Is Windows hard to use?
In my blog entry of July 14, 2013 I commented on Microsoft efforts to re-invent itself. It did not work. Mr Ballmer, 57, announced he will resign "within a year." He is worth $11 billions. Microsoft made all their money by copying the Apple MacIntosh interface, call it Windows 3.0 (which had a general system failure every 30 seconds or so), then 3.1 and made a computer accessible to anyone from kindergarten to an old age home. People will put up with anything, as long as it was easy to use. It made everyone feel good.
The user experience (UX) is what made Windows, Windows.
We live in 2013, when expanding the desktop capabilities to reach clouds and clusters is a must. But to do so, Microsoft takes a step back. It trades simplicity for complexity. It destroys the very reason Windows was Windows and successful.
I, personally, I would take the entire board of Microsoft to watch the movie Jobs. It does not matter whether the movie is good or bad. It doesn't matter whether one likes Ashton Kuchner or not. It is the spirit on this movie that Microsoft must absorb and apply it in their unique way of doing things.
Below is just a sample of the know-how needed to use Windows in Performance Computing.
Oh My God!
The user experience (UX) is what made Windows, Windows.
We live in 2013, when expanding the desktop capabilities to reach clouds and clusters is a must. But to do so, Microsoft takes a step back. It trades simplicity for complexity. It destroys the very reason Windows was Windows and successful.
I, personally, I would take the entire board of Microsoft to watch the movie Jobs. It does not matter whether the movie is good or bad. It doesn't matter whether one likes Ashton Kuchner or not. It is the spirit on this movie that Microsoft must absorb and apply it in their unique way of doing things.
Oh My God!
I have a cluster with local IP addresses as 192.168.1.1~192.168.1.10 (node name: N01~N10) and every node has the Windows 7 64bit installed. I built the program by VS2010 (C++)+Intel Fortran+Intel MPI. Currently I launch my program by Intel MPI with the following command:mpiexec -wdir Z:\ -hosts 10 n01 12 n02 12 n03 12 n04 12 n05 12 n06 12 n07 12 n08 12 n09 12 n10 12 -mapall Z:\testNow the problem is that with the same parameters to program 'test', sometimes the program test is OK but sometimes it has the following error message:Fatal error in MPI_Init: Other MPI error, error stack:
MPIR_Init_thread(659)......................:
MPID_Init(195).............................: channel initialization failed
MPIDI_CH3_Init(106)........................:
MPID_nem_tcp_post_init(344)................:
MPID_nem_newtcp_module_connpoll(3099)......:
recv_id_or_tmpvc_info_success_handler(1328): read from socket failed - No error
Fatal error in MPI_Init: Other MPI error, error stack:
MPIR_Init_thread(659)................:
MPID_Init(195).......................: channel initialization failed
MPIDI_CH3_Init(106)..................:
MPID_nem_tcp_post_init(344)..........:
MPID_nem_newtcp_module_connpoll(3099):
gen_read_fail_handler(1194)..........: read from socket failed - The specified n
etwork name is no longer available.or the following error message:*********** Warning ************
Unable to map \\n01\Debug. (error 71)
*********** Warning ************
launch failed: CreateProcess(\\n01\Debug\directional\fem) on 'N09' failed, error
2 - The system cannot find the file specified.
launch failed: CreateProcess(\\n01\Debug\directional\fem) on 'N07' failed, error
2 - The system cannot find the file specified.
launch failed: CreateProcess(\\n01\Debug\directional\fem) on 'N02' failed, error
2 - The system cannot find the file specified.
*********** Warning ************
Unable to map \\n01\Debug. (error 71)I don't know what could lead to these problems.
Comments