Questions tagged [computer-architecture]

Questions about the organization and design of computer hardware.

Computer architecture is a branch of computer science that deals with the hardware aspects of computers including organization, structure, design, and implementation of hardware components and their combinations used in computers. The main goals relate to function, performance, cost, energy, and the formal modeling of those systems.

Topics in computer architecture include: physical structure of computer systems, organization of processors (superscalar, multithreaded), memory hierarchies, disks and I/O organization, control and sequencing (dynamic and static scheduling, speculative execution), shared-memory multiprocessors, multicomputers, distributed shared memory systems, and energy efficiency.

1129 questions
95
votes
13 answers

What are GPUs bad at?

I understand that GPUs are generally used to do LOTS of calculations in parallel. I understand why we would want to parallelize processes in order to speed things up. However, GPUs aren't always better than CPUs, as far as I know. What kinds of…
ChocolateOverflow
  • 1,111
  • 1
  • 7
  • 12
59
votes
7 answers

Why does a processor have 32 registers?

I've always wondered why processors stopped at 32 registers. It's by far the fastest piece of the machine, why not just make bigger processors with more registers? Wouldn't that mean less going to the RAM?
Matt Capone
  • 711
  • 1
  • 6
  • 5
57
votes
11 answers

Why would anyone want CISC?

In our computer systems lecture we were introduced to the MIPS processor. It was (re)developed over the course of the term and has in fact been quite easy to understand. It uses a RISC design, that is its elementary commands are regularly encoded…
Raphael
  • 72,336
  • 29
  • 179
  • 389
52
votes
10 answers

If the speed of electrical charge hasn't changed, how have computers become faster?

Everyone knows computing speed has drastically increased since their invention, and it looks set to continue. But one thing is puzzling me: if you ran an electrical current through a material today, it would travel at the same speed as if you did it…
leylandski
  • 653
  • 6
  • 7
29
votes
6 answers

Why are reversible gates not used?

I was reading the book "The singularity is near" written by Kurzweil and he mentioned the reversible gates like for example the Fredkin gate. The advantage using such gates is that we could get rid of the thermal waste related to computation where…
Mehdi
  • 443
  • 4
  • 6
19
votes
2 answers

purpose of supercomputers

Last fall I went on a tour of the Blue Waters supercomputer at the University of Illinois. I asked whether anyone ever used the entire computer. I was told that it was always working on multiple projects. That made me wonder about the usefulness…
Mitchell Kaplan
  • 465
  • 3
  • 8
16
votes
4 answers

why do CPU architectures use a flags register (advantages?)

Some CPUs have a flags register (ARM,x86,...), others don't (MIPS,...). What's the advantage of having a CMP instruction to update the flags register followed by a branch instruction instead of using a zero register and conditional branches to check…
model world
  • 382
  • 4
  • 10
15
votes
2 answers

Why did MIPS include shamt and distinguish funct/opcode?

I'm confused as to why the MIPS designers would include 5 bits dedicated to shifting and have separate opcode and function bits. Because MIPS is so RISC I assume that only shifting would be done in a few instructions, so those 5 bits seem like…
qwr
  • 618
  • 1
  • 7
  • 18
14
votes
2 answers

Do computers actually use carry-lookahead adders?

There are plenty of details about carry lookahead adders such as Kogge-Stone, Lander-Fischer, etc. in college CS courses. They are described as "common in the industry". However, I can't find any evidence (aside from maybe the Manchester carry…
qwr
  • 618
  • 1
  • 7
  • 18
11
votes
3 answers

Data General MV/8000 virtues of "No mode bit"

I'm reading Tracy Kidder's "The Soul of a New Machine" where a team at Data General design a new machine (codenamed "Eagle", later named MV/8000). It is 32-bit extension of a previous architecture (the 16-bit Eclipse). One of the revolving themes…
Morty
  • 253
  • 2
  • 7
11
votes
4 answers

Why do we need so many transistors in a chip, and how are they managed?

My knowledge is very vague as all we have are visual diagrams etc, but we have memory address and registers, the ALU being the heart(apparently). Single core CPUs process one instruction at a time AFAIK and multi-core have parallelism to some…
user12979
  • 211
  • 1
  • 2
  • 3
8
votes
4 answers

Which architecture do modern computers use?

Is it one of: Harvard Modified Harvard von Neumann Or are they antiquated models that modern computers are only loosely based on? If you asked Intel or AMD what would they say?
AsksAnyway
  • 183
  • 1
  • 1
  • 5
8
votes
3 answers

Is there anything lower than the bit level of 1s and 0s?

When learning about the architecture of computers and how it works, we are thought that the lowest language that we can find that the machine understands is binary as 1&0. And anything that we input will have to be transformed/converted to binary,…
8
votes
4 answers

What happens at the decode phase of the instruction cycle?

I am reading about the various phases of the Instruction Execution, I found out that we have three phases like below. Fectch Decode Execute Now if the part I don't understand is why do we need a decode phase ? The instruction will already be…
vikkyhacks
  • 399
  • 1
  • 3
  • 9
7
votes
4 answers

The amount of ROM needed to implement a 4-bit multiplier?

For a 4-bit multiplier there are $2^4 \cdot 2^4 = 2^8$ combinations. The output of 4-bit multiplication is 8 bits, so the amount of ROM needed is $2^8 \cdot 8 = 2048$ bits. Why is that? Why does the ROM need all the combinations embedded into…
Ravi Teja
  • 323
  • 2
  • 3
  • 9
1
2 3
20 21