Questions tagged [asic]

An ASIC is an Application Specific IC. It is a custom chip that is made at the factory.

Filter by
Sorted by
Tagged with
6 votes
3 answers
1k views

How does the simple board with a LED work?

I have the simplest board with a LED and a button which powered by 2 CR2032 3V (pictures attached). There is 4 possible states: LED is off. LED flashing slowly. LED flashing fast. LED is constantly ...
0 votes
0 answers
64 views

Clock domain crossing without synchronisers

I am (re)designing an SPI slave module in VHDL for an ASIC. The SPI domain is faster than the main clock domain (~10MHz and ~1MHz), so the SPI state machine operates in the SPI domain. The previous ...
1 vote
0 answers
20 views

Reconciling phase shift error of length-tuned structures in 81-86GHz I/Q direct down-converter ASIC with datasheet specifications

I'm watching a video on reverse engineering a GaAs 81-86GHz I/Q down-converter ASIC. The relevant section of the video for this question is 10 minutes onwards, but watching the video isn't necessary ...
  • 7,887
1 vote
1 answer
41 views

What is name of the technique where we create modules to help us test our digital design?

In my FPGA design project, I created a few modules that can be used to emulate output from another module. Then there were modules that would inject erronous data or signals that signify errors. By ...
  • 9,909
0 votes
1 answer
78 views

Pin vs Port terminology in SDC

In SDC (Synopsys Design Constraints), set_driving_cell is said to be used to model the drive resistance of the cell driving the input port. I'm confused by the word ...
  • 1,002
0 votes
0 answers
32 views

When to use IEEE1687 vs IEEE1500

I'm curious as to the use cases of IEEE1500 (ECT) and IEEE1687 (IJTAG). From what I understand you can have a IEEE1500 Wrapper that is IEEE1687 compliant, but I've been seeing that IEEE1500 is ...
0 votes
0 answers
33 views

Standard cell design flow in an ASIC design flow

I have a question regarding the standard cell design flow in an ASIC design flow. That being said I understand what a gate array design flow is. It being more or less a fixed logic FPGA. Structured ...
  • 101
2 votes
1 answer
95 views

What are horizontal and vertical track pitches?

I was experimenting on OpenLANE with Sky130 PDK and below is the tracks.info file. I learned from a workshop that the values pertain to the track pitches as ...
  • 1,002
2 votes
2 answers
142 views

Why don't 2 flip-flop synchronizers have a reset?

This is similar to this question, asking if a reset is needed in a 2 flip-flop synchronizer. The answer to that question was: "no, not necessarily". So, my question is: Why do almost all of ...
  • 230
2 votes
2 answers
122 views

Why is a reset with asynchronous assert safe?

As far as I understand, a reset with asynchronous assert, synchronous de-assert is considered absolutely safe. I understand that this prevents metastability at the output of a flip-flop using that ...
  • 230
-4 votes
1 answer
116 views

Does an ASIC have an instruction set? [closed]

Does an Application Specific Integrated Circuit have an instruction set like a CPU? If yes, then that would contradict the statement "ASIC is faster than CPU" because having an instruction ...
  • 375
2 votes
3 answers
168 views

Is it true that for asynchronous clock domain crossing, there is always a small chance that data will be lost or corrupted?

There are several techniques that can be used to transfer data between two asynchronous clock domains. For a few bits, and depending on direction of data between the two clock domains, one could use ...
  • 9,909
0 votes
1 answer
43 views

RDC from FF with async reset to FF with sync reset (no reset pin) - what is the design practice to solve this?

Given the below scenario, which is a reset-domain-crossing violation : Can it be resolved using some reset synchronization strategy? Is such design considered bad to begin with, i.e. need to avoid ...
0 votes
1 answer
100 views

ASIC Hardware cost

Why is multiplication with a fixed coefficient cheaper in ASIC as compared to variable multiplication? Would it be faster using an FPGA inferring a DSP Slice?
1 vote
0 answers
43 views

NEC asic information from around 1990

I'm looking for datasheets with specification for the NEC ASIC/Gate Arrays from around 1990. More preciselly, any information with specifications of their ASIC/Gate Array lines. I would like to known ...
1 vote
1 answer
69 views

8bitworkshop(verilog) to terminal transition

I have been working through very basic Verilog code examples at https://8bitworkshop.com (supports a book I am following). I understand there are a few good online options available and will pursue ...
-1 votes
2 answers
185 views

Is it possible for an SoC to have a built-in SSD?

Is it possible to have an SoC that includes an SSD on-chip, or are there technical constraints that prevent that? What are those technical constraints, if any?
1 vote
2 answers
127 views

Why is static power more of a concern in smaller ASIC geometries than dynamic power?

I've read that the challenge of designing smaller ASIC geometry is the leakage current. I'm aware that dynamic power is the cause of most power consumption in CMOS, but leakage current is static power ...
  • 1,002
5 votes
3 answers
1k views

How is clock gating physically achieved inside an FPGA or ASIC?

It is bad idea to add logic gates in clock signal path. How is clock gating achieve in FPGA and ASIC designs and how does it prevent glitch in the output signal i.e the gated clock as it is enabled or ...
  • 9,909
3 votes
2 answers
493 views

Does the term micro-architecture have a meaning outside of microprocessors?

Wikipedia defines microarchitecture as follows: In computer engineering, microarchitecture, also called computer organization and sometimes abbreviated as µarch or uarch, is the way a given ...
  • 1,495
10 votes
3 answers
2k views

How were custom chips designed in the days prior to the arrival of FPGAs as hardware emulation devices? [closed]

One of the applications of FPGAs is to model a computer system/chip/functionality on it prior to mass manufacturing the copies of finalized design. How was this done before FPGAs were used for this ...
2 votes
3 answers
854 views

Why 1.5x ratio limitation for synchronizing slow signals into fast clock domain?

Why 1.5x ratio limitation for Synchronizing Slow Signals Into Fast Clock Domain ?
  • 393
0 votes
3 answers
145 views

What is the difference between "2 synchronize" and "metastability"?

As far as I know, 2 synchronize used to be used in in asynchronous FIFO for preventing metastability in multi clock domain. as the below, cross clock domain databus But I came across about ...
  • 511
-1 votes
1 answer
124 views

Synthesis rules for this procedural assignment (combinational circuit)

I am a noob asking elementary questions. So bear with me. If I have the following code, what would the synthesis result be if it can be synthesized at all. will the synthesizer generate intermediate ...
0 votes
1 answer
304 views

Synthesis output for the following verilog code

I have a somewhat stupid question as I am still a noob. So bear with me. If I have the following statement in Verilog: ...
1 vote
1 answer
218 views

behavior of a pipelined divider

Divider can be made combinational, which uses more logic gates.. Divider can be made sequential, the throughput may stay the same, i.e. use as many stages as the width of the dividend (assuming width ...
0 votes
1 answer
174 views

Is there any reason why the Design Compiler does not optimize a path which it can optimize in a submodule

I have an issue in timing slack got from Design Compiler (DC.) One path Reg2reg in my submodule just was fine, but that path is found to be longer in the top module. It seems that the path was not ...
  • 17
0 votes
4 answers
153 views

Is metastability not a concern in CDC if the signal in source clock is at least 3x wide as that of destination clock's period?

There are so much hype and concern over metastability in cross clock domain. If the goal as an ASIC/FPGA designer is to ensure that the signal in source clock get propagated to destination clock even ...
0 votes
1 answer
25 views

How to Implement Relational Operation using TCAM?

Can we implement relational operations (<, > , >=, <= ) using TCAM? Even if they are possible to implement, are TCAMs used for relational operations in real life? What are the pros and ...
0 votes
2 answers
858 views

ASIC gate count estimation and SRAM vs flip-flops

I'd like to be able to estimate gate counts of different designs for the purpose of architectural exploration. Below is what I found out. Please feel free to correct, comment, expand. Logic gates Two ...
  • 1
2 votes
2 answers
239 views

What is the proper way to reset an output signal back to zero on the next clock edge?

Occasionally writing some FPGA-targeted Verilog code at my job, I often need to drive output signals high during one clock cycle exactly. Sometimes I use the following “trick“ to achieve this (let me ...
-1 votes
2 answers
555 views

What ASIC/MCU is in my keyboard?

I disassembled my unbranded USB keyboard to find out what ASIC/encoder/MCU is inside. The chip is (as expected) covered, like the following example: How to find out which chip is underneath?
user avatar
1 vote
3 answers
997 views

Whats the cost to create your own custom ASIC chip? [closed]

There are never any bitcoin miners available to purchase and whenever Bitmain (the leading bitcoin mining manufacturer) releases a new batch of miners they all get gobbled up in seconds. For those who ...
3 votes
2 answers
220 views

How do ASIC designers approach designing for extremely low supply voltages like 0.3V?

In ASIC design, there is a tradeoff between performance and energy efficiency. Since most consumer CPU's are designed for maximum performance, they operate at high voltages and clock frequencies, ...
  • 147
1 vote
4 answers
1k views

Can an FPGA/ASIC have an operating system?

I know FPGA/ASIC are for a specific task and they are not microprocessors and an OS is needed mainly if multiple processes (tasks) need to be run concurrently. Just wondering if an FPGA/ASIC can have ...
  • 93
1 vote
1 answer
95 views

What is standard coding practice for a non-blocking assignment to a large register array with variable part select in Verilog?

I couldn't find anything in the Verilog-2001 standard about this. For example, the following code works (Xilinx ISE): ...
  • 81
0 votes
1 answer
219 views

Systemverilog interface definition - lint error message

I'm using Systemverilog interfaces to enable the implementation of generic functions. The interface is defined in one file as follows: ...
  • 429
0 votes
0 answers
39 views

Do SRAM Macros register the inputs?

In ASIC design, we often purchase SRAM macros to use in our designs. A typical SRAM macro includes a Verilog description and a timing/layout characterization (lib file). My question is this: SRAMs ...
  • 143
1 vote
2 answers
364 views

Does it make sense to use a clock input for combinational logic?

Today, I came across this problem on QuickSilicon's RTL Hackathon. It was to design an Endian converter. The requirements were The output should be available in the same cycle The module should ...
  • 2,416
1 vote
1 answer
2k views

How to implement Clock Gating Style RTL into synthesis?

I'm studying to implement a Clock Gating in RTL. So I've followed as the below https://www.design-reuse.com/articles/23701/power-analysis-clock-gating-rtl.html ...
  • 511
1 vote
2 answers
322 views

Do I need to make a timing report for min/max at Static Timing Analysis in Four categories of timing paths?

I've been studying to understand Static Timing Analysis aka STA. One of what I can't understand is whether I need to make a report timing for min/max at Static Timing Analysis in Four categories of ...
  • 511
0 votes
1 answer
96 views

How does the hardware realize adding 8 values in 1 clock cycle? [closed]

For example: result= a1+a2+a3+a4+a5+a6+a7+a8 How many adders are needed to perform this in 1 clock cycle? What does the design look in terms of hardware?
-1 votes
1 answer
124 views

Inverter's Chain Sizing

if i have a chain of 4 identical inverters connected in series and i want to size them to obtain a specific propagation delay time, how do I approach this problem ? i know that there are several ...
1 vote
0 answers
235 views

SystemVerilog: copy a slice from a vector to another vector of different size

as per title, I want to copy a slice of fixed size from one vector to another, starting from a variable location. Example: ...
0 votes
1 answer
171 views

How to decide when to use flop or RAM based fifo?

Trying to figure out what are the tradeoff like power, size when deciding between using a flop or RAM based fifo ? Any known publications ?
  • 111
1 vote
1 answer
666 views

Pseudo dual port RAM in verilog

How does one design a pseudo dual port RAM using a single port RAM in Verilog ? What are the design considerations? Are there frequency limitations ? Clarification on 'pseudo dual port - single port ...
  • 111
2 votes
3 answers
209 views

Are FPGAs for experimentation alone?

I have been reading about FPGAs recently and found that they have a lot of applications in many fields. I also read an article that they are used for testing purposes alone. Are FPGAs only for that? ...
1 vote
2 answers
288 views

Shared IC tape out

I have a IC design about 300*300 micrometers. Due to the high cost of IC tape out, is it possible to fabricate the IC jointly with other people? Does the company have such a service?
1 vote
1 answer
93 views

SystemVerilog - Enforcing prevention of inline initialization of logic/reg elements used as flip-flops

Given a SystemVerilog design modeling an ASIC, how can I enforce the rule that all logic/reg elements that are used in flip-flops should not be initialized to a certain value? Is there a directive ...
2 votes
4 answers
360 views

Hardware to run a fixed neural network

Suppose I have a feedforward neural network and I already have decided what its directed graph, weights and activation function should be. I want a device than runs this neural network as quickly as ...
  • 29