Questions tagged [cpu-architecture]

CPU Architecture refers to a collection of parameters about the design of CPU realized by its manufacturer, such as: its bit-ness or data bus width (16, 32, 64 bits) , Instruction Set (RISC, CISC,...), Memory Management, Threading, Virtualization support, etc

Filter by
Sorted by
Tagged with
-1 votes
2 answers
33 views

Exception and Interrupt difference

I know a Exception is a software Interrupt however after a Interrupt the program counter always returns to the address before the Interrupt was thrown but after a Exception a program may be terminated ...
Volpina's user avatar
  • 17
-1 votes
0 answers
30 views

Power consumption with different core cpus under same load

Suppose I am running some 5 applications on a system with two different set of cpus. One is http://ark.intel.com/products/97930/Intel-Atom-Processor-C3508-8M-Cache-up-to-1_60-GHz while the other one ...
Anubhav Rai's user avatar
0 votes
2 answers
86 views

Difference between Number of CPU cycles of a device and CPU frequency of a device

I am a researcher working upon task offloading among IOT devices. While programming for my work, I have come across two terms that is Number of CPU cycles of a device and CPU frequency of a device. I ...
Zainab's user avatar
  • 1
0 votes
0 answers
42 views

Alder Lake On Package Interface speed?

The datasheet is not particularly helpful: OPI Support The processor communicates with the PCIe using an internal interconnect BUS named OPI. Functional Description OPI operates at 4 GT/s bus rate. ...
chx's user avatar
  • 3,623
0 votes
1 answer
133 views

Is the ARM instruction set the same for all ARM processors?

Is the ARM instruction the same on all ARM processors? Or just a subset of it is mandatory and universal? For instance, when Apple was designing the Mac silicon, could they have modified the ...
Caio 's user avatar
  • 13
1 vote
0 answers
64 views

What MSR to read to understand why my laptop CPU is sometimes stuck at 800Mhz?

I have a Dell Precision 7550 with an Intel Xeon W-10885M (Comet Lake), and sometimes, on Ubuntu only (not on Windows), my CPU get stuck at 800Mhz when plugged in (no problem on battery). I'm trying to ...
Vincent's user avatar
  • 377
34 votes
11 answers
8k views

Why are most of the common processors' bit counts powers of 2?

Most of the processors/CPUs widely used today, have a bit count that is a power of 2 (usually 32 and 64, but also 16, 8, and 4 bits). Even though the meaning of bit count isn't consistent (some say it'...
SamFF's user avatar
  • 456
0 votes
1 answer
109 views

Is the ARM specification just an instruction set, or more?

Is ARM specification just an instruction set, or does it include more than that, for instance hardware implementation details? I guess that the value of ARM Limited as a company (around 30G$) does not ...
PierU's user avatar
  • 1,537
0 votes
0 answers
16 views

Fix MBR for a 16-bit intel 80386sx cpu [duplicate]

i have an old classic computer running ms-dos 3.30 on computer architecture running a 16-bit cpu (80386sx, not to mistake with 80386DX which is 32-bit), i was playing around and messed up the MBR. I ...
Aqil Mehmood's user avatar
-1 votes
1 answer
60 views

Computer Architecture – Why are they different even if the machine is the same?

I've got a Raspberry Pi 4. If I install NOOBS / Raspbian and run the comand. uname -m I get armv7l as an output. If I install Ubuntu on the very same Pi (same hardware) Running uname -m yields arm64. ...
Some random IT boy's user avatar
-1 votes
1 answer
34 views

what is the supposed size of address bus 16 bits to address a memory of 8ko?

I don't know how to distinguish between the size of bus address and memory size when I supposed to answer this question in my homework: what is the supposed size of address bus 16 bits to address a ...
Akram BEN GHANEM's user avatar
30 votes
3 answers
22k views

What are performance and efficiency cores in Intel's 12th Generation Alder lake CPU Line?

I watched Intel's Architecture Day 2021 released in August 2021 (last month at the time of writing this). After watching Intel's video about their new CPU, I was — quite honestly — a bit confused. I ...
JΛYDΞV's user avatar
  • 568
1 vote
0 answers
150 views

Can different active cores of a desktop Intel x86 CPU run at different frequencies at the same time?

According to FAQ for Intel® Turbo Boost Technology, the turbo frequency is the same for all active cores. Intel's 8th and 9th Gen Datasheet, Volume 1 (PDF) also mentions that: All active processor IA ...
Wildcat's user avatar
  • 123
0 votes
2 answers
475 views

Processor with a higher IPC vs Processor with lower IPC but specific instructions

Context: Intel and AMD have long been fierce competitors in the CPU industry. As of late, AMD seems to have managed to make processors with a higher IPC on a single core than Intel (e.g. the Ryzen ...
Prithvi Boinpally's user avatar
-1 votes
1 answer
35 views

What was the need to create different processor architectures? [closed]

I have been studying processors for a while and I found out that there are a lot of processor architectures available. Once we got a working processor architecture, why did we create other ...
Shreemaan Abhishek's user avatar
-5 votes
1 answer
219 views

CPU max utilization limited to 1/N CPU’s for MOST multi-threaded Apps on any Win OS : WHY?

I understand multi-threading and tasking to some extent but know that outside of the OS, most Windows Apps are limited to using only 1/N CPU’s for averaged max. utilization. That is 50% for a dual ...
Tony Stewart EE75's user avatar
1 vote
1 answer
125 views

Why aren't CPU instructions decoded before the program runs?

What is it about the decoding step of the instruction cycle that prevents it from being done ahead of time? The Intel 64 manual says things like "decodes instructions into micro-operations". ...
Matt Kleinsmith's user avatar
0 votes
1 answer
101 views

Calculate upper memory limit of M1 chip [duplicate]

Why the M1 chip memory limit is set to 16GB,it is mentioned here that it is based on 64 bit ARM architecture, shouldn't it share the same memory limit which is 16 Exabytes? According to the linked ...
user10191234's user avatar
0 votes
1 answer
18k views

Will Python be able to run on the new Apple machines running with M1 CPUs? [closed]

I am getting the new Apple MacBook with its ARM processors. I am wondering if Python will be supported on this new line of Macs. If it is not supported yet, then when will it be supported?
neuops's user avatar
  • 111
0 votes
4 answers
8k views

How can I find my computer's address bus width and data bus size?

I have a 64 bit x86 (x86-64) computer. Does that mean my address bus is 64 bit? I am trying to calculate addressability and address space as explained here. I don't really have any clue how to find my ...
notacorn's user avatar
  • 113
1 vote
0 answers
23 views

Where are the actual bytes located within DIMM modules in dual or multi-channel mode? [duplicate]

I'm trying to find out how memory is arranged in dual channel mode, i.e. which memory addresses are on which DIMM. What I have currently found out is that there are two modes "ganged" and &...
Maarten Bodewes's user avatar
2 votes
0 answers
122 views

Privilege levels in 64bit Intel architecture [closed]

I'm currently reading this paper and while this is probably a very basic question, I can't find an answer: In the Privilege Level chapter, how does the CPU know in what privilege level it's currently ...
DreamsInHD's user avatar
-2 votes
1 answer
225 views

Do Operating Systems need to know which is the hardware architecture on which they are executing?

Maybe this is a basic theoric question, but I have no idea of the answer and haven't found information of this. Do Operating Systems (imagine Windows or Linux distros) need to know if they are ...
isma's user avatar
  • 1
7 votes
9 answers
7k views

Where does the "2" in 2^n come from when computing max memory size? n=n-bit

So I was reading up on address buses and max memory sizes, so my question is, when computing max memory size for any architecture, where does the 2 in 2^n where n is the address bus bit size come from?...
Sam Pan's user avatar
  • 219
5 votes
2 answers
16k views

GPU cores vs. CPU cores

A (say NVidia) GPU is made of streaming multiprocessors consisting of arrays of streaming processors or CUDA core. There are 5120 CUDA cores on V100. A general purpose (say Intel) CPU has "only" up to ...
kiriloff's user avatar
  • 213
0 votes
0 answers
121 views

running an existing system based on i686 Centos 6 on a 64 bit architecture

I want to run an old Centos 6 based program (i686) on my Core i5 CPU but it doesn't seem to work although I have enabled virtualization. It's a pretty complex system with lots of software libraries ...
peterbrown's user avatar
2 votes
3 answers
3k views

How the CPU determines whether to put data in L1i or L1d

How does CPU decides what cache to use to store data just retrieved from memory? As far as I know the smallest unit of memory that CPU can access (read or write) is 64 Bytes (x86_64, DDR3/DDR4) which ...
turbocoder's user avatar
0 votes
1 answer
170 views

Does the instruction register have to send its memory address to MAR before accessing memory?

I am studying computer systems and operating systems and I have been confused about when a memory address would be transferred to the memory address register (MAR). When the instruction register (IR) ...
Darien Springer's user avatar
0 votes
1 answer
50 views

Do software for creating Live Medias work whatever the CPU architecture of the target is?

So say with a software, you're flashing an image of Linux distro in a certain CPU architecture (say x86-32) to a USB drive & it's been know to work quite well. Then with the image of the same ...
kozner's user avatar
  • 239
2 votes
1 answer
512 views

Can one core perform several operations/instructions during one tick (because core has different execution units)?

A core has its own execution units and load/store buffers (additional "cache" - in addition to L1). Do those execution units have their own registers? Do cores also have their own dedicated registers?...
Code Complete's user avatar
0 votes
1 answer
53 views

Are there recent performance gains in virtualization by newer CPU generations?

I am using a workstation with Westmere Xeon CPUs and the performance I get in Virtual Box is a little bit disappointing. I have a Notebook at work with an i7-8550U at work which performs way better in ...
hex41's user avatar
  • 1
2 votes
0 answers
418 views

Armhf binaries on aarch64

So I'm running Arch Linux (64 bit) on a Raspberry Pi 3. What I'm trying to do is running a few BOINC projects on this machine. While some projects (like SETI@home) supply proper aarch64 binaries that ...
k8ieone's user avatar
  • 21
1 vote
1 answer
54 views

Spectre/Meltdown Windows vs. Ubuntu

I use a Notebook with an AMD E2-1800 processor which did not get any microcode updates. That means it is not quite protected against Spectre/Meltdown. In Ubuntu there is a very well explained wiki ...
Alex's user avatar
  • 11
7 votes
1 answer
8k views

Change CPU MHz from Registry

Is this safe? I was interested about the CPU so I did a little digging and found this location Computer\HKEY_LOCAL_MACHINE\HARDWARE\DESCRIPTION\System\CentralProcessor\0 ~MHz shows your MHz in ...
Ryan Smith's user avatar
0 votes
1 answer
43 views

What are some points to be kept in mind before installing ram sticks of different sizes? (2Gb + 4Gb)

My older Desktop had a 32bit Windows 7. But since the processor was 64bit capable, I dual booted it with a 64bit Windows 7. I want to upgrade the RAM to 6Gbs by installing another 4Gb RAM stick. I ...
Rahul Bhatt's user avatar
1 vote
1 answer
2k views

How does CPU/DMA access hard disk?

Considering x86 CPU / LINUX I want to understand how does cpu or dma access the hard drive ?does hard drive have to be accessed through IO Port addresses or it has to mapped into the memory (MMIO) ?
Usr1's user avatar
  • 157
0 votes
1 answer
229 views

How the speculative load and store happen in modern Intel processor?

I think the store queue is used in modern Intel processors for storing both memory address and store data. They do not go to L1 cache till the commit stage. But I am not 100% sure if it is correct or ...
world_of_science's user avatar
-2 votes
1 answer
324 views

How does multicore CPU thread synchronisation work at the hardware level?

I'm trying to understand how multicore CPU's implement thread synchronisation at the hardware level. From my research so far I've found that the process involves using a location in memory to act as ...
MSD's user avatar
  • 1
3 votes
2 answers
2k views

Virtualization not supported when attempting to run Docker for Windows on an AMD C-60

My Acer Aspire One, model AO725, doesn't support virtualization technology. Is there any alternative way to run Docker for Windows in this case? Processor: AMD C-60 APU with Radeon(tm) HD Graphics 1....
Azi_bel's user avatar
  • 35
0 votes
1 answer
69 views

Instruction set and pseudo-command

I use 'objdump' on linux in a variety of binaries and it returns their assembly. The commands that I receive is 'real' commands or pseudo-command? I have read that there are some commands which are a ...
0sunday's user avatar
5 votes
1 answer
2k views

Does TSX-NI provide an advantage when running virtual machines? [closed]

My question is about CPU architecture and the instruction set extension TSX-NI. For which usage scenario is it useful, and especially is it useful for web development or running virtual machines and ...
ihmels's user avatar
  • 220
0 votes
1 answer
131 views

Optimal CPI calculation confusion

I am reading https://insidehpc.com/2017/07/cycles-per-instruction-matters/: For example, if a certain part of the code takes 1200 cycles and executes 600 instructions, then the CPI would be 1200/...
Wad's user avatar
  • 227
0 votes
1 answer
155 views

Creating vCPU to physical CPU?

Say I have 8 core physical CPU system which supports hyperthreading which is mapped to 16 vCPU. Is it possible to configure increase or decrease the vCPU to 24 vCPU or 12 vCPU or this setting/...
user3198603's user avatar
0 votes
2 answers
1k views

Does conversion from assembly language to Binary language take place during decode stage in a processor?

I am newbie to computer science and here's what I think goes on in the FDEW cycle in a processor, 1.Fetch the instruction in assembly language 2.Decode to Binary language 3.Perform execution 4.Write ...
sham's user avatar
  • 3
13 votes
1 answer
10k views

Linux : Understanding load average and % CPU?

When I execute top command on my ubuntu system I see below results top - 07:58:58 up 1:21, 1 user, load average: 0.82, 0.73, 0.55 Tasks: 293 total, 1 running, 292 sleeping, 0 stopped, 0 ...
user3198603's user avatar
6 votes
1 answer
2k views

How is the micro-op cache tagged?

According to Real World Technologies’ article on “Intel’s Sandy Bridge Microarchitecture”: “Sandy Bridge’s uop cache is organized into 32 sets and 8 ways, with 6 uops per line, for a total of 1.5K ...
Lewis Kelsey's user avatar
0 votes
2 answers
88 views

Find core used from CPU utilization?

I have average and peak CPU utilization(in percentage) of a linux server with me . Mainly couple of web apps are deployed on the machine. I need to decide what AWS machine suits me based on that. AWS ...
user3198603's user avatar
5 votes
4 answers
5k views

How to make a 32-bit program from a 64-bit version?

Many software only supports 64-bit machine because the market for 32-bit is small now. However, for those who are stuck with 32-bit machines, this means newer versions cannot be installed, and this ...
Ooker's user avatar
  • 1,897
0 votes
2 answers
518 views

How to do measure execution time of cpu?

I want to measure execution time of cpus and compare them like bencmark websites. as I know we have a formula for the calculate that. Execution time = CPI * I * 1/CR But I stuck at the formula. I ...
Hasan Tıngır's user avatar
-1 votes
1 answer
40 views

In Linux, is concept of Process similar to Container (in microservices?) [closed]

Process is executing an instance of an application. Every process got its State, ID, address space etc, and isolated to each other. It looks similar to Container that runs a specific service? In some ...
FunctionBlock's user avatar