CTools:ICI:Projects:GSOC09:Function cloning and program instrumentation

From cTuning.org

Revision as of 08:59, 13 August 2009 (view source) Lpeng (Talk | contribs) ← Older edit		Revision as of 09:13, 13 August 2009 (view source) Lpeng (Talk | contribs) Newer edit →
Line 184:		Line 184:
	=== Work flow ===		=== Work flow ===
-	[[Image:Instrumentation.jpg‎]]	+	[[Image:Instrument_new.png‎]]
	=== run-time monitoring routines based on PAPI ===		=== run-time monitoring routines based on PAPI ===

---

Revision as of 09:13, 13 August 2009

Google Summer of Code 2009: Generic function cloning.

Liang Peng (ICT, China)

Based on Run-time Function Adaptation for Statically-Compiled Programs based on function multiversioning and FunctionSpecificOpt, we enabled generic function cloning with low-overhead program behavior monitoring routines. It will enable fine-grain self-tuning binaries and libraries and will increase performance and portability of the static code which is particularly important for rapidly evolving hardware and virtual enviroments.

• GSOC'09 project description
• SVN repository
• cTuning development mailing list

Contents 1 Key data structures 2 New ICI event 3 Function cloning 3.1 Description 3.2 Work flow 3.2.1 Applying different optimization to clone 3.2.2 Selection mechanism and overhead 3.3 TODOs 4 Instrumentation 4.1 Description 4.2 Work flow 4.3 run-time monitoring routines based on PAPI 4.4 Linking external library 4.5 TODOs 5 ICI Adaptation 5.1 Work flow 5.2 Script 5.3 TODOS

Key data structures

Information from xml files for function cloning and instrumentation through Interactive Compilation Interface (ICI).

Defined in both gcc/highlev-plugin-internal.h and gcc/highlev-plugin.h:

typedef struct {
  /* number of function to clone.  */
  int numofclonefun;                           
  /* function name list.  */
  char **clone_function_list;                        
  /* corresponding filename of function.  */
  char **function_filename_list;                   
  /* corresponding number of clones.  */
  int *clones;                                                 
  /* corresponding function name extension for clone.  */
  char **clone_extension;                             
  /* corresponding adaptation function name for current function .  */
  char **adaptation_function;                      
  /* option list for clone .  */
  char **clone_option;                                 
  /* corresponding external libraries.  */
  char *external_libraries;                          
} cloneinfo ;

typedef struct {
  /* number of function to instrument.  */
  int numofinstrfun;
  /* function name list.  */
  char **instrument_function_list;
  /* corresponding filename of function.  */
  char **function_filename_list;
  /* name of function instrument at the begin of function.  */
  char **timer1;
  /* name of function instrument at the end of function.  */
  char **timer2;
  /* flag list whether function is cloned.  */
  char *cloned;
} instrinfo ;

New ICI event

ICI event "load_clone_config"

This event is called at the very beginning of function cloning pass.

• Call back function: load_clone_config () Defined in ICI plugin adapt.c

It gets the current main input filename first using get_feature ("main_input_filename"), then read information from corresponding xml file into datastruct cloneinfo using Mini-XML library.

• ICI event parameter: clone_info A pointer to datastruct cloneinfo

ICI event “load_instr_config”

This event is called at the very beginning of function instrumentation pass.

• Call back function : load_instr_config () Defined in ICI plugin adapt.c

It gets the current main input filename first using get_feature ("main_input_filename"), then read information from corresponding xml file into datastruct instrinfo using Mini-XML library.

• ICI event parameter: clone_info A pointer to datastruct instrinfo

Function cloning

Description

SIMPLE_IPA_PASS "generic_cloning"

This pass performs generic function cloning. It has the ability to create any number of clones for a given function on demand, and aply different fine-grain optimizations for a given clone, also provide mechanism to select different clones at run-time based on optimization scenarios. It's placed before pass_early_local_passes, and we are trying to put it more earlier.

It can be triggered by GCC option -fapi-clone-function and Adapt plugin. The information come from xml files through ICI.

Primary functions

• exec_clone_functions (void)

This is the execute function for gimple_opt_pass pass_clone_functions. It calls event "load_clone_config" to load information needed by cloning, and clone functions that is in the clone list using cgraph_function_versioning, and insert selection mechanism at last.

• add_call_to_clones (struct cgraph_node *orig, int nid)

This function insert selection mechanism, which includes call to clones, call to adaptation function, and build switch statement.

• get_arguments (tree tree_list)

This function get the arguments of original function into tree argv.

• parse_arguments (char *text, unsigned int *argc)

This function parse a option string, and return the number of argument and argument vector.

For example parse string "-O3 -fici -fapi-clone-functions", to int argc=3, char **argv={"-O3","-fici","-fapi-clone-functions"}

• find_clone_options (char *funcname, int *nid)

This function trys to find a option for clone according to clone's name in clone_option list, also records the id.

• is_in_clone_list (const char *func_name, const char *file_name, int *nid)

This function check whether function:func_name in file:file_name needs to be cloned, return true if yes, false if no, nid records the id in the list.

• is_it_clonable (struct cgraph_node *cg_func)

check whether cgraph_node:cg_func is clonable.

• is_it_main (struct cgraph_node *cg_func)

check whether cgraph_node:cg_func is a cgraph node of main/MAIN__.

Work flow

For each cgraph node, we check whether it needs to be cloned.

If yes, clone it using cgraph_function_version, apply options for each clone, and insert selection mechanism into original function.

Applying different optimization to clone

To prevent GCC from bugs, the following flags are not allowed to be changed :

flag_strict_aliasing;

flag_omit_frame_pointer;

flag_pcc_struct_return;

flag_asynchronous_unwind_tables;

Selection mechanism and overhead

Overhead

'Mibench Automotive_susan_e'

Type	average time: O3	average time: clone susan_edges ten times, O3 to all clones	Overhead percent
"real"	8.1588	8.282778	1.5195617%
"user"	7.6258	7.759111	1.7481576%

TODOs

• check and deal with function with name that ends with _clone_%d.
• add support to pragams.
• apply different target optimization to clone.

Instrumentation

Description

SIMPLE_IPA_PASS "instrumentation"

This pass performs function instrumentation. Currently, it has only ability to add function calls. We also have the ability to link external libraries transparently withou Makefile modifications.

This pass also can be triggered by GCC option fapi-instrument-functions and Adapt plugin. Te information come from xml files through ICI.

Primary functions

• exec_instrument_functions (void)

Execute function for instrumentation pass, It calls event "load_instr_config" to load information needed by instrumentation, and instrument a external call at the begin/end of function if function is in the instrument_function_list.

• add_timer_begin (struct cgraph_node *cg_func, char *funname, int cloned)

instrument a external call named funname at the begin of function.

if cloned == '1' , the external call will be inserted after the first gimple statement since this function is cloned before, so the first statement should be call to select function.

• add_timer_end (struct cgraph_node *cg_func, char *funname)

instrument a external call named funname at the end of function.

• is_in_instrument_list (const char *func_name, const char *file_name, int *nid)

This function check whether function:func_name in file:file_name needs to be instrumented, return true if yes, false if no, nid records the id in the list.

• is_it_instrumentable (struct cgraph_node *cg_func)

Check whether cg_func is instrumentable, return true if yes, false if no.

Work flow

run-time monitoring routines based on PAPI

Linking external library

We now have the ability to link external libraries transparently without Makefile modifications. This patch is provided by Yuri Kashnikoff. Currently, we take an enviroment variable ICI_LIBS as input. For example: ICI_LIBS="-Lpath/to/library -lselect".

TODOs

• provide ability to add function calls before or after specific instructions with some program variables as arguments

ICI Adaptation

Work with Fine-grain optimization tuning - another GSOC project by Yuanjie Huang from ICT, China.

Work flow

Three steps compilation:

1: create current XML with the compilation flow and info

> adapt_compile_step.sh 1

all xml files are put in directory $ICI_ADAPT_XMLDIR

2: modify xml files based on an ini format file to turn

on function cloning pass or/and instrumentation pass

> adaptutil.py a.ini $ICI_ADAPT_XMLDIR

xml files in $ICI_ADAPT_XMLDIR will be modified to

enable cloning

option -i: enable instrumentation

option -t <filename>: generate external library template

a.ini controls how to perform function cloning and

instrumentation

(compile the user provided external library)

3: compiles program, clone functions, apply optimization

flags to clones

> adapt_compile_step.sh 2

Script

adaptutil.py

TODOS

• automatically select clones using machine learning techniques based on PAPI and dataset features.
• evaluate different optimizatioins for different datasets and architectures using Continuous Collective Compilation Framework (CCC)