Changes between Initial Version and Version 1 of Workshops/IntroToHpc2015/Programming/CodeDebugging

Timestamp:

10/12/15 16:05:04 (9 years ago)

Author:

pdejesus

Comment:

—

Workshops/IntroToHpc2015/Programming/CodeDebugging

@@ +1 @@
+[[PageOutline]]
+= Code Debugging =
+Ideally, code should be debuged on your desktop computer before being moved to a cluster environment. There are a number of debugging techniques, which you can learn from the internet.
+
+== print ==
+Insert 'print' into the source code.
+
+in C/C++
+{{{#!c 
+ /* check */
+#ifdef DEBUG
+  if (info == 0) printf("successfully done\n"); 
+#endif
+}}}
+
+in Fortran
+{{{#!fortran
+#ifdef debug
+    if (info == 0) then
+       print *,"successfully done"
+    endif
+#endif
+}}}
+
+Compile with ''-DDEBUG'' option
+{{{
+icc -g -pg -DDEBUG -c stokeslet2d.c
+}}}
+
+Makefile
+{{{#!make
+#
+# CCS WORKSHOP
+# Stokes Flow in a Cavity
+#
+# Makefile
+#
+#
+TARGET = ex32s ex32m
+#
+ALL: $(TARGET)
+#
+CC = icc
+ 
+#CFLAGS = -O3
+CFLAGS = -g -pg -DDEBUG
+#
+#
+#
+SRC_EX32c = ex32.c stokeslet2d.c gmres.c
+#
+#
+MKL_SQ_LIBS = -L$(MKLROOT)/lib/intel64/ \
+        -I$(MKLROOT)/mkl/include \
+        -Wl,--start-group \
+        $(MKLROOT)/lib/intel64/libmkl_intel_lp64.a \
+        $(MKLROOT)/lib/intel64/libmkl_sequential.a \
+        $(MKLROOT)/lib/intel64/libmkl_core.a \
+        -Wl,--end-group \
+        -lpthread
+#
+MKL_MT_LIBS = -L$(MKLROOT)/lib/intel64/ \
+        -I$(MKLROOT)/mkl/include \
+        -Wl,--start-group \
+        $(MKLROOT)/lib/intel64/libmkl_intel_lp64.a \
+        $(MKLROOT)/lib/intel64/libmkl_intel_thread.a \
+        $(MKLROOT)/lib/intel64/libmkl_core.a \
+        -Wl,--end-group \
+        -liomp5 \
+        -lpthread
+#
+#
+#
+OBJ_EX32c = $(SRC_EX32c:.c=.o)
+#
+#
+ex32s : $(OBJ_EX32c)
+        $(CC) $(CFLAGS) -o $@ $(OBJ_EX32c) $(MKL_SQ_LIBS)
+ 
+ex32m : $(OBJ_EX32c)
+        $(CC) $(CFLAGS) -o $@ $(OBJ_EX32c) $(MKL_MT_LIBS)
+ 
+#
+#
+%.o : %.c
+        $(CC) $(CFLAGS) -c $<
+ 
+#
+clean:  
+        rm -f *.o $(TARGET)
+}}}
+
+== GDB ==
+GDB is the standard debugger.
+[http://www.gnu.org/software/gdb/documentation/]
+
+To debug with '''GDB''', submit an interactive job. [[https://wiki.hpc.tulane.edu/trac/wiki/cypress/using#SubmittingInteractiveJobs|See here]]
+
+Compiling with '''-g''' option
+{{{
+ icc -g -pg -DDEBUG -c stokeslet2d.c
+}}}
+run '''gdb'''
+{{{
+user@host>gdb ./ex32s 
+GNU gdb (GDB) Red Hat Enterprise Linux (7.2-56.el6)
+Copyright (C) 2010 Free Software Foundation, Inc.
+License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
+This is free software: you are free to change and redistribute it.
+There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
+and "show warranty" for details.
+This GDB was configured as "x86_64-redhat-linux-gnu".
+For bug reporting instructions, please see:
+<http://www.gnu.org/software/gdb/bugs/>...
+Reading symbols from /ccs-autofs/u01/fuji/LabWork/FlowInCavity/ex32s...done.
+(gdb) 
+}}}
+
+show source by command, list '''line#'''
+{{{
+(gdb) list 44
+39          printf("Usage:%s [Depth of Cavity]\n",argv[0]);
+40          exit(-1);
+41        }
+42      
+43        /* get inputed depth */
+44        dp = atof(argv[1]);
+45      
+46        /* # of particles in depth */
+47        numpdepth = (int)(dp / EPSILON + 0.5);
+48        
+(gdb)
+}}}
+set breakpoint by command, '''b line#'''
+{{{
+(gdb) b 47
+Breakpoint 1 at 0x4044c2: file ex32.c, line 47.
+(gdb) 
+}}}
+'''run [command line option]'''
+{{{
+(gdb) run 5
+Starting program: /ccs-autofs/u01/fuji/LabWork/FlowInCavity/ex32s 1
+[Thread debugging using libthread_db enabled]
+
+Breakpoint 1, main (argc=2, argv=0x7fffffffd5c8) at ex32.c:47
+47        numpdepth = (int)(dp / EPSILON + 0.5);
+Missing separate debuginfos, use: debuginfo-install glibc-2.12-1.80.el6_3.3.x86_64
+(gdb) 
+}}}
+
+print values
+{{{
+(gdb) p dp
+$1 = 5
+(gdb) p numpdepth
+$2 = 0
+(gdb) 
+}}}
+
+continue one step
+{{{
+(gdb) next
+50        numpwidth = (int)(1.0 / EPSILON + 0.5);
+(gdb) p numpdepth
+$3 = 1000
+(gdb) 
+}}}
+
+exit
+{{{
+(gdb) quit
+A debugging session is active.
+
+        Inferior 1 [process 6222] will be killed.
+
+Quit anyway? (y or n) y
+}}}
+
+== Valgrind ==
+[http://valgrind.org/]
+
+''Valgrind'' tools can detect many memory management and threading bugs, and profile your programs in detail.
+
+
+=== Detect Invalid Access  ===
+
+Example code: (this code has a bug)
+{{{#!c
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+char * foo() {
+  char a[200];
+  strcpy(a, "hello world cup\n");
+  return a;
+}
+
+int main() {
+  char * a = foo();
+  char c = a[0];
+  printf("a[0] = %c\n", c);
+  printf("a = %s\n", a);
+  return 0;
+}
+}}}
+
+Start an interactive session,
+{{{#!bash
+[fuji@cypress2 ~]$ idev -c 1 --gres=mic:0
+Requesting 1 node(s)  task(s) to workshop queue of workshop partition
+1 task(s)/node, 1 cpu(s)/task, mic:0 MIC device(s)/node
+Time: 0 (hr) 60 (min).
+Submitted batch job 52605
+JOBID=52605 begin on cypress01-089
+--> Creating interactive terminal session (login) on node cypress01-089.
+--> You have 0 (hr) 60 (min).
+Last login: Wed Aug 19 21:05:45 2015 from cypress2.cm.cluster
+[fuji@cypress01-089 ~]$
+}}}
+compile and run,
+{{{#!bash
+[fuji@cypress01-089 ~]$ module load intel-psxe/2015-update1
+[fuji@cypress01-089 ~]$ icc off_stack.c
+off_stack.c(8): warning #1251: returning pointer to local variable
+    return a;
+           ^
+
+[fuji@cypress01-089 ~]$ ./a.out
+a[0] = h
+a = hello world cup
+}}}
+
+{{{#!bash
+[fuji@cypress01-089 ~]$ icc -O0 -g off_stack.c
+off_stack.c(8): warning #1251: returning pointer to local variable
+    return a;
+           ^
+
+[fuji@cypress01-089 ~]$ valgrind ./a.out
+==33367== Memcheck, a memory error detector
+==33367== Copyright (C) 2002-2012, and GNU GPL'd, by Julian Seward et al.
+==33367== Using Valgrind-3.8.1 and LibVEX; rerun with -h for copyright info
+==33367== Command: ./a.out
+==33367==
+==33367== Invalid read of size 1
+==33367==    at 0x4005C5: main (off_stack.c:13)
+==33367==  Address 0x7feffdd50 is just below the stack ptr.  To suppress, use: --workaround-gcc296-bugs=yes
+==33367==
+a[0] = h
+a =
+==33367==
+==33367== HEAP SUMMARY:
+==33367==     in use at exit: 0 bytes in 0 blocks
+==33367==   total heap usage: 0 allocs, 0 frees, 0 bytes allocated
+==33367==
+==33367== All heap blocks were freed -- no leaks are possible
+==33367==
+==33367== For counts of detected and suppressed errors, rerun with: -v
+==33367== ERROR SUMMARY: 1 errors from 1 contexts (suppressed: 6 from 6)
+[fuji@cypress01-089 ~]$
+}}}
+
+=== Detect Uninitialized Data Access  ===
+
+Example code: (this code has a bug)
+{{{#!c
+#include <stdio.h>
+#include <stdlib.h>
+
+int main() {
+  double * p = malloc(sizeof(double) * 10);
+  if (p[0] < 1) {
+    printf("p[0] < 1\n");
+  } else {
+    printf("p[1] >= 1\n");
+  }
+  return 0;
+}
+}}}
+
+{{{#!bash
+[fuji@cypress01-089 Valgrind]$ icc uninit.c
+[fuji@cypress01-089 Valgrind]$ ./a.out
+p[0] < 1
+[fuji@cypress01-089 Valgrind]$ icc -O0 -g uninit.c
+[fuji@cypress01-089 Valgrind]$ valgrind ./a.out
+==34643== Memcheck, a memory error detector
+==34643== Copyright (C) 2002-2012, and GNU GPL'd, by Julian Seward et al.
+==34643== Using Valgrind-3.8.1 and LibVEX; rerun with -h for copyright info
+==34643== Command: ./a.out
+==34643==
+==34643== Conditional jump or move depends on uninitialised value(s)
+==34643==    at 0x4005A9: main (uninit.c:6)
+==34643==
+==34643== Conditional jump or move depends on uninitialised value(s)
+==34643==    at 0x4005AB: main (uninit.c:6)
+==34643==
+p[0] < 1
+==34643==
+==34643== HEAP SUMMARY:
+==34643==     in use at exit: 80 bytes in 1 blocks
+==34643==   total heap usage: 1 allocs, 0 frees, 80 bytes allocated
+==34643==
+==34643== LEAK SUMMARY:
+==34643==    definitely lost: 80 bytes in 1 blocks
+==34643==    indirectly lost: 0 bytes in 0 blocks
+==34643==      possibly lost: 0 bytes in 0 blocks
+==34643==    still reachable: 0 bytes in 0 blocks
+==34643==         suppressed: 0 bytes in 0 blocks
+==34643== Rerun with --leak-check=full to see details of leaked memory
+==34643==
+==34643== For counts of detected and suppressed errors, rerun with: -v
+==34643== Use --track-origins=yes to see where uninitialised values come from
+==34643== ERROR SUMMARY: 2 errors from 2 contexts (suppressed: 6 from 6)
+}}}
+
+
+=== Detect Memory Leaks  ===
+
+Example code: (this code has a bug)
+
+{{{#!c++
+#include <iostream>
+#include <cstring>
+
+char * foo() {
+  char *a = new char[200];
+  std::strcpy(a, "hello workshop");
+  return a;
+}
+
+int main() {
+  char * a = foo();
+  char * b = foo();
+  std::cout << "a = " <<  a << std::endl;
+  std::cout << "b = " <<  b << std::endl;
+  return 0;
+}
+}}}
+
+{{{#!bash
+[fuji@cypress1 TestCodes]$ icpc -g mleak.cpp
+[fuji@cypress1 TestCodes]$ valgrind --leak-check=full ./a.out
+==10272== Memcheck, a memory error detector
+==10272== Copyright (C) 2002-2012, and GNU GPL'd, by Julian Seward et al.
+==10272== Using Valgrind-3.8.1 and LibVEX; rerun with -h for copyright info
+==10272== Command: ./a.out
+==10272==
+a = hello workshop
+b = hello workshop
+==10272==
+==10272== HEAP SUMMARY:
+==10272==     in use at exit: 400 bytes in 2 blocks
+==10272==   total heap usage: 2 allocs, 0 frees, 400 bytes allocated
+==10272==
+==10272== 200 bytes in 1 blocks are definitely lost in loss record 1 of 2
+==10272==    at 0x4C28192: operator new[](unsigned long) (vg_replace_malloc.c:363)
+==10272==    by 0x4009D8: foo() (mleak.cpp:5)
+==10272==    by 0x400A0F: main (mleak.cpp:11)
+==10272==
+==10272== 200 bytes in 1 blocks are definitely lost in loss record 2 of 2
+==10272==    at 0x4C28192: operator new[](unsigned long) (vg_replace_malloc.c:363)
+==10272==    by 0x4009D8: foo() (mleak.cpp:5)
+==10272==    by 0x400A20: main (mleak.cpp:12)
+==10272==
+==10272== LEAK SUMMARY:
+==10272==    definitely lost: 400 bytes in 2 blocks
+==10272==    indirectly lost: 0 bytes in 0 blocks
+==10272==      possibly lost: 0 bytes in 0 blocks
+==10272==    still reachable: 0 bytes in 0 blocks
+==10272==         suppressed: 0 bytes in 0 blocks
+==10272==
+==10272== For counts of detected and suppressed errors, rerun with: -v
+==10272== ERROR SUMMARY: 2 errors from 2 contexts (suppressed: 6 from 6)
+}}}
+
+== Intel® Inspector XE ==
+Memory and Thread Debugger: 
+* Debug memory errors like leaks and allocation errors and threading errors like data races and deadlocks.
+
+==== Setting Environment and Compiling your code ====
+Load module to setup Intel compilers and tools.
+{{{#!bash
+[fuji@cypress1 ~]$ module load intel-psxe/2015-update1
+}}}
+Compiling codes with '-g' option to tells the compiler to generate full debugging information in the object file.
+{{{#!bash
+[fuji@cypress1 ~]$ icc -g -o mytest mytest.c
+}}}
+
+==== Run and Collect Information ====
+Start an interactive job,
+{{{#!bash
+[fuji@cypress1 ~]$ idev
+}}}
+To collect information, run the code, for example,
+{{{#!bash
+[fuji@cypress1 ~]$ inspxe-cl -collect=mi2 -app-working-dir=$PWD -result-dir=$PWD/results $PWD/mytest
+}}}
+
+'''-collect=''' options
+
+Memory error analysis types
+||= mi1 =||  Detect memory leaks ||
+||= mi2 =||  Detect memory leaks and memory access problems ||
+||= mi3 =||  Find locations of memory leaks and memory access problems ||
+
+Threading error analysis_types
+||= ti1 =||  Detect deadlocks ||
+||= ti2 =||  Detect deadlocks and data races ||
+||= ti3 =||  Find locations of deadlocks and data races ||
+
+To show results, for example, 
+{{{#!bash
+[fuji@cypress1 ~]$ inspxe-cl -R problems -r $PWD/results
+}}}
+See [https://software.intel.com/en-us/node/528226 here] for details.
+
+[[Inspector Brief Tutorial]]
+
+== Intel® Advisor XE ==
+Threading design and prototyping tool for software architects:
+* Analyze, design, tune and check your threading design before implementation
+* Explore and test threading options without disrupting normal development
+* Predict threading errors & performance scaling on systems with more cores
+
+=== Survey ===
+Survey the application to determine hotspots. Typically an optimized
+ (non-debug) version of the application is used when surveying an application.
+
+Run and Collect info.
+{{{#!bash
+$ icc -g -O3 mycode.c
+$ advixe-cl --collect survey --project-dir ./advi ./a.out
+}}}
+
+Show report
+{{{#!bash
+$ advixe-cl --report survey --project-dir ./advi ./a.out
+}}}
+
+=== Add Annotations ===
+Add annotations to the application source code, and rebuild the application.
+ Please see the Getting Started Tutorial for more information.
+
+For C/C++
+{{{#!c
+#include "advisor-annotate.h"
+.....
+    ANNOTATE_SITE_BEGIN(sitename1);
+    for ( .... 
+    {
+        ANNOTATE_TASK_BEGIN(taskname1);
+        ...
+        ANNOTATE_TASK_END();
+    }
+    ANNOTATE_SITE_END();
+}}}
+
+Fortran
+{{{#!fortran
+use advisor_annotate
+.....
+call annotate_site_begin(sitename1)
+do .....
+    call annotate_task_begin(taskname1)
+    ....
+    call annotate_task_end()
+enddo
+call annotate_site_end()
+}}}
+
+=== Suitability ===
+Collect suitability data. Note that annotations must be present in the source
+ code for this collection to be successful. Typically an optimized (non-debug) version
+ of the application is used when collecting suitability data.
+
+{{{#!bash
+$ icc -g -O3 mycode.c -I $ADVISOR_XE_2015_DIR/include
+$ advixe-cl --collect suitability --project-dir ./advi ./a.out
+}}}
+
+{{{#!bash
+$ advixe-cl --report suitability --project-dir ./advi ./a.out
+}}}
+
+
+=== Correctness ===
+Collect correctness data. Note that annotations must be present in the source
+ code for this collection to be successful. Typically an application with debug symbols
+ is used when collecting correctness data.
+
+{{{#!bash
+$  icc -g -O0 mycode.c
+$ advixe-cl --collect correctness --project-dir ./advi ./a.out
+}}}
+
+{{{#!bash
+$ advixe-cl --report correctness --project-dir ./advi ./a.out
+}}}
+
+Display a list of annotations present.
+{{{#!bash
+advixe-cl --report annotations --project-dir ./advi ./a.out
+}}}
+Update the application using the chosen parallel coding constructs. Rebuild the application and test.
+
+[[Advisor Brief Tutorial]]
+
+== Intel® VTune™ Amplifier 2015 ==
+* Intuitive CPU & GPU performance tuning, multi-core scalability, bandwidth and more
+* Quick performance insight with advanced data visualization
+* Automate regression tests and collect data remotely 
+
+Compiling codes with '-g' option to tells the compiler to generate full debugging information in the object file.
+{{{#!bash
+[fuji@cypress1 ~]$ icc -g -o mytest mytest.c
+}}}
+
+==== Run and Collect Information ====
+Start an interactive job,
+{{{#!bash
+[fuji@cypress1 ~]$ idev
+}}}
+To collect information, run the code, for example,
+{{{#!bash
+[fuji@cypress1 ~]$ amplxe-cl -collect hotspot ./mytest
+}}}
+This will create a directory like '''r000hs'''.
+
+'''-collect ''' options
+
+||= concurrency =||  Concurrency analysis ||
+||= hotspots =||  Hotspots analysis ||
+||= lightweight-hotspots =||  Lightweight Hotspots analysis ||
+||= locksandwaits =||  Locks and Waits analysis ||
+
+To show results, for example,
+{{{#!bash
+[fuji@cypress1 ~]$ amplxe-cl -report hotspot -r r000hs
+}}}
+
+'''-report ''' options
+
+||= summary =||  Display data for the overall performance of the target. ||
+||= hotspots =||  Display functions with the highest CPU time. ||
+||= wait-time =||  Display Wait time. ||
+||= perf =||  Display performance data for each module of the target. ||
+||= perf-detail =||  Display performance data for each function of the target. ||
+||= callstacks =||  Display CPU or Wait time for call stacks. ||
+||= top-down =||  Display a call tree for your target application and provide CPU and Wait time for each function. ||
+||= gprof-cc =|| Display CPU or wait time in the gprof-like format. ||
+
+[[VTune Brief Tutorial]]