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

Merge branch 'refactoring' into dev

This commit is contained in:
tangxifan 2020-01-27 21:19:19 -07:00
parent de38e8ecd9 82f71e82e8
commit b6b46c5563
19 changed files with 3041 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
CMakeLists.txt
View File

@ -46,6 +46,10 @@ project("OPENFPGA" C CXX)
option(ENABLE_VPR_GRAPHICS "Enables VPR graphics" ON)
option(ENABLE_VPR_GRAPHICS "Enables build with librtlnumber" OFF)
#Allow the user to decide weather to compile the graphics library
set(VPR_USE_EZGL "auto" CACHE STRING "Specify whether vpr uses the graphics library")
set_property(CACHE VPR_USE_EZGL PROPERTY STRINGS auto off on)
# Version number
set(OPENFPGA_VERSION_MAJOR 1)
set(OPENFPGA_VERSION_MINOR 0)
@ -154,6 +158,27 @@ message(STATUS "CMAKE_CXX_FLAGS: ${CMAKE_CXX_FLAGS}")
#
enable_testing()
# set VPR_USE_EZGL in the root of VTR to decide whether to add
# subdirectory of graphics library, which prevents users
# without gtk/x11 libraries installed to build. VPR_USE_EZGL is
# being used in both the vpr CMakeLists and libs/EXTERNAL CMakeLists.
#
# check if GTK and X11 are installed and turn on/off graphics
if (VPR_USE_EZGL STREQUAL "auto")
find_package(PkgConfig REQUIRED)
pkg_check_modules(GTK3 QUIET gtk+-3.0)
pkg_check_modules(X11 QUIET x11)
if(GTK3_FOUND AND X11_FOUND)
set(VPR_USE_EZGL "on")
message(STATUS "VPR Graphics: Enabled")
else()
set(VPR_USE_EZGL "off")
message(STATUS "VPR Graphics: Disabled (required libraries missing, on debia/ubuntu try: sudo apt install libgtk-3 libx11-dev")
endif()
endif()
#
# Sub-projects
#

2
libopenfpga/libopenfpgashell/src/shell.h
View File

@ -115,7 +115,7 @@ class Shell {
bool valid_command_class_id(const ShellCommandClassId& cmd_class_id) const;
public: /* Public executors */
/* Start the interactive mode, where users will type-in command by command */
void run_interactive_mode(T& context);
void run_interactive_mode(T& context, const bool& quiet_mode = false);
/* Start the script mode, where users provide a file which includes all the commands to run */
void run_script_mode(const char* script_file_name, T& context);
/* Print all the commands by their classes. This is actually the help desk */

21
libopenfpga/libopenfpgashell/src/shell.tpp
View File

@ -239,13 +239,15 @@ ShellCommandClassId Shell<T>::add_command_class(const char* name) {
* Public executors
***********************************************************************/
template <class T>
void Shell<T>::run_interactive_mode(T& context) {
VTR_LOG("Start interactive mode of %s...\n",
name().c_str());
void Shell<T>::run_interactive_mode(T& context, const bool& quiet_mode) {
if (false == quiet_mode) {
VTR_LOG("Start interactive mode of %s...\n",
name().c_str());
/* Print the title of the shell */
if (!title().empty()) {
VTR_LOG("%s\n", title().c_str());
/* Print the title of the shell */
if (!title().empty()) {
VTR_LOG("%s\n", title().c_str());
}
}
/* Wait for users input and execute the command */
@ -306,6 +308,9 @@ void Shell<T>::run_script_mode(const char* script_file_name, T& context) {
}
}
fp.close();
/* Return to interactive mode, stay tuned */
run_interactive_mode(context, true);
}
template <class T>
@ -390,6 +395,10 @@ void Shell<T>::execute_command(const char* cmd_line,
free(argv[itok]);
}
free(argv);
/* Change the status of the command */
command_status_[cmd_id] = true;
/* Finish for macro command, return */
return;
}

5
openfpga/src/base/openfpga_context.h
View File

@ -3,6 +3,7 @@
#include "vpr_context.h"
#include "openfpga_arch.h"
#include "vpr_pb_type_annotation.h"
/********************************************************************
* This file includes the declaration of the date structure
@ -34,11 +35,15 @@
class OpenfpgaContext : public Context {
public: /* Public accessors */
const openfpga::Arch& arch() const { return arch_; }
const openfpga::VprPbTypeAnnotation& vpr_pb_type_annotation() const { return vpr_pb_type_annotation_; }
public: /* Public mutators */
openfpga::Arch& mutable_arch() { return arch_; }
openfpga::VprPbTypeAnnotation& mutable_vpr_pb_type_annotation() { return vpr_pb_type_annotation_; }
private: /* Internal data */
/* Data structure to store information from read_openfpga_arch library */
openfpga::Arch arch_;
/* Annotation to pb_type of VPR */
openfpga::VprPbTypeAnnotation vpr_pb_type_annotation_;
};
#endif

342
openfpga/src/base/openfpga_link_arch.cpp Normal file
View File

@ -0,0 +1,342 @@
/********************************************************************
* This file includes functions to read an OpenFPGA architecture file
* which are built on the libarchopenfpga library
*******************************************************************/
/* Headers from vtrutil library */
#include "vtr_time.h"
#include "vtr_assert.h"
#include "vtr_log.h"
#include "vpr_pb_type_annotation.h"
#include "pb_type_utils.h"
#include "openfpga_link_arch.h"
/* Include global variables of VPR */
#include "globals.h"
/* begin namespace openfpga */
namespace openfpga {
/********************************************************************
* This function will traverse pb_type graph from its top to find
* a pb_type with a given name as well as its hierarchy
*******************************************************************/
static
t_pb_type* try_find_pb_type_with_given_path(t_pb_type* top_pb_type,
const std::vector<std::string>& target_pb_type_names,
const std::vector<std::string>& target_pb_mode_names) {
/* Ensure that number of parent names and modes matches */
VTR_ASSERT_SAFE(target_pb_type_names.size() == target_pb_mode_names.size() + 1);
t_pb_type* cur_pb_type = top_pb_type;
/* If the top pb_type is what we want, we can return here */
if (1 == target_pb_type_names.size()) {
if (target_pb_type_names[0] == std::string(top_pb_type->name)) {
return top_pb_type;
}
/* Not match, return null pointer */
return nullptr;
}
/* We start from the first element of the parent names and parent modes.
* If the pb_type does not match in name, we fail
* If we cannot find a mode match the name, we fail
*/
for (size_t i = 0; i < target_pb_type_names.size() - 1; ++i) {
/* If this level does not match, search fail */
if (target_pb_type_names[i] != std::string(cur_pb_type->name)) {
return nullptr;
}
/* Find if the mode matches */
t_mode* cur_mode = find_pb_type_mode(cur_pb_type, target_pb_mode_names[i].c_str());
if (nullptr == cur_mode) {
return nullptr;
}
/* Go to the next level of pb_type */
cur_pb_type = find_mode_child_pb_type(cur_mode, target_pb_type_names[i + 1].c_str());
if (nullptr == cur_pb_type) {
return nullptr;
}
/* If this is already the last pb_type in the list, this is what we want */
if (i == target_pb_type_names.size() - 1) {
return cur_pb_type;
}
}
/* Reach here, it means we find nothing */
return nullptr;
}
/********************************************************************
* This function will identify the physical pb_type for each multi-mode
* pb_type in VPR pb_type graph by following the explicit definition
* in OpenFPGA architecture XML
*******************************************************************/
static
void build_vpr_physical_pb_mode_explicit_annotation(const DeviceContext& vpr_device_ctx,
const Arch& openfpga_arch,
VprPbTypeAnnotation& vpr_pb_type_annotation) {
/* Walk through the pb_type annotation stored in the openfpga arch */
for (const PbTypeAnnotation& pb_type_annotation : openfpga_arch.pb_type_annotations) {
/* Since our target is to annotate the physical mode name,
* we can skip those has not physical mode defined
*/
if (true == pb_type_annotation.physical_mode_name().empty()) {
continue;
}
/* Identify if the pb_type is operating or physical,
* For operating pb_type, get the full name of operating pb_type
* For physical pb_type, get the full name of physical pb_type
*/
std::vector<std::string> target_pb_type_names;
std::vector<std::string> target_pb_mode_names;
if (true == pb_type_annotation.is_operating_pb_type()) {
target_pb_type_names = pb_type_annotation.operating_parent_pb_type_names();
target_pb_type_names.push_back(pb_type_annotation.operating_pb_type_name());
target_pb_mode_names = pb_type_annotation.operating_parent_mode_names();
}
if (true == pb_type_annotation.is_physical_pb_type()) {
target_pb_type_names = pb_type_annotation.physical_parent_pb_type_names();
target_pb_type_names.push_back(pb_type_annotation.physical_pb_type_name());
target_pb_mode_names = pb_type_annotation.physical_parent_mode_names();
}
/* We must have at least one pb_type in the list */
VTR_ASSERT_SAFE(0 < target_pb_type_names.size());
/* Pb type information are located at the logic_block_types in the device context of VPR
* We iterate over the vectors and find the pb_type matches the parent_pb_type_name
*/
bool link_success = false;
for (const t_logical_block_type& lb_type : vpr_device_ctx.logical_block_types) {
/* By pass nullptr for pb_type head */
if (nullptr == lb_type.pb_type) {
continue;
}
/* Check the name of the top-level pb_type, if it does not match, we can bypass */
if (target_pb_type_names[0] != std::string(lb_type.pb_type->name)) {
continue;
}
/* Match the name in the top-level, we go further to search the pb_type in the graph */
t_pb_type* target_pb_type = try_find_pb_type_with_given_path(lb_type.pb_type, target_pb_type_names,
target_pb_mode_names);
if (nullptr == target_pb_type) {
continue;
}
/* Found, we update the annotation by assigning the physical mode */
t_mode* physical_mode = find_pb_type_mode(target_pb_type, pb_type_annotation.physical_mode_name().c_str());
vpr_pb_type_annotation.add_pb_type_physical_mode(target_pb_type, physical_mode);
/* Give a message */
VTR_LOG("Annotate pb_type '%s' with physical mode '%s'\n",
target_pb_type->name, physical_mode->name);
link_success = true;
break;
}
if (false == link_success) {
/* Not found, error out! */
VTR_LOG_ERROR("Unable to find the pb_type '%s' in VPR architecture definition!\n",
target_pb_type_names.back().c_str());
return;
}
}
}
/********************************************************************
* This function will recursively visit all the pb_type from the top
* pb_type in the graph and
* infer the physical pb_type for each multi-mode
* pb_type in VPR pb_type graph without OpenFPGA architecture XML
*
* The following rule is applied:
* if there is only 1 mode under a pb_type, it will be the default
* physical mode for this pb_type
*******************************************************************/
static
void rec_infer_vpr_physical_pb_mode_annotation(t_pb_type* cur_pb_type,
VprPbTypeAnnotation& vpr_pb_type_annotation) {
/* We do not check any primitive pb_type */
if (true == is_primitive_pb_type(cur_pb_type)) {
return;
}
/* For non-primitive pb_type:
* - if there is only one mode, it will be the physical mode
* we just need to make sure that we do not repeatedly annotate this
* - if there are multiple modes, we should be able to find a physical mode
* and then go recursively
*/
t_mode* physical_mode = nullptr;
if (1 == cur_pb_type->num_modes) {
if (nullptr == vpr_pb_type_annotation.physical_mode(cur_pb_type)) {
/* Not assigned by explicit annotation, we should infer here */
vpr_pb_type_annotation.add_pb_type_physical_mode(cur_pb_type, &(cur_pb_type->modes[0]));
VTR_LOG("Implicitly infer physical mode '%s' for pb_type '%s'\n",
cur_pb_type->modes[0].name, cur_pb_type->name);
}
} else {
VTR_ASSERT(1 < cur_pb_type->num_modes);
if (nullptr == vpr_pb_type_annotation.physical_mode(cur_pb_type)) {
/* Not assigned by explicit annotation, we should infer here */
vpr_pb_type_annotation.add_pb_type_physical_mode(cur_pb_type, &(cur_pb_type->modes[0]));
VTR_LOG_ERROR("Unable to find a physical mode for a multi-mode pb_type '%s'!\n",
cur_pb_type->name);
VTR_LOG_ERROR("Please specify in the OpenFPGA architecture\n");
return;
}
}
/* Get the physical mode from annotation */
physical_mode = vpr_pb_type_annotation.physical_mode(cur_pb_type);
VTR_ASSERT(nullptr != physical_mode);
/* Traverse the pb_type children under the physical mode */
for (int ichild = 0; ichild < physical_mode->num_pb_type_children; ++ichild) {
rec_infer_vpr_physical_pb_mode_annotation(&(physical_mode->pb_type_children[ichild]),
vpr_pb_type_annotation);
}
}
/********************************************************************
* This function will infer the physical pb_type for each multi-mode
* pb_type in VPR pb_type graph without OpenFPGA architecture XML
*
* The following rule is applied:
* if there is only 1 mode under a pb_type, it will be the default
* physical mode for this pb_type
*
* Note:
* This function must be executed AFTER the function
* build_vpr_physical_pb_mode_explicit_annotation()
*******************************************************************/
static
void build_vpr_physical_pb_mode_implicit_annotation(const DeviceContext& vpr_device_ctx,
VprPbTypeAnnotation& vpr_pb_type_annotation) {
for (const t_logical_block_type& lb_type : vpr_device_ctx.logical_block_types) {
/* By pass nullptr for pb_type head */
if (nullptr == lb_type.pb_type) {
continue;
}
rec_infer_vpr_physical_pb_mode_annotation(lb_type.pb_type, vpr_pb_type_annotation);
}
}
/********************************************************************
* This function will recursively traverse pb_type graph to ensure
* 1. there is only a physical mode under each pb_type
* 2. physical mode appears only when its parent is a physical mode.
*******************************************************************/
static
void rec_check_vpr_physical_pb_mode_annotation(t_pb_type* cur_pb_type,
const bool& expect_physical_mode,
const VprPbTypeAnnotation& vpr_pb_type_annotation,
size_t& num_err) {
/* We do not check any primitive pb_type */
if (true == is_primitive_pb_type(cur_pb_type)) {
return;
}
/* For non-primitive pb_type:
* - If we expect a physical mode to exist under this pb_type
* we should be able to find one in the annoation
* - If we do NOT expect a physical mode, make sure we find
* nothing in the annotation
*/
if (true == expect_physical_mode) {
if (nullptr == vpr_pb_type_annotation.physical_mode(cur_pb_type)) {
VTR_LOG_ERROR("Unable to find a physical mode for a multi-mode pb_type '%s'!\n",
cur_pb_type->name);
VTR_LOG_ERROR("Please specify in the OpenFPGA architecture\n");
num_err++;
return;
}
} else {
VTR_ASSERT_SAFE(false == expect_physical_mode);
if (nullptr != vpr_pb_type_annotation.physical_mode(cur_pb_type)) {
VTR_LOG_ERROR("Find a physical mode '%s' for pb_type '%s' which is not under any physical mode!\n",
vpr_pb_type_annotation.physical_mode(cur_pb_type)->name,
cur_pb_type->name);
num_err++;
return;
}
}
/* Traverse all the modes
* - for pb_type children under a physical mode, we expect an physical mode
* - for pb_type children under non-physical mode, we expect no physical mode
*/
for (int imode = 0; imode < cur_pb_type->num_modes; ++imode) {
bool expect_child_physical_mode = false;
if (&(cur_pb_type->modes[imode]) == vpr_pb_type_annotation.physical_mode(cur_pb_type)) {
expect_child_physical_mode = true && expect_physical_mode;
}
for (int ichild = 0; ichild < cur_pb_type->modes[imode].num_pb_type_children; ++ichild) {
rec_check_vpr_physical_pb_mode_annotation(&(cur_pb_type->modes[imode].pb_type_children[ichild]),
expect_child_physical_mode, vpr_pb_type_annotation,
num_err);
}
}
}
/********************************************************************
* This function will check the physical mode annotation for
* each pb_type in the device
*******************************************************************/
static
void check_vpr_physical_pb_mode_annotation(const DeviceContext& vpr_device_ctx,
const VprPbTypeAnnotation& vpr_pb_type_annotation) {
size_t num_err = 0;
for (const t_logical_block_type& lb_type : vpr_device_ctx.logical_block_types) {
/* By pass nullptr for pb_type head */
if (nullptr == lb_type.pb_type) {
continue;
}
/* Top pb_type should always has a physical mode! */
rec_check_vpr_physical_pb_mode_annotation(lb_type.pb_type, true, vpr_pb_type_annotation, num_err);
}
if (0 == num_err) {
VTR_LOG("Check physical mode annotation for pb_types passed.\n");
} else {
VTR_LOG("Check physical mode annotation for pb_types failed with %ld errors!\n",
num_err);
}
}
/********************************************************************
* Top-level function to link openfpga architecture to VPR, including:
* - physical pb_type
* - idle pb_type
* - circuit models for pb_type, pb interconnect and routing architecture
*******************************************************************/
void link_arch(OpenfpgaContext& openfpga_context) {
vtr::ScopedStartFinishTimer timer("Link OpenFPGA architecture to VPR architecture");
/* Annotate physical pb_type in the VPR pb_type graph */
build_vpr_physical_pb_mode_explicit_annotation(g_vpr_ctx.device(), openfpga_context.arch(),
openfpga_context.mutable_vpr_pb_type_annotation());
build_vpr_physical_pb_mode_implicit_annotation(g_vpr_ctx.device(),
openfpga_context.mutable_vpr_pb_type_annotation());
check_vpr_physical_pb_mode_annotation(g_vpr_ctx.device(),
openfpga_context.vpr_pb_type_annotation());
/* Annotate idle pb_type in the VPR pb_type graph */
/* Link physical pb_type to circuit model */
/* Link routing architecture to circuit model */
}
} /* end namespace openfpga */

20
openfpga/src/base/openfpga_link_arch.h Normal file
View File

@ -0,0 +1,20 @@
#ifndef OPENFPGA_LINK_ARCH_COMMAND_H
#define OPENFPGA_LINK_ARCH_COMMAND_H
/********************************************************************
* Include header files that are required by function declaration
*******************************************************************/
#include "openfpga_context.h"
/********************************************************************
* Function declaration
*******************************************************************/
/* begin namespace openfpga */
namespace openfpga {
void link_arch(OpenfpgaContext& openfpga_context);
} /* end namespace openfpga */
#endif

18
openfpga/src/base/openfpga_setup_command.cpp
View File

@ -4,6 +4,7 @@
* - read_openfpga_arch : read OpenFPGA architecture file
*******************************************************************/
#include "openfpga_read_arch.h"
#include "openfpga_link_arch.h"
#include "openfpga_setup_command.h"
/* begin namespace openfpga */
@ -36,8 +37,23 @@ void add_openfpga_setup_commands(openfpga::Shell<OpenfpgaContext>& shell) {
ShellCommandId shell_cmd_write_arch_id = shell.add_command(shell_cmd_write_arch, "write OpenFPGA architecture file");
shell.set_command_class(shell_cmd_write_arch_id, openfpga_setup_cmd_class);
shell.set_command_const_execute_function(shell_cmd_write_arch_id, write_arch);
/* The 'write_openfpga_arch' command should be executed before 'read_openfpga_arch' */
/* The 'write_openfpga_arch' command should NOT be executed before 'read_openfpga_arch' */
shell.set_command_dependency(shell_cmd_write_arch_id, std::vector<ShellCommandId>(1, shell_cmd_read_arch_id));
/* Command 'link_openfpga_arch' */
Command shell_cmd_link_openfpga_arch("link_openfpga_arch");
/* Add command 'link_openfpga_arch' to the Shell */
ShellCommandId shell_cmd_link_openfpga_arch_id = shell.add_command(shell_cmd_link_openfpga_arch, "Bind OpenFPGA architecture to VPR");
shell.set_command_class(shell_cmd_link_openfpga_arch_id, openfpga_setup_cmd_class);
shell.set_command_execute_function(shell_cmd_link_openfpga_arch_id, link_arch);
/* The 'link_openfpga_arch' command should NOT be executed before 'read_openfpga_arch' and 'vpr' */
const ShellCommandId& shell_cmd_vpr_id = shell.command(std::string("vpr"));
std::vector<ShellCommandId> cmd_dependency_link_openfpga_arch;
cmd_dependency_link_openfpga_arch.push_back(shell_cmd_read_arch_id);
cmd_dependency_link_openfpga_arch.push_back(shell_cmd_vpr_id);
shell.set_command_dependency(shell_cmd_link_openfpga_arch_id, cmd_dependency_link_openfpga_arch);
}
} /* end namespace openfpga */

67
openfpga/src/base/pb_type_utils.cpp Normal file
View File

@ -0,0 +1,67 @@
/********************************************************************
* This file includes most utilized functions for the pb_type
* and pb_graph_node data structure in the OpenFPGA context
*******************************************************************/
/* Headers from vtrutil library */
#include "vtr_assert.h"
#include "vtr_log.h"
#include "pb_type_utils.h"
/* begin namespace openfpga */
namespace openfpga {
/************************************************************************
* A pb_type is considered to be primitive when it has zero modes
* However, this not always true. An exception is the LUT_CLASS
* VPR added two modes by default to a LUT pb_type. Therefore,
* for LUT_CLASS, it is a primitive when it is binded to a blif model
*
* Note:
* - if VPR changes its mode organization for LUT pb_type
* this code should be adapted as well!
************************************************************************/
bool is_primitive_pb_type(t_pb_type* pb_type) {
if (LUT_CLASS == pb_type->class_type) {
/* The first mode of LUT is wire, the second is the regular LUT */
VTR_ASSERT(std::string("wire") == std::string(pb_type->modes[0].name));
VTR_ASSERT(std::string(pb_type->name) == std::string(pb_type->modes[1].name));
return true;
}
return 0 == pb_type->num_modes;
}
/************************************************************************
* A pb_type is the root pb_type when it has no parent mode
************************************************************************/
bool is_root_pb_type(t_pb_type* pb_type) {
return pb_type->parent_mode == nullptr;
}
/************************************************************************
* With a given mode name, find the mode pointer
************************************************************************/
t_mode* find_pb_type_mode(t_pb_type* pb_type, const char* mode_name) {
for (int i = 0; i < pb_type->num_modes; ++i) {
if (std::string(mode_name) == std::string(pb_type->modes[i].name)) {
return &(pb_type->modes[i]);
}
}
/* Note found, return a nullptr */
return nullptr;
}
/************************************************************************
* With a given pb_type name, find the pb_type pointer
************************************************************************/
t_pb_type* find_mode_child_pb_type(t_mode* mode, const char* child_name) {
for (int i = 0; i < mode->num_pb_type_children; ++i) {
if (std::string(child_name) == std::string(mode->pb_type_children[i].name)) {
return &(mode->pb_type_children[i]);
}
}
/* Note found, return a nullptr */
return nullptr;
}
} /* end namespace openfpga */

26
openfpga/src/base/pb_type_utils.h Normal file
View File

@ -0,0 +1,26 @@
#ifndef PB_TYPE_UTILS_H
#define PB_TYPE_UTILS_H
/********************************************************************
* Include header files that are required by function declaration
*******************************************************************/
#include "physical_types.h"
/********************************************************************
* Function declaration
*******************************************************************/
/* begin namespace openfpga */
namespace openfpga {
bool is_primitive_pb_type(t_pb_type* pb_type);
bool is_root_pb_type(t_pb_type* pb_type);
t_mode* find_pb_type_mode(t_pb_type* pb_type, const char* mode_name);
t_pb_type* find_mode_child_pb_type(t_mode* mode, const char* child_name);
} /* end namespace openfpga */
#endif

44
openfpga/src/base/vpr_pb_type_annotation.cpp Normal file
View File

@ -0,0 +1,44 @@
/************************************************************************
* Member functions for class VprPbTypeAnnotation
***********************************************************************/
#include "vtr_log.h"
#include "vtr_assert.h"
#include "vpr_pb_type_annotation.h"
/* namespace openfpga begins */
namespace openfpga {
/************************************************************************
* Constructors
***********************************************************************/
VprPbTypeAnnotation::VprPbTypeAnnotation() {
return;
}
/************************************************************************
* Public mutators
***********************************************************************/
t_mode* VprPbTypeAnnotation::physical_mode(t_pb_type* pb_type) const {
/* Ensure that the pb_type is in the list */
std::map<t_pb_type*, t_mode*>::const_iterator it = physical_pb_modes_.find(pb_type);
if (it == physical_pb_modes_.end()) {
return nullptr;
}
return physical_pb_modes_.at(pb_type);
}
/************************************************************************
* Public mutators
***********************************************************************/
void VprPbTypeAnnotation::add_pb_type_physical_mode(t_pb_type* pb_type, t_mode* physical_mode) {
/* Warn any override attempt */
std::map<t_pb_type*, t_mode*>::const_iterator it = physical_pb_modes_.find(pb_type);
if (it != physical_pb_modes_.end()) {
VTR_LOG_WARN("Override the annotation between pb_type '%s' and it physical mode '%s'!\n",
pb_type->name, physical_mode->name);
}
physical_pb_modes_[pb_type] = physical_mode;
}
} /* End namespace openfpga*/

43
openfpga/src/base/vpr_pb_type_annotation.h Normal file
View File

@ -0,0 +1,43 @@
#ifndef VPR_PB_TYPE_ANNOTATION_H
#define VPR_PB_TYPE_ANNOTATION_H
/********************************************************************
* Include header files required by the data structure definition
*******************************************************************/
#include <map>
/* Header from archfpga library */
#include "physical_types.h"
/* Header from openfpgautil library */
#include "circuit_library.h"
/* Begin namespace openfpga */
namespace openfpga {
/********************************************************************
* This is the critical data structure to link the pb_type in VPR
* to openfpga annotations
* With a given pb_type pointer, it aims to identify:
* 1. if the pb_type is a physical pb_type or a operating pb_type
* 2. what is the circuit model id linked to a physical pb_type
* 3. what is the physical pb_type for an operating pb_type
* 4. what is the mode pointer that represents the physical mode for a pb_type
*******************************************************************/
class VprPbTypeAnnotation {
public: /* Constructor */
VprPbTypeAnnotation();
public: /* Public accessors */
t_mode* physical_mode(t_pb_type* pb_type) const;
public: /* Public mutators */
void add_pb_type_physical_mode(t_pb_type* pb_type, t_mode* physical_mode);
private: /* Internal data */
std::map<t_pb_type*, bool> is_physical_pb_types_;
std::map<t_pb_type*, t_pb_type*> physical_pb_types_;
std::map<t_pb_type*, t_mode*> physical_pb_modes_;
std::map<t_pb_type*, CircuitModelId> pb_type_circuit_models_;
};
} /* End namespace openfpga*/
#endif

4
openfpga/src/vpr_wrapper/vpr_command.cpp
View File

@ -10,13 +10,13 @@ namespace openfpga {
void add_vpr_commands(openfpga::Shell<OpenfpgaContext>& shell) {
/* Add a new class of commands */
ShellCommandClassId arith_cmd_class = shell.add_command_class("VPR");
ShellCommandClassId vpr_cmd_class = shell.add_command_class("VPR");
/* Create a macro command of 'vpr' which will call the main engine of vpr
*/
Command shell_cmd_vpr("vpr");
ShellCommandId shell_cmd_vpr_id = shell.add_command(shell_cmd_vpr, "Start VPR core engine to pack, place and route a BLIF design on a FPGA architecture");
shell.set_command_class(shell_cmd_vpr_id, arith_cmd_class);
shell.set_command_class(shell_cmd_vpr_id, vpr_cmd_class);
shell.set_command_execute_function(shell_cmd_vpr_id, vpr::vpr);
}

8
openfpga/src/vpr_wrapper/vpr_main.cpp
View File

@ -48,7 +48,7 @@ int vpr(int argc, char** argv) {
vpr_install_signal_handler();
/* Read options, architecture, and circuit netlist */
vpr_init(argc, (const char**)argv, &Options, &vpr_setup, &Arch);
vpr_init(argc, const_cast<const char**>(argv), &Options, &vpr_setup, &Arch);
if (Options.show_version) {
return SUCCESS_EXIT_CODE;
@ -70,8 +70,10 @@ int vpr(int argc, char** argv) {
timing_ctx.stats.num_full_hold_updates,
timing_ctx.stats.num_full_setup_hold_updates);
/* free data structures */
vpr_free_all(Arch, vpr_setup);
/* TODO: move this to the end of flow
* free data structures
*/
/* vpr_free_all(Arch, vpr_setup); */
VTR_LOG("VPR suceeded\n");

90
openfpga/test_blif/s298.blif Normal file
View File

@ -0,0 +1,90 @@
# Benchmark "s298" written by ABC on Tue Mar 12 09:40:31 2019
.model s298
.inputs clock G0 G1 G2
.outputs G117 G132 G66 G118 G133 G67
.latch n21 G10 re clock 0
.latch n26 G11 re clock 0
.latch n31 G12 re clock 0
.latch n36 G13 re clock 0
.latch n41 G14 re clock 0
.latch n46 G15 re clock 0
.latch n51 G66 re clock 0
.latch n55 G67 re clock 0
.latch n59 G117 re clock 0
.latch n63 G118 re clock 0
.latch n67 G132 re clock 0
.latch n71 G133 re clock 0
.latch n75 G22 re clock 0
.latch n80 G23 re clock 0
.names n56 n57 G10 n63
0-0 1
11- 1
.names G15 G11 G13 G22 G14 G12 n56
01---- 1
0-0--- 1
0--0-- 1
0---1- 1
0----1 1
-11000 1
.names G14 G13 G12 G118 G11 n57
01--- 1
100-0 1
1-11- 1
-1-1- 1
.names n56 n59_1 G10 n67
0-0 1
11- 1
.names G14 G13 G12 G132 G11 n59_1
100-0 1
11-1- 1
1-11- 1
.names G0 G10 n21
00 1
.names G10 G11 G0 G12 G13 n26
010-- 1
1001- 1
100-0 1
.names G12 G0 G11 G10 n31
0011 1
100- 1
10-0 1
.names G13 G0 G11 G12 G10 n36
00111 1
1001- 1
1010- 1
10--0 1
.names n65 G14 G0 n41
000 1
110 1
.names G23 G10 G13 G11 G12 n65
1---- 0
-1100 0
.names G0 n56 n46
00 1
.names n56 G66 G14 G13 G12 n51
111-1 1
11-1- 1
1-01- 1
.names n56 G13 G14 G11 G67 G12 n55
1000-- 1
10-1-0 1
111-1- 1
1-1-11 1
.names n56 G13 G117 G14 G12 G11 n59
10-0-- 1
10--01 1
1111-- 1
1-111- 1
.names n56 G14 G12 G13 G133 G11 n71
1010-1 1
111-1- 1
11-11- 1
.names G2 G22 G0 n75
010 1
100 1
.names G1 G23 G0 n80
010 1
100 1
.end

234
openfpga/test_openfpga_arch/k6_N10_40nm_openfpga.xml Normal file
View File

@ -0,0 +1,234 @@
<!-- Architecture annotation for OpenFPGA framework
This annotation supports the k6_N10_40nm.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
-->
<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="INVTX1" prefix="INVTX1" is_default="true">
<design_technology type="cmos" topology="inverter" size="1"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" 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="buf4" prefix="buf4" is_default="false">
<design_technology type="cmos" topology="buffer" size="1" num_level="2" f_per_stage="4"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" 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="tap_buf4" prefix="tap_buf4" is_default="false">
<design_technology type="cmos" topology="buffer" size="1" num_level="3" f_per_stage="4"/>
<port type="input" prefix="in" size="1"/>
<port type="output" prefix="out" 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="pass_gate" name="TGATE" prefix="TGATE" is_default="true">
<design_technology type="cmos" topology="transmission_gate" nmos_size="1" pmos_size="2"/>
<input_buffer exist="false"/>
<output_buffer exist="false"/>
<port type="input" prefix="in" size="1"/>
<port type="input" prefix="sel" size="1"/>
<port type="input" prefix="selb" size="1"/>
<port type="output" prefix="out" size="1"/>
<delay_matrix type="rise" in_port="in sel selb" out_port="out">
10e-12 5e-12 5e-12
</delay_matrix>
<delay_matrix type="fall" in_port="in sel selb" out_port="out">
10e-12 5e-12 5e-12
</delay_matrix>
</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_2level" prefix="mux_2level" dump_structural_verilog="true">
<design_technology type="cmos" structure="multi_level" num_level="2" add_const_input="true" const_input_val="1"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<!--mux2to1 subckt_name="mux2to1"/-->
<pass_gate_logic circuit_model_name="TGATE"/>
<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_2level_tapbuf" prefix="mux_2level_tapbuf" dump_structural_verilog="true">
<design_technology type="cmos" structure="multi_level" num_level="2" add_const_input="true" const_input_val="1"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="tap_buf4"/>
<!--mux2to1 subckt_name="mux2to1"/-->
<pass_gate_logic circuit_model_name="TGATE"/>
<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_1level_tapbuf" prefix="mux_1level_tapbuf" is_default="true" dump_structural_verilog="true">
<design_technology type="cmos" structure="one_level" add_const_input="true" const_input_val="1"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="tap_buf4"/>
<!--mux2to1 subckt_name="mux2to1"/-->
<pass_gate_logic circuit_model_name="TGATE"/>
<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="static_dff" prefix="dff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<pass_gate_logic circuit_model_name="TGATE"/>
<port type="input" prefix="D" size="1"/>
<port type="input" prefix="set" size="1" is_global="true" default_val="0" is_set="true"/>
<port type="input" prefix="reset" size="1" is_global="true" default_val="0" is_reset="true"/>
<port type="output" prefix="Q" size="1"/>
<port type="clock" prefix="clk" size="1" is_global="true" default_val="0" />
</circuit_model>
<circuit_model type="lut" name="lut5" prefix="lut5" dump_structural_verilog="true">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<lut_input_inverter exist="true" circuit_model_name="INVTX1"/>
<lut_input_buffer exist="true" circuit_model_name="buf4"/>
<pass_gate_logic circuit_model_name="TGATE"/>
<port type="input" prefix="in" size="5"/>
<port type="output" prefix="out" size="1"/>
<port type="sram" prefix="sram" size="32"/>
</circuit_model>
<!--Scan-chain DFF subckt ports should be defined as <D> <Q> <Qb> <CLK> <RESET> <SET> -->
<circuit_model type="ccff" name="sc_dff_compact" prefix="scff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<pass_gate_logic circuit_model_name="TGATE"/>
<port type="input" prefix="pReset" size="1" is_global="true" default_val="0" is_reset="true" is_prog="true"/>
<port type="input" prefix="D" size="1"/>
<port type="output" prefix="Q" size="1"/>
<port type="output" prefix="Qb" size="1"/>
<port type="clock" prefix="prog_clk" size="1" is_global="true" default_val="0" is_prog="true"/>
</circuit_model>
<circuit_model type="iopad" name="iopad" prefix="iopad" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/io.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/io.v">
<design_technology type="cmos"/>
<input_buffer exist="true" circuit_model_name="INVTX1"/>
<output_buffer exist="true" circuit_model_name="INVTX1"/>
<pass_gate_logic circuit_model_name="TGATE"/>
<port type="inout" prefix="pad" size="1"/>
<port type="sram" prefix="en" size="1" mode_select="true" circuit_model_name="sc_dff_compact" default_val="1"/>
<port type="input" prefix="outpad" size="1"/>
<port type="output" prefix="inpad" size="1"/>
</circuit_model>
</circuit_library>
<configuration_protocol>
<organization type="scan_chain" circuit_model_name="sc_dff_compact"/>
</configuration_protocol>
<connection_block>
<switch name="ipin_cblock" circuit_model_name="mux_2level_tapbuf"/>
</connection_block>
<switch_block>
<switch name="0" circuit_model_name="mux_2level_tapbuf"/>
</switch_block>
<routing_segment>
<segment name="L4" circuit_model_name="chan_segment"/>
</routing_segment>
<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="iopad" 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">
<!-- Binding interconnect to circuit models as their physical implementation, if not defined, we use the default model -->
<interconnect name="crossbar" circuit_model_name="mux_2level"/>
</pb_type>
<pb_type name="clb.fle[n1_lut6].ble6.lut6" circuit_model_name="lut6"/>
<pb_type name="clb.fle[n1_lut6].ble6.ff" circuit_model_name="static_dff"/>
<!-- End physical pb_type binding in complex block IO -->
</pb_type_annotations>
</openfpga_architecture>
<openfpga_simulation_setting>
<clock_setting>
<operating frequency="200e6" num_cycles="auto" slack="0.2"/>
<programming frequency="10e6"/>
</clock_setting>
<simulator_option>
<operating_condition temperature="25"/>
<output_log verbose="false" captab="false"/>
<accuracy type="abs" value="1e-13"/>
<runtime fast_simulation="true"/>
</simulator_option>
<monte_carlo num_simulation_points="2"/>
<measurement_setting>
<slew>
<rise upper_thres_pct="0.95" lower_thres_pct="0.05"/>
<fall upper_thres_pct="0.05" lower_thres_pct="0.95"/>
</slew>
<delay>
<rise input_thres_pct="0.5" output_thres_pct="0.5"/>
<fall input_thres_pct="0.5" output_thres_pct="0.5"/>
</delay>
</measurement_setting>
<stimulus>
<clock>
<rise slew_type="abs" slew_time="20e-12" />
<fall slew_type="abs" slew_time="20e-12" />
</clock>
<input>
<rise slew_type="abs" slew_time="25e-12" />
<fall slew_type="abs" slew_time="25e-12" />
</input>
</stimulus>
</openfpga_simulation_setting>

8
openfpga/test_script/s298.openfpga Normal file
View File

@ -0,0 +1,8 @@
# Run VPR for the s298 design
vpr ./test_vpr_arch/k6_N10_40nm.xml ./test_blif/s298.blif
# Read OpenFPGA architecture definition
read_openfpga_arch -f ./test_openfpga_arch/k6_N10_40nm_openfpga.xml
# Annotate the OpenFPGA architecture to VPR data base
link_openfpga_arch

308
openfpga/test_vpr_arch/k6_N10_40nm.xml Normal file
View File

@ -0,0 +1,308 @@
<!--
Architecture with no fracturable LUTs
- 40 nm technology
- General purpose logic block:
K = 6, N = 10
- 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"/>
<clock name="clock" 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 io.clock</loc>
<loc side="top">io.outpad io.inpad io.clock</loc>
<loc side="right">io.outpad io.inpad io.clock</loc>
<loc side="bottom">io.outpad io.inpad io.clock</loc>
</pinlocations>
</tile>
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I" num_pins="40" equivalent="full"/>
<output name="O" num_pins="10" equivalent="instance"/>
<clock name="clk" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="spread"/>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout>
<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>
</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"/>
<clock name="clock" 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" 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>
<!-- 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="40" equivalent="full"/>
<output name="O" num_pins="10" equivalent="instance"/>
<clock name="clk" num_pins="1"/>
<!-- Describe basic logic element.
Each basic logic element has a 6-LUT that can be optionally registered
-->
<pb_type name="fle" num_pb="10">
<input name="in" num_pins="6"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- 6-LUT mode definition begin -->
<mode name="n1_lut6">
<!-- Define 6-LUT mode -->
<pb_type name="ble6" num_pb="1">
<input name="in" num_pins="6"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut6" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="6" 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="lut6.in" out_port="lut6.out">
261e-12
261e-12
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="ble6.in" output="lut6[0:0].in"/>
<direct name="direct2" input="lut6.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble6" in_port="lut6.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble6.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut6.out" output="ble6.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut6.out" out_port="ble6.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble6.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble6.in"/>
<direct name="direct2" input="ble6.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble6.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[9:0].out" output="fle[9:0].in">
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[9:0].in"/>
<delay_constant max="75e-12" in_port="fle[9:0].out" out_port="fle[9:0].in"/>
</complete>
<complete name="clks" input="clb.clk" output="fle[9:0].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[9:0].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>
<power>
<local_interconnect C_wire="2.5e-10"/>
<mux_transistor_size mux_transistor_size="3"/>
<FF_size FF_size="4"/>
<LUT_transistor_size LUT_transistor_size="4"/>
</power>
<clocks>
<clock buffer_size="auto" C_wire="2.5e-10"/>
</clocks>
</architecture>

351
openfpga/test_vpr_arch/k6_frac_N10_40nm.xml Normal file
View File

@ -0,0 +1,351 @@
<!--
Flagship Heterogeneous Architecture (No Carry Chains) for VTR 7.0.
- 40 nm technology
- General purpose logic block:
K = 6, N = 10, fracturable 6 LUTs (can operate as one 6-LUT or two 5-LUTs with all 5 inputs shared)
with optionally registered outputs
- 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.
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>
</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"/>
<clock name="clock" 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 io.clock</loc>
<loc side="top">io.outpad io.inpad io.clock</loc>
<loc side="right">io.outpad io.inpad io.clock</loc>
<loc side="bottom">io.outpad io.inpad io.clock</loc>
</pinlocations>
</tile>
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I" num_pins="40" equivalent="full"/>
<output name="O" num_pins="20" 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="spread"/>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout>
<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>
</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 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"/>
<clock name="clock" num_pins="1"/>
<!-- 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="40" equivalent="full"/>
<output name="O" num_pins="20" equivalent="none"/>
<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="10">
<input name="in" num_pins="6"/>
<output name="out" num_pins="2"/>
<clock name="clk" num_pins="1"/>
<!-- Dual 5-LUT mode definition begin -->
<mode name="n2_lut5">
<pb_type name="lut5inter" num_pb="1">
<input name="in" num_pins="5"/>
<output name="out" num_pins="2"/>
<clock name="clk" num_pins="1"/>
<pb_type name="ble5" num_pb="2">
<input name="in" num_pins="5"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define the LUT -->
<pb_type name="lut5" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="5" 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="lut5.in" out_port="lut5.out">
235e-12
235e-12
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="ble5.in[4:0]" output="lut5[0:0].in[4:0]"/>
<direct name="direct2" input="lut5[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="ble5" in_port="lut5[0:0].out" out_port="ff[0:0].D"/>
</direct>
<direct name="direct3" input="ble5.clk" output="ff[0:0].clk"/>
<mux name="mux1" input="ff[0:0].Q lut5.out[0:0]" output="ble5.out[0:0]">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut5.out[0:0]" out_port="ble5.out[0:0]"/>
<delay_constant max="45e-12" in_port="ff[0:0].Q" out_port="ble5.out[0:0]"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="lut5inter.in" output="ble5[0:0].in"/>
<direct name="direct2" input="lut5inter.in" output="ble5[1:1].in"/>
<direct name="direct3" input="ble5[1:0].out" output="lut5inter.out"/>
<complete name="complete1" input="lut5inter.clk" output="ble5[1:0].clk"/>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in[4:0]" output="lut5inter.in"/>
<direct name="direct2" input="lut5inter.out" output="fle.out"/>
<direct name="direct3" input="fle.clk" output="lut5inter.clk"/>
</interconnect>
</mode>
<!-- Dual 5-LUT mode definition end -->
<!-- 6-LUT mode definition begin -->
<mode name="n1_lut6">
<!-- Define 6-LUT mode -->
<pb_type name="ble6" num_pb="1">
<input name="in" num_pins="6"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut6" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="6" 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="lut6.in" out_port="lut6.out">
261e-12
261e-12
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="ble6.in" output="lut6[0:0].in"/>
<direct name="direct2" input="lut6.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble6" in_port="lut6.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble6.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut6.out" output="ble6.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut6.out" out_port="ble6.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble6.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble6.in"/>
<direct name="direct2" input="ble6.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble6.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[9:0].out" output="fle[9:0].in">
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[9:0].in"/>
<delay_constant max="75e-12" in_port="fle[9:0].out" out_port="fle[9:0].in"/>
</complete>
<complete name="clks" input="clb.clk" output="fle[9:0].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[9:0].out[0:0]" output="clb.O[9:0]"/>
<direct name="clbouts2" input="fle[9:0].out[1:1]" output="clb.O[19:10]"/>
</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>
<power>
<local_interconnect C_wire="2.5e-10"/>
<mux_transistor_size mux_transistor_size="3"/>
<FF_size FF_size="4"/>
<LUT_transistor_size LUT_transistor_size="4"/>
</power>
<clocks>
<clock buffer_size="auto" C_wire="2.5e-10"/>
</clocks>
</architecture>

1438
openfpga/test_vpr_arch/k6_frac_N10_frac_chain_depop50_mem32K_40nm.xml Normal file
View File

File diff suppressed because it is too large Load Diff