Stack Overflow
Stack Overflow

Questions tagged [smp]

Symmetric multiprocessing

"Symmetric multiprocessing (SMP) involves a multiprocessor computer hardware architecture where two or more identical processors are connected to a single shared main memory and are controlled by a single OS instance. Most common multiprocessor systems today use an SMP architecture." [Source: Wikipedia.]

151 questions
2
votes
1 answer

Why interrupts are globally disabled before connecting ISR?

I'm going through the probe function of the following driver /drivers/net/ethernet/smsc/smsc911x.c Inside the probe function it has been commented that /* Ensure interrupts are globally disabled before connecting ISR */ …
Amit Singh Tomar
  • 8,380
  • 27
  • 120
  • 199
2
votes
1 answer

How to start additional cores on the Raspberry Pi 2 under bare-metal?

The question is rather broad but I couldn't even find a starting point in the ARMv7 ARM, MPCore TRM, GIC architecture manual, ... So please excuse the vagueness. I have a simple bare-metal kernel for the Raspberry Pi 2 that initializes the activity…
Goswin von Brederlow
  • 11,875
  • 2
  • 24
  • 42
2
votes
1 answer

Process Address space with multi-core Systems UMA NUMA

I have a doubt with the concept of Process address space when involving multi core processor architectures, for the case when both Processors share a common physical address space (I guess this is what they call UMA). So, if a 32 bit processor can…
RootPhoenix
  • 1,626
  • 1
  • 22
  • 40
2
votes
1 answer

Putting powerpc 476 in spin loop in uboot

I have two core PPC476 on my SOC. On one core I am able to run linux kernel. Can anyone suggest me how I can put 2nd core in spin loop in uboot and later bring it out and map it into the linux kernel. Regards.
user2504047
  • 25
  • 3
2
votes
0 answers

Why ARM Process IPI at the end of ISR

I am studying IRQ handling on Linux. I have a question, why we need to handle IPI at the end of each ISR[for SMP]. Is there something special with IPI? why not we process in do_asm_IRQ with other interrupts. Any suggestion would be appreciated. 6 …
Dongguo
  • 379
  • 2
  • 4
  • 14
2
votes
1 answer

How do I tell the Hotspot JVM whether to use single or multi-processor thread-synchronization?

The Machine is Dual-Core, the OS uses a Multi-Processor kernel. In order to run some performance assessments, I want to set the thread-affinity of the JVM to a single core. However, I am worried that I will get skewed performance measurements as the…
edgar.holleis
  • 4,803
  • 2
  • 23
  • 27
2
votes
1 answer

How to get the current task for a given cpu in SMP linux?

I am writing a kernel module which tries to get the current task for a given cpu, for example, for_each_possible_cpu(cpu) { p = curr_task(cpu); printk("current task on cpu %d is %d\n", cpu, p->pid); } In our kernel module we could only…
T_Txiaokucha
  • 21
  • 2
1
vote
4 answers

In what order does user space code execute?

Hi I'm writting a char driver that reads and writes to a particular device. Since I'm a noob, this is a very simple and easy char drive that only utilizes the simplest of protocols such as open, read, write, and release. To test my driver I am using…
Dr.Knowitall
  • 10,080
  • 23
  • 82
  • 133
1
vote
2 answers

How are light weight threads scheduled by the linux kernel on a multichip multicore SMP system?

I am running a parallel algorithm using light threads and I am wondering how are these assigned to different cores when the system provides several cores and several chips. Are threads assigned to a single chip until all the cores on the chip are…
rreyes1979
  • 1,855
  • 3
  • 23
  • 34
1
vote
1 answer

How is ARM PPI is triggered and handled by an SMP ARM system?

I am working on an ARMv7 project, which has 2 cores. According to ARM GICv2 spec. there are 16 PPIs for each core. So my understanding is the PPI is local to each ARM core, and it should be signaled to and handled by the core. According to ARM GICv2…
wangt13
  • 959
  • 7
  • 17
1
vote
0 answers

Why atomic_thread_fence need atomic operation to work correctly

c++ memory mode: Establishes memory synchronization ordering of non-atomic and relaxed atomic accesses, as instructed by order, without an associated atomic operation. Note however, that at least one atomic operation is required to set up the…
user2256177
  • 69
  • 5
1
vote
1 answer

Why Linux distributes threads among NUMA nodes almost equally?

I'm running an application with multiple threads and it seems Linux is distributing threads among NUMA nodes almost equally. Say my application spawns 4 threads and my machine has 4 sockets. I observe that each thread is assigned to a NUMA node…
Mohammad Siavashi
  • 1,192
  • 2
  • 17
  • 48
1
vote
1 answer

How to find the thread affinity in Linux other than using the affinity mask?

We have an embedded MIPS 2-core processor running SMP Linux (2.6.18). We are planning to assign the affinity of the main GUI threads to one of the two cores, and the other core used for driver/data path processing. However, the questions has been…
user626201
  • 1,623
  • 3
  • 19
  • 36
1
vote
3 answers

Large RAM Requirements and Clusters/Clouds

This is really a bioinformatics question, but I'll make it as general as I can. Here's the semi-hypothetical situation: Let's say I have access to a cluster or even a cloud. I want to run some very specific programs on this cluster/cloud…
Pete
  • 11
  • 3
1
vote
0 answers

"SMP is not supported on this platform"

I am currently trying to use an eBPF program on a Raspberry Pi 3 Model B V1.2, that has Ubuntu installed. For managing the compilation, system calls and all that, I use the BPF compiler collection. Whenever BCC tries to compile the program, I get a…
ObiBabobi
  • 63
  • 4
1 2 3
…
10 11