="1"/>
<port type="output" prefix="out" lib_name="Y" size="1"/>
<delay_matrix type="rise" in_port="in" out_port="out">
10e-12
</delay_matrix>
<delay_matrix type="fall" in_port="in" out_port="out">
10e-12
</delay_matrix>
</circuit_model>
<circuit_model type="gate" name="sky130_fd_sc_hd__or2_1" prefix="sky130_fd_sc_hd__or2_1" is_default="true">
<design_technology type="cmos" topology="OR"/>
<device_technology device_model_name="logic"/>
<input_buffer exist="false"/>
<output_buffer exist="false"/>
<port type="input" prefix="a" lib_name="A" size="1"/>
<port type="input" prefix="b" lib_name="B" size="1"/>
<port type="output" prefix="out" lib_name="X" size="1"/>
<delay_matrix type="rise" in_port="a b" out_port="out">
10e-12 5e-12
</delay_matrix>
<delay_matrix type="fall" in_port="a b" out_port="out">
10e-12 5e-12
</delay_matrix>
</circuit_model>
<!-- Define a circuit model for the standard cell MUX2
OpenFPGA requires the following truth table for the MUX2
When the select signal sel is enabled, the first input, i.e., in0
will be propagated to the output, i.e., out
If your standard cell provider does not offer the exact truth table,
you can simply swap the inputs as shown in the example below
-->
<circuit_model type="gate" name="sky130_fd_sc_hd__mux2_1" prefix="sky130_fd_sc_hd__mux2_1">
<design_technology type="cmos" topology="MUX2"/>
<device_technology device_model_name="logic"/>
<input_buffer exist="false"/>
<output_buffer exist="false"/>
<port type="input" prefix="in0" lib_name="A1" size="1"/>
<port type="input" prefix="in1" lib_name="A0" size="1"/>
<port type="input" prefix="sel" lib_name="S" size="1"/>
<port type="output" prefix="out" lib_name="X" size="1"/>
</circuit_model>
<circuit_model type="chan_wire" name="chan_segment" prefix="track_seg" is_default="true">
<design_technology type="cmos"/>
<input_buffer exist="false"/>
<output_buffer exist="false"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" size="1"/>
<wire_param model_type="pi" R="101" C="22.5e-15" num_level="1"/>
<!-- model_type could be T, res_val and cap_val DON'T CARE -->
</circuit_model>
<circuit_model type="wire" name="direct_interc" prefix="direct_interc" is_default="true">
<design_technology type="cmos"/>
<input_buffer exist="false"/>
<output_buffer exist="false"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" size="1"/>
<wire_param model_type="pi" R="0" C="0" num_level="1"/>
<!-- model_type could be T, res_val cap_val should be defined -->
</circuit_model>
<circuit_model type="mux" name="mux_tree" prefix="mux_tree" is_default="true" dump_structural_verilog="true">
<design_technology type="cmos" structure="tree" add_const_input="true" const_input_val="1"/>
<input_buffer exist="false"/>
<output_buffer exist="false"/>
<pass_gate_logic circuit_model_name="sky130_fd_sc_hd__mux2_1"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" size="1"/>
<port type="sram" prefix="sram" size="1"/>
</circuit_model>
<circuit_model type="mux" name="mux_tree_tapbuf" prefix="mux_tree_tapbuf" dump_structural_verilog="true">
<design_technology type="cmos" structure="tree" add_const_input="true" const_input_val="1"/>
<input_buffer exist="false"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__buf_4"/>
<pass_gate_logic circuit_model_name="sky130_fd_sc_hd__mux2_1"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" size="1"/>
<port type="sram" prefix="sram" size="1"/>
</circuit_model>
<!--DFF subckt ports should be defined as <D> <Q> <CLK> <RESET> <SET> -->
<circuit_model type="ff" name="SDFFSRQ" prefix="SDFFSRQ" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/dff.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<port type="input" prefix="D" size="1"/>
<port type="input" prefix="DI" lib_name="SI" size="1"/>
<port type="input" prefix="Test_en" lib_name="SE" size="1" is_global="true" default_val="0"/>
<port type="input" prefix="reset" lib_name="RST" size="1" is_global="true" default_val="0" is_reset="true"/>
<port type="input" prefix="set" lib_name="SET" size="1" is_global="true" default_val="0" is_set="true"/>
<port type="output" prefix="Q" size="1"/>
<port type="clock" prefix="clk" lib_name="CK" size="1" is_global="true" default_val="0" />
</circuit_model>
<circuit_model type="lut" name="frac_lut4" prefix="frac_lut4" dump_structural_verilog="true">
<design_technology type="cmos" fracturable_lut="true"/>
<input_buffer exist="false"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__buf_2"/>
<lut_input_inverter exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<lut_input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__buf_2"/>
<lut_intermediate_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__buf_2" location_map="-1-"/>
<pass_gate_logic circuit_model_name="sky130_fd_sc_hd__mux2_1"/>
<port type="input" prefix="in" size="4" tri_state_map="---1" circuit_model_name="sky130_fd_sc_hd__or2_1"/>
<port type="output" prefix="lut3_out" size="2" lut_frac_level="3" lut_output_mask="0,1"/>
<port type="output" prefix="lut4_out" size="1" lut_output_mask="0"/>
<port type="sram" prefix="sram" size="16"/>
<port type="sram" prefix="mode" size="1" mode_select="true" circuit_model_name="DFF" default_val="1"/>
</circuit_model>
<!--Scan-chain DFF subckt ports should be defined as <D> <Q> <Qb> <CLK> <RESET> <SET> -->
<circuit_model type="ccff" name="DFF" prefix="DFF" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/dff.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<port type="input" prefix="D" size="1"/>
<port type="output" prefix="Q" size="1"/>
<port type="output" prefix="QN" size="1"/>
<port type="clock" prefix="prog_clk" lib_name="CK" size="1" is_global="true" default_val="0" is_prog="true"/>
</circuit_model>
<circuit_model type="iopad" name="EMBEDDED_IO" prefix="EMBEDDED_IO" is_default="true" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/gpio.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<port type="input" prefix="SOC_IN" lib_name="SOC_IN" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="output" prefix="SOC_OUT" lib_name="SOC_OUT" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="output" prefix="SOC_DIR" lib_name="SOC_DIR" size="1" is_global="true" is_io="true"/>
<port type="output" prefix="inpad" lib_name="FPGA_IN" size="1"/>
<port type="input" prefix="outpad" lib_name="FPGA_OUT" size="1"/>
<port type="sram" prefix="en" lib_name="FPGA_DIR" size="1" mode_select="true" circuit_model_name="DFF" default_val="1"/>
</circuit_model>
</circuit_library>
<configuration_protocol>
<organization type="scan_chain" circuit_model_name="DFF" num_regions="1"/>
</configuration_protocol>
<connection_block>
<switch name="ipin_cblock" circuit_model_name="mux_tree_tapbuf"/>
</connection_block>
<switch_block>
<switch name="L1_mux" circuit_model_name="mux_tree_tapbuf"/>
<switch name="L2_mux" circuit_model_name="mux_tree_tapbuf"/>
<switch name="L4_mux" circuit_model_name="mux_tree_tapbuf"/>
</switch_block>
<routing_segment>
<segment name="L1" circuit_model_name="chan_segment"/>
<segment name="L2" circuit_model_name="chan_segment"/>
<segment name="L4" circuit_model_name="chan_segment"/>
</routing_segment>
<direct_connection>
<direct name="shift_register" circuit_model_name="direct_interc" type="column" x_dir="positive" y_dir="positive"/>
<direct name="scan_chain" circuit_model_name="direct_interc" type="column" x_dir="positive" y_dir="positive"/>
</direct_connection>
<pb_type_annotations>
<!-- physical pb_type binding in complex block IO -->
<pb_type name="io" physical_mode_name="physical" idle_mode_name="inpad"/>
<pb_type name="io[physical].iopad" circuit_model_name="EMBEDDED_IO" mode_bits="1"/>
<pb_type name="io[inpad].inpad" physical_pb_type_name="io[physical].iopad" mode_bits="1"/>
<pb_type name="io[outpad].outpad" physical_pb_type_name="io[physical].iopad" mode_bits="0"/>
<!-- End physical pb_type binding in complex block IO -->
<!-- physical pb_type binding in complex block CLB -->
<!-- physical mode will be the default mode if not specified -->
<pb_type name="clb.fle" physical_mode_name="physical"/>
<pb_type name="clb.fle[physical].fabric.frac_logic.frac_lut4" circuit_model_name="frac_lut4" mode_bits="0"/>
<pb_type name="clb.fle[physical].fabric.ff" circuit_model_name="SDFFSRQ"/>
<!-- Binding operating pb_type to physical pb_type -->
<pb_type name="clb.fle[n2_lut3].lut3inter.ble3.lut3" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut4" mode_bits="1" physical_pb_type_index_factor="0.5">
<!-- Binding the lut3 to the first 3 inputs of fracturable lut4 -->
<port name="in" physical_mode_port="in[0:2]"/>
<port name="out" physical_mode_port="lut3_out[0:0]" physical_mode_pin_rotate_offset="1"/>
</pb_type>
<pb_type name="clb.fle[n2_lut3].lut3inter.ble3.ff" physical_pb_type_name="clb.fle[physical].fabric.ff"/>
<!-- Binding operating pb_types in mode 'ble4' -->
<pb_type name="clb.fle[n1_lut4].ble4.lut4" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut4" mode_bits="0">
<!-- Binding the lut4 to the first 4 inputs of fracturable lut4 -->
<port name="in" physical_mode_port="in[0:3]"/>
<port name="out" physical_mode_port="lut4_out"/>
</pb_type>
<pb_type name="clb.fle[n1_lut4].ble4.ff" physical_pb_type_name="clb.fle[physical].fabric.ff" physical_pb_type_index_factor="2" physical_pb_type_index_offset="0"/>
<!-- Binding operating pb_types in mode 'shift_register' -->
<pb_type name="clb.fle[shift_register].shift_reg.ff" physical_pb_type_name="clb.fle[physical].fabric.ff"/>
<!-- End physical pb_type binding in complex block IO -->
</pb_type_annotations>
</openfpga_architecture>

4
openfpga_flow/openfpga_arch/k4_frac_N8_register_scan_chain_embedded_io_skywater130nm_fdhd_cc_openfpga.xml
View File

@ -188,14 +188,14 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<port type="inout" prefix="PAD" lib_name="A" size="1" is_global="true" is_io="true" />
<port type="inout" prefix="PAD" lib_name="A" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>
</circuit_model>
<circuit_model type="iopad" name="GPOUT" prefix="GPOUT" is_default="false" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/gpio.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
<port type="inout" prefix="PAD" lib_name="Y" size="1" is_global="true" is_io="true" />
<port type="inout" prefix="PAD" lib_name="Y" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
</circuit_model>
</circuit_library>

2
openfpga_flow/openfpga_arch/k6_N10_40nm_openfpga.xml
View File

@ -160,7 +160,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_N10_intermediate_buffer_40nm_openfpga.xml
View File

@ -161,7 +161,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_40nm_openfpga.xml
View File

@ -179,7 +179,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_frac_mem32K_frac_dsp36_40nm_openfpga.xml
View File

@ -179,7 +179,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_40nm_openfpga.xml
View File

@ -179,7 +179,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_aib_40nm_openfpga.xml
View File

@ -179,7 +179,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_column_chain_40nm_openfpga.xml
View File

@ -179,7 +179,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_chain_40nm_openfpga.xml
View File

@ -179,7 +179,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_scan_chain_40nm_openfpga.xml
View File

@ -184,7 +184,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_scan_chain_depop50_40nm_openfpga.xml
View File

@ -184,7 +184,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_scan_chain_depop50_spypad_40nm_openfpga.xml
View File

@ -199,7 +199,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_behavioral_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_local_encoder_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_stdcell_mux_40nm_openfpga.xml
View File

@ -170,7 +170,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N10_tree_mux_40nm_openfpga.xml
View File

@ -169,7 +169,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_debuf_mux_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_inbuf_only_mux_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_local_encoder_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_outbuf_only_mux_40nm_openfpga.xml
View File

@ -178,7 +178,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_stdcell_mux_40nm_openfpga.xml
View File

@ -170,7 +170,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

2
openfpga_flow/openfpga_arch/k6_frac_N8_tree_mux_40nm_openfpga.xml
View File

@ -169,7 +169,7 @@
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true"/>
<port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
<port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
<port type="input" prefix="outpad" lib_name="A" size="1"/>
<port type="output" prefix="inpad" lib_name="Y" size="1"/>

19
openfpga_flow/openfpga_cell_library/verilog/gpio.v
View File

@ -38,3 +38,22 @@ module GPOUT (
);
assign Y = A;
endmodule
//-----------------------------------------------------
// Function : A minimum embedded I/O
// just an overlay to interface other components
//-----------------------------------------------------
module EMBEDDED_IO (
input SOC_IN, // Input to drive the inpad signal
output SOC_OUT, // Output the outpad signal
output SOC_DIR, // Output the directionality
output FPGA_IN, // Input data to FPGA
input FPGA_OUT, // Output data from FPGA
input FPGA_DIR // direction control
);
assign FPGA_IN = SOC_IN;
assign SOC_OUT = FPGA_OUT;
assign SOC_DIR = FPGA_DIR;
endmodule

35
openfpga_flow/tasks/basic_tests/tile_organization/bottom_right_custom_pins/config/task.conf Normal file
View File

@ -0,0 +1,35 @@
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# Configuration file for running experiments
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# timeout_each_job : FPGA Task script splits fpga flow into multiple jobs
# Each job execute fpga_flow script on combination of architecture & benchmark
# timeout_each_job is timeout for each job
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
[GENERAL]
run_engine=openfpga_shell
power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
power_analysis = true
spice_output=false
verilog_output=true
timeout_each_job = 20*60
fpga_flow=yosys_vpr
[OpenFPGA_SHELL]
openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_frame_openfpga.xml
openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
[ARCHITECTURES]
arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_N4_tileable_TileOrgzBr_40nm.xml
[BENCHMARKS]
bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/or2/or2.v
[SYNTHESIS_PARAM]
bench0_top = or2
bench0_chan_width = 300
[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
end_flow_with_test=
vpr_fpga_verilog_formal_verification_top_netlist=

35
openfpga_flow/tasks/basic_tests/tile_organization/top_left_custom_pins/config/task.conf Normal file
View File

@ -0,0 +1,35 @@
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# Configuration file for running experiments
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# timeout_each_job : FPGA Task script splits fpga flow into multiple jobs
# Each job execute fpga_flow script on combination of architecture & benchmark
# timeout_each_job is timeout for each job
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
[GENERAL]
run_engine=openfpga_shell
power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
power_analysis = true
spice_output=false
verilog_output=true
timeout_each_job = 20*60
fpga_flow=yosys_vpr
[OpenFPGA_SHELL]
openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_frame_openfpga.xml
openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
[ARCHITECTURES]
arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_N4_tileable_TileOrgzTl_40nm.xml
[BENCHMARKS]
bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/or2/or2.v
[SYNTHESIS_PARAM]
bench0_top = or2
bench0_chan_width = 300
[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
end_flow_with_test=
vpr_fpga_verilog_formal_verification_top_netlist=

35
openfpga_flow/tasks/basic_tests/tile_organization/top_right_custom_pins/config/task.conf Normal file
View File

@ -0,0 +1,35 @@
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# Configuration file for running experiments
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# timeout_each_job : FPGA Task script splits fpga flow into multiple jobs
# Each job execute fpga_flow script on combination of architecture & benchmark
# timeout_each_job is timeout for each job
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
[GENERAL]
run_engine=openfpga_shell
power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
power_analysis = true
spice_output=false
verilog_output=true
timeout_each_job = 20*60
fpga_flow=yosys_vpr
[OpenFPGA_SHELL]
openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_frame_openfpga.xml
openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
[ARCHITECTURES]
arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_N4_tileable_TileOrgzTr_40nm.xml
[BENCHMARKS]
bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/or2/or2.v
[SYNTHESIS_PARAM]
bench0_top = or2
bench0_chan_width = 300
[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
end_flow_with_test=
vpr_fpga_verilog_formal_verification_top_netlist=

37
openfpga_flow/tasks/fpga_verilog/io/soc_io/config/task.conf Normal file
View File

@ -0,0 +1,37 @@
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# Configuration file for running experiments
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# timeout_each_job : FPGA Task script splits fpga flow into multiple jobs
# Each job execute fpga_flow script on combination of architecture & benchmark
# timeout_each_job is timeout for each job
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
[GENERAL]
run_engine=openfpga_shell
power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
power_analysis = true
spice_output=false
verilog_output=true
timeout_each_job = 20*60
fpga_flow=vpr_blif
[OpenFPGA_SHELL]
openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/fix_device_example_script.openfpga
openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_frac_N8_register_scan_chain_caravel_io_skywater130nm_fdhd_cc_openfpga.xml
openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
openfpga_vpr_device_layout=2x2
[ARCHITECTURES]
arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_frac_N8_tileable_register_scan_chain_nonLR_caravel_io_skywater130nm.xml
[BENCHMARKS]
bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2/and2.blif
[SYNTHESIS_PARAM]
bench0_top = and2
bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2/and2.act
bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2/and2.v
[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
end_flow_with_test=
vpr_fpga_verilog_formal_verification_top_netlist=

4
openfpga_flow/vpr_arch/README.md
View File

@ -13,5 +13,9 @@ Please reveal the following architecture features in the names to help quickly s
- multi\_io\_capacity: If I/O capacity is different on each side of FPGAs.
- reduced\_io: If I/Os only appear a certain or multiple sides of FPGAs
- <feature\_size>: The technology node which the delay numbers are extracted from.
- TileOrgz<Type>: How tile is organized.
* Top-left (Tl): the pins of a tile are placed on the top side and left side only
* Top-right (Tr): the pins of a tile are placed on the top side and right side only
* Bottom-right (Br): the pins of a tile are placed on the bottom side and right side only
Other features are used in naming should be listed here.

298
openfpga_flow/vpr_arch/k4_N4_tileable_TileOrgzBr_40nm.xml Normal file
View File

@ -0,0 +1,298 @@
<!--
Architecture with no fracturable LUTs
- 40 nm technology
- General purpose logic block:
K = 4, N = 4
- Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
Details on Modelling:
Based on flagship k6_frac_N10_mem32K_40nm.xml architecture. This architecture has no fracturable LUTs nor any heterogeneous blocks.
Authors: Jason Luu, Jeff Goeders, Vaughn Betz
-->
<architecture>
<!--
ODIN II specific config begins
Describes the types of user-specified netlist blocks (in blif, this corresponds to
".model [type_of_block]") that this architecture supports.
Note: Basic LUTs, I/Os, and flip-flops are not included here as there are
already special structures in blif (.names, .input, .output, and .latch)
that describe them.
-->
<models>
<!-- A virtual model for I/O to be used in the physical mode of io block -->
<model name="io">
<input_ports>
<port name="outpad"/>
</input_ports>
<output_ports>
<port name="inpad"/>
</output_ports>
</model>
</models>
<tiles>
<tile name="io" capacity="8" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left">io.outpad io.inpad</loc>
<loc side="top">io.outpad io.inpad</loc>
<loc side="right">io.outpad io.inpad</loc>
<loc side="bottom">io.outpad io.inpad</loc>
</pinlocations>
</tile>
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left"></loc>
<loc side="top"></loc>
<loc side="right">clb.I[5:9] clb.O[2:3]</loc>
<loc side="bottom">clb.clk clb.I[0:4] clb.O[0:1]</loc>
</pinlocations>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout tileable="true">
<auto_layout aspect_ratio="1.0">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</auto_layout>
<fixed_layout name="2x2" width="4" height="4">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</fixed_layout>
</layout>
<device>
<!-- VB & JL: Using Ian Kuon's transistor sizing and drive strength data for routing, at 40 nm. Ian used BPTM
models. We are modifying the delay values however, to include metal C and R, which allows more architecture
experimentation. We are also modifying the relative resistance of PMOS to be 1.8x that of NMOS
(vs. Ian's 3x) as 1.8x lines up with Jeff G's data from a 45 nm process (and is more typical of
45 nm in general). I'm upping the Rmin_nmos from Ian's just over 6k to nearly 9k, and dropping
RminW_pmos from 18k to 16k to hit this 1.8x ratio, while keeping the delays of buffers approximately
lined up with Stratix IV.
We are using Jeff G.'s capacitance data for 45 nm (in tech/ptm_45nm).
Jeff's tables list C in for transistors with widths in multiples of the minimum feature size (45 nm).
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply drive strength sizes in this file
by 2.5x when looking up in Jeff's tables.
The delay values are lined up with Stratix IV, which has an architecture similar to this
proposed FPGA, and which is also 40 nm
C_ipin_cblock: input capacitance of a track buffer, which VPR assumes is a single-stage
4x minimum drive strength buffer. -->
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
<!-- The grid_logic_tile_area below will be used for all blocks that do not explicitly set their own (non-routing)
area; set to 0 since we explicitly set the area of all blocks currently in this architecture file.
-->
<area grid_logic_tile_area="0"/>
<chan_width_distr>
<x distr="uniform" peak="1.000000"/>
<y distr="uniform" peak="1.000000"/>
</chan_width_distr>
<switch_block type="wilton" fs="3"/>
<connection_block input_switch_name="ipin_cblock"/>
</device>
<switchlist>
<!-- VB: the mux_trans_size and buf_size data below is in minimum width transistor *areas*, assuming the purple
book area formula. This means the mux transistors are about 5x minimum drive strength.
We assume the first stage of the buffer is 3x min drive strength to be reasonable given the large
mux transistors, and this gives a reasonable stage ratio of a bit over 5x to the second stage. We assume
the n and p transistors in the first stage are equal-sized to lower the buffer trip point, since it's fed
by a pass transistor mux. We can then reverse engineer the buffer second stage to hit the specified
buf_size (really buffer area) - 16.2x minimum drive nmos and 1.8*16.2 = 29.2x minimum drive.
I then took the data from Jeff G.'s PTM modeling of 45 nm to get the Cin (gate of first stage) and Cout
(diff of second stage) listed below. Jeff's models are in tech/ptm_45nm, and are in min feature multiples.
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply the drive strength sizes above by
2.5x when looking up in Jeff's tables.
Finally, we choose a switch delay (58 ps) that leads to length 4 wires having a delay equal to that of SIV of 126 ps.
This also leads to the switch being 46% of the total wire delay, which is reasonable. -->
<switch type="mux" name="0" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<!--switch ipin_cblock resistance set to yeild for 4x minimum drive strength buffer-->
<switch type="mux" name="ipin_cblock" R="2231.5" Cout="0." Cin="1.47e-15" Tdel="7.247000e-11" mux_trans_size="1.222260" buf_size="auto"/>
</switchlist>
<segmentlist>
<!--- VB & JL: using ITRS metal stack data, 96 nm half pitch wires, which are intermediate metal width/space.
With the 96 nm half pitch, such wires would take 60 um of height, vs. a 90 nm high (approximated as square) Stratix IV tile so this seems
reasonable. Using a tile length of 90 nm, corresponding to the length of a Stratix IV tile if it were square. -->
<segment name="L4" freq="1.000000" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="0"/>
<sb type="pattern">1 1 1 1 1</sb>
<cb type="pattern">1 1 1 1</cb>
</segment>
</segmentlist>
<complexblocklist>
<!-- Define I/O pads begin -->
<!-- Capacity is a unique property of I/Os, it is the maximum number of I/Os that can be placed at the same (X,Y) location on the FPGA -->
<!-- Not sure of the area of an I/O (varies widely), and it's not relevant to the design of the FPGA core, so we're setting it to 0. -->
<pb_type name="io">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<!-- A mode denotes the physical implementation of an I/O
This mode will be not packable but is mainly used for fabric verilog generation
-->
<mode name="physical" packable="false">
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="iopad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
</direct>
<direct name="inpad" input="iopad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<!-- IOs can operate as either inputs or outputs.
Delays below come from Ian Kuon. They are small, so they should be interpreted as
the delays to and from registers in the I/O (and generally I/Os are registered
today and that is when you timing analyze them.
-->
<mode name="inpad">
<pb_type name="inpad" blif_model=".input" num_pb="1">
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="inpad" input="inpad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<mode name="outpad">
<pb_type name="outpad" blif_model=".output" num_pb="1">
<input name="outpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="outpad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="outpad.outpad"/>
</direct>
</interconnect>
</mode>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- IOs go on the periphery of the FPGA, for consistency,
make it physically equivalent on all sides so that only one definition of I/Os is needed.
If I do not make a physically equivalent definition, then I need to define 4 different I/Os, one for each side of the FPGA
-->
<!-- Place I/Os on the sides of the FPGA -->
<power method="ignore"/>
</pb_type>
<!-- Define I/O pads ends -->
<!-- Define general purpose logic block (CLB) begin -->
<!--- Area calculation: Total Stratix IV tile area is about 8100 um^2, and a minimum width transistor
area is 60 L^2 yields a tile area of 84375 MWTAs.
Routing at W=300 is 30481 MWTAs, leaving us with a total of 53000 MWTAs for logic block area
This means that only 37% of our area is in the general routing, and 63% is inside the logic
block. Note that the crossbar / local interconnect is considered part of the logic block
area in this analysis. That is a lower proportion of of routing area than most academics
assume, but note that the total routing area really includes the crossbar, which would push
routing area up significantly, we estimate into the ~70% range.
-->
<pb_type name="clb">
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="1"/>
<!-- Describe basic logic element.
Each basic logic element has a 4-LUT that can be optionally registered
-->
<pb_type name="fle" num_pb="4">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- 4-LUT mode definition begin -->
<mode name="n1_lut4">
<!-- Define 4-LUT mode -->
<pb_type name="ble4" num_pb="1">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut4" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="4" port_class="lut_in"/>
<output name="out" num_pins="1" port_class="lut_out"/>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
261e-12
261e-12
261e-12
261e-12
</delay_matrix>
</pb_type>
<!-- Define flip-flop -->
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="ble4.in" output="lut4[0:0].in"/>
<direct name="direct2" input="lut4.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble4" in_port="lut4.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble4.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut4.out" output="ble4.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut4.out" out_port="ble4.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble4.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble4.in"/>
<direct name="direct2" input="ble4.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble4.clk"/>
</interconnect>
</mode>
<!-- 6-LUT mode definition end -->
</pb_type>
<interconnect>
<!-- We use a full crossbar to get logical equivalence at inputs of CLB
The delays below come from Stratix IV. the delay through a connection block
input mux + the crossbar in Stratix IV is 167 ps. We already have a 72 ps
delay on the connection block input mux (modeled by Ian Kuon), so the remaining
delay within the crossbar is 95 ps.
The delays of cluster feedbacks in Stratix IV is 100 ps, when driven by a LUT.
Since all our outputs LUT outputs go to a BLE output, and have a delay of
25 ps to do so, we subtract 25 ps from the 100 ps delay of a feedback
to get the part that should be marked on the crossbar. -->
<complete name="crossbar" input="clb.I fle[3:0].out" output="fle[3:0].in">
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[3:0].in"/>
<delay_constant max="75e-12" in_port="fle[3:0].out" out_port="fle[3:0].in"/>
</complete>
<complete name="clks" input="clb.clk" output="fle[3:0].clk">
</complete>
<!-- This way of specifying direct connection to clb outputs is important because this architecture uses automatic spreading of opins.
By grouping to output pins in this fashion, if a logic block is completely filled by 6-LUTs,
then the outputs those 6-LUTs take get evenly distributed across all four sides of the CLB instead of clumped on two sides (which is what happens with a more
naive specification).
-->
<direct name="clbouts1" input="fle[3:0].out" output="clb.O"/>
</interconnect>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- Place this general purpose logic block in any unspecified column -->
</pb_type>
<!-- Define general purpose logic block (CLB) ends -->
</complexblocklist>
</architecture>

298
openfpga_flow/vpr_arch/k4_N4_tileable_TileOrgzTl_40nm.xml Normal file
View File

@ -0,0 +1,298 @@
<!--
Architecture with no fracturable LUTs
- 40 nm technology
- General purpose logic block:
K = 4, N = 4
- Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
Details on Modelling:
Based on flagship k6_frac_N10_mem32K_40nm.xml architecture. This architecture has no fracturable LUTs nor any heterogeneous blocks.
Authors: Jason Luu, Jeff Goeders, Vaughn Betz
-->
<architecture>
<!--
ODIN II specific config begins
Describes the types of user-specified netlist blocks (in blif, this corresponds to
".model [type_of_block]") that this architecture supports.
Note: Basic LUTs, I/Os, and flip-flops are not included here as there are
already special structures in blif (.names, .input, .output, and .latch)
that describe them.
-->
<models>
<!-- A virtual model for I/O to be used in the physical mode of io block -->
<model name="io">
<input_ports>
<port name="outpad"/>
</input_ports>
<output_ports>
<port name="inpad"/>
</output_ports>
</model>
</models>
<tiles>
<tile name="io" capacity="8" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left">io.outpad io.inpad</loc>
<loc side="top">io.outpad io.inpad</loc>
<loc side="right">io.outpad io.inpad</loc>
<loc side="bottom">io.outpad io.inpad</loc>
</pinlocations>
</tile>
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="top">clb.clk clb.I[0:4] clb.O[0:1]</loc>
<loc side="left">clb.I[5:9] clb.O[2:3]</loc>
<loc side="right"></loc>
<loc side="bottom"></loc>
</pinlocations>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout tileable="true">
<auto_layout aspect_ratio="1.0">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</auto_layout>
<fixed_layout name="2x2" width="4" height="4">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</fixed_layout>
</layout>
<device>
<!-- VB & JL: Using Ian Kuon's transistor sizing and drive strength data for routing, at 40 nm. Ian used BPTM
models. We are modifying the delay values however, to include metal C and R, which allows more architecture
experimentation. We are also modifying the relative resistance of PMOS to be 1.8x that of NMOS
(vs. Ian's 3x) as 1.8x lines up with Jeff G's data from a 45 nm process (and is more typical of
45 nm in general). I'm upping the Rmin_nmos from Ian's just over 6k to nearly 9k, and dropping
RminW_pmos from 18k to 16k to hit this 1.8x ratio, while keeping the delays of buffers approximately
lined up with Stratix IV.
We are using Jeff G.'s capacitance data for 45 nm (in tech/ptm_45nm).
Jeff's tables list C in for transistors with widths in multiples of the minimum feature size (45 nm).
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply drive strength sizes in this file
by 2.5x when looking up in Jeff's tables.
The delay values are lined up with Stratix IV, which has an architecture similar to this
proposed FPGA, and which is also 40 nm
C_ipin_cblock: input capacitance of a track buffer, which VPR assumes is a single-stage
4x minimum drive strength buffer. -->
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
<!-- The grid_logic_tile_area below will be used for all blocks that do not explicitly set their own (non-routing)
area; set to 0 since we explicitly set the area of all blocks currently in this architecture file.
-->
<area grid_logic_tile_area="0"/>
<chan_width_distr>
<x distr="uniform" peak="1.000000"/>
<y distr="uniform" peak="1.000000"/>
</chan_width_distr>
<switch_block type="wilton" fs="3"/>
<connection_block input_switch_name="ipin_cblock"/>
</device>
<switchlist>
<!-- VB: the mux_trans_size and buf_size data below is in minimum width transistor *areas*, assuming the purple
book area formula. This means the mux transistors are about 5x minimum drive strength.
We assume the first stage of the buffer is 3x min drive strength to be reasonable given the large
mux transistors, and this gives a reasonable stage ratio of a bit over 5x to the second stage. We assume
the n and p transistors in the first stage are equal-sized to lower the buffer trip point, since it's fed
by a pass transistor mux. We can then reverse engineer the buffer second stage to hit the specified
buf_size (really buffer area) - 16.2x minimum drive nmos and 1.8*16.2 = 29.2x minimum drive.
I then took the data from Jeff G.'s PTM modeling of 45 nm to get the Cin (gate of first stage) and Cout
(diff of second stage) listed below. Jeff's models are in tech/ptm_45nm, and are in min feature multiples.
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply the drive strength sizes above by
2.5x when looking up in Jeff's tables.
Finally, we choose a switch delay (58 ps) that leads to length 4 wires having a delay equal to that of SIV of 126 ps.
This also leads to the switch being 46% of the total wire delay, which is reasonable. -->
<switch type="mux" name="0" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<!--switch ipin_cblock resistance set to yeild for 4x minimum drive strength buffer-->
<switch type="mux" name="ipin_cblock" R="2231.5" Cout="0." Cin="1.47e-15" Tdel="7.247000e-11" mux_trans_size="1.222260" buf_size="auto"/>
</switchlist>
<segmentlist>
<!--- VB & JL: using ITRS metal stack data, 96 nm half pitch wires, which are intermediate metal width/space.
With the 96 nm half pitch, such wires would take 60 um of height, vs. a 90 nm high (approximated as square) Stratix IV tile so this seems
reasonable. Using a tile length of 90 nm, corresponding to the length of a Stratix IV tile if it were square. -->
<segment name="L4" freq="1.000000" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="0"/>
<sb type="pattern">1 1 1 1 1</sb>
<cb type="pattern">1 1 1 1</cb>
</segment>
</segmentlist>
<complexblocklist>
<!-- Define I/O pads begin -->
<!-- Capacity is a unique property of I/Os, it is the maximum number of I/Os that can be placed at the same (X,Y) location on the FPGA -->
<!-- Not sure of the area of an I/O (varies widely), and it's not relevant to the design of the FPGA core, so we're setting it to 0. -->
<pb_type name="io">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<!-- A mode denotes the physical implementation of an I/O
This mode will be not packable but is mainly used for fabric verilog generation
-->
<mode name="physical" packable="false">
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="iopad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
</direct>
<direct name="inpad" input="iopad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<!-- IOs can operate as either inputs or outputs.
Delays below come from Ian Kuon. They are small, so they should be interpreted as
the delays to and from registers in the I/O (and generally I/Os are registered
today and that is when you timing analyze them.
-->
<mode name="inpad">
<pb_type name="inpad" blif_model=".input" num_pb="1">
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="inpad" input="inpad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<mode name="outpad">
<pb_type name="outpad" blif_model=".output" num_pb="1">
<input name="outpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="outpad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="outpad.outpad"/>
</direct>
</interconnect>
</mode>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- IOs go on the periphery of the FPGA, for consistency,
make it physically equivalent on all sides so that only one definition of I/Os is needed.
If I do not make a physically equivalent definition, then I need to define 4 different I/Os, one for each side of the FPGA
-->
<!-- Place I/Os on the sides of the FPGA -->
<power method="ignore"/>
</pb_type>
<!-- Define I/O pads ends -->
<!-- Define general purpose logic block (CLB) begin -->
<!--- Area calculation: Total Stratix IV tile area is about 8100 um^2, and a minimum width transistor
area is 60 L^2 yields a tile area of 84375 MWTAs.
Routing at W=300 is 30481 MWTAs, leaving us with a total of 53000 MWTAs for logic block area
This means that only 37% of our area is in the general routing, and 63% is inside the logic
block. Note that the crossbar / local interconnect is considered part of the logic block
area in this analysis. That is a lower proportion of of routing area than most academics
assume, but note that the total routing area really includes the crossbar, which would push
routing area up significantly, we estimate into the ~70% range.
-->
<pb_type name="clb">
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="1"/>
<!-- Describe basic logic element.
Each basic logic element has a 4-LUT that can be optionally registered
-->
<pb_type name="fle" num_pb="4">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- 4-LUT mode definition begin -->
<mode name="n1_lut4">
<!-- Define 4-LUT mode -->
<pb_type name="ble4" num_pb="1">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut4" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="4" port_class="lut_in"/>
<output name="out" num_pins="1" port_class="lut_out"/>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
261e-12
261e-12
261e-12
261e-12
</delay_matrix>
</pb_type>
<!-- Define flip-flop -->
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="ble4.in" output="lut4[0:0].in"/>
<direct name="direct2" input="lut4.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble4" in_port="lut4.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble4.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut4.out" output="ble4.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut4.out" out_port="ble4.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble4.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble4.in"/>
<direct name="direct2" input="ble4.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble4.clk"/>
</interconnect>
</mode>
<!-- 6-LUT mode definition end -->
</pb_type>
<interconnect>
<!-- We use a full crossbar to get logical equivalence at inputs of CLB
The delays below come from Stratix IV. the delay through a connection block
input mux + the crossbar in Stratix IV is 167 ps. We already have a 72 ps
delay on the connection block input mux (modeled by Ian Kuon), so the remaining
delay within the crossbar is 95 ps.
The delays of cluster feedbacks in Stratix IV is 100 ps, when driven by a LUT.
Since all our outputs LUT outputs go to a BLE output, and have a delay of
25 ps to do so, we subtract 25 ps from the 100 ps delay of a feedback
to get the part that should be marked on the crossbar. -->
<complete name="crossbar" input="clb.I fle[3:0].out" output="fle[3:0].in">
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[3:0].in"/>
<delay_constant max="75e-12" in_port="fle[3:0].out" out_port="fle[3:0].in"/>
</complete>
<complete name="clks" input="clb.clk" output="fle[3:0].clk">
</complete>
<!-- This way of specifying direct connection to clb outputs is important because this architecture uses automatic spreading of opins.
By grouping to output pins in this fashion, if a logic block is completely filled by 6-LUTs,
then the outputs those 6-LUTs take get evenly distributed across all four sides of the CLB instead of clumped on two sides (which is what happens with a more
naive specification).
-->
<direct name="clbouts1" input="fle[3:0].out" output="clb.O"/>
</interconnect>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- Place this general purpose logic block in any unspecified column -->
</pb_type>
<!-- Define general purpose logic block (CLB) ends -->
</complexblocklist>
</architecture>

298
openfpga_flow/vpr_arch/k4_N4_tileable_TileOrgzTr_40nm.xml Normal file
View File

@ -0,0 +1,298 @@
<!--
Architecture with no fracturable LUTs
- 40 nm technology
- General purpose logic block:
K = 4, N = 4
- Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
Details on Modelling:
Based on flagship k6_frac_N10_mem32K_40nm.xml architecture. This architecture has no fracturable LUTs nor any heterogeneous blocks.
Authors: Jason Luu, Jeff Goeders, Vaughn Betz
-->
<architecture>
<!--
ODIN II specific config begins
Describes the types of user-specified netlist blocks (in blif, this corresponds to
".model [type_of_block]") that this architecture supports.
Note: Basic LUTs, I/Os, and flip-flops are not included here as there are
already special structures in blif (.names, .input, .output, and .latch)
that describe them.
-->
<models>
<!-- A virtual model for I/O to be used in the physical mode of io block -->
<model name="io">
<input_ports>
<port name="outpad"/>
</input_ports>
<output_ports>
<port name="inpad"/>
</output_ports>
</model>
</models>
<tiles>
<tile name="io" capacity="8" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left">io.outpad io.inpad</loc>
<loc side="top">io.outpad io.inpad</loc>
<loc side="right">io.outpad io.inpad</loc>
<loc side="bottom">io.outpad io.inpad</loc>
</pinlocations>
</tile>
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left"></loc>
<loc side="top">clb.clk clb.I[0:4] clb.O[0:1]</loc>
<loc side="right">clb.I[5:9] clb.O[2:3]</loc>
<loc side="bottom"></loc>
</pinlocations>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout tileable="true">
<auto_layout aspect_ratio="1.0">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</auto_layout>
<fixed_layout name="2x2" width="4" height="4">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</fixed_layout>
</layout>
<device>
<!-- VB & JL: Using Ian Kuon's transistor sizing and drive strength data for routing, at 40 nm. Ian used BPTM
models. We are modifying the delay values however, to include metal C and R, which allows more architecture
experimentation. We are also modifying the relative resistance of PMOS to be 1.8x that of NMOS
(vs. Ian's 3x) as 1.8x lines up with Jeff G's data from a 45 nm process (and is more typical of
45 nm in general). I'm upping the Rmin_nmos from Ian's just over 6k to nearly 9k, and dropping
RminW_pmos from 18k to 16k to hit this 1.8x ratio, while keeping the delays of buffers approximately
lined up with Stratix IV.
We are using Jeff G.'s capacitance data for 45 nm (in tech/ptm_45nm).
Jeff's tables list C in for transistors with widths in multiples of the minimum feature size (45 nm).
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply drive strength sizes in this file
by 2.5x when looking up in Jeff's tables.
The delay values are lined up with Stratix IV, which has an architecture similar to this
proposed FPGA, and which is also 40 nm
C_ipin_cblock: input capacitance of a track buffer, which VPR assumes is a single-stage
4x minimum drive strength buffer. -->
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
<!-- The grid_logic_tile_area below will be used for all blocks that do not explicitly set their own (non-routing)
area; set to 0 since we explicitly set the area of all blocks currently in this architecture file.
-->
<area grid_logic_tile_area="0"/>
<chan_width_distr>
<x distr="uniform" peak="1.000000"/>
<y distr="uniform" peak="1.000000"/>
</chan_width_distr>
<switch_block type="wilton" fs="3"/>
<connection_block input_switch_name="ipin_cblock"/>
</device>
<switchlist>
<!-- VB: the mux_trans_size and buf_size data below is in minimum width transistor *areas*, assuming the purple
book area formula. This means the mux transistors are about 5x minimum drive strength.
We assume the first stage of the buffer is 3x min drive strength to be reasonable given the large
mux transistors, and this gives a reasonable stage ratio of a bit over 5x to the second stage. We assume
the n and p transistors in the first stage are equal-sized to lower the buffer trip point, since it's fed
by a pass transistor mux. We can then reverse engineer the buffer second stage to hit the specified
buf_size (really buffer area) - 16.2x minimum drive nmos and 1.8*16.2 = 29.2x minimum drive.
I then took the data from Jeff G.'s PTM modeling of 45 nm to get the Cin (gate of first stage) and Cout
(diff of second stage) listed below. Jeff's models are in tech/ptm_45nm, and are in min feature multiples.
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply the drive strength sizes above by
2.5x when looking up in Jeff's tables.
Finally, we choose a switch delay (58 ps) that leads to length 4 wires having a delay equal to that of SIV of 126 ps.
This also leads to the switch being 46% of the total wire delay, which is reasonable. -->
<switch type="mux" name="0" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<!--switch ipin_cblock resistance set to yeild for 4x minimum drive strength buffer-->
<switch type="mux" name="ipin_cblock" R="2231.5" Cout="0." Cin="1.47e-15" Tdel="7.247000e-11" mux_trans_size="1.222260" buf_size="auto"/>
</switchlist>
<segmentlist>
<!--- VB & JL: using ITRS metal stack data, 96 nm half pitch wires, which are intermediate metal width/space.
With the 96 nm half pitch, such wires would take 60 um of height, vs. a 90 nm high (approximated as square) Stratix IV tile so this seems
reasonable. Using a tile length of 90 nm, corresponding to the length of a Stratix IV tile if it were square. -->
<segment name="L4" freq="1.000000" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="0"/>
<sb type="pattern">1 1 1 1 1</sb>
<cb type="pattern">1 1 1 1</cb>
</segment>
</segmentlist>
<complexblocklist>
<!-- Define I/O pads begin -->
<!-- Capacity is a unique property of I/Os, it is the maximum number of I/Os that can be placed at the same (X,Y) location on the FPGA -->
<!-- Not sure of the area of an I/O (varies widely), and it's not relevant to the design of the FPGA core, so we're setting it to 0. -->
<pb_type name="io">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<!-- A mode denotes the physical implementation of an I/O
This mode will be not packable but is mainly used for fabric verilog generation
-->
<mode name="physical" packable="false">
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="iopad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
</direct>
<direct name="inpad" input="iopad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<!-- IOs can operate as either inputs or outputs.
Delays below come from Ian Kuon. They are small, so they should be interpreted as
the delays to and from registers in the I/O (and generally I/Os are registered
today and that is when you timing analyze them.
-->
<mode name="inpad">
<pb_type name="inpad" blif_model=".input" num_pb="1">
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="inpad" input="inpad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<mode name="outpad">
<pb_type name="outpad" blif_model=".output" num_pb="1">
<input name="outpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="outpad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="outpad.outpad"/>
</direct>
</interconnect>
</mode>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- IOs go on the periphery of the FPGA, for consistency,
make it physically equivalent on all sides so that only one definition of I/Os is needed.
If I do not make a physically equivalent definition, then I need to define 4 different I/Os, one for each side of the FPGA
-->
<!-- Place I/Os on the sides of the FPGA -->
<power method="ignore"/>
</pb_type>
<!-- Define I/O pads ends -->
<!-- Define general purpose logic block (CLB) begin -->
<!--- Area calculation: Total Stratix IV tile area is about 8100 um^2, and a minimum width transistor
area is 60 L^2 yields a tile area of 84375 MWTAs.
Routing at W=300 is 30481 MWTAs, leaving us with a total of 53000 MWTAs for logic block area
This means that only 37% of our area is in the general routing, and 63% is inside the logic
block. Note that the crossbar / local interconnect is considered part of the logic block
area in this analysis. That is a lower proportion of of routing area than most academics
assume, but note that the total routing area really includes the crossbar, which would push
routing area up significantly, we estimate into the ~70% range.
-->
<pb_type name="clb">
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="1"/>
<!-- Describe basic logic element.
Each basic logic element has a 4-LUT that can be optionally registered
-->
<pb_type name="fle" num_pb="4">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- 4-LUT mode definition begin -->
<mode name="n1_lut4">
<!-- Define 4-LUT mode -->
<pb_type name="ble4" num_pb="1">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut4" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="4" port_class="lut_in"/>
<output name="out" num_pins="1" port_class="lut_out"/>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
261e-12
261e-12
261e-12
261e-12
</delay_matrix>
</pb_type>
<!-- Define flip-flop -->
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="ble4.in" output="lut4[0:0].in"/>
<direct name="direct2" input="lut4.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble4" in_port="lut4.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble4.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut4.out" output="ble4.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut4.out" out_port="ble4.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble4.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble4.in"/>
<direct name="direct2" input="ble4.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble4.clk"/>
</interconnect>
</mode>
<!-- 6-LUT mode definition end -->
</pb_type>
<interconnect>
<!-- We use a full crossbar to get logical equivalence at inputs of CLB
The delays below come from Stratix IV. the delay through a connection block
input mux + the crossbar in Stratix IV is 167 ps. We already have a 72 ps
delay on the connection block input mux (modeled by Ian Kuon), so the remaining
delay within the crossbar is 95 ps.
The delays of cluster feedbacks in Stratix IV is 100 ps, when driven by a LUT.
Since all our outputs LUT outputs go to a BLE output, and have a delay of
25 ps to do so, we subtract 25 ps from the 100 ps delay of a feedback
to get the part that should be marked on the crossbar. -->
<complete name="crossbar" input="clb.I fle[3:0].out" output="fle[3:0].in">
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[3:0].in"/>
<delay_constant max="75e-12" in_port="fle[3:0].out" out_port="fle[3:0].in"/>
</complete>
<complete name="clks" input="clb.clk" output="fle[3:0].clk">
</complete>
<!-- This way of specifying direct connection to clb outputs is important because this architecture uses automatic spreading of opins.
By grouping to output pins in this fashion, if a logic block is completely filled by 6-LUTs,
then the outputs those 6-LUTs take get evenly distributed across all four sides of the CLB instead of clumped on two sides (which is what happens with a more
naive specification).
-->
<direct name="clbouts1" input="fle[3:0].out" output="clb.O"/>
</interconnect>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- Place this general purpose logic block in any unspecified column -->
</pb_type>
<!-- Define general purpose logic block (CLB) ends -->
</complexblocklist>
</architecture>

665
openfpga_flow/vpr_arch/k4_frac_N8_tileable_register_scan_chain_nonLR_caravel_io_skywater130nm.xml Normal file
View File

@ -0,0 +1,665 @@
<!--
Low-cost homogeneous FPGA Architecture.
- Skywater 130 nm technology
- General purpose logic block:
K = 4, N = 8, fracturable 4 LUTs (can operate as one 4-LUT or two 3-LUTs with all 3 inputs shared)
with optionally registered outputs
- Routing architecture:
- 10% L = 1, fc_in = 0.15, Fc_out = 0.10
- 10% L = 2, fc_in = 0.15, Fc_out = 0.10
- 80% L = 4, fc_in = 0.15, Fc_out = 0.10
- 100 routing tracks per channel
Authors: Xifan Tang
-->
<architecture>
<!--
ODIN II specific config begins
Describes the types of user-specified netlist blocks (in blif, this corresponds to
".model [type_of_block]") that this architecture supports.
Note: Basic LUTs, I/Os, and flip-flops are not included here as there are
already special structures in blif (.names, .input, .output, and .latch)
that describe them.
-->
<models>
<!-- A virtual model for I/O to be used in the physical mode of io block -->
<model name="io">
<input_ports>
<port name="outpad"/>
</input_ports>
<output_ports>
<port name="inpad"/>
</output_ports>
</model>
<model name="frac_lut4">
<input_ports>
<port name="in"/>
</input_ports>
<output_ports>
<port name="lut3_out"/>
<port name="lut4_out"/>
</output_ports>
</model>
<!-- A virtual model for scan-chain flip-flop to be used in the physical mode of FF -->
<model name="scff">
<input_ports>
<port name="D" clock="clk"/>
<port name="DI" clock="clk"/>
<port name="clk" is_clock="1"/>
</input_ports>
<output_ports>
<port name="Q" clock="clk"/>
</output_ports>
</model>
</models>
<tiles>
<!-- Do NOT add clock pins to I/O here!!! VPR does not build clock network in the way that OpenFPGA can support
If you need to register the I/O, define clocks in the circuit models
These clocks can be handled in back-end
-->
<!-- Top-side has 1 I/O per tile -->
<tile name="io_top" capacity="1" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="bottom">io_top.outpad io_top.inpad</loc>
</pinlocations>
</tile>
<!-- Right-side has 1 I/O per tile -->
<tile name="io_right" capacity="1" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left">io_right.outpad io_right.inpad</loc>
</pinlocations>
</tile>
<!-- Bottom-side has 6 I/O per tile -->
<tile name="io_bottom" capacity="6" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="top">io_bottom.outpad io_bottom.inpad</loc>
</pinlocations>
</tile>
<!-- Left-side has 1 I/O per tile -->
<tile name="io_left" capacity="1" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="right">io_left.outpad io_left.inpad</loc>
</pinlocations>
</tile>
<!-- CLB has most pins on the top and right sides -->
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I0" num_pins="3" equivalent="full"/>
<input name="I0i" num_pins="1" equivalent="none"/>
<input name="I1" num_pins="3" equivalent="full"/>
<input name="I1i" num_pins="1" equivalent="none"/>
<input name="I2" num_pins="3" equivalent="full"/>
<input name="I2i" num_pins="1" equivalent="none"/>
<input name="I3" num_pins="3" equivalent="full"/>
<input name="I3i" num_pins="1" equivalent="none"/>
<input name="I4" num_pins="3" equivalent="full"/>
<input name="I4i" num_pins="1" equivalent="none"/>
<input name="I5" num_pins="3" equivalent="full"/>
<input name="I5i" num_pins="1" equivalent="none"/>
<input name="I6" num_pins="3" equivalent="full"/>
<input name="I6i" num_pins="1" equivalent="none"/>
<input name="I7" num_pins="3" equivalent="full"/>
<input name="I7i" num_pins="1" equivalent="none"/>
<input name="regin" num_pins="1"/>
<input name="scin" num_pins="1"/>
<output name="O" num_pins="16" equivalent="none"/>
<output name="regout" num_pins="1"/>
<output name="scout" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10">
<fc_override port_name="regin" fc_type="frac" fc_val="0"/>
<fc_override port_name="regout" fc_type="frac" fc_val="0"/>
<fc_override port_name="scin" fc_type="frac" fc_val="0"/>
<fc_override port_name="scout" fc_type="frac" fc_val="0"/>
</fc>
<!--pinlocations pattern="spread"/-->
<pinlocations pattern="custom">
<loc side="left">clb.clk</loc>
<loc side="top">clb.regin clb.scin clb.O[7:0] clb.I0 clb.I0i clb.I1 clb.I1i clb.I2 clb.I2i clb.I3 clb.I3i </loc>
<loc side="right">clb.O[15:8] clb.I4 clb.I4i clb.I5 clb.I5i clb.I6 clb.I6i clb.I7 clb.I7i</loc>
<loc side="bottom">clb.regout clb.scout </loc>
</pinlocations>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout tileable="true">
<auto_layout aspect_ratio="1.0">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<row type="io_top" starty="H-1" priority="100"/>
<row type="io_bottom" starty="0" priority="100"/>
<col type="io_left" startx="0" priority="100"/>
<col type="io_right" startx="W-1" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</auto_layout>
<fixed_layout name="2x2" width="4" height="4">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<row type="io_top" starty="H-1" priority="100"/>
<row type="io_bottom" starty="0" priority="100"/>
<col type="io_left" startx="0" priority="100"/>
<col type="io_right" startx="W-1" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</fixed_layout>
<fixed_layout name="12x12" width="14" height="14">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<row type="io_top" starty="H-1" priority="100"/>
<row type="io_bottom" starty="0" priority="100"/>
<col type="io_left" startx="0" priority="100"/>
<col type="io_right" startx="W-1" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</fixed_layout>
</layout>
<device>
<!-- VB & JL: Using Ian Kuon's transistor sizing and drive strength data for routing, at 40 nm. Ian used BPTM
models. We are modifying the delay values however, to include metal C and R, which allows more architecture
experimentation. We are also modifying the relative resistance of PMOS to be 1.8x that of NMOS
(vs. Ian's 3x) as 1.8x lines up with Jeff G's data from a 45 nm process (and is more typical of
45 nm in general). I'm upping the Rmin_nmos from Ian's just over 6k to nearly 9k, and dropping
RminW_pmos from 18k to 16k to hit this 1.8x ratio, while keeping the delays of buffers approximately
lined up with Stratix IV.
We are using Jeff G.'s capacitance data for 45 nm (in tech/ptm_45nm).
Jeff's tables list C in for transistors with widths in multiples of the minimum feature size (45 nm).
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply drive strength sizes in this file
by 2.5x when looking up in Jeff's tables.
The delay values are lined up with Stratix IV, which has an architecture similar to this
proposed FPGA, and which is also 40 nm
C_ipin_cblock: input capacitance of a track buffer, which VPR assumes is a single-stage
4x minimum drive strength buffer. -->
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
<!-- The grid_logic_tile_area below will be used for all blocks that do not explicitly set their own (non-routing)
area; set to 0 since we explicitly set the area of all blocks currently in this architecture file.
-->
<area grid_logic_tile_area="0"/>
<chan_width_distr>
<x distr="uniform" peak="1.000000"/>
<y distr="uniform" peak="1.000000"/>
</chan_width_distr>
<switch_block type="wilton" fs="3" sub_type="subset" sub_fs="3"/>
<connection_block input_switch_name="ipin_cblock"/>
</device>
<switchlist>
<!-- VB: the mux_trans_size and buf_size data below is in minimum width transistor *areas*, assuming the purple
book area formula. This means the mux transistors are about 5x minimum drive strength.
We assume the first stage of the buffer is 3x min drive strength to be reasonable given the large
mux transistors, and this gives a reasonable stage ratio of a bit over 5x to the second stage. We assume
the n and p transistors in the first stage are equal-sized to lower the buffer trip point, since it's fed
by a pass transistor mux. We can then reverse engineer the buffer second stage to hit the specified
buf_size (really buffer area) - 16.2x minimum drive nmos and 1.8*16.2 = 29.2x minimum drive.
I then took the data from Jeff G.'s PTM modeling of 45 nm to get the Cin (gate of first stage) and Cout
(diff of second stage) listed below. Jeff's models are in tech/ptm_45nm, and are in min feature multiples.
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply the drive strength sizes above by
2.5x when looking up in Jeff's tables.
Finally, we choose a switch delay (58 ps) that leads to length 4 wires having a delay equal to that of SIV of 126 ps.
This also leads to the switch being 46% of the total wire delay, which is reasonable. -->
<switch type="mux" name="L1_mux" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<switch type="mux" name="L2_mux" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<switch type="mux" name="L4_mux" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<!--switch ipin_cblock resistance set to yeild for 4x minimum drive strength buffer-->
<switch type="mux" name="ipin_cblock" R="2231.5" Cout="0." Cin="1.47e-15" Tdel="7.247000e-11" mux_trans_size="1.222260" buf_size="auto"/>
</switchlist>
<segmentlist>
<!--- VB & JL: using ITRS metal stack data, 96 nm half pitch wires, which are intermediate metal width/space.
With the 96 nm half pitch, such wires would take 60 um of height, vs. a 90 nm high (approximated as square) Stratix IV tile so this seems
reasonable. Using a tile length of 90 nm, corresponding to the length of a Stratix IV tile if it were square. -->
<!-- GIVE a specific name for the segment! OpenFPGA appreciate that! -->
<segment name="L1" freq="0.10" length="1" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="L1_mux"/>
<sb type="pattern">1 1</sb>
<cb type="pattern">1</cb>
</segment>
<segment name="L2" freq="0.10" length="2" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="L2_mux"/>
<sb type="pattern">1 1 1</sb>
<cb type="pattern">1 1</cb>
</segment>
<segment name="L4" freq="0.80" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="L4_mux"/>
<sb type="pattern">1 1 1 1 1</sb>
<cb type="pattern">1 1 1 1</cb>
</segment>
</segmentlist>
<directlist>
<direct name="shift_register" from_pin="clb.regout" to_pin="clb.regin" x_offset="0" y_offset="-1" z_offset="0"/>
<direct name="scan_chain" from_pin="clb.scout" to_pin="clb.scin" x_offset="0" y_offset="-1" z_offset="0"/>
</directlist>
<complexblocklist>
<!-- Define input pads begin -->
<pb_type name="io">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<!-- Do NOT add clock pins to I/O here!!! VPR does not build clock network in the way that OpenFPGA can support
If you need to register the I/O, define clocks in the circuit models
These clocks can be handled in back-end
-->
<!-- A mode denotes the physical implementation of an I/O
This mode will be not packable but is mainly used for fabric verilog generation
-->
<mode name="physical" disabled_in_pack="true">
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="iopad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
</direct>
<direct name="inpad" input="iopad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<!-- IOs can operate as either inputs or outputs.
Delays below come from Ian Kuon. They are small, so they should be interpreted as
the delays to and from registers in the I/O (and generally I/Os are registered
today and that is when you timing analyze them.
-->
<mode name="inpad">
<pb_type name="inpad" blif_model=".input" num_pb="1">
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="inpad" input="inpad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<mode name="outpad">
<pb_type name="outpad" blif_model=".output" num_pb="1">
<input name="outpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="outpad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="outpad.outpad"/>
</direct>
</interconnect>
</mode>
<power method="ignore"/>
</pb_type>
<!-- Define I/O pads ends -->
<!-- Define general purpose logic block (CLB) begin -->
<!-- -Due to the absence of local routing,
the 4 inputs of fracturable LUT4 are no longer equivalent,
because the 4th input can not be switched when the dual-LUT3 modes are used.
So pin equivalence should be applied to the first 3 inputs only
-->
<pb_type name="clb">
<input name="I0" num_pins="3" equivalent="full"/>
<input name="I0i" num_pins="1" equivalent="none"/>
<input name="I1" num_pins="3" equivalent="full"/>
<input name="I1i" num_pins="1" equivalent="none"/>
<input name="I2" num_pins="3" equivalent="full"/>
<input name="I2i" num_pins="1" equivalent="none"/>
<input name="I3" num_pins="3" equivalent="full"/>
<input name="I3i" num_pins="1" equivalent="none"/>
<input name="I4" num_pins="3" equivalent="full"/>
<input name="I4i" num_pins="1" equivalent="none"/>
<input name="I5" num_pins="3" equivalent="full"/>
<input name="I5i" num_pins="1" equivalent="none"/>
<input name="I6" num_pins="3" equivalent="full"/>
<input name="I6i" num_pins="1" equivalent="none"/>
<input name="I7" num_pins="3" equivalent="full"/>
<input name="I7i" num_pins="1" equivalent="none"/>
<input name="regin" num_pins="1"/>
<input name="scin" num_pins="1"/>
<output name="O" num_pins="16" equivalent="none"/>
<output name="regout" num_pins="1"/>
<output name="scout" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Describe fracturable logic element.
Each fracturable logic element has a 6-LUT that can alternatively operate as two 5-LUTs with shared inputs.
The outputs of the fracturable logic element can be optionally registered
-->
<pb_type name="fle" num_pb="8">
<input name="in" num_pins="4"/>
<input name="regin" num_pins="1"/>
<input name="scin" num_pins="1"/>
<output name="out" num_pins="2"/>
<output name="regout" num_pins="1"/>
<output name="scout" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Physical mode definition begin (physical implementation of the fle) -->
<mode name="physical" disabled_in_pack="true">
<pb_type name="fabric" num_pb="1">
<input name="in" num_pins="4"/>
<input name="regin" num_pins="1"/>
<input name="scin" num_pins="1"/>
<output name="out" num_pins="2"/>
<output name="regout" num_pins="1"/>
<output name="scout" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<pb_type name="frac_logic" num_pb="1">
<input name="in" num_pins="4"/>
<output name="out" num_pins="2"/>
<!-- Define LUT -->
<pb_type name="frac_lut4" blif_model=".subckt frac_lut4" num_pb="1">
<input name="in" num_pins="4"/>
<output name="lut3_out" num_pins="2"/>
<output name="lut4_out" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="direct1" input="frac_logic.in" output="frac_lut4.in"/>
<direct name="direct2" input="frac_lut4.lut3_out[1]" output="frac_logic.out[1]"/>
<!-- Xifan Tang: I use out[0] because the output of lut6 in lut6 mode is wired to the out[0] -->
<mux name="mux1" input="frac_lut4.lut4_out frac_lut4.lut3_out[0]" output="frac_logic.out[0]"/>
</interconnect>
</pb_type>
<!-- Define flip-flop with scan-chain capability, DI is the scan-chain data input -->
<pb_type name="ff" blif_model=".subckt scff" num_pb="2">
<input name="D" num_pins="1"/>
<input name="DI" num_pins="1"/>
<output name="Q" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_setup value="66e-12" port="ff.DI" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="fabric.in" output="frac_logic.in"/>
<direct name="direct2" input="fabric.scin" output="ff[0].DI"/>
<direct name="direct3" input="ff[0].Q" output="ff[1].DI"/>
<direct name="direct4" input="ff[1].Q" output="fabric.scout"/>
<direct name="direct5" input="ff[1].Q" output="fabric.regout"/>
<direct name="direct6" input="frac_logic.out[1:1]" output="ff[1:1].D"/>
<complete name="complete1" input="fabric.clk" output="ff[1:0].clk"/>
<mux name="mux1" input="frac_logic.out[0:0] fabric.regin" output="ff[0:0].D">
<delay_constant max="25e-12" in_port="frac_logic.out[0:0]" out_port="ff[0:0].D"/>
<delay_constant max="45e-12" in_port="fabric.regin" out_port="ff[0:0].D"/>
</mux>
<mux name="mux2" input="ff[0].Q frac_logic.out[0]" output="fabric.out[0]">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="frac_logic.out[0]" out_port="fabric.out[0]"/>
<delay_constant max="45e-12" in_port="ff[0].Q" out_port="fabric.out[0]"/>
</mux>
<mux name="mux3" input="ff[1].Q frac_logic.out[1]" output="fabric.out[1]">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="frac_logic.out[1]" out_port="fabric.out[1]"/>
<delay_constant max="45e-12" in_port="ff[1].Q" out_port="fabric.out[1]"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="fabric.in"/>
<direct name="direct3" input="fle.regin" output="fabric.regin"/>
<direct name="direct4" input="fle.scin" output="fabric.scin"/>
<direct name="direct5" input="fabric.out" output="fle.out"/>
<direct name="direct7" input="fabric.regout" output="fle.regout"/>
<direct name="direct8" input="fabric.scout" output="fle.scout"/>
<direct name="direct9" input="fle.clk" output="fabric.clk"/>
</interconnect>
</mode>
<!-- Physical mode definition end (physical implementation of the fle) -->
<!-- Dual 3-LUT mode definition begin -->
<mode name="n2_lut3">
<pb_type name="lut3inter" num_pb="1">
<input name="in" num_pins="3"/>
<output name="out" num_pins="2"/>
<clock name="clk" num_pins="1"/>
<pb_type name="ble3" num_pb="2">
<input name="in" num_pins="3"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define the LUT -->
<pb_type name="lut3" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="3" port_class="lut_in"/>
<output name="out" num_pins="1" port_class="lut_out"/>
<!-- LUT timing using delay matrix -->
<!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
we instead take the average of these numbers to get more stable results
82e-12
173e-12
261e-12
263e-12
398e-12
-->
<delay_matrix type="max" in_port="lut3.in" out_port="lut3.out">
235e-12
235e-12
235e-12
</delay_matrix>
</pb_type>
<!-- Define the flip-flop -->
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="ble3.in[2:0]" output="lut3[0:0].in[2:0]"/>
<direct name="direct2" input="lut3[0:0].out" output="ff[0:0].D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble3" in_port="lut3[0:0].out" out_port="ff[0:0].D"/>
</direct>
<direct name="direct3" input="ble3.clk" output="ff[0:0].clk"/>
<mux name="mux1" input="ff[0:0].Q lut3.out[0:0]" output="ble3.out[0:0]">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut3.out[0:0]" out_port="ble3.out[0:0]"/>
<delay_constant max="45e-12" in_port="ff[0:0].Q" out_port="ble3.out[0:0]"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="lut3inter.in" output="ble3[0:0].in"/>
<direct name="direct2" input="lut3inter.in" output="ble3[1:1].in"/>
<direct name="direct3" input="ble3[1:0].out" output="lut3inter.out"/>
<complete name="complete1" input="lut3inter.clk" output="ble3[1:0].clk"/>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in[2:0]" output="lut3inter.in"/>
<direct name="direct2" input="lut3inter.out" output="fle.out"/>
<direct name="direct3" input="fle.clk" output="lut3inter.clk"/>
</interconnect>
</mode>
<!-- Dual 3-LUT mode definition end -->
<!-- 4-LUT mode definition begin -->
<mode name="n1_lut4">
<!-- Define 4-LUT mode -->
<pb_type name="ble4" num_pb="1">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut4" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="4" port_class="lut_in"/>
<output name="out" num_pins="1" port_class="lut_out"/>
<!-- LUT timing using delay matrix -->
<!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
we instead take the average of these numbers to get more stable results
82e-12
173e-12
261e-12
263e-12
398e-12
397e-12
-->
<delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
261e-12
261e-12
261e-12
261e-12
</delay_matrix>
</pb_type>
<!-- Define flip-flop -->
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="ble4.in" output="lut4[0:0].in"/>
<direct name="direct2" input="lut4.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble4" in_port="lut4.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble4.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut4.out" output="ble4.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut4.out" out_port="ble4.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble4.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble4.in"/>
<direct name="direct2" input="ble4.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble4.clk"/>
</interconnect>
</mode>
<!-- 4-LUT mode definition end -->
<!-- Define shift register begin -->
<mode name="shift_register">
<pb_type name="shift_reg" num_pb="1">
<input name="regin" num_pins="1"/>
<output name="regout" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<pb_type name="ff" blif_model=".latch" num_pb="2" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="shift_reg.regin" output="ff[0].D"/>
<direct name="direct2" input="ff[0].Q" output="ff[1].D"/>
<direct name="direct3" input="ff[1].Q" output="shift_reg.regout"/>
<complete name="complete1" input="shift_reg.clk" output="ff.clk"/>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.regin" output="shift_reg.regin"/>
<direct name="direct2" input="shift_reg.regout" output="fle.regout"/>
<direct name="direct3" input="fle.clk" output="shift_reg.clk"/>
</interconnect>
</mode>
<!-- Define shift register end -->
</pb_type>
<interconnect>
<!-- We use direct connections to reduce the area to the most
The global local routing is going to compensate the loss in routability
-->
<direct name="direct_fle0" input="clb.I0" output="fle[0:0].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle0i" input="clb.I0i" output="fle[0:0].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle1" input="clb.I1" output="fle[1:1].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle1i" input="clb.I1i" output="fle[1:1].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle2" input="clb.I2" output="fle[2:2].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle2i" input="clb.I2i" output="fle[2:2].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle3" input="clb.I3" output="fle[3:3].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle3i" input="clb.I3i" output="fle[3:3].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle4" input="clb.I4" output="fle[4:4].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle4i" input="clb.I4i" output="fle[4:4].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle5" input="clb.I5" output="fle[5:5].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle5i" input="clb.I5i" output="fle[5:5].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle6" input="clb.I6" output="fle[6:6].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle6i" input="clb.I6i" output="fle[6:6].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle7" input="clb.I7" output="fle[7:7].in[0:2]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<direct name="direct_fle7i" input="clb.I7i" output="fle[7:7].in[3]">
<!-- TODO: Timing should be backannotated from post-PnR results -->
</direct>
<complete name="clks" input="clb.clk" output="fle[7:0].clk">
</complete>
<!-- This way of specifying direct connection to clb outputs is important because this architecture uses automatic spreading of opins.
By grouping to output pins in this fashion, if a logic block is completely filled by 6-LUTs,
then the outputs those 6-LUTs take get evenly distributed across all four sides of the CLB instead of clumped on two sides (which is what happens with a more
naive specification).
-->
<direct name="clbouts1" input="fle[3:0].out[0:1]" output="clb.O[7:0]"/>
<direct name="clbouts2" input="fle[7:4].out[0:1]" output="clb.O[15:8]"/>
<!-- Shift register chain links -->
<direct name="shift_register_in" input="clb.regin" output="fle[0:0].regin">
<!-- Put all inter-block carry chain delay on this one edge -->
<delay_constant max="0.16e-9" in_port="clb.regin" out_port="fle[0:0].regin"/>
<!--pack_pattern name="chain" in_port="clb.regin" out_port="fle[0:0].regin"/-->
</direct>
<direct name="shift_register_out" input="fle[7:7].regout" output="clb.regout">
<!--pack_pattern name="chain" in_port="fle[7:7].regout" out_port="clb.regout"/-->
</direct>
<direct name="shift_register_link" input="fle[6:0].regout" output="fle[7:1].regin">
<!--pack_pattern name="chain" in_port="fle[6:0].regout" out_port="fle[7:1].regin"/-->
</direct>
<!-- Scan chain links -->
<direct name="scan_chain_in" input="clb.scin" output="fle[0:0].scin">
<!-- Put all inter-block carry chain delay on this one edge -->
<delay_constant max="0.16e-9" in_port="clb.scin" out_port="fle[0:0].scin"/>
</direct>
<direct name="scan_chain_out" input="fle[7:7].scout" output="clb.scout">
</direct>
<direct name="scan_chain_link" input="fle[6:0].scout" output="fle[7:1].scin">
</direct>
</interconnect>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- Place this general purpose logic block in any unspecified column -->
</pb_type>
<!-- Define general purpose logic block (CLB) ends -->
</complexblocklist>
</architecture>