Sponsored Content
Special Forums UNIX and Linux Applications High Performance Computing Memory Barriers for (Ubuntu) Linux (i686) Post 302430141 by gorga on Wednesday 16th of June 2010 06:01:30 PM
Old 06-16-2010
Hi Corona, (small world Smilie)

Quote:
Originally Posted by Corona688
You could try using Linux futexes, which handle the nonblocking case completely in userspace, but I'm not sure what that'd do for memory barriers
I hadn't heard of futexes until you mentioned them, but I did some reading and it seems they still use atomic instructions to update shared variables. In that case I could just use one of GCC's built-in atomic operations like "__sync_fetch_ and_ add" or "__sync_bool_compare_and_swap" as described here...

Atomic Builtins - Using the GNU Compiler Collection (GCC)

The thing with these is they use the asm op-code "lock", which issues a hardware lock on the data-bus effectively locking every other process out of memory. Because I'm writing an application that should be scalable for a system with many cores, I'm discouraged by this.

Quote:
Besides, what if you need to move it to MIPS or something?
Could be a possibility, I believe they have made advances into highly parrallel architectures recently, but the project is at a research stage right now so if I can get it to work well on x86 that's good enough for now. I like the sound of this idea though...

Quote:
Could you perhaps reorder it to put prefix, instance, and state in order in memory? You could assemble the data in an MMX or SSE register, then overwrite several structure members in one assembly op.
This could be a good solution, but I'm not sure how to do it. Do you have any examples of similar code as a guide?

Quote:
One thought does occur to me. How large are these structures?
prefix and instance are both uint32_t while state is an enum (guess that means its a uint32_t also?).
 

4 More Discussions You Might Find Interesting

1. UNIX for Dummies Questions & Answers

Memory-waste in Ubuntu/Debian?

I have 512 mem on this laptop, though 'top' tells me I only have 380. However, Ubuntu is using 288 mb of memory, when I only have 3 terminals, running lynx, vim(for this file) and (of course) top. Considering it I have lynx running a 600 page txt file, which of course would eat some memory but 300?... (0 Replies)
Discussion started by: riwa
0 Replies

2. Linux

i686, x86 64, ppc

Hi, i am quite new to linux. I am interested in fedora linux distro. Fedora Project I dont know which one to choose, either i686, x86 64 or ppc. I prefer a live cd, coz its easy to use. And what is the difference between "Fedora Desktop Live Media" and "Fedora KDE Live Media". (3 Replies)
Discussion started by: superblacksmith
3 Replies

3. Programming

Getting the total virtual memory for ubuntu in c++

Hi guys , i need to get the total virtual memory in ubuntu but i need to write a C++ code for that, any idea on how to go about doing it? any references? or website that i can refer to ? (6 Replies)
Discussion started by: xiaojesus
6 Replies

4. Ubuntu

XP and Linux (Ubuntu) on same disk, Can I install Ubuntu on not-yet partitioned portion of disk?

My PC (Esprimo, 3 yeas old) has one hard drive having 2 partitions C: (80 GB NTFS, XP) and D: (120 GB NTFS, empty) and and a 200 MB area that yet is not-partitioned. I would like to try Ubuntu and to install Ubuntu on the not-partitioned area . The idea is to have the possibility to run... (7 Replies)
Discussion started by: C.Weidemann
7 Replies
ERROR::SDT(7stap)														 ERROR::SDT(7stap)

NAME
error::sdt - <sys/sdt.h> marker failures DESCRIPTION
Systemtap's <sys/sdt.h> probes are modeled after the dtrace USDT API, but are implemented differently. They leave a only a NOP instruction in the userspace program's text segment, and add an ELF note to the binary with metadata. This metadata describes the marker's name and parameters. This encoding is designed to be parseable by multiple tools (not just systemtap: GDB, the GNU Debugger, also contains sup- port). These allow the tools to find parameters and their types, wherever they happen to reside, even without DWARF debuginfo. The reason finding parameters is tricky is because the STAP_PROBE / DTRACE_PROBE markers store an assembly language expression for each op- erand, as a result of use of gcc inline-assembly directives. The compiler is given a broad gcc operand constraint string ("nor") for the operands, which usually works well. Usually, it does not force the compiler to load the parameters into or out of registers, which would slow down an instrumented program. However, some instrumentation sites with some parameters do not work well with the default "nor" con- straint. unresolveable at run-time GCC may emit strings that an assembler could resolve (from the context of compiling the original program), but a run-time tool can- not. For example, the operand string might refer to a label of a local symbol that is not emitted into the ELF object file at all, which leaves no trace for the run-time. Reference to such parameters from within systemtap can result in "SDT asm not understood" errors. too complicated expression GCC might synthesize very complicated assembly addressing modes from complex C data types / pointer expressions. systemtap or gdb may not be able to parse some valid but complicated expressions. Reference to such parameters from within systemtap can result in "SDT asm not understood" errors. overly restrictive constraint GCC might not be able to even compile the original program with the default "nor" constraint due to shortage of registers or other reasons. A compile-time gcc error such as "asm operand has impossible constraints" may result. There are two general workarounds to this family of problems. change the constraints While compiling the original instrumented program, set the STAP_SDT_ARG_CONSTRAINT macro to different constraint strings. See the GCC manual about various options. For example, on many machine architectures, "r" forces operands into registers, and "g" leaves operands essentially unconstrained. revert to debuginfo As long as the instrumented program compiles, it may be fine simply to keep using <sys/sdt.h> but eschew extraction of a few indi- vidual parameters. In the worst case, disable <sys/sdt.h> macros entirely to eschew the compiled-in instrumentation. If DWARF debuginfo was generated and preserved, a systemtap script could refer to the underlying source context variables instead of the positional STAP_PROBE parameters. SEE ALSO
stap(1), stapprobes(3stap), error::dwarf(7stap), http://gcc.gnu.org/onlinedocs/gcc/Constraints.html, http://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation, error::reporting(7stap) ERROR::SDT(7stap)
All times are GMT -4. The time now is 06:16 AM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy